International Journal of Engineering Research in Computer Science and Engineering:



ISSN:

2394-2320

Number of Papers:

1100

Journal Site:



'Prediction of Students’ Performance: Artificial Neural Network Approach

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th January 2018

K. G. Nandha Kumar | 

Abstract

Neural network techniques are applied in an ample number of fields in the recent decades. Educational data mining is one among them where the data mining could be carried out effectively. The core tasks are classification, clustering and grasping of association rules. These could be accomplished with suitable educational data. Enormous algorithms, techniques, and tools are available for data mining. Identifying a best suitable algorithm for a specific task is still intricate. This paper deals with the performance of some well formed neural network methods on students’ performance prediction. Predictive analysis is a significant task in the education domain. Exploitation of students’ mark data leads to the better predictive analysis. In the field of educational data mining, most of the research work focuses on predictive analysis and models. There is a scope for multidimensional predictions. This paper indicates some viewpoints of neural network based educational data mining.

3D Face Recognition

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th October 2017

Mr. Jayraj |  Nilabja Roy, Swapnil Aryan Sinha

Abstract

3D face recognition is one of the novel ways of having a security feature. This could be considered much more safer than a finger print scanner as it uses the crests and troughs on the face to accurately map every centimeter of the face, now because of his technology the machine cannot be fooled by showing a photo of the person because it won't be able to detect the crests and troughs on the face. In order to cheat the machine, one would have to make a 3D model of the face with exact depths at every centimeter which is very difficult. PCA algorithms, resulting in improved recognition performance, both individually and in combination. We have also examined the effect of depth resolution on performance of 3D recognition which is very accurate.

4G Wireless Security Threats Due To the Interference

International Journal of Engineering Research in Computer Science and Engineering, Available online 10th January 2018

Nagesha A. G. |  Dr. Gowrishankar S. S.

Abstract

The 4G wireless network standards are motivated to frequency reuse, where it will raise the system capacity and normalize the planning of radio networks. As the system capacity increases, the signal to noise (SNR) ratio will be degraded due to the interference in the cells. The present security will not suitable for the physical layer of Long Term Evolution (LTE) networks. The key characteristics of the channels of wireless networks are open and broadcasting. As these networks can be attacked easily through interference, signal jamming and eavesdropping. Hence the security issues in physical design will be considered as the critical issues in LTE networks. So, before discussing security issues, we should identify the threats and vulnerabilities raised in the low-level layer of wireless networks. Later in this paper, the secure schemes and other procedures will be explained where that can be adopted in the physical layer.

5G technology: The Key Enabler in Reaching the Unreached, Its Advantages and Initiatives Government Can Take to Empower Indians Compete Globally.

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th December 2017

Skanda Kumar.B | Nandan goud.B

Abstract

A new revolution of the telecommunication is the 5G technology where various mobile phones will be able to leverage data anywhere, anytime that is expected to spread rapidly, over the coming years.In this paper the author is trying to portray its advantages over previous generations of internet, and some of the initiatives that can be taken by the government are discussed that can put 5G into mainstream ,this is necessary because the advancements in mobile technology and web technology with current old school 2G internet which majority of the rural Indians have, can be regarded as unusable internet and obsolete in nature because most needed features like e-Education, E-medication, E-commerce which lead to symbiotically beneficiary between rural and urban India is restricted by 2g internet there by proving just connecting people to the internet is not the solution for modern India instead it is the connecting people to the high-speed internet is the answer for which 5G will play a huge role.

5G Wireless Mobile Network

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

MS. S. Pavithra | MS.J.Uma Sawmiya, MS.R.Bavani , MS.Smitha

Abstract

5th generation mobile network or simply 5G isthe forthcoming revolution ofwireless technology.It is beyond the thinking of normal human.With its ultra-high speed ,it changes the usability of a mobile phone.

6*6 Radom Color Grid Authentication (2 Step)

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th August 2017

Sudershan M | Veena Potdar, Madhu B

Abstract

Security in the computer is largely supported by passwords for authentication process. Use of alphanumeric passwords is the most common Authentication method. This conventional authentication method has been shown to have significant drawbacks. To overcome the vulnerabilities of traditional methods, numerous graphical password authentication systems have been proposed. These graphical passwords are usually seen as complex and time consuming. Furthermore, the existing graphical passwords are susceptible to spyware and shoulder surfing attacks. In this paper we propose this novel graphical password scheme to abolish well known security threats like brute force attacks, dictionary attacks, phishing attacks and spyware attacks.

A Body Wearable Antenna for Online Real-Time Health Monitoring System

International Journal of Engineering Research in Computer Science and Engineering, Available online 28th March 2018

Mohd Kashif | Zeeshan Ali Haq

Abstract

Healthcare system in India is very fragile in a sense that that ratio between doctors and patients is very poor. Also, the medical cost is very high. In such situation, there arises a purpose of online health monitoring which would reduce the ratio and cut down on the medical cost. A textile antenna for online health monitoring is proposed in this paper. The antenna is designed to operate at 2.54 GHz frequency in ISM band. It will enable the patient to easily wear the system and transmit the real-time health monitoring data to the nearby hospital system. The ISM band ensures the licence free data transmission over the channel. The designed antenna is a rectangular patch of wearable textile material.

A Brief Review On The Application Of Swarm Intelligence To Web Information Retrieval

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Ramya C | Dr. Shreedhara K S

Abstract

Web Information Retrieval process has become one of the most focused research paradigms because of large quantity of growing web data as internet is ubiquitous. To this distributed, uncertain and volatile data, accurate and speed access is required. So there is a need to optimize the search process using some efficient approaches. For such novel approach a literature survey is presented on evolutionary bio-inspired Swarm Intelligence techniques to optimize search process in Web Information Retrieval Systems.

A Case Study of Association Rule for the Confidence and Support Using Apriori Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

S.Uma Gowri | Dr V. Lakshmi Praba

Abstract

The data mining approach, a relatively new technique, is deployed in large databases to find novel and useful patterns that might otherwise remain unknown. Association rule learning which follows the apriori algorithm is a popular and well research technique for discovering interesting relations between variables in large databases. Among various algorithms available for mining frequent item set we include apriori algorithm. Main objective of apriori algorithm is to find out hidden information which is the major goal data mining. In this study, we use United States Congressional Voting dataset and analyze the information based on predefined rules

A cloud based bus alert system for navigation of blind people

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

Dr.R.Thendral | A.Gayathri, P.Kalaivani, T.Kiruthika

Abstract

Generally, journey in bus is a safe and comfort factor, but due to increase in number of buses and passengers its going be tougher and it will be more difficult for blind people to travel in bus. In this project, we proposed a novel system which can help blind people to find the bus at the bus stop. The main problem is navigation in real time traffic and checking the available buses along with their routes. In this project the blind person will get the information from the bus depository database. The desired output will be announced earphone and the bus is tracked by GPS. The blind people in the bus station are provided with a smart phone which is connected by the cloud. The cloud will store the information about the bus number and timings. Blind people instructions goes to cloud platform then cloud will process the corresponding response then get the desired result. So that blind people can clearly know about bus location and timings of bus arrival to their respective places. For developing this project, we used Voice Activity Detector algorithm, Route Selection algorithm, DTW algorithm for location estimation

A Combination Technique of Multi-wavelets and Interpolation for Resolution Enhancement of Digital Images

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th July 2017

Sreeletha S H | M Abdul Rahiman

Abstract

This paper explains the effect of various multi-wavelet interpolation methods on digital images to enhance the resolution of the images. A high resolution image is a major challenge for any image processing application, especially in defense and medical scenario. Here resolution enhancement technique is done in wavelet domain using multi-wavelets and interpolation methods. Visual perception of an image has to be improved by various enhancement techniques since the hardware image acquisition methods drops to a limit. Some spectral and spatial problems such as motion blur, pixilation and poor perception may still prevail in digital images which requires rectification before processing further. The Super Resolution images are generated by applying enhancement techniques on a set of noisy and blurred low resolution images . In this paper, some of the resolution enhancement techniques such as Discrete Wavelet Transform, Stationery Wavelet Transform and a combination of DWT and SWT with various interpolation techniques are experimented. The DWT-SWT with Bilinear interpolation method illustrates the improvement in the resolution factor of the image, thereby improving the visual perception of images

A Comparative Analysis between Traditional Virtualization and Container Based Virtualization for Advancement of Open Stack Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th May 2018

Krishna Parihar | Arjun Choudhary, Vishrant Ojha

Abstract

LXD based machine containerized new concept in the virtualization world. Its give performance to the bare metal virtualizations. A Centralized system is accessed through IP and can be scalable on demand as per requirement, Technology that eases the user problem like hardware, as well as software most popular technologies, is known as Cloud Computing. As per enterprise and industries demand cloud computing holds a big part of IT world. An OpenStack is a way to manage public and private cloud computing platform. A Linux Container Hypervisor brings Cloud Computing to the next generation Hypervisor with its features Fast, Simple, Secure. The main goal of this paper is factual calibrate is determine various virtualization technique and performance analysis.

A Comparative Study on Fake Review Detection Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

A.Lakshmi Holla | Dr Kavitha K.S

Abstract

Opinion mining has played a significant role in providing product recommendations to users. Efficient recommendation systems help in improving business and also enhance customer satisfaction. The credibility of purchasing a product highly depends on the online reviews. However many people wrongly promote or demote a product by buying and selling fake reviews. Many websites have become source of such opinion spam. This in turns leads to recommending undeserving products. This literature survey is done to study the various fake review detection techniques in detail and to get ourselves familiar with the works done on this subject.

A Comprehensive Review on Recent Development of Islanding Detection Method

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th April 2018

Diksha A.Shinde | Prof. R. S. Somalwar

Abstract

Incredible growth in demand of electricity with efficient, reliable and eco-friendly power has motivated progress of distributed generation (DG). This is located at distribution system and now a day renewable energy sources used as a DG. But problem of using DG is unintentional islanding, which has perspective to make voltage and frequency out of synchronism and can damage equipment along with thoughtful issue of worker safety. Hence system should identify islanding and avoid its adverse effect. There are many islanding detection methods (IDM) but there is no such technique by which all the problems related to islanding being solved. In this paper new islanding detection technique is proposed on the basis of voltage ripple at inverter side of micro-grid base system. Its performance will be verified under wide range of operating condition in MATLAB/Simulink software.

A Data Centric Access Control Solution with Role Based Expressiveness for Protecting User Data on Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Nisha Ranjan Sah | Tejashwini P, Veeresh S, Yathish,Mrs. Prema.

Abstract

Most current security solutions are based on perimeter security. However, Cloud computing breaks the organization perimeters. When data resides in the Cloud, they reside outside the organizational bounds. This leads users to a loss of control over their data and raises reasonable security concerns that slow down the adoption of Cloud computing. Is the Cloud service provider accessing the data? Is it legitimately applying the access control policy defined by the user? This paper presents a datacentric access control solution with enriched role-based expressiveness in which security is focused on protecting user data regardless the Cloud service provider that holds it. Novel identity-based and proxy re-encryption techniques are used to protect the authorization model. Data is encrypted and authorization rules are cryptographically protected to preserve user data against the service provider access or misbehavior. The authorization model provides high expressiveness with role hierarchy and resource hierarchy support. The solution takes advantage of the logic formalism provided by Semantic Web technologies, which enables advanced rule management like semantic conflict detection. A proof of concept implementation has been developed and a working prototypical deployment of the proposal has been integrated within Google services

A Data Centric Access Control Solution with Role Based Expressiveness for Protecting User Data on Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th August 2017

Nisha Ranjan Sah | Tejashwini P, Veeresh S, Yathish, Mrs. Prema.

Abstract

Most current security solutions are based on perimeter security. However, Cloud computing breaks the organization perimeters. When data resides in the Cloud, they reside outside the organizational bounds. This leads users to a loss of control over their data and raises reasonable security concerns that slow down the adoption of Cloud computing. Is the Cloud service provider accessing the data? Is it legitimately applying the access control policy defined by the user? This paper presents a datacentric access control solution with enriched role-based expressiveness in which security is focused on protecting user data regardless the Cloud service provider that holds it. Novel identity-based and proxy re-encryption techniques are used to protect the authorization model. Data is encrypted and authorization rules are cryptographically protected to preserve user data against the service provider access or misbehavior. The authorization model provides high expressiveness with role hierarchy and resource hierarchy support. The solution takes advantage of the logic formalism provided by Semantic Web technologies, which enables advanced rule management like semantic conflict detection. A proof of concept implementation has been developed and a working prototypical deployment of the proposal has been integrated within Google service

A Data Mining Approach With Anonymization Techniques Using Keyword Search On Health Based Records

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th January 2018

Sri. E. Ramesh | Dr. B Tarakeswara Rao

Abstract

A medicinal services framework incredibly upgrades the patient social insurance records which are put away in the cloud server. Accessible encryption conspire is utilized which improves the inquiry system. Conjunctive watchword look encourages the approved clients to get to the records by giving numerous catchphrases, so it ends up plainly troublesome for the aggressors to figure the watchword and recover the records. Re-encryption conspire gives greater security to the records by re- scrambling the encoded list before transferring them to the cloud server. Since the patient's social insurance records comprise of touchy data, it might be badly designed for the patient when his records are gotten to by everybody. To beat the issue in our proposed work we present the idea called K-Anonymity which is utilized so it gives just an incomplete access to the approved clients by utilizing two techniques concealment and speculation. This has been exceptionally productive in the standard model.

A Detailed Study on Fundamental Characteristics and Functional Operations of Manet

International Journal of Engineering Research in Computer Science and Engineering, Available online 28th August 2017

Narayanasamy Rajendran | Dr. E.R.Naganathan

Abstract

A MANET is a collection of independent mobile nodes that communicates with each other through wireless medium. The MANET architecture is dynamic in nature, the nodes act as transmitter and receiver. The vehicular ad hoc network topology changes frequently due to the dynamic nature of the autonomous mobile nodes. MANET is exposed to multiple kinds of attacks due to its fundamental characteristics like no security mechanism, dynamic topology, no central control devices and open wireless medium. The impact of attacks affects the security, quality of service and the performance of MANET. MANET is the best alternative for developing countries where communications infrastructure doesn’t exist. To understand the how MANET is created, configured and controlled we need to understand the following area: MANET Architecture, Clustering Formation, Identification of Host and IP address auto configuration, Handover mechanisms on MANET, Routing on MANET, MANET file sharing, Different types of attacks and Security on MANET.

A Detailed Study on Security Threat Analysis in Wearable Devices

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th August 2017

Srimanth DS | Sudhanva Krishna V, Vishwajith M V,Venkatesan S

Abstract

Wearable devices can be anything from small wrist-mounted systems to bulky backpack computers. Wearable device is a combination of devices typically a belt or backpack PC, head-mounted display, wireless hardware and some input devices. The fundamental principle of wearable device is to collect data ubiquitously and continuously, about the individual user and also their surroundings. This can pose many privacy challenges and are hindered by poor security. They are not mature yet in term of device security and privacy acceptance of the public. Low processing power of wearable device leads to developer’s inability to implement certain complicated security mechanisms and algorithms on the device. This paper analyzes various security issues and attacks on the user’s data

A Detailed Survey on Big Data Application in Global Banking Data Management & Decision Making

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th December 2017

Kavyashree. J | Gouri Jambure, Vasudeva. R

Abstract

In today’s world of Investment Banking and other financial domain areas, the requirement and demand for the automation in data processing is very high. The data is accumulated from different data sources with an increase in the rules and regulations, but that should also come with a plan of cost reduction without compromising in quality and scalability. The underlining technologies that handle big data with should guarantee of optimization and also keep global financial institutions interest in it. So this paper or case study covers the Big Data architecture and design that would help banking institutions make key decisions. We have used Hadoop map-reduce and no-SQL flexibility also maintaining the quality, banking rules and standards. The data that is proposed to be consumed or used for this analysis is from different sources and techniques, techniques that are followed in regular banking practices. That would include “front end” or “backend data processing”. Business process modelling would require data transmission OR orchestration from different sources that are required to make key and important financial decisions.

A Distributed Publisher Driven Secure Data Sharing Scheme for Information Centric Iot

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th April 2018

Ch.Tishitha | N.Kesava Rao, M.Anupa, A.Jyothsna, K.Mounika

Abstract

This paper presents a critical review of Failure Modes and Effect Analysis (FMEA). Although the method is almost 70 years old, in literature there are still many researchers, both from academy and industry, devoted to improve it and overcoming unsolved and still open problems. The aim of this work consists in analysing a representative pool of scientific papers (220) and patents (109), in order to have an overview of the evolution of the method and try to understand if the efforts spent to improve it effectively answer to the several criticisms found in literature. All documents have been classified according to authors, source, and four technical classes dealing with the applicability of the method, representation of the cause and effect chain, risk analysis and integration with the problem-solving phase. A detailed analysis of the results allowed us to identify the most current problems, the improvement paths, and which other methods and tool are proposed to be integrated with FMEA.

A Dual Band Microstrip Double Slot Antenna for Wi-Fi and WIMAX Applications

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th June 2017

N.Parthiban | Dr. M. Mohamed Ismail

Abstract

In this paper a dual band microstrip slotted antenna is proposed. This antenna has a simpler structure than other antennas designed for realizing dual band characteristics. Simulation studies of the proposed structure are studied and analyzed using High Frequency Structure Simulator (HFSS) software. The design antennas are then fabricated and tested using Vector Network Analyzer. We obtained good results in testing. The radiating patch is placed on a FR-4 dielectric substrate ( =4.3, tan δ = 0.02) with conducting ground. The Co-axial feeding technique is used. In the Operating frequency range of 2.4-2.48 GHz, have a return loss of less than -10 dB for Wi-Fi applications. Operating frequency range of 2.66-2.77 GHz, 4.28-4.4 GHz and have a return loss of less than -10 dB for WIMAX applications.

A Exposure Based Technique With Dwt To Enhance The Image

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th September 2017

Abhay Verma | Manish Dixit

Abstract

This paper gives a technique to enhance the contrast of low exposure gray image. For this threshold is calculated of gray image and it is utilized to clip the gray image into different images. And then this clipped image is individually equalized utilizing histogram equalization with discrete wavelet transform for the enhancement of the image.

A Flexible Approach of Mobile Cloud Computing and Big Data Analytics for Networked Healthcare Applications

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th June 2017

Hemalatha T | K Venkata Chalapathi

Abstract

Now a day’s Mobile devices were rapidly growing as indispensable part in our daily life, facilitating to do various useful tasks. Mobile cloud computing combines mobile with cloud computing to enlarge their capabilities, benefits and reduces their limitations, like battery life less memory and CPU power. Big data analyzing technologies facilitate extracting value from data consisting four Vs: volume, velocity, variety and veracity. This paper focuses networked healthcare as well as the task of mobile cloud computing and big data analytics in its enablement. The inspiration and development of applications over networked healthcare and systems were offered along with the adoption of healthcare cloud. A cloudlet based infrastructure of mobile cloud-computing to be utilized for healthcare. The methods, tools, and applications of big data analytics were focused. Experimental results are considered in the design of networked healthcare systems with big data as well as the technologies of mobile cloud-computing.

A Framework Designing For RDF Smart Crawler for Extracting Semantic Information

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th April 2018

Gurdas Singh | Brijesh Bakariya

Abstract

Currently, Search engines only provide URL links for search queries. Crawling strategy adopted by most search engines only search on HTML keywords and index the pages, but semantic web retains most rich information in RDF files and crawlers don’t index the RDF. In this work, we deal with the problem and design a smart crawler which can retrieve semantic information for keyword queries. In addition to retrieving the information, the proposed solution also focus on ranking the semantic information. Ordinarily, a covetous framework is used to pick the terms that enlarge the new returns each cost unit. We comprehended that not each record is square with while selecting the request to cover them. Broad reports can be secured by various requests, paying little respect to how the inquiries are picked. In like manner, the criticalness of a record is then again with respect to its size. Our further examination of this issue finds that the noteworthiness of the record depends not simply on the amount of the terms it contains, furthermore the sizes of those terms.

A Futuristic Approach for Towerless Mobile Networks Contributing to Digital India

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Jyothi Sulochana | K Hemavathi ,P Kalamani ,Lorate Shiny

Abstract

This project is an attempt to develop the mobile networks to have a wireless voice call happening without the help of the towers. Our main aim is to remove the towers in the communication process. The towers have been hazardous to many birds and animals. This project uses the Raspberry Pi boards with the inbuilt wi-fi on board. The Raspberry Pi with the wi-fi is used for the prototype, which would be used to develop a voice call application which would transfer the voice through the wifi communication. It is proposed to develop this technology to be able to access only till the distance of 30 meters which is the distance limit of the wi-fi communication. It would be possible to move this communication to be expanded by the use of the Wimax technology which would be able to communicate in the range of kilometers. This project uses two Raspberry Pi kits with Wi-fi inbuilt on it and would be able to communicate by developing the voice call application and would be able to use the audio jack on the kit. A hardware implementation would be developed and the results would be analyzed for performance.

A Fuzzy Controlled IUPQC for Grid Voltage Regulation as a STATCOM

International Journal of Engineering Research in Computer Science and Engineering, Available online 24th November 2017

B. Divya sree | 

Abstract

This paper shows A improved controller for the dual topology of the unified power quality conditioner (iUPQC) broadening its relevance in power-quality pay, and additionally in microgrid applications. iUPQC will act as a static synchronous compensator (STATCOM) at the grid side, while giving likewise conventional UPQC pay at the load or microgrid side. Another control procedure with Fuzzy logic controller is given here. Past the conventional UPQC power quality highlights, including voltage sag/swell remuneration, the iUPQC will likewise give reactive power support to direct the load-bus voltage as well as the voltage at the grid-side bus by utilizing this controller. Expansion of Fuzzy controller gives low total harmonic distortions in the system. Simulation results are given to confirm the new functionality of the hardware.

A Fuzzy Logic Based Techniques for content based image Retrieval and Digital Data Transmission

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th September 2017

Dr.Ruksar Fatima | Prof Jyoti Neginal

Abstract

Today’s demand of internet in applications in large amount requires to be transmitted in a secure manner. In communication system transmission of digital data is not secure because interception and improper manipulation done by the eavesdropper. We can send digital data in such a way that no one, except the sender and the receiver can suspect the existing of data. In this paper we propose a new fuzzy logic based technique for content based image retrieval and digital data transmission, which transforms a secret digital data by embedding in another digital data with the same size and looking like selected target image. The transformation process can be controlled by a secret key generated by fuzzy logic

A Greedy Search Aware Fuzzy Scheduling in Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th June 2018

Sirisati Ranga Swamy | Dr. Sridhar Mandapati

Abstract

Cloud computing can provide on-demand storage as well as computing services that have a high performance level along with high scalability. The increasing consumption of energy in the cloud data centers is a very prominent problem today. The cloud performance has been affected because of the issues in security. Thereby, the service providers have been held responsible for taking proper care of these systems here and the scheduling will be held responsible for the choice of best and also most suitable resources in the task execution by means of taking certain types of static as well as dynamic parameters along with the restrictions of such tasks into consideration. The scheduling in that of cloud computing will belong to one category of the problems that are called the Non-deterministic Polynomial (NP)-hard based problems owing to the solution space and so it takes a long time in identifying an optimal solution. Here in this work, the fuzzy logic and the methods are greedy in terms of the methods that were proposed. For calculating the value of the fitness in the fuzzy inference system the membership function is used to determine the degree until which these parameters belonging to a fuzzy set which is relevant. The work also introduced another new idea for integrating the approaches in solving the hard problems that are combinatorial. This proposed methodology which shall evaluate all the objects in a manner that can combine the fuzzy reasoning along with a greedy mechanism. It also means that the fuzzy solution space is exploited with some greedy methods. The results of the experiment proved that this method proposed can achieve better performance than that of the fuzzy logic

A High Sensitive Approach for Gender Detection Based on Human Iris

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

B.Ishwarya | Dr.G. Heren Chellam

Abstract

Now a day’s iris patterns play a vital role in gender classification. Iris patterns are distinctive and cannot be changed until it becomes unnatural. This paper focus on gender has been detected using iris images. This work presents a new method for gender classification based on features of the iris texture selected by mutual information to improve gender classification of iris images For determining the recognition performance of the system database of digitized grayscale eye images were used. This grayscale images are segmented. Traditional iris segmentation methods always time-consuming and sensitive to noise. Here, in iris recognition, the segmentation is based on Hough transform used for automatic segmentation and able to localize the circular iris and pupil region. Edge points of iris boundaries are detected with canny edges steps and the threshold values are matched with the hamming distance. The Hamming distance was employed for classification of iris images. This work comes to the conclusion that iris segmentation is an essential part of recognition system and the prediction is based on iris texture features and stop matching when a generation of Iris close match is found

A Honeypot based Attack Detection and Prevention System for Smart Cities Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Rohit Kumar | Surbhi Khare, Deepa Kale

Abstract

In today’s world, technology is changing almost every second day. This rapidly changing technology offers lots of benefits but also put some great challenges. Smart city is a concept that merges various Information and Communication Technology (ICT) and Internet of Things(IoT) based service solutions, together. Thus, the concept of smart cities uses all possible technologies in the state-of-the-art form. Hence, there is a need to make sure that the no one could use our networks for their own benefits. Malicious users always wait for the perfect opportunities and attack on the most vulnerable part of the network. A strong defense mechanism is needed to defend against them, otherwise the concept of smart cities would only be a chaos. In this paper, we will explain the different types of possible attacks, analyze them and will propose a mechanism to defend against them, based on Honeypot based services.

A Hybrid Approach for Improving Text Document Clustering

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th December 2017

R.Janani | Dr. S.Vijayarani

Abstract

Text document clustering is the process of distributing documents into similar groups called clusters, in order that documents within a cluster have the great affinity in comparison to other documents in different clusters. It has been taken into consideration intensified due to the fact of its substantial applicability in various areas like information retrieval, web mining and search engines like Google. It is determining the similarity among documents and based on the similarity it will organize the documents together. Fast and greatness of text document clustering algorithms perform a vital role in dramatically navigating, encapsulating, and establishing the information. The clustering algorithms can only generate the optimal solution. A globally optimal solution can be attained by applying high-geared and high-quality optimization. The main objective of this research work is to group the documents based on their contents and also to improve the clustering accuracy based on the content of the documents. In order to perform this task this research work uses the existing algorithms DBSCAN and PSO. A hybrid algorithm which is a combination of PSO and DBSCAN algorithm is also proposed. The outcome of this research work is the identification of the cluster of documents which has the same contents.

A Hybrid Image Binarization Technique for Enhancement of Degraded Document Images

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th October 2017

Dr. S.Vijayarani | M.Geetha

Abstract

Image processing is a process of analysis and manipulation of digital images, which improves the quality of an image. Image binarization is a pre-processing step which improves the quality of the image. Image binarization is used to improve the image quality and it segment the pixel values into two categories; i.e. black pixel as foreground and white pixel as background. In this research work, binarization techniques are applied to improve the quality of the degraded document images. Different types of image binarization methods used in this work are Otsu, Nick, Niblack and Sauvola. In addition to this, a new hybrid binarization method is proposed which is a combination of local and global method. Performance factors used are PSNR (Peak Signal to Noise Ratio) and NRM (Negative Rate Metric). From the results, it is observed that the proposed hybrid binarization has produced good results than existing methods.

A Hybrid Intrusion Detection System Using KMeans Clustering and J48 Classification

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th April 2018

Navita Datta | 

Abstract

This paper is based on a hybrid intrusion detection system by using integrating K-means clustering and J48 classification. Firstly, the features are selected using correlation based feature selection, so that the number of attributes participating in detection of attacks can only be taken into concern and then it reduces the dimensionality of the attributes using Principal Component and Analysis. This algorithm works on the NSL-KDD dataset which is an improved version of the previously used KDD CUP’99 Dataset. Then we apply K-Means clustering over the obtained attributes and lastly we apply J48 classification for its evaluation. The proposed work has been fulfilled with an increase in accuracy and decrease in False Positive Rate

A Hybrid Technique to Perform Retinal Vessel Enhancement by Contrast Correction and Morphological Operations for Segmentation

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th January 2018

Mishal Bansal | Navdeep Singh

Abstract

Diabetic Retinopathy is a disease which affects the eyes and may cause vision loss. It can be detected by analyzing the vessels of a retinal vessel. In this paper, we present a blood vessel enhancement and segmentation approach, which is used for analysis of blood vessels. Contrast correction and mathematical morphological operations are used to enhance the blood vessels and then segmentation is performed. The proposed approach is tested on DRIVE dataset and it achieves an average accuracy of 95.40%.

A Implementation on Predictive Analytics for Banking Issues using Mining Technique Algorithms

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2018

Shahina Farheen | Manika Manerkar, Trupti Payal, Dr. K. Vikram

Abstract

Nowadays, there are many risks related to bank loans, health loan, car loan, for the bank and for those who get the loans. The analysis of risk in bank loans need understanding what is the meaning of risk. In addition, the number of transactions in banking sector is rapidly growing and huge data volumes are available which represent the customers behavior and the risks around loan are increased. Data Mining is one of the most motivating and vital area of research with the aim of extracting information from tremendous amount of accumulated data sets. In this paper a new model for classifying loan in banking sector by using data mining. The model has been built using data form banking sector to predict the status of loans particular user if they want. Here we find out the interested user who are want the service form the banking only those user meet them and discuss them without wasting time, money, man power

A Keyword based Scheme to depict organizing standard research as a field and its part

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th February 2018

G.Sumalatha | S.Swapna

Abstract

Over the most recent three decades, designing instruction explore (EER) has gained noteworthy ground towards a field of interdisciplinary grant. This paper characterizes EER by building up a watchword based plan for investigating EER- related logical distributions and coordinated effort. The catchphrase based plan alludes to a theoretical structure we have created for producing a stingy rundown of watchwords which are remarkable in EER. The produced watchwords were utilized to gather bibliographic records from ISI Web of Science® (WoS), a reference list giving access to the world's driving reference databases and diaries. To play out a far reaching look for EER-related writing by utilizing the scope of truncation rules and the propelled seek choices accessible in WoS, the venture influences following commitments to the flow information to base on interdisciplinary research in EE: (1) building training research is operationalized as a modern and deliberately determined an arrangement of catchphrases and (2) the strategy for the ebb and flow study may fill in as a noteworthy advance towards quantitative examination of the new logical field.

A Lightweight Secure Data Sharing Scheme for Mobile Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

R.Gokula Priya | Unnimaya P Madhu, M.Yuvashree, M.Karthikeyan

Abstract

With the popularity of cloud computing, mobile devices can store/retrieve personal data from anywhere at any time. Consequently, the data security problem in mobile cloud becomes more and more severe and prevents further development of mobile cloud. There are substantial studies that have been conducted to improve the cloud security. However, most of them are not applicable for mobile cloud since mobile devices only have limited computing resources and power. Solutions with low computational overhead are in great need for mobile cloud applications. In this paper, we propose a lightweight data sharing scheme (LDSS) for mobile cloud computing. It adopts CP-ABE, an access control technology used in normal cloud environment, but changes the structure of access control tree to make it suitable for mobile cloud environments. LDSS moves a large portion of the computational intensive access control tree transformation in CP-ABE from mobile devices to external proxy servers. Furthermore, to reduce the user revocation cost, it introduces attribute description fields to implement lazy-revocation, which is a thorny issue in program based CP-ABE systems. The experimental results show that LDSS can effectively reduce the overhead on the mobile device side when users are sharing data in mobile cloud environments

A Lightweight Secure knowledge Sharing theme for Mobile Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

D. Bhanu Pratap | CH.D. Sunil Kumar, K.Dumas Sam, P.Goutham, A.Raghavulu

Abstract

With the recognition of cloud computing, mobile devices will store/retrieve personal knowledge from anyplace at any time. Consequently, the information security drawback in mobile cloud becomes additional and additional severe and prevents additional development of mobile cloud. There square measure substantial studies that are conducted to enhance the cloud security. However, most of them don't seem to be applicable for mobile cloud since mobile devices solely have restricted computing resources and power. Solutions with low process overhead square measure in nice want for mobile cloud applications. during this paper, we tend to propose a light-weight knowledge sharing theme (LDSS) for mobile cloud computing. It adopts CP-ABE, AN access management technology employed in traditional cloud surroundings, however changes the structure of access management tree to create it appropriate for mobile cloud environments. LDSS moves an outsized portion of the process intensive access management tree transformation in CP-ABE from mobile devices to external proxy servers. what is more, to cut back the user revocation value, it introduces attribute description fields to implement lazy-revocation, that could be a thorny issue in program based mostly CP-ABE systems. The experimental results show that LDSS will effectively cut back the overhead on the mobile device aspect once users square measure sharing knowledge in mobile cloud environments.

A Literature Review on the Framework of Camouflage of RIT with RDH Methods for Plain Text Images towards Better Outsourcing

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

S.Tamilselvi | R.Sasikala

Abstract

Nowadays there is the very big problem of data hacking into the networking era. There is the number of techniques available to overcome this problem. So, Data hiding is a technique for embedding information into covers such as image, audio, and video files, which can be used for media notation, copyright protection, integrity authentication, covert communication, etc., In this thesis, various existing Data Hiding techniques are studied and reviewed. In this thesis mainly focus on embedding data and restore data with better quality. This thesis discusses Reversible Data Hiding techniques based on Reversible image transformation to embed data and then extract data. The proposed techniques are applied and compared to find which methods are suitable for hiding data into the camouflage image and then losslessly restore the information

A Literature Study on Selenium Webdriver 2.0

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Ms.R. Anitha | 

Abstract

Selenium is a open source automated testing suite for web applications across different web browsers and platforms. It is similar to HP Quick Test Pro but the Selenium focuses on automating web-based applications. The testing is done by using selenium is called selenium testing. This paper studies on selenium Webdriver 2.0 which uses mozilla firefox browser and how it is implemented by using Eclipse IDE. WebDriver calls the Web browser directly and all the test script is executed similarly to make the automation.

A Map Reduce Methodology based Novel Parallel Particle Swarm Optimization Clustering Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 24th November 2017

G.Akhilesh | 

Abstract

Over the most recent couple of decades overseeing huge information has turned out to be testing assignment on account of the expanding volume and many-sided quality of the information being made or gathered. The issue here is the means by which to viably oversee and investigate the information and coming about data. The arrangement requires an extensive approach that contains every one of the phases from the underlying information accumulation to its last analysis..Traditional grouping methods don't address every one of the prerequisites satisfactorily. The new methods need to make utilization of practically equivalent to registering ideas keeping in mind the end goal to have the capacity to scale with rising informational collection sizes. In this paper, we suggest a parallel molecule swarm streamlining bunching (MRCPSO) calculation that depends on MapReduce. The test comes about demonstrates The proposed framework is versatile in preparing extensive information on item equipment. Expanding informational collection sizes and accomplishes a near the direct speedup while keeping up the grouping quality.

A measure of Temporal Contextual Information on Trust based Recommender Systems

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

Ankur Chaturevdi | Dilip Kumar Sharma

Abstract

In an era of information age, recommender system helps users to make an effective decision. Collaborative filtering is one of the techniques to provide a personalized recommendation to users. Collaborative filtering based recommender technique provides the recommendation by aggregating ratings from similar users to predict ratings for an active user (who wants a recommendation). The similarity has a greater impact because it acts as a criterion to identify a group of similar users whose ratings will be merged to generate a recommendation for the new item for an active user. However, there are a lot of issues in Collaborative filtering for e.g. data sparsity and cold start, which can be removed by incorporating trust information. We propose a methodology to include temporal context information in providing accurate rating prediction along with Trust matrix and also propose a framework to analyze the performance of Trust-based recommender algorithms on Film Trust dataset which includes temporal context information.

A Metamorphosis Approach to Software Engineering

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th December 2017

M.Rithvik | Merugu Naresh Babu, Ch.Ambedkhar, Narala Sudhakar Reddy, Puli Nageswara Rao

Abstract

The most important industry that is going to play a key role nowadays is the software industry because it’s the only industry which has high return values.For any industry to have a good survival application plays a key role because an industry growth can be estimated by its outcomes those are nothing but products and services. Software Engineering is the subject that deals with various methodologies in order to ensemble software. This Paper represents a metamorphosis approach to software because when we perform Engineering we also need to know about reengineering sometimes many interventions may come up with reengineering process.Here we represent such type of reengineering approach with the help of a demo application.

A model-based scheduling approach for selection of Real-Time Scheduling Algorithm on basis of Different Parameters

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th March 2018

Ajitesh Kumar | Mona Kumari, S.K.Gupta

Abstract

In Modern days, the real-time system plays an important role in our modern and digital society. The success of any real-time application totally depends upon the selection of optimal scheduling algorithm. In real time application, every task should have the nature of deadlines and time when they arrived, on the basis of these parameters we observe the response time of different scheduling algorithm then we select the optimal algorithm for a particular application. So in this paper, our aim is to reduce the complexity of real-time system researcher for selection of scheduling algorithm for a particular application. This model-based approach is an extent the state of any real-time system in the area of scheduling. This approach works in any uniprocessor system

A Modernization Approach to Software Engineering

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th August 2017

K.Nirmal Raju | Ch.Sowjanya, N.Susmitha,Ch.Ambedkar,M.Rithvik

Abstract

The Technology is rapidly growing day by day. In this regard the utility of software also is rapidly increasing day by day in many forms like ROBOTICS,ARTIFICIAL INTELLIGENCE,MACHINE LEARNING etc .The tools used in this software are also increased which we call it as an automation that is going to play a key role in the software industry replacing some persons with that particular tool may result in increase of productivity of the company as well as in attaining a reliable product .This paper communicates a meaningful tool that is available at a free of cost to use for a layman to build up a software on his own .This paper entirely presents the communication between a layman and that tool its name is CONSTRUCT2D.Along with the middleware application. The central idea of the paper deals with the scenario of SOFTWARE INDUSTRY,A Start UP.

A Modified Algorithm for finding Representative Pattern Sets

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

R.Prabamanieswari | D.S.Mahendran, T.C. Raja Kumar

Abstract

Many algorithms and techniques are developed for enumerating itemsets from transactional databases. They produce a large number of frequent itemsets when the minimum support threshold is low and /or the dataset is dense. A large number of discovered patterns makes further analysis of generated patterns troublesome. Therefore, it is important to find a small number of representative patterns to best approximate all other patterns. This paper modifies the algorithm MinRPset for finding representative pattern sets. It follows the same concepts such as - covered and greedy method in MinRPset but, it uses NCFP-tree instead of CFP-tree for storing frequent itemsets in a compressed manner. The experiment results show that our algorithm gives better execution time to generate representative patterns sets for the mushroom dataset in an efficient manner comparing to the algorithm MinRPset

A Multi-Authority Access Control System in Cloud Computing Using Network Security

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Ms. Vibhute Shubhangi Prakash | Prof. Mr. Kale Navnath D.

Abstract

Data access control is an efficient way to provide the data security in the cloud.and Attribute-based Encryption (ABE) technique cryptographic conducting tool to guarantee data owners direct control on their data in public cloud storage. In this paper, from another point of view, system lead an edge multi-power CP-ABE access control plan for open distributed storage, named TMACS. In TMACS, exploiting (t; n) limit mystery sharing, When system verify to the user the TTP work like a SDN. Its having data controller that can evaluate the each request base on ad-hoc data table, if user is authenticated system can provide the access to specific user. Besides, by proficiently joining the customary multi-power plan with system, system build a half and half one, which fulfils the situation of traits originating from various powers and accomplishing security and framework level strength. The network security mechanism also fulfil with this approach, the system has evaluate on physical network environment with 2 to 4 physical devices and got satisfactory results than existing TMACS

A Multi-Gating Security Framework to Prevent Tailgating Attack of the Host Agent Platform in a Mobile Agent System

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th April 2018

Aboloko .S. Oberoro | S.A. Idowu, Y.A Adekunle, O.D.Alao

Abstract

Mobile agents can be described as programs that perform a given task on behalf of its owner. The growing need for Mobile Agent Technology (MAT) has been accompanied by corresponding issues like security and ethics. These challenges have resulted in global cold-feet towards mobile agent technology. The fundamental security issues in a mobile agent system are masquerading, denial of service, eavesdropping, alteration, repudiation and tailgating. Various models and techniques to detect and prevent these attacks, especially the host agent platform, have been proposed and implemented. However, most of these existing studies on the host agent platform dwelt mainly on authorized access security issues. An unauthorized social engineering security issue like tailgating attack is yet to be given the deserved consideration. This study developed a Multi gating Security The framework that detects and prevents a tailgating attack of the host agent platform in a mobile agent system.

A New Approach for Secure Traffic Data Analytics using Hadoop

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th November 2017

Phani Raja.I | 

Abstract

Nowadays traffic congestion is an extreme difficulty. Traffic congestion is most predominant in metro towns. There are distinct reasons for traffic congestion such as growing population, rising earning main to greater automobiles on the road, the inadequate capability of roads to address traffic and so on. A cluster of garage devices is wanted to save such big amounts of data and also a parallel computing version for studying the ones huge inputs of data. Hadoop is one such framework that gives the reliable cluster of storage facility, which stores huge statistics in an allotted way using a unique report machine, known as Hadoop Distributed File System and presents efficient parallel processing feature through MapReduce framework. Using Map Reduce the filtered traffic data may be fetched without problems, to offer quit user with traffic analysis and giving beneficial predictions.

A New Approach to Fuzzy Bitopological Space via γ-Open Sets

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Birojit Das | Baby Bhattacharya

Abstract

B. C. Tripathy and S. Debnath [B. C. Tripathy, S. Debnath, -Open Sets and -Continuous Mappings in Fuzzy Bitopological Spaces, J. of Intelligence and Fuzzy Systems, 24, 631-635 (2013)] first introduced the concept of fuzzy -open set in a fuzzy bitopological space to show that the collection of all these sets forms a fuzzy topology and also studied fuzzy pairwise - continuity. In this present treatise, we redefine this set as fuzzy -open set with the help of fuzzy preopen set to show that it is completely independent from fuzzy open set. Moreover, we introduce fuzzy -generalized closed set as a generalization of fuzzy closed set and then we establish various properties and characterizations along with interrelationship among them. Also, we show an important result which states that though every fuzzy closed set is a fuzzy generalized closed set and fuzzy -generalized closed set but fuzzy generalized closed set and fuzzy -generalized closed set are totally independent of each other. Furthermore, we introduce the notion of fuzzy continuous function, continuous function, fuzzy -continuous function and - continuous function in a fuzzy bitopological space and study those functions with various properties and interrelationships. Lastly, we define a new type of closure operator and prove certain results based on this conception.

A new approach to secure internet of things(IoT) devices using encryption and anonymity capabilities of The Onion Router (TOR)

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th December 2017

Skanda Kumar.B | Nandan goud.B

Abstract

A new revolution of the Internet is the Internet of things (IoT) where various devices and systems are connected to leverage data anywhere, anytime that is expected to spread rapidly, over the coming years.it is estimated that IOT is beneficial for smart home devices as nearly 40 billion connected devices are expected to be in use by 2020 but the biggest problem with such it devices is with limited functionalities is the security. Securing communications between devices and their back-end systems is one of the most severe problems. In some specific IoT cases, VPN can handle the secure connection, but VPN is not always possible. Hence there Is an immediate need for better technologies and innovative methods through which the hot network security can be greatly enhanced by using The Onion Router(TOR )By default, all traffic in the Tor network is encrypted and the identities and locations of traffic sources are very effectively concealed. Thanks to this, someone intercepting traffic from Tor networks is neither able to identify the sender nor view or alter the messages. These features would be useful when securing an IoT system. Tor network is commonly considered only something which is criminal. in this paper the author is trying to look TOR objectively which is perfectly legal and show its positives uses like securing IoT devices preventing any future catastrophic large-scale cyber attacks.

A New Incremental Mining of Frequent Item Set On Large Unstructured Dataset

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

G.K.Sharmila | Dr. T. Hanumantha Reddy

Abstract

The information present in the unstructured dataset are often inaccurate in nature.In this paper we examine the problem of preserving the mining result for a dataset that is changing by pushing a new tuple into the dataset. The problem is technically difficult because an uncertain[14] dataset contains an exponential number of possible worlds. To overcome this problem we proposed a KNN (k-nearest neighbor) algorithm to get the content of each review.Here we need to apply k-value based on that display the review with the classification. All our approaches support both tuple and attribute uncertainty, which are two common uncertain data set models.

A New Optimization Technique for Performance and Energy Preservation In Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Javed Hussain | Durgesh Kumar Mishra

Abstract

The rapid growth of the computational requirement need to develop effective and efficient technologies for serving better. In various research domains in computational cloud the security, resource utilization and energy preservation are the main area of research and development. In this paper we are going to discuss the capability of optimization algorithm for scheduling the resources and allocating the virtual machines for improving the performance and energy efficiency of the computational cloud. Therefore the detailed discussion on the required objectives and the solution formulation is provided. In further the simulation technique of the proposed model and their results are also reported for analysis. According to the gain performance and experimental observations the proposed technique is suitable for both the kinds of resource scheduling and optimization.

A New Situational Based Security Model in Offline Distributed Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th December 2017

Dr. Cuddapah Anitha | Prof.M.Padmavathamma

Abstract

As we are aware that software can easily be copied or moved from one system to another by any means, software developers define various measures for protecting their products from unauthorized usage. This has become a major challenge in the software industry and for the developers of the software products in protecting their intellectual property rights. To overcome the hazards associated with these problems, this paper presents a mechanism called Node Lock Licensing Methodology and its variants to safeguard the software product or sensitive information from unauthorized disclosure thereby defining certain access permissions on the product.

A New Technique for Secured Authentication with Pc Control through SMS

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

Birundha.K | Harini.S, Hemalatha.G, Kalaiselvi. P, A.V.Santhosh Babu

Abstract

Short message service (SMS) is a technology that can use mobile devices to send and receive text message, with wide coverage area, high popularity, high reliability, low expenditure, easy development and other characteristics. Using GSM modem or short message platform of network, short messages can be send and receive between the computer and the mobile terminal. PC can be secured by using GSM without internet.Any user trying to misbehave in the system, then the application will send alert message to the administrator’s mobile, then the administrator can shut down the system from any remote location through his mobile by sending a SMS

A Novel Approach for Identification of Hadoop Cloud environment

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th November 2017

Swathi Agarwal | 

Abstract

Because of the advanced propensities inside the teaching of science and innovation brought about the trends of the viable data switch, the capacity of dealing with colossal data and the recovery of information effectively. On account that the data that is spared is expanding voluminously, strategies to retrieve relative comprehension and assurance associated concerns are to be tended to viable to quiet this bulk information. Moreover, with rising benchmarks of mammoth information, these security issues are a testing undertaking. This paper addresses the constraint of agreeable information switch utilizing the principles of learning mining in cloud condition making use of Hadoop MapReduce. In light of the experimentation, achievedoutcome are examined and spoken to with perceiving to time and space unpredictability when thought about Hadoop with non Hadoop approach

A Novel Approach For Image Security

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Jyoti T. G. Kankonkar | Nitesh Naik

Abstract

Image security is a major concern as the digital communication and digital data is growing rapidly. Image data is generated in loads every day. We need faster and robust mechanisms to secure the image data. Various fields such as military scopes, security firms, social network etc. need systems that can protect the images while communicating and data transfers. In this paper the proposed idea involves use of image encryption using chaotic approach with a combination of image stitching mechanism. This unique combination provides double layered protection to the images. In order to transfer an image, the image is first partitioned, encrypted and then transferred making it difficult for attackers to access the whole image. On the other end, the encrypted image is decrypted using a symmetric key generated using chaotic approach that uses logistic map function and linear feedback shift register which is followed by image stitching procedure..

A Novel Approach for Smart Hydroponic Farming Using IoT

International Journal of Engineering Research in Computer Science and Engineering, Available online 25th May 2018

R.Rajkumar | R.Dharmaraj

Abstract

The effects of the global warming make more difficult for planting in uncontrolled environment. In traditional farming method, farmers require fine quality of soil with natural mineral strengths. It also requires working cost for ploughing and removal of weeds and also needs large amount of space and water. In case of seasonal plants, the yield does not satisfy the customer needs and the expectation of farmers in productivity. For these reasons, a farming method which needs lesser requirements in cost factor and also it easy to maintain and control the important factors such as light, water level temperature, and humidity throughout the year is needed. This proposed work presents a Hydroponic style of farming which is the method of growing plants without soil & sunlight. In this method the plants are grown with only their roots exposed to the mixture of ash fertilizer with water instead of underground soil. This method is a type of indoor agriculture style which is independent of weather, and it also avoids the cost of ploughing and labour works. Watering and controlling of humidity is done with the help of a microcontroller Kit connected to Wireless sensor network with internet which senses the humidity, temperature and water level. With the help of this IoT technology, the real time status of plant’s growth could be monitored by the authorized person from remote location. This technology helps efficiently for the agricultural development with minimum resource utilization.

A Novel Approach to Control Speed of an Automobile

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th October 2017

Dr.Manoj Priyatham M | Aishwarya. B, Aishwarya. K, Lakshmi Mache, Likitha. A

Abstract

Speed Control of automobiles is very much required in our daily life due to the increased rate of accidents reported. Hence, there is a need of a novel approach by which vehicles speed can be automatically controlled. This paper presents a novel approach to control the speed of the automobiles at remote places for fixed time. In this approach, automobile throttle position is controlled not only by Control Unit [CU] also accordingly to one of the inputs received from the accelerator pedal position sensor, but also by a microcontroller unit which receives the pedal position from the sensor and then microcontroller unit transfer to the CU. The Microcontroller Unit also interfaced is capable of detecting any other trans receiver. Threshold level is set to the pedal sensor which alerts the system by a buzzer sound, when the speed of automobile exceeds the pre-determined value. The microcontroller controls the speed accordingly at desired places. When we deploy, the transmitter sense data frames with field containing maximum speed and time.

A Novel Approach to Street Light Automation

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th October 2017

Dr. Manoj Priyatham M | B.R.Pallavi, Shruthi A.S, Pallavi R

Abstract

Sometimes street lights will be ON even if it is day time, power wastage takes place due to continuous lightening of street light. So, the concept of Automatic Street light system can be introduced which will save our natural resources and is also a powerful technique .In this paper, we propose a design which consists of microcontroller with intensity regulator in it. Here, light can be sensed by LDR (or) by solar panel, we have proposed two sensors LDR and photoelectric sensor (PES) which recognizes the movement of street. Whereas, LDR senses the light. Here PICmicrocontroller is used .This system is totally automatic which turns ON when sunlight goes down and turns OFF during daytime. So maximum power will be saved.

A Novel Approach to Student Information Broadcasting via GSM Network

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Mr. Ankit Pande | Mr. ShubhamKakade ,Mr. Kushal V. Kothari, Mr. Akshit Wankhede , Dr.NitaThakre

Abstract

Broadcasting of Student information via GSM Network is a modern approach to send the academic information to the parents in regular manner. This will be helpful for parents to receive on demand service of information regarding daily progress of student like Attendance, exam forms, Examination marks, Event in college, Placement related Info, Fees information etc. As the information world is changing into digital, it is important to transform the information stored in colleges in traditional manner into digital manner. As the information stored into digital manner will be available at 24*7. GSM network is one of the low cost technologies which is helpful to broadcast the information stored in central database in rapidly.

A Novel Attribute Based Data Sharing With Attribute Weights in Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th January 2018

V.Geetha | V.Sridhar Reddy

Abstract

Data sharing scheme by using attribute-based to reduce the key escrow issue but also develops the expressiveness of attribute, because of that the resulting scheme is more user-friendly to cloud computing. In this proposed work we are introducing an improved two-party key issuing protocol that can guarantee that neither key authority nor cloud service operator can compromise the whole secret key of a user individually. We introduce the concept of the attribute with weight, being provided to enhance the expression of the attribute, which can not only extend the expression from binary to the arbitrary state but also lighten the complexity of access policy. So that, both storage cost and encryption complexities for a ciphertext are relieved. In our proposed work the modification process is after the data owner sends the secret key to the user, the particular cloud user can view the data which is stored on the cloud server. Once the user used that secret key means the key will be automatically changed for that shared data, this dynamic key will be sent to the data owner also.

A Novel Authentication and Key Agreement Scheme for Implantable Medical Devices Deployment

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

R.Poornimadevi | P.Valvarasi, M.Ambika, A.K.Punitha

Abstract

Implantable medical devices (IMDs) are man-made devices, which can be implanted in the human body to improve the functioning of various organs. The IMDs monitor and treat physiological condition of the human being (for example, monitoring of blood glucose level by insulin pump). The advancement of information and communication technology (ICT) enhances the communication capabilities of IMDs. In healthcare applications, after mutual authentication, a user (for example, doctor) can access the health data from the IMDs implanted in a patient’s body. However, in this kind of communication environment, there are always security and privacy issues such as leakage of health data and malfunctioning of IMDs by an unauthorized access. We propose a new secure remote user authentication scheme for IMDs communication environment to overcome security and privacy issues in existing schemes. We provide the formal security verification using the widely-accepted Automated Validation of Internet Security Protocols and Applications (AVISPA) tool. We also provide the informal security analysis of the proposed scheme. The formal security verification and informal security analysis prove that proposed scheme is secure against known attacks

A Novel Framework for Context Based Focused Search Engine

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th May 2018

Dr.K.Vaishali | 

Abstract

Context based Focused search engine is the information retrieval tool that narrows the search space by finding the documents relevant to user query only. The objective of a focused search engine is to return more specific results in response to a user query rather than large number of results. In this paper, the architecture for such a focused search engine has been proposed that works on the basis of the context of web pages and serve the user with contextually more related web pages semantically.

A Novel Framework for Traffic Flow Prediction with Deep Learning Algorithms

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

S.Narmadha | Dr.V.Vijayakumar

Abstract

Traffic flow prediction is the process of predicting future traffic conditions in short-term or long term basis, based on real time and the past traffic data. It is an important component of an Intelligent Transportation System (ITS) in smart city development. Apart from traffic data from sensors, Incidents detection, Lane closure and Weather data also some of the main reasons to cause the congestion. Combine factors and provide an efficient prediction of congestion. It provides innovative and smarter services to the transport users. Deep learning is a promising technology used to predict the traffic congestion with high accuracy. Deep belief network, Recurrent neural network, Convolutional neural network are some of the well known existing algorithms used in transportation analysis. In this paper a novel framework is proposed for intelligent transport systems which can solve so many issues such as pollution, accidents, and unwanted delays.

A Novel Low-Power Reversible Vedic Multiplier

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th April 2018

P.Kiran Kumar | E.Padmaja

Abstract

In reversible computing, modelling low-power circuits is one of the most important technique. As a result of its wide range of applications, major works have been proposed in realizing reversible circuits including primary reversible gates and adders. In reversible computation, multiplier circuits play a vital role in practical applications like quantum dot cellular automata, DNA computing, nanotechnology and low-power CMOS designs. Hence superior multiplier architectures are bound to increase the efficiency of the system. The Vedic multiplier is one such optimistic solution. Implementing this with reversible logic further decreases power dissipation. In this paper, a novel reversible Vedic multiplier is proposed by making use of an algorithm or sutra called Urdhva Tiryagbhyam meaning vertical & crosswise. The power dissipation of proposed reversible multiplier design is reduced by 72.47 %. The reduction in power dissipation is highly achieved by reducing the number of gates which comprise reduction of 12.5 %. The constant inputs are reduced by 16.5 % and a reduction of 28 % is obtained in garbage outputs.

A Novel Structure of the Data Objects in Data Aware Networking

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2018

M. Ravi Kumar | V. Sujatha Lakshmi, Y.K Sundara Krishna

Abstract

Innovative progressions in technologies, in particular, the proliferating smart livelihood systems provoking a gigantic data hardship on the networks these days. The proclamation of brand new technologies every day might significantly demand a thumping data to be disseminated around, which causes the existing networks awkward to handle it copiously. In order to address such impediments and to instigate diverse services to be flourished in the prospective networks, the ITU-T recommended a state-ofthe- art network paradigm, known to be as the Data Aware Networking (DAN). This recent approach structures its data in the form of data objects that lets the users have a quick name-based identification and retrieval of the desired data nevertheless of its location, which significantly curtails the burden on the networks and also greatly reduce the blockades in today’s host centric networks. In this paper, we classified the data objects into various categories and proposed a novel structure for the data objects that empowers the DANs intermediary elements to identify a requested data object, process it accordingly in order to disseminate the same to its requester possibly from a nearest DAN element. This novel approach makes the DAN an imperative architecture to realize the future networks

A Novel Structure of the Data Objects in Data Aware Networking

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd April 2018

M. Ravi Kumar | V.Sujatha Lakshmi, Y.K Sundara Krishna

Abstract

Innovative progressions in technologies, in particular, the proliferating smart livelihood systems provoking a gigantic data hardship on the networks these days. The proclamation of brand new technologies every day might significantly demand a thumping data to be disseminated around, which causes the existing networks awkward to handle it copiously. In order to address such impediments and to instigate diverse services to be flourished in the prospective networks, the ITU-T recommended a state-of-the-art network paradigm, known to be as the Data Aware Networking (DAN). This recent approach structures its data in the form of data objects that lets the users have a quick name-based identification and retrieval of the desired data nevertheless of its location, which significantly curtails the burden on the networks and also greatly reduce the blockades in today’s host centric networks. In this paper, we classified the data objects into various categories and proposed a novel structure for the data objects that empowers the DANs intermediary elements to identify a requested data object, process it accordingly in order to disseminate the same to its requester possibly from a nearest DAN element. This novel approach makes the DAN an imperative architecture to realize the future networks.

A Novel Study on Pre-copy Method for Classification of Live Migration of Virtual Machines in Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th March 2018

Minal Patel | 

Abstract

Cloud computing is the framework of recent technology and it can set the vision of computing utilities into a reality. The most promising part of cloud computing is that it provides dynamic provisioning and delivers facility for computation, networking, storage etc using datacenters. The working of cloud resources provided through the Internet and it gives services on a pay-per-use basis from different cloud vendors. IaaS services used to develop background processing, PaaS provides programming platforms for developing applications and SaaS provides benefit to cloud users from the elastic scalability without making processes such as software development, installation, configuration, maintenance etc. The migration of a virtual machine has advantages such as increasing energy efficiency, resource sharing and load balancing, fault resilience etc. The pre-copy algorithm of Xen hypervisor is very well known and it is also used in real applications to run migration activities. The migration is categorized into three major types to improve pre-copy: i) compressing memory pages ii) predicting dirty pages iii) reducing dirty pages (performance modelling). Each category has its own importance for the live migration. At first, the compression model is proposed to achieve efficient virtual machine migration. Time series based techniques are developed using historical analysis of past data in the second category. The time series is generated with consecutive iterations of memory pages. Here, two different regression-based models of time series are proposed. In the third category, the performance modelling of live migration is proposed by the measured approach. These models are evaluated for measuring the computation of virtual machine (VM) downtime, the total number of pages transferred and total migration time

A Novel Text Detection Technique Based On Corner Response

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

Nishant Singh | Charul Bhatnagar

Abstract

Data about the text incorporated in pictures and videos have a cardinal role in semantic assessments. In this paper, Novel text Detection and Localization (NTDL) algorithm is presented for text detection and localization in the background that incorporates noise in it. This algorithm is constituted by corner response. In contrast to the portions that do not contain text, there are some edges that are dense and corners in portions having text. So, some related strong reactions from regions of text and minimal reactions from portions that do not have text. These reactions furnish some cues that are highly useful for text detection and localization of pictures. By employing a basic schema constituted on the threshold, we obtain regions of candidates for text. These portions are evaluated by interlinking several characteristics like size and colour of linked devices. Lastly, the text line is identified exactly by the projection of response from corners. The outcomes from illustrations present exactness, speed and recalling for suggested methodology and we have obtained the recall of 93.25%, accuracy 97.96% and speed of 98.14% that greatly enhanced the performance of the system.

A Pattern Prediction on Electricity Consumption using Hidden Markov Model

International Journal of Engineering Research in Computer Science and Engineering, Available online 28th March 2018

Dr. Kishore Kumar Senapati | 

Abstract

The present era is the digital era and digital technologies are many impacts on human life as well as societies. Starting from Smart city design to social networking peoples are now using digital technologies. As the use of technologies grows the demand for its source that is electricity grows. Predication of electricity demand is a crucial problem and providing a solution through statistical rules is a big challenge. Present day Electricity demand pattern is considered to play a crucial role in the modernization of community. So, forecasting of household energy consumption precisely is essential due to the fluctuating demand –response of energy. It is also considered very significant for energy planning, development mechanism and economic success. In this paper, Statistical technique model is used to predict future consumption demand of electrical consumption rate. The prediction with output likely sequence works significantly by the implementation of Hidden Markov Model (HMM) using the Viterbi Algorithm with emphasis is given to forecasting future energy consumption demand where data pattern changes monthly and shows non-linear trends. This paper uses an extensive data sample of author’s working university database. The final forecasted outcome is tested and compared with actual data. Experimental results show an aggregate of 0.0366 error rate showing non–linear trends of household electricity consumption with respect to factors concerning such as population, climatic conditions and financial strength. The prediction model based on the small-scale fraction of households summarizing for most likely aggregate consumption response. The proposed model helps in recognizing future electricity consumption pattern which will be used in smart city design and provide a solution for electrification of urban and rural as well as any planning in government and non-government organizations for electricity consumption.

A Personalized Web Search for Relevant Web Pages: A Survey

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd May 2018

Arati Anilrao Wardekar | Poonam Gupta

Abstract

Due to heavy usage of internet large amount of diverse data is spread over it which provides access to particular data or to search most relevant data. It is very challenging for search engine to retrieve required data as per user’s need and which takes more time. So, to reduce large amount of time spend on searching most relevant data we proposed the “Smartcrawler”. In this proposed approach, results taken from different web search engines to achieve relevant pages. Take online link from web and performing two stages crawling on that data or URL’s. In which sight locating and in-site exploring is carried out or obtaining most relevant site with the help of page ranking and reverse searching techniques. This system can works online and offline manner. This survey presents the fundamental challenges and studies existing models and solutions. It also highlights direction or way for future work.

A Preliminary Study about an emerging approach in Cryptography: Quantum Cryptography

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

Poornachander V | 

Abstract

The word cryptography is the artwork of mystery writing. Generally, humans consider cryptography because the art of mangling data into obvious unintelligibility in a way permitting a secret technique of untangling. The fundamental provider supplied by cryptography is the potential to send data among members in a manner that others can’t read in a right format. Here we will give attention to the sort of cryptography this is based on representing information as numbers and mathematically manipulating those numbers. And we have various encryption techniques to send data in a cryptographic manner. Here we have an emerging technology for this new era called Quantum cryptography. The first-rate and famous instance of quantum cryptography is the quantum key distribution which gives an information-theoretically comfy method to the important thing change trouble. Presently used famous public-key encryption and signature schemes may be damaged by using quantum adversaries. The benefit of quantum cryptography lies in the truth that it permits the completion of diverse cryptographic responsibilities which can be established or conjectured to be not possible the usage of simplest classical (i.e. non-quantum) verbal exchange. This paper deals with the detailed technology about Quantum Cryptography

A Privacy-Preserving Data-Sharing Framework for Smart Grid

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th April 2018

SK.Dayeen Sidhika | Dr.P.Venkateswara Rao, S.Yamini, T.Hemalatha

Abstract

Distributed energy resources (ERs), featured with small-scale power generation technologies and renewable energy sources, are considered as necessary supplements for smart grid. To ensure that merged resources contribute effectively to the grid, data generated by consumer side should be shared among the ERs. However, it also introduces challenges of the protection of consumer privacy. To address these difficulties, we propose a new framework to share data in smart grid by leveraging new advances in homomorphic encryption and proxyre-encryption. Our proposed framework allows ERs to analyze consumer data while ensuring consumer privacy. An additional benefit of our proposed framework is that consumer data is transmitted over the smart grid only once. Furthermore, we present a concrete scheme falling into the proposed framework. Extensive analysis shows that the concrete scheme is secure and efficient.

A Process for Implementation of Data Preprocessing In Weka & Datapreparator Tool

International Journal of Engineering Research in Computer Science and Engineering, Available online 24th March 2018

Vani .N  | Dr. Veeragangadhar Swamy .T.M

Abstract

Data Preprocessing is an important task in today technology to convert raw data into a knowledgeable format from web log file which helps identify individual user and session, path completion and removes inconsistent data, noisy data and irrelevant data with the help of data cleaning process. We propose tools for data cleaning processes such as Weka and DataPreparator to execute cleaning data which results in an efficient analysis of raw data into useful information and improves quality of data. In this paper, we use Weka and Data Preparator tool for data cleaning, visualization, integration data and produces the needy data for mining

A Proficient Unambiguous Congestion Control Model for High Rate Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th January 2018

Vivek J. Vyas | Dr. Kishor H. Atkotiya

Abstract

The traditional TCP observes after a destitute performance on high bandwidth intermission creation links projected for associate information broadcast frequency of thousands of Megabits per seconds (Mbps). This is common because of the point of over congestion, the Transmission Control Protocol’s algorithm for controlling drips window of the congestion window to half of the current window size and drives interested in additive increase methodology that might be sluggish for the captivating comfort of immense magnitude of practicable bandwidth. In this paper, we have open a renewed version and to remove the deficiencies of the TCP protocol then remark to take out a knowledge of the alike built on a range of factors that are., Stability, Fairness, Bandwidth Utilization, Performance and Throughput, intended as long as associate information broadcast through the Networks of High Rate.

A Proposal for Epidemic Prediction using Deep Learning

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Sagar Palao | Abhishek Shahasane,Siddhesh Dighe, Harsh Gupta,Anjali Yeole

Abstract

HealthCare has been a surging need in India. The inception of Smart India, Smart Villages has further emphasized the need of a Smart & Healthy India. However little reflection of such digitally empowered country has been seen in the field of healthcare. This has further increased the importance of the definition of ubiquity of information and computing technology in healthcare that demand constant surveillance and vigilance of healthcare to predict epidemic outbreak and biological attack. The paper’s primary focus is to analyze and determine the spread of diseases and epidemic in cities/villages. And using this analysis to predict where the next outbreak of epidemic will be. This prediction helps the health authorities to take necessary action in terms of assuring that sufficient resources are available to suffice the need and if possible stop the occurrence of such epidemic by taking necessary actions. To achieve this, we use deep neural network as the heart of our prediction. It receives its training from the past experiences of data which we have collected from hospitals and our spread network. Using this training with our dynamic data it makes predictions as well as adaptively learns from the real time data.

A Proposed Bring Your Own Device eLearning Framework for Private Secondary Schools in Dubai, UAE

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd March 2018

Manoj Mechankara Varghese | Varughese K. John, Poonsri Vate-U-Lan

Abstract

Objectives This paper aims to study the impact of BYOD implementation on learning outcomes of ninth grade students in the subjects of Science and Mathematics. The target sample size of this study will involve 48 teachers and 1800 ninth grade students from six private schools in Dubai, UAE. Methods/Statistical Analysis The study is based on the principles of quantitative research. The casual comparative study will be based on independent and dependent variable. The examination scores in Science and Mathematics, student age and gender of the 1,800 ninth grade students will be collected as quantitative data for descriptive statistical and comparative analysis using the IBM SPSS software. The two examination scores of the students will be used to determine the level of academic achievement and will become the dependent variables of the study. The information on BYOD Implementation and the level of usage of technology by 48 teachers and 1800 students will be tested by administering a survey questionnaire research instrument to 10 teachers and 50 students who are representative of the larger population of the study. The information collected from the survey questionnaire instruments will become the independent variables for the study. Findings The two major findings of this study were that students' achievement has been significantly improved by the use of BYOD tools and applications with the traditional teaching methods and that students' achievement has been varying significantly in relation to gender as far as BYOD tools and applications are implemented and practiced. The benefits of BYOD on student learning include increased engagement, communication, collaboration, interaction and personalization. The factors that were crucial to effective BYOD implementation include adequate teachers training, a proper BYOD eLearning Framework, the availability of virtual learning environment (VLE's) and the availability of relevant pedagogy based digital curriculum content (DCC). Application/Improvement The research findings of this work will be used to develop a BYOD eLearning Framework for private secondary schools in Dubai which will help school to effectively implement BYOD programs.

A Proposed System on Detecting Stress Based On Social Interactions on Social Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd May 2018

Indu Dokare | Gayatri Pawar, Manisha Mirchandani, Shreya Narsapur, Kajal Rajani

Abstract

Stress is essentially humans' response to various types of desires or threats. This response, when working properly, can help us to stay focussed, energized and intellectually active; but if it is out of proportion, it can certainly be harmful leading to depression, anxiety, hypertension and a host of threatening disorders. Cyberspace is a huge soap box for people to post anything and everything that they experience in their day-to-day lives. Subsequently, it can be used as a very effective tool in determining the stress levels of an individual based on the posts and status updates shared by him/her. This is a proposal for a website which takes the Twitter username of the subject as an input, scans and analyses the subject's profile by performing Sentiment Analysis and gives out results. These results suggest the overall stress levels of the subject and give an overview of his/her mental and emotional state. The tool used for analysis of the social media account is Rapidminer. Rapidminer is an environment for various data mining and machine learning procedures with a very effective and simple GUI.[1]

A Proxy-based Collaboration System to Minimize Content transfer Time and Energy Consumption

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

P. Hruday Kumar | A.Narayana Rao, K.V.Venkatramana, S.S.Phani, P.Kiran

Abstract

Mobile cooperative community (MCC) is associate degree rising technology that enables multiple mobile nodes (MNs) to perform a resource intensive task, lovemassive content transfer, during a cooperative manner. during this paper, we have a tendency to introduce a proxy-based collaboration system for the MCC wherever a content proxy (CProxy) determines the number of chunks and therefore the sharing order scheduled to every MN, and therefore the received chunks area unit shared among MNs via Wi-Fi Direct. we have a tendency to formulate a multi-objective optimisation drawback to attenuate each the cooperative content transfer time and therefore the energy consumption in associate degree MCC, and propose a heuristic algorithmic rule for resolution the optimisation drawback. intensive simulations area unit applied to guage the results of the amount of MNs, the wireless information measure, the content size, and dynamic channel conditions on the content transfer time and therefore the energy consumption. Our results demonstrate that the projected algorithmic rule are able to do near-optimal performance associate degreed considerably cut back the content transfer time and has an energy consumption adore that of alternative algorithms. Index Terms Mobile cooperative community, content transfer, proxy-based collaboration system, _-local search of sharing order (_-LSSO).

A Ranking Based Recommendations System for Web Pages Using Sentiment Analysis and Demographics

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th April 2018

M.Mallikarjuna Rao | Dr.K.Fayaz

Abstract

Nowadays, the quantities of internet business organizations are expanding step by step and likewise immense number of items is coming into the market. At the point when clients need to purchase the items and large simply observe a numerical rating of the items and then buy them. Later they come to realize that items are bad. The present rating frameworks includes collaborative rating, content rating and substance construct rating based with respect to the exchanges of client after the item is acquired. This does not think about the slants communicated on the item not at all like couple of which consider the reviews and perform opinion examination on the reviews yet they don't consider different features conceivable in the item and slant investigation in light of those features. In the paper we exhibit an approach in which the slant investigation will be performed per review and per feature. Likewise the feature based assessment investigation calculation is executed for 3 distinct situations specifically single Feature, Multiple Features and No Feature. For No feature we much consider the calculation of Frequency on every token in the sought question. At last charts are likewise gotten in light of each feature which items are the best. For gathering of reviews the approach considers a disconnected review inside the application and continuous reviews for any sort of online business site by utilizing Web Crawler calculation. The execution influences utilization of most recent innovation to stack to be specific spring system for the backend and Ext JS Framework for the front end

A Recent Survey on Multiclass Object Recognition and Classification based on Machine learning methods

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

Harpreet Singh | Dinesh Gupta, Alok Kumar Singh Kushwaha

Abstract

Multiclass object recognition and classification from the video stream is active research topic in computer vision due to its wide range of application in many emerging areas such as surveillance, medical, safety, vehicle detection. Object recognition and classification task are far more challenging because of image and video data are of heavy and highly variable in nature and harsh nature of real-world recognition and classification scenarios. The processing of image and video data is required to be in real-time. The objective of this paper presents a comprehensive qualitative and quantitative comparative study of several state-of-the-art object recognition and classification methods. We have also examined merits, demerits efficiency of pioneering machine learning methods being used for object recognition and classification.

A Reliable Congestion Control Framework for Wireless Sensor Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th October 2017

P.Prittopaul | R.Vijayalakshmi

Abstract

Well designed congestion control techniques allow efficient transmission of significant volumes of data from a large number of nodes along one or more routes towards the data processing centers. Since the priority of generated traffic in network level is not uniform in WSNs, an architecture framework is proposed based on priority of generated traffics for service identification in network level in order to meet better service quality and efficiency. The proposed method is efficient in terms of end to end delay, throughput, power consumption and lifetime of network.

A Remote User Authentication Operation using CaRP schemes

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th December 2017

Mrs.Sindhu M.R | Mrs.Sarita Patil, Mrs.UrmilaBiradar, Nilesh P Sable

Abstract

Image based password schemes are constructed to authenticate users. Graphical passwords are composed of images and sketches with human memory for visual information. Improved password memorability and strength against guessing attacks are the key benefits of graphical password schemes. Graphical passwords are classified into three main categories. They are recall, recognition and cued-recall methods. Recall based graphical password systems are drawn metric systems. Recognition based systems, also known as cogno metric systems or search metric systems. Cued recall systems typically require that users remember and target specific locations within an image. Graphical passwords and Captcha schemes are integrated to perform the user authentication with improved security mechanism. Captcha as graphical passwords (CaRP) is a graphical password scheme used for user authentication. Online guessing attacks, relay attacks and shoulder surfing attacks are handled in CaRP. CaRP is click-based graphical passwords where a sequence of clicks on an image is used to derive a password. Dynamic captcha challenge image is used for each login attempt in CaRP. Text Captcha and image-recognition Captcha are used in CaRP scheme. Text CaRP scheme constructs the password by clicking the right character sequence on CaRP images. CaRP schemes can be classified into two categories recognition based CaRP and recognition-recall based CaRP. Recognition-based CaRP seems to have access to an infinite number of different visual objects. Recognition-recall based CaRP requires recognizing an image and using the recognized objects as cues to enter a password. Recognition-recall combines the tasks of both recognition and cued-recall. Password information is transferred and verified using hash codes. Secure channels between clients and the authentication server through Transport Layer Security (TLS). The system is improved with distribution analysis and transmission security features. Pattern based attacks are handled with Color and Spatial patterns. Pixel colors in click points are considered in the color pattern analysis model. Pixel location patterns are considered in the spatial pattern analysis model.

A Report on Business Intelligence The Role of Data Analysis and Data Mining in Contemporary Organizations and The Ethical Implications of Collecting, Storing and Using Data

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Mr. Richardson Lawrence | 

Abstract

Diabetic Retinopathy (DR) is an eye disease due to diabetes which causes visual loss. So it is rational to provide treatment for DR at first stages of disease. Hemorrhages are the first symptoms that signify person have diabetic retinopathy. Therefore, their recognition is very essential. In this paper image contrast is improved by pre-processing and then blood vessels are detected as the boundaries of hemorrhages are not differentiate when they are in contact with blood vessels.then classify the image on the basis texture feature such as area, standard deviation etc. finally normal, moderate or Severe DR is detected on the basis of texture feature

A Resource Allocation Strategy using PSO in Heterogeneous Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th March 2018

Neeraj Kumar Pandey | N.K.Joshi

Abstract

The most important problem in the cloud service provider is to maintain the elastic property of the cloud in such a way that user will pretend the cloud as limitless. So the challenge is how to make the limited sources unlimited. Every task must be granted what it requires by any mean otherwise it will degrade the performance of cloud. So resource allocation has a lot of solution. Resource allocation is an NP-hard problem so no particular solution can perform well always. But these kinds of problems are solved by nature in many ways such that such as ant colony optimization (ACO) algorithm, particle swarm optimization (PSO) algorithm and firefly algorithm. In this paper, a particle swarm optimization technique has been used to resolve the most critical problem of the cloud service provider at cloud data centre. This technique is basically taken from the collective and collaborative nature of the nature swarm. This technique can be used to allocate the resource to the task request by minimizing the makes span, flow time and task execution cost. The simulation and test results show the better efficiency than the other similar existing technique.

A Review of Advantages and Limitations of Cloud Centric Analytics

International Journal of Engineering Research in Computer Science and Engineering, Available online 10th January 2018

Richa Mehra | Deepak Agarwal

Abstract

Cloud analytics signifies any Data Analytics or Business Intelligence process that is performed in collaboration with a cloud service provider. Cloud-based business intelligence arrived soon after the first wave of cloud applications but several early pioneers -- LucidEra, Oco, PivotLink -- didn't survive. Fears about putting data in the cloud were among the early impediments to success. Now that mission-critical apps and sensitive corporate data are increasingly moving online, it makes sense that cloud- based analytics and BI platforms are gaining customers. Cloud Analytics is a Cloud based service model which comprises of the elements of the data analytics process are provided by a public or a private cloud. Various applications and services of Cloud Analytics are being offered under a subscription-based or pay-per-use model, which is also known as Software as a Service (SaaS)- based business intelligence (BI). Cloud analytics is a cloud-enabled solution which allows an organization or individual to carry out business analysis or intelligence procedures. These solutions and services are provided through various cloud models, such as hosted data warehouses, SaaS business intelligence (BI) and social media analytics products powered by the cloud. Cloud analytics services and a typical data analytics service, both are the same in features and capabilities. But the cloud analytics integrates some or all of the service models of cloud computing in delivering that solution. [1][2].

A Review of Digital Watermarking and Its Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th August 2017

Anu | 

Abstract

This is agreed by one and all that today’s era is IT oriented and Internet has reached to every corner of our lives. Communicating over Internet or networks is a routine for us, this leads to the need of transmission security and safety of our confidential information which is being communicated. Digital Watermarking is a medium to assure integrity, piracy detection and knowing any kind of tempering done with the communicated data. It is also used for applications like owner’s authentication, copyright maintenance and monitoring broadcasts. In this paper we will review digital watermarking with its techniques, applications, classification and factors effecting watermarking

A Review of Virtual Machine Placement algorithm in Cloud Datacenters for Server Consolidation

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

C.Pandi Selvi | Dr.S.Sivakumar

Abstract

Cloud datacenters contain the number of servers, that there are some servers put in idle, as workload is distributed to all the active servers on the network called server virtualization. In order to minimize the number of active servers, we use server consolidation technique. The four major steps in server consolidation technique are namely hosted overload detection, host underload detection, virtual machine selection & migration and virtual machine placement. Virtual machine placement is the process of mapping physical machine to virtual machine for maximizing the resource utilization, minimizing energy consumption and maximizing the cloud profit. In this paper, an effective virtual machine placement algorithms and widely used approaches, parameters and optimization techniques to reduce the total energy consumption in data centers are analyzed

A Review on Comparative Study of Various Rating Systems

International Journal of Engineering Research in Computer Science and Engineering, Available online 21st July 2017

Dakhole Namita.G | Gadgil J.M

Abstract

Now a days building energy efficiency rating system have been developed worldwide to manage the energy consumption of existing buildings. There are various rating systems accepted in India like LEED, GRIHA and IGBC which have their various rating criteria and rating thresholds. These various certification programs are dedicated to the design sustainable buildings by incentivizing reductions in energy, water, and building materials consumption, while at the same time enhancing occupant health and overall community connectivity. The increasing population growth, demands for buildings, services and comfort, which results in an increasing energy demand. For this reason design of energy efficient buildings are the main objective of upcoming era. The rating systems mainly focuses on energy efficiency, the reduction of the use of resources, water and materials, as well as the reduction of impacts on human health and the environment during the building's lifecycle. In this research paper, various studies are discussed related to comparison of green ratings in various countries and the performance of green buildings. This shows that various rating systems emphasizes on different criteria according to their priorities whereas, criteria should be set according to the topographical and climatic conditions of particular place

A Review on Image Enhancement Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th April 2018

S.Deepa | K.Krishnaveni

Abstract

The quality of an image is mostly affected due to weather, lighting or equipment that has been used for image capture. Image enhancement is the process of adjusting or enhancing the digital images by altering its structural features like contrast and resolution so that the results are more suitable for display or further image analysis. The enhancement process includes removal of noise, sharpen or brighten the image and making it clearer to identify the key features. In this paper, Image Enhancement techniques such as Point processing and Histogram Equalization techniques are reviewed and discussed. Point processing operations contain image negative, contrast stretching, thresholding transformation, gray level slicing, logarithmic transformation and power-law transformation. Under Histogram Equalization, Contrast Limited Adaptive Histogram Equalization (CLAHE), Equal Area Dualistic Sub-Image Histogram Equalization (DSIHE), Dynamic Histogram Equalization (DHE) Algorithms are reviewed. The concepts of all these techniques are discussed, compared and their performances are evaluated based on the parameters Absolute Mean Brightness Error (AMBE), Contrast and Peak-Signal-to-Noise-Ratio (PSNR) values

A Review on Image Forgery Detection Techniques on Passive attacks

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th March 2018

Jitesh Kumar Bhatia | Anand Singh Jalal

Abstract

In the today’s era, nearly all of us rely on the images of the memories of our lives and loved ones. The images are useful in proving anything in the court of law by showing them as an evidence of the event, getting insurance of a mishappening, getting appreciation, or for conveying personal lifestyle to their friends through social media. However, various Image editing tools like Adobe Photoshop, Picasa, and Lightroom, etc. can produce forged images, thus changing the perspective of the viewer about the event. Image Forgery has become much prominent nowadays and is being done either for fun or for an intention. Many researchers have worked in finding techniques that can classify the forged and authentic images. This objective of this paper is to provide a glimpse of work done so far in the field of Image Forgery detection.In the today’s era, nearly all of us rely on the images of the memories of our lives and loved ones. The images are useful in proving anything in the court of law by showing them as an evidence of the event, getting insurance of a mishappening, getting appreciation, or for conveying personal lifestyle to their friends through social media. However, various Image editing tools like Adobe Photoshop, Picasa, and Lightroom, etc. can produce forged images, thus changing the perspective of the viewer about the event. Image Forgery has become much prominent nowadays and is being done either for fun or for an intention. Many researchers have worked in finding techniques that can classify the forged and authentic images. This objective of this paper is to provide a glimpse of work done so far in the field of Image Forgery detection.

A Review on Load Flow Analysis of Ring Main System

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

Abhilash D. Pisey | Nandkumar Wagh, Rakesh Shriwastava

Abstract

Load flow analysis of the complex power system is very much essential for operation, planning and sharing of power to the electrical power utilities and power engineers. In an interconnected Ring mains system, the bus voltages and complex power comprising of active and reactive components have to be assessed. Various methods are available to evaluate the system under normal and abnormal conditions. In this paper, a review of various methods available and the recent advancements in the techniques of load flow analysis has been made and presented. In particular iterative methods has been proposed to be applied to 132 KV Nagpur Ring Main System with the data of seven bus system. The overview of the performance of the said system to be tested in MATLAB Simulink environment for all the proposed methods of load flow in normal and abnormal conditions shall be presented in further work.

A Review Paper on Content Based Image Retrieval Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 18th July 2018

Ankita Gajanan Tandale | N. M. Kandoi

Abstract

Content-based image retrieval (CBIR) is a technique used for retrieving similar images from the large collection of image database. CBIR basically responsible for extracting features of images. A ‘feature’ means anything that is localized, meaningful and detectable. Almost all the CBIR techniques start from the query by example i.e. one image. The system first extracts the feature of the query image, searches the database for images with similar features, and exhibits relevant images to the user in order of similarity to the query. In this, the content of the image is nothing but the features of the image like color, texture and shape etc. This paper presents review of different CBIR techniques which are helpful for finding relevant images for the query image

A Review Paper on the Most Trending Technology: “ Big Data & it’s Processing using Hadoop ”

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd September 2017

Harshini Tanuku | Keerthi Bangari

Abstract

Big data is defined as a collection of big and complex data sets that have gigantic amount of data, that encompass social media data analytics, data management efficiency and real-time data. Big data analytics is termed as the process in which huge amounts of data are studied for further processing and industrial usage. Big data is processed using a technology known as “Hadoop” that uses the MapReduce paradigm for processing the huge datasets

A Revocable Two Factor Data Security Model for Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th January 2018

Padakanti Sabitha | V.Sridhar Reddy

Abstract

Since data in cloud will be placed anywhere, because of the critical nature of the applications, it is important that clouds be secure. The major security challenge with clouds is that the owner of the data may not have control of where the data is placed. This is because if one wants to exploit the benefits of using cloud computing. This requirement imposes clear data management choices: original plain data must be accessible only by trusted parties that do not include cloud providers, intermediaries, and Internet; in any untrusted context, data must be encrypted. Satisfying these goals has different levels of complexity depending on the type of cloud service. This system proposed an improve data security protection mechanism for cloud using two components. In this system sender sends an encrypted message to a receiver with the help of cloud system. The sender requires to know identity of receiver but no need of other information such as certificate or public key. To decrypt the cipher text, receiver needs two parts. The first thing is a unique personal security device or some hardware device connected to the computer system. Second one is private key or secrete key stored in the computer. Without having these two things cipher text never decrypted. The import ant thing is the security device lost or stolen, then cipher text cannot be decrypted and hardware device is revoked or cancelled to decrypt cipher text.

A Robust Encryption and Searching System to Share Confidential Data onto the Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Mr. Thejas S | Dr. G. Raghavendra Rao

Abstract

as cloud computing provides storing and sharing records via a cloud service because of on demand resource access and elasticity. For secure record sharing requires encryption of records before outsourcing. Key management system is one of the important aspects of the system. For sharing large number of documents, each record needs to be encrypted using different keys. Since to decrypt these records requires all keys which is very different task. Hence this approach uses aggregated key system, which aggregates all the keys. Later at the time of decryption of all records it requires one aggregated key. Considering large number of records in the cloud. For the efficient access of these records, it is necessary to search for the records over encrypted file. For this purpose , required to build for the index file. Multi keyword entries searches for the relevance record by matching keywords with the index file

A Secure and Dynamic Multi-Keyword Ranked Search Scheme over Encrypted Cloud Data

International Journal of Engineering Research in Computer Science and Engineering, Available online 24th January 2018

Dasari Madhavi | V.Sridhar Reddy, N. Srinivas

Abstract

In view of extending omnipresence of dispersed registering, a consistently expanding number of data proprietors are energized to outsource their data to cloud servers for uncommon solace and reduced cost in data organization. Regardless, fragile data should be encoded before outsourcing for security [1] necessities, which obsoletes data utilization like watchword based record recuperation. In this paper, I present an ensured multi-catchphrase situated look scheme over mixed cloud data, which at same time reinforces dynamic revive operations like cancelation and incorporation of reports. Specifically, vector space appear and for most part used TF_IDF show are participated in document advancement and request age. I assemble an exceptional tree-based record structure and propose an "Unquenchable Depth-first Search" count to give gainful multi-watchword situated look. The ensured kNN computation is utilized to scramble the document and question vectors, and meanwhile ensure correct substance attain figuring between encoded record and request vectors. Remembering ultimate objective to restrict quantifiable strikes, apparition terms are added to rundown vector for blinding inquiry things. In view of usage of our outstanding tree-based rundown structure, the proposed plan can achieve sub-straight request time and deal with cancelation and incorporation of proceedings of adaptably. Expansive tests are coordinated to demonstrate the efficiency of proposed plot

A Secure and Dynamic Multi-keyword Ranked Search Scheme over Encrypted Cloud Data

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th March 2018

P.Rasagna | Rafia Tamkeen, T.Srikanth, Syed Abdul Moeed

Abstract

Due to the increasing popularity of cloud computing, more and more data owners are motivated to outsource their data to cloud servers for great convenience and reduced cost in data management. However, sensitive data should be encrypted before outsourcing for privacy requirements, which obsoletes data utilization like keyword-based document retrieval. In this paper, we present a secure multi-keyword ranked search scheme over encrypted cloud data, which simultaneously supports dynamic update operations like deletion and insertion of documents. Specifically, the vector space model and the widely-used TF_IDF model are combined in the index construction and query generation. We construct a special tree-based index structure and propose a “Greedy Depth-first Search” algorithm to provide efficient multi-keyword ranked search. The secure kNN algorithm is utilized to encrypt the index and query vectors, and meanwhile ensure accurate relevance score calculation between the encrypted index and query vectors. In order to resist statistical attacks, phantom terms are added to the index vector for blinding search results. Due to the use of our special tree-based index structure, the proposed scheme can achieve sub-linear search time and deal with the deletion and insertion of documents flexibly. Extensive experiments are conducted to demonstrate the efficiency of the proposed scheme.

A Secure and Efficient ID-Based Aggregate Signature Scheme for Wireless Sensor Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd May 2018

Y.Kalyani | N.Yedukondalu, Sk.Alma, T.Sujitha, S.Sindhu Priya

Abstract

Affording secure and economical massive knowledge aggregation ways is incredibly enticing within the field of wireless device networks (WSNs) analysis. In real settings, the WSNs are broadly speaking applied, comparable to target pursuit and atmosphere remote watching. However, knowledge will be simply compromised by a colossal of attacks, comparable to knowledge interception and knowledge meddling, etc. during this paper, we have a tendency to principally concentrate on knowledge integrity protection, provide Associate in Nursing identity-based mixture signature (IBAS) theme with a chosen booster for WSNs According to the advantage of mixture signatures,our theme not solely will keep knowledge integrity, however can also scale back information measure and storage value for WSNs. what is more, the protection of our IBAS theme is strictly bestowed supported the procedure Diffie–Hellman assumption in random oracle model.

A Secure Deduplication Mechanism for Sensitive Data in Public Cloud Storage

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th August 2017

Deepa P.B | Dr.Rudramurthy M.S

Abstract

nowadays, cloud-based services are gaining more importance in leveraging services for large scale storage and distribution. These provide cost effectiveness, time saving and efficient utilization of computing resources. Many enterprises have decided to envision a staged migration for their data to public cloud, for better management of backup data. As data progressively grows, the cloud storage systems continuously face challenges in saving storage capacity. Data Deduplication gives solution to such challenges. It is a data compression technique for eliminating the redundant data. Assuming that cloud service provider may not be trustworthy (i.e. is honest but curious). The security, bandwidth and latency are of top concerns for an enterprise to store sensitive data in the public cloud storage. Considering these security challenges, we propose and implement a client side deduplication scheme for securely storing enterprise sensitive data via the pubic cloud. Efficiently and reliably managing the huge number of convergent keys by the user is a critical issue. Hence we have built a system where each convergent key is secured and the same is outsourced to the cloud. To avoid the weakness of convergent encryption, double encryption is done. By following this method, we can save storage space and cost. It also reduces bandwidth and ensures better confidentiality towards unauthorized users.

A Secure Parallel Network File System using Protocols

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Digambar Waghole | Jabbar Tamboli, Shrutika Chintal , Supriya Vinode , VaishaliShinde

Abstract

We examine the issue of key foundation for secure numerous correspondences. The issue is enlivened by the multiplication of huge scale dispersed file frameworks supporting parallel access to numerous capacity gadgets. Our work concentrates on the present Internet standard for such file frameworks, i.e. parallel Network File System (pNFS), which makes utilization of Kerberos to establishparallelsessionkeys between clientsandstoragedevices. Our survey of the current Kerberos-based convention demonstrates that it has various impediments: (i) a metadata server encouraging key trade between the customers and the stockpiling gadgets has overwhelming workload that confines the adaptability of the convention; (ii) the convention does not give forward mystery; (iii) the metadata server creates itself all the session keys that are utilized between the customers and capacity gadgets, and this naturally prompts key escrow. In this paper, we propose a mixed bag of confirmed key trade conventions that are intended to address the above issues. We demonstrate that our conventions are fit for decreasing up to give or take 54% of the workload of the metadata server and simultaneously supporting forward mystery and escrow-freeness.

A Secured Cryptographic Technique for Protecting Online data in the Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th April 2018

Ashish Ladda | Sandhya Mekala

Abstract

Cloud computing may be an in style space of analysis for inventors. And it's important in information sharing applications. On cloud the info being shared should be secure. The pliability and therefore the potency of the info is rely upon the protection parameter. To attain purpose we tend to outline new algorithms that is rely upon public key cryptography and outline constant size cipher text by exploitation these key we are able to decode cipher text. The opposite encrypted files except this cipher stay personal. The survey depicts some encoding schemes introduced during this information privacy for firmly and economical sharing of confidential information over a secure channel. Recently analysis concentrate on aggregation of keys of the keys in signal aggregation key that is assistance on load of network information sharing being vital practicality in cloud storage implement show to firmly, expeditiously, and flexibly share information with others.

A Secured Public key Exchange Technique for Elliptic Curve Cryptography

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

A.Vithya Vijayalakshmi | A. Dalvin Vinoth Kumar, Er. Karthigai Priya Govindrajan, Dr. L. Arockiam

Abstract

Security is the most important factor in Internet of Things (IoT). The public key cryptography systems like RSA, DSA are not suitable for IoT Devices because of the key size and energy consumption. ECC cryptography system is more suitable for IoT lightweight devices. ECC provides same level of security as like RSA with small key size and less energy computation. Key exchange is challengeable task due to Routing transmission attacks like DoS attack. The proposed technique is to enhance key exchange system in ECC based security protocols. The public key is encrypted before shared into network. The path selection algorithm is used to choose two different paths. One is for encrypted public key sharing and another is for unlock-key for encrypted public key sharing. The possibility of attacks during key sharing is investigated; the key size and energy consumption is compared. This technique is suitable for Tmote Sky and MICAz nodes

A Smart Automatic Mains Failure Panel with Diesel Generator Control and Wi-Fi

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Abhijith Mohanan. N | Kiranlal. C, Anju, G.R, Krupa Mariam, Jacob, Sharmila

Abstract

This paper focuses on the development of a smart Auto Mains Failure (AMF) panel meant for day to day electrical applications. AMF panel is unavoidable in industries, hospitals, educational industries etc. where generator is compulsory. It acts as the switching mechanism between the generator, load and the main power supply. It ensures consistent power supply to the load. An AMF panel, which can be controlled from a distance using Wi-Fi is presented here. The proposed system displays the generator parameters and indicates the type of fault in the supply mains and saves energy. The hardware model of the system is explained, which can be used for the validation of the results.

A Smart Intiative for Automobiles and Road Safety

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Nisha MS | Nanda Kumar V, Karthika K, Latha S, Geethika k

Abstract

The project is to engender a progressive city by utilizing today’s available premium technological resources by constructing our planet to be a better and safe place to live based on the idea of smart cities. In this proposed project, the Automobiles are equipped with RFID tags, audio instructor and roadside unit with RFID detector. When the vehicle enters those restricted zones, automatically speed will be controlled using the 89S52 microcontroller as well as an audio is heard in the vehicle. Whenever a red signal jump has been found by using sensors on the roadside automatically penalty amount from the prepaid smart card inside the vehicle will be deducted and credited to RTO account

A state-of-the-art review of FMEA/FMECA including patents

International Journal of Engineering Research in Computer Science and Engineering, Available online 28th April 2018

Jyoti | 

Abstract

This paper presents a critical review of Failure Modes and Effect Analysis (FMEA). Although the method is almost 70 years old, in literature there are still many researchers, both from academy and industry, devoted to improve it and overcoming unsolved and still open problems. The aim of this work consists in analysing a representative pool of scientific papers (220) and patents (109), in order to have an overview of the evolution of the method and try to understand if the efforts spent to improve it effectively answer to the several criticisms found in literature. All documents have been classified according to authors, source, and four technical classes dealing with the applicability of the method, representation of the cause and effect chain, risk analysis and integration with the problem-solving phase. A detailed analysis of the results allowed us to identify the most current problems, the improvement paths, and which other methods and tool are proposed to be integrated with FMEA.

A Study in Knowledge Acquisition in AI Systems through Genetic Algorithms

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th June 2017

Kumar Shekhar Singh | 

Abstract

Knowledge Base in an integral part of any AI system. Knowledge Acquisition refers to purposeful addition or refinements of knowledge structures to a knowledge Base. However knowledge acquisition is a complex and difficult task for AI researchers.Machine learning is the autonomous/mechanical procedure involving computers through which an AI. System itself enriches its knowledge Base.A useful taxonomy for machine learning is one that is based on the behavarioul strategy employed in the learning process. Some important conventional methods depending upon the degree of inference procedure are memorization, Analogy Inductive &Deductive inference.Attempts to develop machine learning systems began in 1950s. These design included self Adaptive system which modified their own structures in an attempt to produce an optional response to some input stimuli.Genetic Algorithms (GA) are based on population genetics. GAs learn through crossovers and mutations to provide optimum results. Higher performing knowledge structures can be mated (cross-over) to give birth to offsprings which possess many of their parent traits. Generations of structures are thus created until an acceptable level of performance has been reached. The following paper presents a study in different aspects of implementation of GAs for knowledge Acquisition in AI systems

A Study of Brain Tumor MRI Image Using Distance Based Clustering Algorithms

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd January 2018

Dr. O.A. Mohamed Jafar | J. Zehara Sulthana

Abstract

Brain tumor segmentation is a challenging problem. The medical expert can analyze the MRI (Magnetic Resonance Imaging) but this activity is error-prone and time consuming process. Data clustering is the process of grouping similar objects. Existing brain tumor segmentation methods use Euclidean distance metric. In this paper, a study of hard and fuzzy methods based on different distance metrics – Manhattan and Chebyshev used for brain tumor segmentation is done. The result of Adaptive Fuzzy K-means (AFKM) is compared with K-means and Fuzzy K-means (FKM) algorithms. The AFKM based on Chebyshev distance gives better result than K-means and FKM techniques in terms of accuracy and quantitative measurements.

A Study of Graph Kernels through Two Decades

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th May 2018

Jyoti | 

Abstract

In the real world all events are connected. There is a hidden network of dependencies that governs behavior of natural processes. Without much argument it can be said that, of all the known data- structures, graphs are naturally suitable to model such information. But to learn to use graph data structure is a tedious job as most operations on graphs are computationally expensive, so exploring fast machine learning techniques for graph data has been an active area of research and a family of algorithms called kernel based approaches has been famous among researchers of the machine learning domain. With the help of support vector machines, kernel based methods work very well for learning with Gaussian processes. In this survey we will explore various kernels that operate on graph representations. Starting from the basics of kernel based learning we will travel through the history of graph kernels from its first appearance to discussion of current state of the art techniques in practice

A Study of New Horizon on Emerging IoT Technology

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th March 2018

Pallavi Singh | Durgesh Kumar Keshar, V.K. Patle, Sanjay Kumar

Abstract

Nowadays, IoT (internet of thing) has a great impact on emerging technology with the internet. There is a number of IoT applications which used to make human’s life easier. IoT can be defined as an electrical or electronic device. IoT devices have the capability to exchange the information between IoT devices as well as communicate with the global world. Generally, IoT devices are considered as a wireless device. Therefore the reliability, security and accuracy are the new areas of research on IoT Technology. In this paper, we have studied the various IoT communication technologies and compare their features

A Study of WannaCry Ransomware Attack.

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th September 2017

Dr Supreet Kaur Sahi | 

Abstract

The problem with Cyber security is continuously evolving nature of security threats. The traditional approach focused on high demand resources ignoring less important components at dangerous risks. Such an approach is insufficient in current environment and biggest example of this is WannaCry Ransomware attacks. This article highlights different characteristics of security threats. The globe has experienced a Ransomware cyber-attack “WannaCry” that has infected thousand computers worldwide. WannaCry has ability to spread through network by exploiting a critical vulnerability. This article also highlights preventive steps against the attack. Finally a formula is discussed to enhance Network Security.

A study of Wireless Sensor Network Data Acquisition

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th March 2018

D.Priyanka | D.Bhagyalaxmi

Abstract

Wireless sensor network (WSN) data acquisition has the unparalleled advantage of other networks due to its self-organizing network structure. However, its limited resources many key problems have not been solved well. This paper summarizes the key technologies and the main challenges in WSN data acquisition, WSN network protocol and its main performance indicators, and several current technologies and the combination of WSN were analyzed and discussed, and finally, the wireless transmission future research on key technologies of sensor network data acquisition has prospected.

A Study of Wireless Sensor Networks and Its Revolutionary Changes

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th May 2018

Akhil Chowdary D | Dr Sai Madhavi D, Muneeshwara

Abstract

Many evolutionary changes are brought into WSN in the past few years, may be due to advancement in networking, semiconductor technologies giving a scope for low cost deployment as well as maintenance with long lasting life, giving a scope for WSN to be a part of many applications .In future WSN can be expected to grab the role of standardized mix of hardware and software giving solutions to many new upcoming applications. The embedded designers must be able to make proper choices in selecting transducer, battery technologies, frequency, networking protocols, semiconductor design, and sensor/actuator technology including energy storage.

A Study on Agent-Based Modeling - Topological Interactions

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd February 2018

R.Saradha | Dr. X. Mary Jesintha

Abstract

Agent-Based Model (ABM) is a class of computational models for simulating the actions and interactions of autonomous agents with a view to accessing their effects on the system as a whole. It combines elements of game theory, complex system, emergence, computational sociology, multi-agent system and evolutionary programming. ABMs are also called individual-based models (IBMs). ABMs are a kind of micro sale model that simulate the simultaneous operations and interactions of multiple agents to re-create and predict the appearance of complex phenomena. The key notion is that simple behavioral rules generate complex behavior. Most Agent-Based Models are composed of numerous agents specified at various scales, Decision-making heuristics, Learning rules or adaptive processes, An interaction topology, Non-agent environment. ABMs are typically implemented as computer simulations, either as custom software or via ABM toolkit, and this software can be used to test how changes in individual behavior will affect the system’s emerging overall behavior. This paper presents an overview of how agents communicate agent communication languages and interaction protocols.

A Study on Basic Aspects of Coding a Website

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th October 2017

Raja Mohamed S | Mrinal Anand, Raj Kumar G

Abstract

A web site is a collection of pages of information. Creating a web page is similar to writing a letter with a word processor and saving it on the computer, but the pages have to be saved as HTML format, rather than as Word documents, Excel spreadsheets, PDF files, Zip files etc., is that the way we read web sites with a program called a web browser. The designing of a website can be pushed on the server using CSS and HTML and this is called the Front-End. After finishing the Frond-End, the Back-End turns the Front-End into the action, for example, making the forms as records in the database. We use any Server-Side Languages such as PHP and JS for doing this using MySQL as Database. This paper presents the coding basics of designing a website. A basic e-commerce website is also created.

A Study on Keystroke Dynamics for Touch Screen

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd February 2018

Dr Sonali Vyas | Pragya Vaishnav

Abstract

At present maximum people store private and sensitive data on their Smartphone. Consequently, the demand is growing for secure mobile authentication methods. Setting a password-based authentication is the most frequently used method to protect data from intruders. However, people tend to use password, which can be easily remembered, hence easy to crack. Therefore, an additional mechanism is needed to enhance the security of password based authentication. One such complementary method is to use the typing pattern of the user, known as keystroke dynamics. Keystroke dynamics or typing dynamics refers to the automated method of identifying or confirming the identity of an individual based on the manner and the pattern of typing on a keyboard. Keystroke dynamics is a behavioural biometric, Keystroke dynamics on mobile referred as Touch dynamics and refers to the process of measuring and assessing human touch rhythm on touchscreen mobile devices (e.g. smartphones and digital tablets). In this paper, we are mentioning the different patterns to authenticate the touch screen mobiles

A Study on Mining Applications in Uncertain RFID Data

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

N.Bala Vignesh | Dr. V. Joseph Peter

Abstract

RFID technology is an emerging technology uses radio frequency waves to transfer data between readers and tagged objects, and provides fast data collection with precise identification of objects with unique identifications without line-of-sight. RFID technology consists of data gathering, distribution, and management systems that have an ability to identify or scan information with increased speed and accuracy. RFID technology can be used for locating, tracking and monitoring physical objects. Sensors in RFID devices are intrinsically sensitive to environmental factors. The signal from sensors suffers from high uncertainties due to the nature of signal fluctuation in real-world conditions. The uncertainties that exist in RFID data complicate tasks of determining objects positions and containment relationships. This technology has significant advantages, RFID has been widely used for access control, objects tracking, smart box, highway tolls, logistics and supply chain, security and healthcare, etc. In particular, RFID has been adopted and deployed to collect various types of data in the manufacturing field. In this paper we focus on study of data mining applications of uncertain RFID data

A Study on Mining High Utility Item sets for Promoting Business Activities

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

R. Sheeba Mary Ananthi | Dr. V. Joseph Peter

Abstract

In recent era, High Utility Itemset Mining (HUIM) is an emerging critical research topic. In traditional approach, the items which occur frequently together are extracted from a database. But the frequency of Itemset is not sufficient to reflect the actual utility. Utility mining is an extension of frequent Itemset mining by considering the utility of an item. Utility Mining is the process of discovering all item sets whose utility values are equal to or greater than the user specified threshold in a transaction database. Utility Mining covers all aspects of economic utility in data mining and helps in direction of itemset having high utility. The main objective of high utility itemset mining is to find the itemset having maximum utility values. We can extract the high utility from rare itemsets, irregular occurrence, from different discount strategies. In this paper, we present a various algorithms for High Utility Mining to promote business activities

A Study on Near-Duplicate Image Detection System

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th April 2018

Dr.A.Mercy Rani | B.Anitha, K.Anukeerthi

Abstract

Due to the abundant increase of imaging technologies, manipulation of digital images create a severe problem in various fields such as medical imaging, journalism, scientific publications, digital forensics etc. This gives the challenges in a matching of slightly modified images to their original ones which are called as Near-Duplicate image detection. The images are altered using some features such as cropping, changing its shape, contrast, saturation, framing etc. Digital Image Processing plays a vital role in finding Near-duplicate images in various applications. The near-duplication image detection process is used to find the duplicate image by comparing the slightly altered images to the original one to assist in the detection of forged images. This paper presents the overview of near duplication images, near duplicate image detection system, algorithms and it gives the analysis of the various researchers held in this field

A Study on Pattern Recognition of Tumor images in Medical Image Analysis

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th February 2018

Dr. V. Usharani | 

Abstract

Medical image investigation is carried out through some intelligent ideas and techniques that require distinctive solid information and reports. Nobody is very clear about what type of information and proofs are used for the sharp finding but however some low ranking features like shapes, texture and other pixel related statistics which are taken from the images may be used for prediction. Based on this understanding medical images can be identified through the use of exclusive pattern recognition algorithms. In this paper for cancer analysis through the use of unique forms in medical pictures, varieties of tumours’ and pattern recognition process in medical image diagnosis might be studied considerably.

A Study on Software Development Life Cycle & its Model

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th September 2017

Navita | 

Abstract

Software development life cycle (SDLC) is a well defined and systematic approach. It practiced for the development of a reliable high quality software system. There are many SDLC models available. This paper describes five SDLC model , namely ;waterfall model ,iterative model, v shaped model ,spiral model, prototype model. Each development model has their advantages and disadvantages. The aim of this paper is to present a study on software development life cycle (SDLC) and SDLC models with their advantages and disadvantages.

A Study on Trends, Reviews and Effects of Online Shopping in India

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

Tushti .P. Bakrania | 

Abstract

In the recent scenario of E - business online shopping has developed a huge importance. The development and growth of online shopping has given n number of opportunities to the organization to provide competitive advantages. There are n number of companies which are selling their products through on line portals or provides service online. Compared to other countries online shopping in India is not very common but it is growing at an immense speed then other countries. This paper gives brief idea of online shopping in India its positive and negative effects. It also provides scope of upgrading in online shopping websites. A finding says that online shopping is the best convenient way for consumers. But people also worry with the risk associated with it like privacy and security risk. Many organizations uses Internet to provide information and communicate with people which helps them to get idea what consumers exactly want, what are there demands and organization can also get feedback through them. But, there are various uncertainties attached with online shopping such as misuse of personal data, return or exchange policies, testing of product etc.

A Study on various Cryptographic Techniques used in Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th December 2017

Mr. Girish Kumar D | Dr. Rajashree V Biradar

Abstract

Cloud Computing (CC)is the delivery of on-demand shared computing resources to computer or other devices, CC has changed the way we think about the way we perform our day to day operation and now a day’s almost all applications are using CC to meet their requirements without actually licensing or purchasing the software and also the infrastructure. There is a lot of chance to misuse of data by the third party (Cloud Service Provider) and the main security factors which affect the performance of the system are confidentiality, availability and integrity of data. Many encryption algorithms have been developed and implemented to provide security for the data which is stored in the cloud, but no algorithm provides 100% security for the data which is stored in the cloud. This paper gives a study of different encryption techniques used in CC that is used to provide security for the data stored in the cloud.

A Study User Behavior Using Phishing Education and Training

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th November 2017

Ms. Vidya Mhaske-Dhamdhere | Dr. Prasanna Joeg, Dr. Sandeep Vanjale

Abstract

In this paper, we present results of surveys of users on their ability to recognize phishing emails as opposed to legitimate emails. User awareness is one of the most important approaches to phishing detection. We first conducted a survey of user confidence in their ability to detect phishing. We then designed a survey questionnaire that contained some legitimate emails and some phishing emails. We conducted a second survey to test the ability of a sample set of users to detect phishing. The results were mixed. After the second survey, we conducted a training session on the same group of users to train them to detect phishing. After the training we conducted a third survey with a somewhat different questionnaire to test their ability to detect phishing. Our results suggest that training considerably improves the ability to detect phishing. However, a significant minority are still not able to detect phishing.

A Subset Sparse Based Subspace Clustering on High Dimensional Data

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd July 2018

Prathima V.R | Dr. Fayaz.K

Abstract

- Data mining and machine learning has been an important research topic in recent years. The topic of sparsely distributed data and the various issues related with curse of dimensionality of high-dimensional data, make most of the traditional clustering algorithm, lose action in high dimensional space. Therefore, clustering of data in high dimensional space is becoming the hot research areas. Clustering in data mining can be used as a data exploration or future prediction tool. With the advent of raise in huge data or high dimensional data such as DNA arrays, Images or GPS data, bag-of-words document representation etc., the goal of clustering is to group multiple data points in such way that they can be represented more efficiently for better understanding of the data. In this context we study the pitfalls of high dimensional data clustering concepts and algorithms are discussed then we study the SSC, SSSC, SMRS algorithms. This paper offers a subset based algorithm for automatically determining the optimal number of clusters on high dimensional data. The Main aim of this paper is to design an algorithm with reasonable complexity which computes representatives and clustering high-dimensional data accurately. In this paper we have made the following contributions i.e. designing of algorithm which used the divide-and-conquer strategy, which can able to compute the representatives within reasonable time and this algorithm is named as Hierarchical Sparse representatives.

A Survey of Cluster Ensembles and its Applications: Specific Problem Domains

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th May 2018

Jyoti | 

Abstract

Cluster ensembles have been shown to be better than any standard clustering algorithm at improving accuracy and robustness across different data collections. This meta-learning formalism also helps users to overcome the dilemma of selecting an appropriate technique and the corresponding parameters, given a set of data to be investigated. Almost two decades after the first publication of a kind, the method has proven effective for many problem domains, especially microarray data analysis and its down- streaming applications. Recently, it has been greatly extended both in terms of theoretical modelling and deployment to problem solving. The survey attempts to match this emerging attention with the provision of fundamental basis and theoretical details of state-of-the-art methods found in the present literature. It yields the ranges of ensemble generation strategies, summarization and representation of ensemble members, as well as the topic of consensus clustering. This review also includes different applications and extensions of cluster ensemble, with several research issues and challenges being highlighted

A Survey of Image Mining Techniques for Diagnosing Heart Disease

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

M.Umamaheswari | K.Krishnaveni

Abstract

Image mining refers to a data mining technique which is used to extract the knowledge directly from the images. It supports a large field of applications such as medical diagnosis, agriculture, industrial work, space research and the educational field. Heart disease is one of the popular causes of death in the world. Heart disease diagnosis is a most important challenge faced by medical fields and hospitals. The goal of this paper is to present a study of various image mining techniques and different algorithms used to diagnose the heart diseases

A Survey of Recent Approaches for Detection of Alzheimers Disease

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Arpita Raut | Vipul Dalal

Abstract

Alzheimers is a progressive and irreversible neurological disease. It is the most common cause of dementia in people of the age group 65 years and above. Detection of Alzheimers disease in the early stage is very crucial as it can prevent serious damage to the patients brain. Many different methods have been proposed to detect Alzheimers disease. In this paper, we have surveyed different techniques and approaches for detection of Alzheimers disease.

A Survey of Routing Protocols in Mobile Ad Hoc Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th July 2017

Sahana T S | Sandhya A S, Pooja B N,Priya J, Mrs. Sheela Devi.M

Abstract

Mobile Ad Hoc Network (MANET) is collection of multi-hop wireless mobile nodes that communicate with each other without centralized control or established infrastructure. The wireless links in this network are highly error prone and can go down frequently due to mobility of nodes, interference and less infrastructure. Therefore, routing in MANET is a critical task due to highly dynamic environment. In recent years, several routing protocols have been proposed for mobile ad hoc networks and prominent among them are DSR, AODV and TORA. This research paper provides an overview of these protocols by presenting their characteristics, functionality, benefits and limitations and then makes their comparative analysis so to analyze their performance. The objective is to make observations about how the performance of these protocols can be improved.

A Survey of Various Routing Algorithms for Mobile Ad-Hoc Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

P. Roselin | Dr. M. Sivajothi, Dr.T.C. Raja kumar

Abstract

A Mobile Ad-hoc Network (MANET) is form over wireless media by the various mobile nodes. In other word we can say if various mobile nodes from a network without any infrastructure, such kind of network is known as Mobile Ad-hoc Network. In MANET communication between two mobile devices are performed by routing protocol. This paper presents a coherent survey on routing algorithm of ad hoc mobile networks, with the intent of serving as a quick reference to the current research issues in ad hoc networking. In this survey paper we proved an overview of various routing protocols proposed by various researchers. We will also provide comparative study of all routing protocol to find out the performance of protocol for large MANET

A Survey on a Hadoop Framework for Big Data Applications

International Journal of Engineering Research in Computer Science and Engineering, Available online 21st November 2017

B.Swathi | Dr. P.Niranjan

Abstract

The big data is the idea of the gigantic scope of information, which is being made step by step. In current years dealing with this information is the significance test. Hadoop is an open source proposition which is utilized successfully to deal with the big data applications. The two central ideas of the Hadoop are MapReduce and Hadoop conveyed document framework. HDFS is the capacity system and guide lessen is the programming dialect. Results are created quicker than other customary database operations. A few dialects which encourage us to program the MapReduce system inside brief time frame.

A Survey on Artificial Intelligence In Internet of Things

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

S.Thyanesh Pandi | K.Niranjana, R.Vignesh, R.Abishek, J.Suriya Prabha

Abstract

IOT is the internetworking of things that collects and exchanges information from the environment. AI, on the other hand, is the engine or the brain that will enable analytics and decision making from the data collected by IoT. In other words, IoT collects the data and AI processes this data in order to make sense of it. The AI and IOT systems are working together in devices like fitness trackers and Google Home. AI can be used to make inferences about this data and summarize it before transmitting it to other devices. This would reduce the flood of data to a manageable level. This would enable the attachment of a larger number of devices to the network. This paper describes the advantages, applications, analysis and result of using Artificial Intelligence in Internet of Things.

A Survey on Association Rule Mining using Apriori Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Sneha R. M | B. S. Varsha, G. K. Meghana, Anusha, S Sahitya

Abstract

Data mining refers to the process of extracting useful and interesting knowledge from large set of data. There are many aspects like clustering techniques, classification, association rule mining etc. Among these, association rule mining is the important aspect for data mining. The algorithm’s performance directly effects the efficiency , integrity and effectiveness of ultimate data mining results. Apriori algorithm is one of the influential algorithm for mining association rules. The basic idea of this Apriori algorithm is to identify all the frequent itemsets.

A Survey on Electroencephalography (EEG)-Based Brain Computer Interface

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

K.Aparna | R.Chandana Priya

Abstract

In this paper the main objective is to develop a system which allows disabled people to communicate with other persons and helps to interact with external environment and also to establish a communication system which will translate the human intentions reflected by brain signals into analog speech signals those are audible via speakers. Brain–computer interface i.e., (BCI) is a new emerging area is mainly for the patients in the treatment bed. TheBrain Computer Interface will receive brain signals, analyze them, and then translate them into commands those are transfer to output devices which will carry out desired actions. Electroencephalography records the brain’s electrical activity, obtained by firing of neurons within the brain. If, we find out the difference in those low signal frequencies, those will yields to design a BCI. Based on variation in those frequencies, human thoughts can be recognized as a prototype mechanism.

A Survey on Heart Disease Prediction Using Data Mining Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

A.Sahaya Arthy | G.Murugeswari

Abstract

Data Mining is the process of transforming the raw data into useful information for decision making. Medical Data mining has potential to explore the hidden pattern in data set of the medical domain. These hidden patterns can be used for clinical diagnosis and disease prediction. Heart disease is one of the common and major causes for death in India. According to the report of Global Burden of Disease, 1.7 million Indians died because of cardiovascular illnesses. The number of deaths due to cardiovascular illnesses has grown up by 53% since 2005. According to ASSOCHAM-Deloitte joint study, the cases of cardiovascular diseases are growing at 9.5% annually. At the same time, it is considered to be the most preventable and controllable disease. There are certain factors which may cause heart diseases. The factors include change in life style, food habits, mental stress, smoking, alcohol consumption, obesity, blood pressure and diabetes etc. This research paper intends to provide a survey of data mining techniques used in medical field particularly in heart disease prediction. Various research works on association rule mining, classification and Ontology approaches for disease prediction are analyzed and presented in this paper

A Survey on interactive multi-label segmentation using cellular automata

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Monika | 

Abstract

Image segmentation is the process of partitioning a digital image into multiple segments. The goal of segmentation is to change the representation of an image into more meaningful and easier to analyze format. There are various interactive approaches to segment the area of interest from the given image. In this paper a survey on various image segmentation techniques has been performed and the methods are classified and compared as per the techniques used. The results of the segmentations are also compared both quantitatively and qualitatively. This survey provide a base for the future research in field of image segmentation.

A Survey on Key Frame Based Video Summarization Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th November 2017

Himani Parekh | 

Abstract

The large amount of videos usage increase the volume of data, more time to access and more man power is required. Video summarization is the solution for this problem. Summarized video can be used to review the important aspect of particular video, indexing and faster browsing. Video summarization techniques are classified into key frame based classification and skim based classification. This paper focuses on process and techniques of key frame based classification.

A Survey on MapReduce for Dynamic Job Ordering and Slot Configaration

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th November 2017

J .Sravanthi | Dr. P.Niranjan

Abstract

MapReduce is a well known parallel registering worldview for vast scale information preparing in groups and information centers. A MapReduce workload for the most part contains an arrangement of jobs, each of which comprises of various guide tasks took after by two diminish assignments that guide undertakings can just keep running in delineate and lessen tasks can just keep running in decrease spaces, and the general execution limitations that guide undertakings are executed before lessen tasks, diverse employment execution requests and guide/lessen opening setups for a MapReduce workload have essentially extraordinary execution and framework use. This study proposes two classes of calculations to limit the influence traverse and the aggregate finishing to time for a disconnected MapReduce workload. Our top of the line of calculations concentrates at work requesting streamlining for a MapReduce workload under a given direct/lessen space arrangement. Interestingly, our inferior of calculations considers the situation that we can perform advancement for outline for a MapReduce workload.

A Survey on Reversible Image Data Hiding with Contrast Enhancement

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

SK Taj Mahaboob | Shaik Baba Fakruddin

Abstract

The main aim of this paper is to explain different watermarking techniques. In this paper we will give an overview on different types of techniquesused for preparation ofreversible data hiding and explain the significant growth in reversible watermarking and increase of embedding payload in the host image withoutdistortion in many fields. The paper focus on comparative analysis of different watermarking techniques and explaining their significance briefly

A Survey On Secure Connectivity Techniques For Internet Of Things Environment

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Mr. Vikram Neerugatti | Dr. A. Rama Mohan Reddy

Abstract

Internet of things involves network of Nodes (sensors, Actuators, fog, cloud etc). Sensor node is a small in size, computing power and storage capacity is less. Due to this nature of Sensor the security module is not incorporated in it. So IoT Nodes has more scope for the Intruders, to attack the systems by using this weak connection of Nodes. Lot of research work has to do in this area, to establish a secure connectivity among various IoT nodes. While accomplishing the secure connectivity of things in IoT, need to consider all the security parameters like (confidentiality, authentication, integrity, etc.). The existing techniques/ Algorithms for secure connectivity of devices are not developed for nodes that which used in an IoT technology and not deal with all security parameters. This paper addressed the various existing secure connectivity techniques with advantages and disadvantages, that which is used to direct Research towards development of secure connectivity Techniques for IoT nodes.

A Survey on Security Features Based on Some Interactions and TheirRespective Co-Operation in Handheld Devices for Communication

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th August 2017

Arogia Victor Paul M | Numan Shaikh, Sharon M, Anil Sagar T, S. Venkatesan

Abstract

Since from the last decade mobile communication and its usage have grown drastically, also it has become a serious business tool nowadays. Mobile devices are the major platform for the users to transfer and exchange a very huge and critical data for communication. Also most of the communications are based on handheld devices like smart phones, palmtops, tablets etc. These devices are variably used for applications like banking sector, personal digital assistance, remote login, m-commerce, e-commerce, internet access, entertainment and also medical usage. However due to usage of handheld devices rapidly, there might be a security issues which might restrict the usage of mobile devices. This article survey gives some basic glimpses about the security features such as authentication, authorization, privacy, confidentiality, and data securityin handheld devices and it briefs an idea on how to overcome various issues like threats and vulnerabilities that effect the human interactions and their cooperation using handheld devices, and also it provides various solutions to the mobile devices ensuring security.

A Survey on Security Issues in Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th June 2017

D.Divya | T.Lakshmi

Abstract

Cloud computing is a rising innovation worldview that moves ebb and flow mechanical and figuring ideas into utilitylike arrangements like power and water frameworks. Mists draw out an extensive variety of advantages including configurable registering assets, financial reserve funds, and administration adaptability. In any case, security and protection concerns are appeared to be the essential impediments to a wide selection of mists. The new ideas that mists present, for example, multi-tenure, asset sharing and outsourcing, make new difficulties to the security group. Tending to these difficulties requires, notwithstanding the capacity to develop and tune the safety efforts produced for customary processing frameworks, proposing new security strategies, models, and conventions to address the interesting cloud security challenges. In this work, we give a far reaching investigation of distributed computing security and protection concerns. We recognize cloud vulnerabilities, arrange known security dangers and assaults, and present the best in class practices to control the vulnerabilities, kill the dangers, and adjust the assaults. Moreover, we examine and distinguish the constraints of the present arrangements and give bits of knowledge without bounds security points of view. At long last, we give a cloud security system in which we exhibit the different lines of barrier and recognize the reliance levels among them. We recognize 28 cloud security dangers which we arrange into five classifications. We additionally introduce nine general cloud assaults alongside different assault episodes, and give viability examination of the proposed countermeasures

A Survey on Segment Based Evaluation of Co- factor Used in Human Gait Recognition

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th October 2017

Dr. P.S.Smitha | Sruthi Nath C

Abstract

Gait recognition is an effective biometric feature to identify persons from a distance by the way people walk or run. While gait has several attractive properties as a biometric, the greatest disadvantage in gait recognition is to identify an individual with cofactors and in different emotional and environmental conditions. Different views and angles of the camera also constitutes in degradation of the gait identification. Thus different measures and methods have been proposed for enhancing the gait identification in these cases. This paper is study of gait recognition during these conditions and discussing ways for lowering the degradations. This paper presents a literature review of cofactor affected gait recognition and propose a method to identify cofactor affected probes in certain view angles. Recent researches in gait identification techniques are presented in this paper.

A Survey on Smart Cities using IoT

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th March 2018

M. Soujanya | R.Sushmitha

Abstract

The city of today and tomorrow is an intelligent city, synchronized, and able to optimize information, its flows and its energies. Smart city refers to using information and communication technology to sense, analyze and integrate the key information of urban operation core system so as to make various demands including livelihood, environmental protection, public security, urban services and industrial and commercial activities Smart response. Its essence is to make use of advanced information technology to realize the city's smart management and operation so as to create a better life for people in the city and promote the harmonious and sustainable growth of the city. With the continuous development of human society, the future city will host an increasingly large population. At present, our country is in a period of accelerating urbanization. The problem of "urban disease" in some areas is becoming more and more serious. In order to solve the difficult problem of urban development and realize the sustainable development of the city, building a smart city has become an irreversible historical trend in urban development in the world today.

A Survey on Streaming Video

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th February 2018

N.J.Satheesh Kumar | Dr. B. Ramakrishnan

Abstract

This study presents a video streaming system for wireless networks that employ effective optimization of the pre-compressed video. Among the different approaches, the video Stream-switching technique is getting wide receiving the data. We assessment the VoD and Live streaming data video in crossing through different paths from compression. The case of multicast video can be delivered to the high performance of the proposed scheme, ie significantly improvement for good channel conditions, while improving is utilization minimized in the low. This routing metric takes a report of geometric proximity and congestion degree in order to enlarge delivery ratio and decrease end-to-end delay, which determines the quality of the delivered video. To offer high playback quality to users by maintaining high effective data.

A Survey on the issues of Refactoring

International Journal of Engineering Research in Computer Science and Engineering, Available online 24th May 2018

Aparna K S | Sai Deepthi.K, Sharan Kumar.R, Syeda Shameemunnisa, Sree Geethika.M

Abstract

In this paper, a tremendous attitude of research towards refactoring the software is presented. This paper presents the areas where refactoring can be applied. The Scope of refactoring, how to refactor, when to refactor, impact of refactoring an a quality of software, different methods used, basic principles in refactoring software artifacts and the related work which needs to improve are presented. This paves the way for improvement, giving rise to many more research fields.

A Survey on Travel Based Application using Social Media

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Shanker Shalini | Dr.M.Sheerin Banu

Abstract

Big data provides analysis of large amount of dataset and accurate result can be obtained using this dataset analysis. When considering travel application many user opt for static travel planning without any now feature that incorporates in the application. Blindly they agree any travel plan thats been listed in the application. In this paper various analysis is done and survey is been done to make user friendly travel application so that user can specify their Point Of Interest (POI) and as such planning is done dynamically based on users location with the help of geo-tagging and collaborative filtering. We find here what are all recommendation system that can suitable to incur in the travel application with the help of geo-tagging and location based filtering. Thus to find user friendly travel based application this survey is done.

A Survey on Twitter as a Corpus for Sentimental Analysis and Opinion Mining

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th March 2018

Roopa V | Induja K, Abdul Basith P, Manikandan R.M, Deepak P.M

Abstract

Today, Microblogging is the most popular statement tool among Internet users. Every day people share their opinions on different aspects of life. Therefore, these websites have become rich sources of data for opinion mining and sentiment analysis. Because microblogging has appeared comparatively, there are few research works that were dedicated to this topic. In our paper, we focus on using Twitter, the most popular platform, for the task of sentiment analysis. It shows how we group a corpus for sentiment analysis and opinion mining which discovers phenomena of the corpus by linguistic analyzing. Using corpus, we build a sentiment classifier that is able to determine positive, negative and neutral sentiments for a document. Experimental evaluations show that our proposed techniques are efficient and perform better than previously proposed methods. In our research, we worked with English, however, the proposed technique can be used with any other language.

A Survey on User Behavior Clustering in Multimedia Social Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 25th November 2017

Swetha Koduri | T. Satya kiranmai

Abstract

This Survey investigates how quantitative user data, extracted from server logs, and clustering algorithms can be used to model and understand user-behavior. The Survey also investigates how the results compare to the more traditional method of qualitative user-behavior analysis through observations. The results show that clustering of all user data, only a small subset of users increases the reliability of findings. However, the quantitative method has a risk of missing important insights that can only be discovered through observation of the user. The conclusion drawn in this survey is that a combination of both is necessary to truly understand the user-behavior.

A survey on various types of Sentiment Analysis Approaches from Big data

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd October 2017

Navaneethakrishnan P | Ravikumar B

Abstract

In recent years, Big Data Analytics has become an essential topic for researchers.It gains more popularity due to immense data set that becomes overwhelming to users. Therefore itis essential to extract opinions from the internet and predict online customer’s preferences, which could prove valuable for economic or marketing research.This inspire the researcher to develop a system that can identify and classify opinion the huge amount of text data based on the approach of Sentiment Analysis or Opinion Mining. The paper presents a survey covering the techniques and methods in sentiment analysis and challenges appear in the field. Sentiment analysis is done in data from applications like social network. There is a need for analyzing the sentiments of data and thereby defining the behaviour of the user. This involves feature extraction and thereby developing relationship trees within the scope of data.

A Survey on Vehicle Classification Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th April 2018

G.Sundaravalli | K.Krishnaveni

Abstract

Vehicle classification has emerged as a significant field of study because of its importance in the variety of applications like surveillance, security system, traffic congestion, avoidance, accident prevention etc. So far numerous algorithms have been implemented for classifying vehicles; the aim of this paper is to give the opportunity to the researcher to become closely familiar with the methods used for classification of vehicles. Methods based on Image Processing, Neural Networks, and Data Mining are reviewed, discussed and compared. This survey emphasizes that Canny Edge Detection technique gives the better solution than other edge detective techniques in terms of vehicle identification. The Fuzzy c-means clustering and K nearest neighbor algorithms prove better for extracting the features of a vehicle like an area, length-width ratio etc

A Survey on Water Quality Analysis for Industrial Application under IOT Environment

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th July 2017

P.Kalamani, | Divya R Krishnan, Meghana B.V, Mary Theresa M, Himadri Sengupta

Abstract

Internet of Things (IoT) is global network of “smart device” that can sense and interrelate with their environment using the internet for their communication and interaction with users and other systems. The traditional method of testing Turbidity, PH & Temperature is to collect samples manually and then send them to laboratory for analysis. However, it has been unable to meet the demands of water quality monitoring today. By manually monitoring the water quality is very time consuming as well as its complicated to get water parameter in real time. To overcome this a set of Monitoring of Turbidity, PH & Temperature of Water quality are going to be placed in the reservoir as the variations in these parameter will get to know the presence of pollutants. In this paper a new approach has been adopted to analyze the quality of the water under IoT environment. The proposed system contains data acquisitions node, controlling unit as ARM, base station and monitoring unit, where all these units are connected to each other .Data can be collected from various sensor and each sensors has its own way to read the data about physical phenomenon ,so necessity to write diverse code for each sensor for data collection procedures. Meanwhile to control and to do some pre-processing work MCU unit has been adopted, after data collection from various sensor such as its Temperature, Turbidity, PH, etc at base station is sent to display on monitoring node and also compared with standard values .By continually monitoring water quality people get awareness locality water condition so we can minimize its critical effect on human life ,filed, animals etc with high frequency.

A survey on Wireless Sensor Network Attacks And Defenses

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Pramod Nath | Pragya Rajput

Abstract

Wireless Sensor Networks (WSN) are combination of several thousand sensor nodes that have several capabilities such as to detect, to sense, to monitor, to process and to compute. WSN have many applications in real time scenarios such as in military, industries, health care and so on. WSN has infrastructure less structure, so the ability to cope with the node failure, fault tolerance and its security attack are the main concern. The sensor nodes are more vulnerable to security threats and attacks because of the harsh and hostile environment. Efficient implementation of different security protocols has huge impact to adverse the potential threat. The main aim of this paper is to present security issues and challenges faced by WSN. This paper explains attacks in WSN, its flaws and their countermeasures that can be used to handle the pitfall.

A Survey Paper on Diabetes Retinopathy

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th September 2017

Dr.Ruksar Fatima | Laxmi Math

Abstract

The retina is the only part of the human body where the blood circulation can be observed directly. Several systemic diseases can affect the retinal blood vessels, which makes the retinal image analysis a potential diagnostic tool, as it allows assessing vascular changes in an easy and non-invasive way. Retinal image analysis is one of the active research areas with the goal of providing computer-aided methods to help the quantification, measurement and visualization of retinal landmarks and biomarkers. In diabetic retinopathy (DR), the blood vessels often show abnormalities at early stages [1], as well as vessel diameter alterations [2]. Changes in retinal blood vessels, such as significant dilatation and elongation of main arteries, veins, and their branches [2, 3], are also frequently associated with hypertension and other cardiovascular pathologies.

A Survey Report on Elliptic Curve Cryptography

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th January 2018

Ajit Karki | 

Abstract

Information is an asset that has a value like any other asset. As an asset, information needs to be secured from attacks. To be secured, information needs to be hidden from unauthorized access (confidentiality), protected from unauthorized change (integrity), and available to an authorized entity when it is needed (availability).During the last three decades, Computer networks created a revolution in the use of information. Information is now distributed. Authorized people can send and receive information from a distance using computer networks. Although the three above mentioned requirements- confidentiality, integrity, and availability- have not changed, they now have some new dimensions. Not only should information be confidential when it is stored; there should also be a way to maintain its confidentiality when it is transmitted from one computer to another. The scorching enlargement in the use of mobile and wireless devices demands a new generation of Public Key Cryptography schemes that have to accommodate limitations on power and bandwidth, at the same time, to provide an ample level of security for such devices. Elliptic Curve Cryptography (ECC) is rising as an attractive public-key cryptosystem for mobile/wireless environments. Compared to long- established cryptosystems like RSA, ECC offers the same security with smaller key sizes, which results in faster computations; lower power consumption, as well as memory and bandwidth savings. This is particularly useful for mobile devices which are typically limited in terms of their CPU, power and network connectivity. Nevertheless, the true crash of any public-key cryptosystem can only be evaluated in the context of a security protocol. Elliptic Curve Cryptography (ECC) has become the ideal choice for the insidious computing environment because of its suitability to the devices having limited bandwidth, battery power, less computational resources and less memory.

A Systematic Performance of Various Multi Class Imbalance Data Classification in Data Mining

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th April 2018

Ganesh.T | Nirmal Kumar.A, Sankara Gomathi.S

Abstract

The usage of data is increasing day by day. There is a huge amount of data storage is required for handling the millions of twits, shares in social networks (twitter, facebook, WhatsApp, and youtube) per second. Databases are playing a vital role in data warehousing and mining. The process of storing the data in large repository place is known as Data Warehousing. Nowadays, Search Engines are struggling to follow the Search Engine Optimization techniques. So there is a pressure for the data analyst to fetch the data from the data warehouse efficiently. The task of classification with imbalanced datasets have attracted quite an interest from researchers in the recent years. Accordingly, various classification techniques are used to handle the newly arrived large amount of data. So many applications have been designed to address this problem from the different perspective such as data pre-processing, algorithm modification and sensitive learning. The problem of constructing fast and accurate classifiers in large data set is an important task in data mining and knowledge discovery. This paper illustrates the various classification techniques and also to improve the correctness of classifier for Classification Techniques in Data Mining

Aadhaar and Server based Electoral system

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Yugansh Garg | Sakshi Mishra

Abstract

This paper describes an advance Aadhaar and server based electoral system for Indian elections. The voting systems in an easier way that all voter can cast votes via biometric Aadhaar based authentication .It provides a higher security pre-casting which could reduce the chances of temperance as a simultaneous backup is created at State/Central level servers. In this system we renounce the use of traditional voter ID cards and election voter verification list. This method would help us to eliminate invalid votes, ends booth capturing and makes counting easier, faster and accurate

Abnormality Feature Extraction in the Spinal Cord MRI Using K-Means Clustering

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

S.Shyni Carmel Mary | S.Sasikala

Abstract

Research on Medical Image proposes an efficient platform for automatic analysis and detection of any Deformations in a given medical image data set especially in Spinal Cord for an effective and better understanding of diagnosis. The abnormality of the spinal cord may include Tumor, Disc a hernia, Fracture, swelling etc., which has been detected from any given modality of Medical images such as MRI, CT, and fMRI etc. In this work, Automated Decision support system is introduced for fast and accurate analysis which will help to confirm the existence of affected part of the Spinal Cord MR image. It has two phases. Phase I: Identifying any anomaly features or distortion is found to have existed in the given image or not by using histograms. Phase II: Involves in Clustering of the image which is used to find the depth of the existence of the calcification in the MRI Spinal Image. The performance of the algorithm and the time taken to complete every cluster phase is analyzed. Further, the algorithm’s efficiency is being observed to prove that it gives a perfect accuracy

Accident Avoidance During Poor Visibility Conditions

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd March 2018

D.Manoj Kumar | Mugdha, Shahzeb F. Ali, G. Sreeja, S.R Siddharth

Abstract

T With the dramatic increase in population, the vehicles on the road have increased too. Hence, it has become a necessity to provide a means for a safer and more convenient traveling experience. The present paper focuses on providing a technology which will help people in navigating through roads where visibility conditions are poor and they are more prone to accidents like, in hilly areas where there are blind turns and in foggy weather conditions where visibility is nearly zero.

Accident Detection and Anti-Theft for Automobiles Using Bump Sensor, GPS and GSM Modules

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Sharath Kumar K | Swetha S, T Mounika, Soumya E, Kavitha Juliet

Abstract

The objective of this paper is to detect the accident of an automobile and theft of an automobile. The accident and anti-theft module is integrated the in automobile where the module detects the occurrence of accident or theft of vehicle. This reduces the loss of life or theft of vehicle is detected by android application. The accelerometer sensor and bump sensor detects the accident. The theft of the vehicle is detected by vehicle tracker android application which is provided to the owner of vehicle. If an automobile is met with an accident then the sensors will be activated and the location of the accident will be sent to emergency stations. If the vehicle has been stolen, then the owner of the vehicle will receive the SMS and owner can stop the vehicle.

Accuracy of speech emotion recognition through deep neural network and k-nearest

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th March 2018

R.B Pradeeba | K.Tarunika, Dr.P.Aruna

Abstract

Emotion is a positive or negative state of a person’s mind which is related to physiological activities. The main objective of the paper is to apply Deep Neural Network (DNN) and k-nearest neighbour (k-NN) in recognition of emotion from speech-especially scary state of mind. The most precise model will be utilized to generate alert signals through the cloud. Health care system and in particular intensive and palliative care is supposed to be the area of application. Utterance level is the main feature for analysis with special emphasis. Raw data collection, conversion of acoustic signals to waveforms, probable emotion classification and recognition using databases existing, creating alert signals through the cloud is the sequence of steps followed. The finding of the paper is a fruitful contribution to the palliative care system.

Achieving Efficient and Privacy-Preserving Cross-Domain Big Data Deduplication in Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th April 2018

V.Neeraja | N.Koteswara R, T.Manjari, P.Yamini, V.Keerthana

Abstract

Secure data deduplication can significantly reduce the communication and storage overheads in cloud storage services, and has potential applications in our big data-driven society. Existing data deduplication schemes are generally designed to either resist brute-force attacks or ensure the efficiency and data availability, but not both conditions. We are also not aware of any existing scheme that achieves accountability, in the sense of reducing duplicate information disclosure (e.g., to determine whether plaintexts of two encrypted messages are identical). In this paper, we investigate a three-tier cross-domain architecture, and propose an efficient and privacy-preserving big data deduplication in cloud storage (hereafter referred to as EPCDD). EPCDD achieves both privacy-preserving and data availability, and resists brute-force attacks. In addition, we take accountability into consideration to offer better privacy assurances than existing schemes. We then demonstrate that EPCDD outperforms existing competing schemes, in terms of computation, communication and storage overheads. In addition, the time complexity of duplicate search in EPCDD is logarithmic.

Adaptive Head-Light System For Vehicle

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th February 2018

Priyanka M Dubal | Dr. Alam N. Shaikh

Abstract

Night time driving with conventional headlamps is particularly unsafe Major road accidents occur during night time. About 25% of driving done at night time. About 55% of accidents occur during this period. The highest fatal traffic accident rate occurs on curved roads at nighttime. The existing conventional light systems do not provide illumination in the right direction on curvy roads. Due to this constraint, a need to understand an alternative technology solution. The aim is to improve visibility for driver and so achieve a significant increase in safety and driving comfort. This calls for a flexible front light for automobiles to illuminate the road ahead in the night corner. Adaptive front lighting system (AFS) helps improve driver’s visibility at night time hence achieving enhance safety. AFS (adaptive front-lighting system) used to detect information about the corner in advance with help of sensor which detects the information send it to the motor to adjust headlamps to get the lighting beam which was suitable for the corner. Through this way, it could avoid "blind spot" caused by the fixed lighting area when coming into the corner, and improve driving safety

Addressing the Issues of Text Analytics

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd February 2018

S.N.Sithi Shamila | Dr.D.S.Mahendran, Dr.Mohamed Sathik

Abstract

The revolution that has swept through information Processing arena has placed the modern world in a unique vantage position. Huge quantum of data has been generated through the normal operations of day-to-day business activities in various fields such as public services, Research, Education, Industries and Institutes. The multiple level transactions captured in these fields have generated such an enormous amount of data which are so challenging to handle as it swings from megabytes to petabytes, and in a swift, to zettabytes as well. The inevitability of the dependence on the Internet in this technologically revolutionized context has paved way for the increased use of data, and this situation has obviously generated considerable research interest to study user view analysis in order to determine the several characteristics of the users which might influence the development of software systems and several other technological products. It has been observed that more than 90 percent of today’s data is either unstructured or semi-structured, and this has complicated and challenged the study of decoding knowledge and information embedded in different recognizable patterns and analyze the text documents from the huge volume of accumulated data. It is in this context, the study of text mining, which is essentially a process of extracting interesting and non-trivial patterns from a large number of text documents, assumes significance. Although there are innumerable techniques and tools to mine the text in order to discover valuable information which with not only future predictions in several areas of business, social, political and economic interest can be made, also it will influence the process of decision making in several spheres. Thus, Sentiment Analysis or Opinion Mining has attained an enormous importance in the modern world today, and it is in this context, an attempt has been made in this paper to briefly discuss and analyze text mining techniques and the issues connected to text mining which affect accuracy and relevance of the results obtained.

Admission Control based Delay-Aware Routing Protocol for MANETs

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd April 2018

Sunil Kumar Jangir | Naveen Hemrajani

Abstract

Due to the recent developments in the hand-held devices and communication enhancements in wireless networks like mobile ad-hoc network (MANETs), these networks are targeted for providing real time services like video streaming, video conferencing, VOIP etc. Although, the basic design of MANETs is not fully capable to provide multimedia services, therefore some sort of quality-of-service is required in these networks. Providing requisite QoS guarantees in wireless multihop networks is much more challenging than in wired networks. In particular, it is important for routing protocols to provide QoS guarantees by incorporating metrics like achievable throughput, delay, jitter, packet loss ratio, etc. In this paper, we proposed an admission control based delay-aware routing protocol for reliable transmission of delay-sensitive multimedia applications over mobile ad-hoc wireless networks. To show the correctness and effectiveness of proposed scheme we perform simulations on various scenarios. The results obtained through simulation shows that our scheme is able to provide delay guarantees to an application whenever required.

Advanced communication Through Fleshredtacton

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th August 2017

Haritha K Sankari | B.S.Vignesh, K.R.Pooja, S.Kousika

Abstract

Our body could soon be the backbone of a broadband personal data network linking your mobile phone or MP3 player to a cordless headset, your digital camera to a PC or printer, and all the gadgets you carry around to each other. RedTacton is a new; it is completely distinct from wireless and infrared. A transmission path is formed at the moment a part of the human body in contact with a RedTacton transceiver. Physically separating ends the contact and thus ends communication. Human Area Networking technology that uses the surface of the human body as a safe, high speed network transmission path. Uses the minute electric field emitted on the surface of the human body .Technically according to the user's natural, physical movements. Communication is possible using any body surfaces, such as the hands, fingers, arms, feet, face, legs or torso. RedTacton works through shoes and clothing as well. Here, the human body acts as a transmission medium supporting half-duplex communication at 10Mbit/s. The key component of the transceiver is an electric-field sensor implemented with an electro optic crystal and laser light.

Advanced Control of DFIG for Wind Energy Conversion System Using Integrated Active Filter

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th December 2017

C.Mohan Krishna | T.Manohar, K Purushotham, S.Imrankhan, A.Venkata Prasad

Abstract

Now a day’s harmonics are a serious problem in power systems. Due to non-linear loads being added to electrical systems harmonics are generated, which causes the system equipment damage. For improvement of power quality, we are using DFIG with active filters. Doubly Fed Induction Generator for Wind Energy Conversion Systems deals with the operation of doubly fed induction generator (DFIG) with an integrated active filter capabilities using the grid-side converter (GSC). The main contribution of this work lies in the control of GSC for supplying harmonics in addition to its slip power transfer. The rotor-side converter (RSC) is used for attaining maximum power extraction and to supply required reactive power to DFIG. Wind energy conversion system (WECS) works as a static compensator (STATCOM) for supplying harmonics even when the wind turbine is in the shutdown condition. Control algorithms of both GSC and RSC are presented in detail. Implemented project DFIG-based WECS are simulated using MATLAB/Simulink.

Advanced Recent Trends in Computing & Information Technology

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd May 2018

Ameet Kurli | Nancy Dias

Abstract

21st century has been defined by application of and advancement in information technology. Information technology has become an integral part of our daily life. Information technology has served as a big change agent in different aspect of business and society. It has proven game changer in resolving economic and social issues. Information technology has been one of the most encouraging research areas throughout the globe over the past two decades. From commerce and government to scientific discovery, healthcare, education, entertainment, and environmental management, information technology is indispensable and will continue to fuel further advances in all facets of human endeavours. The focus is mainly on the intelligent computing techniques as well as the emerging applications of information technology. Its aim is to unify the picture of contemporary intelligent computing techniques as an integral concept that highlights the trends in advanced computational intelligence and bridges theoretical research with applications.

Advanced Vehicle Tracking and Trapping System

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th October 2017

Vishnu C.R | Surag M.T, C. Raseek

Abstract

The advanced vehicle tracking and trapping system is very much useful in the increasing vehicle robberies of the world. This system has been implemented with Arduino, Global Positioning System(GPS) and Global system for mobile communication (GSM) technology, with a relay in order to stop the vehicle and android phone application in order to provide a user friendly environment. In addition to this a trapping and locking system is implemented. Trapping system is an internal ring gear attached with a DC motor which lock the driver in the seat and don’t let him escape. The locking system is a rack and pinion arrangement with a DC motor, installed inside the door by making a hole. In this advanced world simple tracking system is not effective, by chance we reach the vehicle there is a chance to the escape of the thief. We can’t control these robberies if the thief is escaped. This system is helpful to give real punishment to the intruder. In such a situation everything set in a simple mobile application in a cost effective way is very convenient for the user.

Advancement of BLE Supported Healthcare System with Cloudlet

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

Atrayee Gupta | Nandini Mukherjee

Abstract

Previously, we defined Predictor virtual sensor as a precognitive sensor that can be utilized to track events in the priory, which is otherwise impossible for the resource-constrained physical sensor. In this paper, we explain how to embed intelligence with Bluetooth Low Energy supported health sensors, such as smart bands, using a PaaS based cloudlet architecture and Predictor virtual sensor. Here, we provide results using graphical analysis and mathematical models of case studies for precognition, which can be used for other kinds of sensors as well.

Agribot-“Future Farmer’s Friend"

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th July 2017

P.Santhi Priya | Angel Prescilla Jean Pierre, Somdutta Bose, Dilli Babu.U, Indumathi.K

Abstract

This robotic vehicle is an agricultural machine of a considerable power and great soil clearing capacity. This multipurpose system gives an advance method to sow, plough, water and cut the crops with minimum man power and labour making it an efficient vehicle. The machine will cultivate the farm by considering particular rows and specific column at fixed distance depending on crop. Moreover the vehicle can be controlled through Bluetooth medium using an Android smart phone. The whole process calculation, processing, monitoring are designed with motors & sensor interfaced with microcontroller

Agrikart: A New Revolution Agriculture

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th July 2017

Dr. B Shadaksharappa | Mr. Venkatesh Kumar M, Rajesh G,S Srijayanth, Mrs. Myneni Chandana, Chaithra R S

Abstract

The project is based upon Wireless Sensor Network and an android based interface. The advanced development in wireless sensor networks can be used in monitoring various parameters in agriculture. Due to uneven natural distribution of rain water, it is very difficult for the farmers to monitor and control the distribution of water to agricultural field as per the requirements of the crop. There is no ideal irrigation method for all weather conditions, soil structure and variety of crop cultures. The sensors are used to collect various data which is to be then analyzed. The android interface provides the farmer with a framework to communicate with experts and get immediate response. It also provides them detailed information about the governmental policies which they can make use of. The main motive of this idea is to provide the analyzed soil sample and the best suggestion on which crop will minimize the cost and maximize the profit. The application also gives specific weather predictions for the day/week. Details on agricultural loans with their interest rates are also shown in the android application interface. This project aims to reduce the stress and problems that adversely affect the farmers resulting in the loss of crops and human lives.

AI in Cyber Security

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

B.Arshia | M.Gayathri,P.Manaswini

Abstract

Today cyber security is something which can’t be handled by human security analysts alone. They need some degree of automation and this is where AI (Artificial Intelligence) comes into the picture. Today the world has coupled with the widespread absorption of cloud and mobile technologies having made an infinite platform to cyber security problem. AI-driven cyber security methods are able to learn and get better as they evolve by using the technique like AI2 (AI square), QRadar. By using these methods we show that the system learns to defend against unseen attacks and thus detection rates are reduced fivefold. This in turn helps to keep the systems, networks and sensitive data secure.

Algorithm for Protection of Key in Private Key Cryptography

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Neha Tyagi | Ashish Agarwal, Anurag Katiyar, Shubham Garg,Shudhanshu Yadav

Abstract

This paper is in reference with our previous paper entitled “Protection of Key in Private Key Cryptography” published by “International Journal of Advanced Research” in Feb 2017 edition... In this paper we have tried to devise an algorithm that would protect the key in transmission, as in the era of digitization, threats to information security instigate the concerned people to take proactive measures for communication between two communicating parties. Since our major focus is on the symmetric key cryptography, also called as private key cryptography, we have studied different techniques of securing a private key or shared key or secret key that are used to shield information in such systems. The different statistical data being published so far and recent phishing scam which plays with the information transfer by taking away the user’s identity highlights the need to make our security measures strong enough to counter such unwanted accesses. After looking into the functioning of widely accepted protocols and thinking of introducing a few changes to enhance their functionality, we here, are going to focus mainly on application of asymmetric key cryptographic algorithm named RSA algorithm. We have already referred to suggestions by means of several research papers being published so far related to our area of interest such as N-Prime RSA, magic rectangle, etc. We have tried to present a method taking one step ahead in the available sketch and without diminishing the basic essence of the algorithm. We also refer to some examples and its application as thought of in its modified form to further support our idea.

Algorithms for Underwater Video Enhancement

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th July 2017

Ketan Awade | Tejashree Badve, Mohit Dhale, Prof. S. M. Kulkarni

Abstract

The paper describes the techniques for underwater images and videos enhancement. Initially the conventional approaches like wavelength compensation and image dehazing (WCID), dark channel prior method, contrast limited adaptive histogram equalization (CLAHE) have been studied and analysed. Analysis of all the three methods have highlighted the shortcomings of the individual methods. The fusion method is described in this paper which has exhibited comparatively better results for the enhancement of underwater images and videos. In the proposed method the inputs are taken from the degraded images, the colour correction and the contrast enhancement techniques are applied on the input image. The weighted maps are used for increasing the visibility of the degraded object due to absorption and scattering. The resultant output is characterized by lower noise, improved contrast and better exposed dark regions.

Alternative Optimization Algorithm for Channel and Clipping Amplitude Estimation in IoT-based Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th June 2018

Thasni mol.K | 

Abstract

- Internet of Things (IoT) is the idea to connect all devices to the internet. In IoT based devices the transmitter side should be low cost and low power. So the complexity of transmitter side should be transferred to the receiver side. Orthogonal Frequency Division Multiplexing (OFDM) is widely recognized as one of the key techniques for high data rate communications in wireless networks. The advantages of OFDM include high spectral efficiency, immunity against multipath fading and negligible inter-symbol interference. But it has a drawback of high PAPR. Among the PAPR reduction techniques clipping is selected because it is the simplest and cost-effective method. In this work, the joint estimation of clipping Amplitude and MMSE based channel estimation method has been proposed and evaluated. Here the channel is estimated by using MMSE technique and an iterative amplitude reconstruction method is used to estimate the clipping amplitude. An alternative optimization algorithm is used for the joint estimation of channel and clipping amplitude which is based on frequency domain block type training symbols. Here the channel is estimated by using LS and MMSE and made a comparison between them. The simulation results show that the MMSE has better performance than LS channel estimation in terms of SNR and MSE. The efficiency of these algorithms is evaluated by using CRLB calculation and achieves that lower bound at medium SNR. The simulation result shows a good performance without any prior information.

Amalgamation of Mind Wandering with Military and Defence

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Priyanka Tripathi | Tanu Varshney, Priyanka Chaudhary , Vimal Singh

Abstract

In this paper we are going to present, how to curb the affect of mind wandering during military training and in the field of defence. Basically, mind wandering software will check the ability to stay focused on the task and make t imely decisions. This paper also discuss about the different types of training that is provided to the soldiers and about the consequences of the mind wanderi ng pills.

An Adaptive Method for Multi-Level De- Duplication With the Improved Encryption Techniques in Cloud Environment

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th December 2017

Aruna T M | Rajeswari R, Lavanya H V , Meghana B S

Abstract

As we all know that the sensors are the most important part of the embedded system and the robotics world. By using different types of sensors, we can minimize the logic circuits and also make the system more efficient to get output by taking less input. Therefore, here is detailed view of different types of sensors and their applications in the different fields

An Adaptive Method for Multi-Level De- Duplication With the Improved Encryption Techniques in Cloud Environment

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th December 2017

C.Edward Jaya Singh | E.Baburaj

Abstract

These In the present scenario the magnitude of Information Technology dominates each and every field of cells of research. Due to the rapid development in Information Technology, various issues and challenges in storage and security hit the top corner of the atmosphere which provides a solution in the form of cloud technology. In order to make use of the technology in an efficient fruitful manner de-duplication is a concept of elimination and replication which improves the storage and the base of encryption leads to the better contribution in the level of security. Various methods and techniques are been developed for secured storage level in cloud based environments. In order to overcome the complexities and to make an optimal solution; Here, it is proposed a novel method for de-duplication with the improved encryption techniques with the hybridization of AES and RNG Crypto technique. The performance is evaluated with parameters such as Size and computational time. Based on the experimentation results the proposed method provides better results compared to the existing methods.

An Agglomerative Clustering Method for Solving Vehicle Routing Problem

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th November 2017

P Praveen | B. Rama

Abstract

A magnified arrangement is intended for the vehicles to diminish the aggregate cost of dissemination by which it can supply the products to the clients with its referred to limit can be named as a vehicle directing issue. In factor neighbourhood look technique, chiefly a productive vehicle steering can be accomplished by figuring the separation network esteem in view of the client's area or the way where the client's lives. The fundamental target of the paper is to lessen the aggregate separation made a trip to convey the products to the clients. The proposed calculation is a chain of importance based upgraded agglomerative bunching calculation procedure which is utilized as a part of the information mining situation successfully. The proposed calculation diminishes the aggregate separation doing out to every course and the vital thing need to consider is that the improved grouping calculation can decrease the aggregate separation when contrasted with the beforehand proposed variable neighborhood seek strategy.

An Analysis of Image Enhancement Based On Histogram Equalization Methods

International Journal of Engineering Research in Computer Science and Engineering, Available online 18th April 2018

S. Dhivya Bharkavi | Dr. Grasha Jacob

Abstract

Histogram Equalization is the most familiar method used in the analysis of contrast and brightness in images. The objective of image enhancement techniques is to process images based on Histogram Equalization so that the result is more suitable than the original image for a specific application. The choice of the technique depends upon the requirement. Histogram equalization method is powerful compared to other methods as it increases the global contrast of many images, especially when the usable data of the image is represented by close contrast values. Through histogram equalization, the intensities can be better spread on the histogram and this allows for areas of lower local contrast to improvement a higher contrast. Various methods have been proposed for limiting the levels of enhancement and most of the enhancement algorithms are based on Histogram Equalization. A comparative study is done on Brightness Preserving System with histogram equalization (BBHE) and Recursive Method of BBHE. Recursive Mean-Separate Histogram Equalization (RMSHE) is another improvement of BBHE. These algorithms clearly state that the Image enhancement using Histogram equalization significantly improve the visual appearance of the image.

An Analysis of Keyword Search Retrieval Techniques on Multi-Dimensional Datasets

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th October 2017

Mrs. R.Ramya Devi | T.Shanmuga Priya

Abstract

Information retrieval (IR) is the activity of obtaining information resources relevant to an information need from a collection of information resources. Searches can be based on full-text or other content-based indexing. Information retrieval is the most concentrated research field in the real world environment which enables users to retrieve the contents stored in the web. Keyword based search retrieval make ease of this task which can find the most similar information present web source accurate by computing similarity distance between the keywords submitted and the information present on web source. However keyword based similarity finding on multi-dimensional data would be more difficult task which required more computation to be performed. In this analysis work, comparison evaluation of different methodologies that are implemented to perform keyword based search retrieval on multi-dimensional data set has been discussed. Those research methodologies have been discussed based on their working procedures in detail. The different existing research methods are compared in detail based on their merits and demerits. The comparison analysis of research methods are conducted by comparing them with each other in terms of their merits and demerits. From this analysis, efficient research methodology that can perform key word based search retrieval in the flexible and accurate way can be identified in terms of performance improvement.

An Analytical approach on Data Mining in AgriClinics-A Survey

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd March 2018

K.P.Mangani | Dr. R.Kousalya

Abstract

“Most things except Agriculture can wait” is the statement by Jawaharlal Nehru. To utilize the agriculture in a better way this paper handshakes with the Information technology and establish Agri Clinics which are envisaged to provide expert advice and services to farmers on various aspects like cropping practices, plant protection, crop insurance, post-harvest technology, clinical services for animals, feed and fodder management and crop prices to enhance the productivity of crops and increase the incomes of farmers. The goal of this survey provides a review of different types of data mining approaches and problems being addressed in agriculture-related fields.The agriculture-related data are recorded but they are not digitized so they are integrated in the standardized format which deals with big data that bridge the knowledge of the data to the yield estimation and gives an analytical approach to support decision-making system and recommendations for farmers in agriculture-related fields.

An approach for classification of plant leaf disease using back propagation neural network

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

V.Gayathri | S.Sakkaravarthi

Abstract

In rural field loss of yield for the most part happens because of broad of ailment. Generally the discovery and recognizable proof of the ailment is seen when the ailment advances to extreme stage. The framework is proposed to recognize and characterize the infections in leaf utilizing the picture handling procedures beginning from picture securing, pre-preparing, preparing and testing. . Picture handling strategies for this sort of choice examination includes preprocessing, highlight extraction and characterization arrange. At Processing, an info picture will be resized and area of intrigue choice performed if necessary. Here, shading and surface highlights are extricated from a contribution for arrange preparing and order. Shading highlights like mean, standard deviation of HSV shading space and surface highlights like vitality, complexity, homogeneity and relationship. . Highlights are extricated by the GLCM. BPN-FF classifier will be utilized for arrangement in view of learning with the preparation tests and along these lines giving the data on the irregularity (Early leaf spot, late leaf spot). The framework will be utilized to characterize the test pictures naturally to choose leaf either variation from the norm or great one

An Approach for Managing Different Applications Using Centralized Load Balancer in Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Abhishek | Akash Kumar , Kunal Gautam, Suresh, Mrs Vani.K.A

Abstract

The data centers and end users are distributed across the globe in a large cloud environment. It is a tiresome situation for cloud data centers to serve huge requests coming from these end users. As a consequence, load balancing mechanism is used to distribute the loads efficiently and effectively among different nodes. To achieve high user contentment and high resource employment ratio, load balancers are used. In this paper we have used a central load balancer to balance the loads among different virtual machines in cloud data centers.

An Arduino Uno Microcontroller Based Prototype Overvoltage and Overcurrent Protection System

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th November 2017

Sourin Bhattacharya | Victor Sarkar, Priyam Sadhukhan, Nirab Majumder, Sarbojit Mukherjee, Sourav Saha

Abstract

It is of significant academic interest to develop cheap, dependable and robust protection systems for simple electrical circuitries for both academic and commercial usage. This research paper is intended to propose and implement a prototype overvoltage and overcurrent protection scheme of single phase two terminal passive circuits utilizing the Arduino Uno microcontroller and the Arduino Software (IDE). The proposed scheme would acquire and process conditioned analog input values of voltage and current of a system in real time and the implemented Arduino programmes would monitor whether those values exceed a predefined threshold; exceeding that will trip a relay to protect the system. The scheme would have three major segments that are the current sensing segment, the voltage sensing segment and the relay module and these segments shall be properly interfaced with the Arduino Uno Microcontroller and the load. The scheme is tested on a resistive and a lamp load and an analysis of the obtained data through experimentation on these electrical loads suggest that the proposed scheme is essentially feasible with moderate sensitivity

An Assimilated Face Recognition System With effective Gender Recognition Rate

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th September 2017

K. Akhil Sreenivasulu | L. Guru Kumar,Dr. G. Harinatha Reddy

Abstract

Gender Recognition in Face Recognition System has prevalent applications in the fields of demographic data collection, video surveillance, security, retail advertising and marketing and it also plays a vital role on object recognition in robot research area, which has shown an intensive attention in the past few years.However, face recognition is still a challenging task since face images are easily confused by changes of the facial factors, such as illumination, pose, the different expressions, or glasses. The goal of this paper is to improve the effectiveness of gender recognition when there are affected(blurred) images in the dataset. We applied novel descriptor based COSFIRE filters to achieve the Gender Recognition[1] in the Face Recognition System. A COSFIRE filter is trainable, in that its selectivity is determined in an automatic configuration process that analyses a given prototype pattern of interest on FERET training set. Extensive experiments were conducted on the GENDER-FERET dataset which contains 474 training and 472 test samples and demonstrated robustness and effectiveness of the proposed model. It also outperforms an approach that relies on handcrafted features and an ensemble of classifiers.

An Effective Approach for Detection of Various Brain Diseases from MRI Using Classification

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th May 2018

Sibi K | Palraj K, Dr.V.Kalaivani

Abstract

Image processing is used in most of the medical applications to diagnose wide variety of diseases. Brain tumor or neoplasm is the abnormal growth of tissues in brain and its surrounding regions. Image processing consists of preprocessing, segmentation and classification techniques which consists of methods for noise removal, feature extraction and morphological operations approach which helps in detecting and extracting the brain tumor from MRI images. In this way, MRI has become a useful medical diagnostic tool for detecting abnormalities in brain images. MRI provides better results than all other medical imaging tools. MR image is a sensitive tool in detecting the brain abnormalities such as tumors and infections during the early stage of the disease. Nowadays various applications are available for diagnosing the diseases from brain images. In our proposed method, a single system is used to detect various brain diseases such as birth defects in the brain, brain tumors and stroke. The abnormalities present in the MRI image are diagnosed based on some metric values. A region-based segmentation technique is used to extract the abnormalities such as brain tumors. A decision-based classification technique is also used which gives optimized results on detecting the range and type of abnormality from the brain images.

An Effective Approach for Diagnosis of Plant Disease using ELM

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th February 2018

S.Vijayalakshmi | D.Murugan

Abstract

The objective of this paper is to identify the diseases in the leaves of all plants. The detection of disease is one of the crucial importance to increase the productivity of plants. Plant pathology is the scientific study of plant diseases, based on this study, to identify the pathogen, and classification under different kind of circumstances. In existing, the automatic plant disease detection without the training set using only prior knowledge. The proposed method, to use detects the diseases by using the ELM (Extreme Learning Machine) techniques. In the above method, initially, the ABC Clustering has approached for segments the affected area. Secondly, using TELP (Transform Encoded Local Pattern), Gradient Features, Color Histogram Techniques for extracting the features from that affected area. Finally, these extracted features are given to the ELM classifier to get the exact type of disease affected by a leaves

An Effective Candidate Refinement Approach for High Dimensional Of K-Nearest Neighbour Search

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th December 2017

Guddati Venkata Satya Sriram | Dr.N.K.Kameswara Rao

Abstract

The volume of various non-textual content data is growing exponentially in the present viable universe. A conventional way of extracting helpful information from such records is to direct substance material generally in view of likenesses exertion. The most effective method to manufacture data frameworks to enable youthful comparability to discover on a major scale is an issue of developing significance. The endeavor is that trademark stacked actualities are normally spoken to as unreasonable dimensional trademark vectors, and the scourge of dimensionality orders that as dimensionality develops, any hunt methodology analyzes an expanding number of huge parts of the dataset lastly worsens its execution. In this article, we take a gander at a few key issues to enhance the precision and effectiveness of high-dimensional comparability asks. This paper is set non-surmised quickening of high-dimensional nonparametric operation including k closest neighbor classifiers. We endeavor to make the most the way that despite the fact that we require particular responses to nonparametric questions, we by and large don't have to expressly find the records directs close Toward the Inquiry, however simply need to answer inquiries concerning the homes of that arrangement of records focuses

An Effective model for mutagenesis prediction using Multi-relational Fuzzy Tree

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Dr. C.R.Vijayalakshmi | Dr. P.G Sivagaminathan, Dr.M.Thangaraj

Abstract

Most of the real world applications such as Loan approval, Credit card fraud detection etc uses relational databases which contain multiple relations that are inter-linked with the help of primary and foreign keys. It is very tricky to examine these applications with the help of traditional classification methods such as RIPPER and RIDOR. These methods are suitable for single relation and generate simple and comprehensible rules. But it cannot handle uncertainties and noises present in the real dataset. This paper presents a novel method for generating multi-relational classification model for mutagenesis prediction. The classifier is constructed based on the fuzzy extension of the decision tree. The experimental results show the efficiency of the proposed method compared to the existing algorithms

An Efficient and Fine-grained Big Data Access Control Scheme with Privacy preserving Policy

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd May 2018

M. Leela Amani | PK. VenkateswarLal, M. Sujatha, D. samatha, G. Subhasri

Abstract

How to manage the access of the massive amount of huge knowledge becomes a awfully difficult issue, particularly once huge knowledge ar keep within thecloud. Ciphertext-Policy Attribute based Encryption (CP-ABE) may be a promising secret writing technique that {allows} end-users to encode their knowledge beneath the access policies outlined over some attributes {of knowledge |of knowledge| of information} shoppers and solely allows data shoppers whose attributes satisfy the access policies to decode the information. In CP-ABE, the access policy is connected to the ciphertext in plaintext type, which can also leak some non-public data regarding end-users. Existing ways solely part hide the attribute values within the access policies, whereas the attribute names ar still unprotected. During this paper, we have a tendency to propose AN economical and fine-grained huge knowledge access management theme with privacy-preserving policy. Specifically, we have a tendency to hide the complete attribute (rather than solely its values) within the access policies. to help knowledge coding, we have a tendency to additionally style a unique Attribute Bloom Filter to judge whether or not AN attribute is within the access policy and find the precise position within the access policy if it's within the accesspolicy. Security analysis and performance analysis show thatour theme will preserve the privacy from any LSSS accesspolicy while not using a lot of overhead.

An Efficient and Reliable Diverse Keyword Ranked Search Scheme Over Ciphered Cloud Data

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Ms. Shruthi | Mehul Bhatt, Pushpa J, Sobin Baby, Akhil K. Manoj

Abstract

Due to the increasing popularity of cloud computing, more and more data owners are motivated to outsource their data to cloud servers for great convenience and reduced cost in data management. However, sensitive data should be encrypted before outsourcing for privacy requirements, which obsoletes data utilization like keyword-based document retrieval. In this paper, we present a secure multi-keyword ranked search scheme over encrypted cloud data, which simultaneously supports dynamic update operations like deletion and insertion of documents. Specifically, the vector space model and the widely-used TFxIDF model are combined in the index construction and query generation. We construct a special tree-based index structure and propose a “Greedy Depth-first Search” algorithm to provide efficient multi-keyword ranked search. The secure kNN algorithm is utilized to encrypt the index and query vectors, and meanwhile ensure accurate relevance score calculation between encrypted index and query vectors. In order to resist statistical attacks, phantom terms are added to the index vector for blinding search results. Due to the use of our special tree-based index structure, the proposed scheme can achieve sub-linear search time and deal with the deletion and insertion of documents flexibly.

An Efficient and Secure Anti-Collusion Data Sharing Scheme for Dynamic Groups in the Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd August 2017

Nagesh S | A H Shanthakumara

Abstract

In cloud giving security, ensures for the sharing information record. Sadly, in view of0the continuous variation of the participation, allocation files while giving protection careful is so far a difficult issue, specially for an untrusted0cloud on account of the arrangement assault. In this exploration work, we propose an ensured information sharing course of action for dynamic individuals. Right off the bat, we propose a protected course for key appointment with no secured correspondence channels, and the clients can safely get their private keys from social event boss. Moreover, our course of action can complete fine-grained find the opportunity to control, any client in the party can utilize the source in the cloud and denied clients can't get to the cloud again after they are repudiated. Thirdly, we can shield the plan from intrigue strike, which proposes that deny clients can't get the exceptional information record paying little regard to the probability that they outline with the untrusted cloud. This course of action can accomplish fine practicality, which gathers past clients require not to revive their private keys for the circumstance either another client appreciates the social event or a client is denied from the party.

An Efficient Approach for Image Retrieval Based on Xor Distance Using Binary Hash Codes

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th May 2018

Prateek Prince Thakur | Arpit Chaudhary, Vibhav Prakash Singh, Rajeev Srivastava

Abstract

Deep learning has given very promising results in the field of image retrieval. These results are generally built on the already existing deep learning systems that are used for the standard classification problem. A popular techniques in this domain employees binary hash codes which are used as the semantic representation of the image. The approach has a major bottleneck relating to the time of computation. Our idea is built around combining this approach and performing clustering based upon the hash code. The relevant clusters are then obtained by both direct matching as well as appropriate clusters within some small hamming distance.

An Efficient Loom of Vegetation Exploration in Remote Sensing Images Using Object-Based Threshold Classification

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th November 2017

Dr. D. Napoleon | S. Dhanya Shree

Abstract

In recent years, despite the increased availability of high resolution satellite images there is a growth of extensive research in field of remote sensing image analysis. As such, there is a need for simple and efficient image classification technique to classify the remote data. The input data is obtained from the Landsat-7 satellite, which formulates to accomplish remote sensing image classification. This research work has been done with Object Based Threshold Classification to find the vegetation exploration with Normalized Vegetation Index, Near Infra-Red and visible brightness. The resultant land cover image with Object-Based Threshold The classification has more data classes and higher resolution than the normal image classification techniques. This research paper discusses an efficient and effective use of image classification which helps to classify the vegetation exploration in remote sensing images.

An Efficient Method for Software Reliability Using Modified Genetic Algorithm: Inflection S-Shaped Model

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th November 2017

Dr. R.Satyaprasad | G. Bharathi

Abstract

In order to assess software reliability, many software reliability growth models (SRGMs) have been proposed in the past four decades. In principle, two widely used methods for the parameter estimation of SRGMs are the maximum likelihood estimation (MLE) and the least squares estimation (LSE). However, the approach of these two estimations may impose some restrictions on SRGMs, such as the existence of derivatives from formulated models or the needs for complex calculation. In this paper, we propose a modified genetic algorithm (MGA) to assess the reliability of software considering the Time domain software failure data using Inflection S-shaped model which is NonHomogenous Poisson Process (NHPP) based. Experiments based on real software failure data are performed, and the results show that the proposed genetic algorithm is more effective and faster than traditional algorithms

An Efficient Restoration Mechanism for Big Data Analysis of Cloud Using Compression Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th February 2018

M. Bairavi | M.Chandraleka, A.Meenakshi, S.RAMPRAKASH

Abstract

With the rapidly increasing amounts of data produced worldwide, networked and multi-user storage systems are becoming very popular. However, concerns over data security still prevent many users from migrating data to remote storage. The conventional solution is to encrypt the data before it leaves the owner’s premises. While sound from a security perspective, this approach prevents the storage provider from effectively applying storage efficiency functions, such as compression and deduplication, which would allow optimal use of the resources and consequently lower service cost. Client-side data deduplication, in particular, ensures that multiple uploads of the same content only consume network bandwidth and storage space of a single upload. Deduplication is actively used by a number of cloud backup providers as well as various cloud services. Unfortunately, encrypted data is pseudorandom and thus cannot be deduplicated: as a consequence, current schemes have to entirely sacrifice either security or storage efficiency. In this paper, we present schemes that permit a more fine-grained trade-off in data chunk similarity. The intuition is that outsourced data may require different levels of protection, depending on how popular it is: content shared by many users. Various deduplication schemes are analyzed and provide experimental results that show proposed secure data chunk similarity provide improved results in real time cloud environments

An Efficient Reversible Data Hiding Approach on Digital Video for Secret Data Communication

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

M.Rajakumari | S.Muthukumar

Abstract

The undertaking proposes the upgrade of security framework for mystery information correspondence through encoded information inserting in Shading pictures. In this examination, the writers propose a steganalytic plot for advanced video spread range (SS) information covering up. The proposed technique gauges both the shrouded message and the pickup factor of the SS installing rules. In this strategy, the cover outlines are first assessed and are contrasted and the gotten video outlines. At that point, the remaining lattice is processed and particular highlights are extricated from this framework and additionally the video outlines and assessed outlines. The help vector machine, at that point applies to the extricated highlights to arrange the video as either spotless or suspicious. In the event that the video is announced suspicious, both the shrouded message and the installing procedure pick up factor are assessed and subsequently the first video is remade. The reproduction comes about affirm the achievement of the creators' proposed strategy in identifying the stego video, estimation of the shrouded message and pick up factor and in addition recreation of the first video.

An Efficient Routing and Security Based on CBZA Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th June 2018

S. Muneeswari | N. Venkatesan

Abstract

MANET is one of the wireless Ad Hoc networks with wireless nodes under mobility. Due to its configuration and maintenance capabilities arises the security challenges in MANET. In this paper, an efficient routing with security based protocol towards mobile ad hoc networks is proposed. To provide security against malicious attacks an effective Cluster Based Zone Allocation (CBZA) algorithm is presented. Through NS2 simulations, the proposed CBZA method is compared with the MDR protocol. The proposed method achieves better reliability along with reduced energy consumption and improve the security also. Key generation is used for point to point and end to end communication achieved by Elliptic Curve Cryptography (ECC), is more scalable and requires lesser memory for storing keys. Also, the simulation results promises the detection of misbehaviour nodes and improved security

An Efficient Steganographic Approach for H.264/AVC Compressed Videos

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th March 2018

Saurabh Anand | Anand Singh Jalal

Abstract

Steganography is the art and science of communication which hides the presence of secret information. In this paper, a novel approach to hide the secret information in videos has been proposed for H.264/AVC compressed videos. H.264/AVC is known to be highly efficient and network friendly coding technique. In the proposed approach, we have utilized the F5 algorithm for preventing statistical attacks and improving embedding efficiency. Perceptual quality has been taken into consideration while using the Steganographic technique as well as after the compression by the H.264 method. Firstly, the videos are compressed and then the Steganographic method is applied. From the results, it is evident that F5 method gives the better PSNR values as far as perceptual quality is concerned.

An Empirical Analysis of Component Based Software Engineering and Critical Evaluation of Component Selection using Analytic Hierarchy Process: A Quantitative Approach

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd February 2018

Jogannagari Malla Reddy | S.V.A.V. Prasad

Abstract

The Component Based Software Engineering (CBSE) is a sub discipline in Software Engineering, which would build the complex systems with integration of reusable prebuilt components. The reusable components are available in the Commercial of the Shelf (COTS), which are developed by third parties. The reusable concept reduces the development time, budget and human efforts in the software process. The requirement engineer performs crucial role in examining and selecting the proper component based on multiple criteria from the COTS. Analytic Hierarchy Process (AHP) provides the effective quantitative approach, which tackles such critical Multi Criteria Decision making problems. The intent of the paper is to evaluate and select the proper component from COTS using AHP, which leads to the customer satisfaction, reduces ambiguity, and prevents the software failure.

An Implementation of Algorithm based on Back Pressure using Shadow in Wireless Ad Hoc Network

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th November 2017

Mohammad Sirajuddin | 

Abstract

In this work, organize coding has been as of late connected to remote systems to build throughput. Back-weight sort calculations in light of the calculation by Tassiulas and Ephremides have as of late gotten much consideration for mutually directing and planning over multi-bounce remote systems. We investigate the execution of backpressure directing and booking for TCP streams over remote systems. TCP and backpressure are not perfect because of a crisscross between the clog control system of TCP and the line measure based steering and planning of the backpressure structure. We decouple the steering and planning segments of the calculation by outlining a probabilistic directing table that is utilized to course bundles to per-goal lines. The planning choices on account of remote systems are made utilizing counters called shadow lines.

An Improved Genetic Algorithm in C for Knapsack Problem

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th August 2017

Manpreet Kaur | 

Abstract

Genetic Algorithms (GA) provide a simple method to solve complex optimization problems. The performance of a Genetic Algorithm mainly depends on the genetic parameters, operators and the fitness function used. This paper proposed an improved Genetic Algorithm to solve a NP-hard problem i.e. Knapsack problem. The Improved GA is implemented using C programming language. It gives better results when compared against an existing GA to solve the Knapsack Problem. This paper also proposes an optimal parameter setting for Knapsack Problem using GA.

An Inexpensive Vision-Based System to Accurately Detect EOR for Automobile Safety

International Journal of Engineering Research in Computer Science and Engineering, Available online 18th November 2017

A.Sri Lakshmi | D.Shekar Goud

Abstract

Distracted driving is one of the main causes of vehicle collisions in the United States. Passively monitoring a driver’s activities constitutes the basis of an automobile safety system that can potentially reduce the number of accidents by estimating the driver’s focus of attention. This paper proposes an inexpensive vision-based system to accurately detect Eyes Off the Road (EOR). The system has three main components: 1) robust facial feature tracking; 2) head pose and gaze estimation; and 3) 3-D geometric reasoning to detect EOR. From the video stream of a camera installed on the steering wheel column, our system tracks facial features from the driver’s face. Using the tracked landmarks the system computes head pose and gaze direction

An Innovative Approach for Age and Gender Estimation from Facial Images

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th January 2018

J. Suneetha | 

Abstract

In this paper, an innovative approach age estimation method based on decision level fusion of global and local characteristics is proposed. The structure and occurrence knowledge of human faces which are extracted with active appearance representations (AAR) are used as global facial characteristics. The local facial characteristics are the wrinkle characteristics extracted with Gabor filters and skin characteristics extracted with local binary patterns (LBP). Then facial characteristic classification is performed using an Innovative classifier which is the combination of an age group classification and specific age estimation. In the age group classification level, three distinct support vector machines (SVM) classifiers are trained using each characteristic vector. Then decision level fusion is performed to combine the results of these classifiers. The specific age of the classified image is then estimated in that age group, using the aging functions modeled with global and local characteristics, separately. Aging functions are modeled with multiple linear regressions. To make a final decision, the results of these aging functions are also fused in decision level.

An Innovative High-Performance E-Governance of Its Citizens To The Services of The Center in Rajasthan State

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th July 2017

Praveen Kumar Sharma | Vijay Singh Rathore

Abstract

The growth of the internet is due primarily to the interests of the private sector, but the Government is now one of the revolutions. Governments all over the world are taking important steps to make their services and on the Internet to provide information. A range of e- Government have taken the initiative to improve the efficiency and effectiveness of the Government's internal operations, communications and civil and transactions of individuals and organizations. The Government of the use of information and communications technology tools to have a significant impact on the development and growth of the country. The importance of the major e-management in the current system is to enable national success and leading countries in this era of the digital economy in the context of government, IT and communications resources, is a concept is called e-governance.The purpose of this paper is to explore the e-Government of Rajasthan is the largest of the National is India. It is a typical task is to explore the integration of e-Government of Rajasthan, still in this article is simply trying to representatives of every aspect of governance in the State of Rajasthan in summary form.

An Insight into Plant Disease Detection Using Image Processing- A Review

International Journal of Engineering Research in Computer Science and Engineering, Available online 25th April 2018

Babu Kumar S | J Nagaraja, S Venkatesan

Abstract

India mainly depends on Agriculture, as 60-75% of Indian population depends on source of Agriculture directly or indirectly. Agriculture plays a very vital role in terms of social and economic aspects of the country. The crop productivity reduces automatically due to disease that may affect the plants, and also may reduce the quality of the crops. This paper includes a detailed survey on plant disease detection from leaf using image processing. The reason for considering leaf as a source for plant disease detection is, studies have shown that the diagnosis of diseased plant can be achieved better from properties of leaf. The better productivity of the crops is achieved if the plants have resistance against various types of diseases, which may be caused due to Bacteria, Virus or Fungi. But due to external factors and internal factors most of the plants are easily prone to get attacked by various diseases easily, resulting in reduced quality and quantity of crops or fruits. Hence detection and diagnosis of the plant disease at the right time helps in proper productivity of crops. Detection can be achieved using various features like color, intensity, region of attack, size, shape, dimensions etc. This paper presents an overview of various techniques using different methods available for plant disease detection.

An Integrated Intrusion Detection Model of Cluster- Based Visual Sensor Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd June 2018

J.Beryl Tahpenes | R.Nirmalan

Abstract

Visual sensor networks (VSNs) are highly exposed to attacks since they are arranged openly in possibly solitary environments. Due to the bulky and bursty data traffic in VSN, it thrusts the need to establish mechanisms which provide reliable data communication across the network over the unreliable channels. Optimized Adaptive Boosting (OAB) algorithm is used for detection of anomalies in sensor nodes, cluster head nodes and Sink nodes. In this paper, in order to identify the modified packets or attacked packets at the receiver side, we propose a protocol named Efficient Secure Routing for Attacker Identification (ESRAI). This paper proposes an integrated intrusion detection model of cluster-based visual sensor network by combining anomaly and misuse detection, aiming at enhancing overall detection, security and System Accuracy. The proposed integrated model provides high throughput and more security, and it increases the efficiency of entire network when compared to the existing network.

An Intelligent Appliance with Multimedia Capability

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Pooja.N | Ramya Sai.M,Rekha.P,Radha.S

Abstract

Smart refrigeration with the help of a smart fridge is a concept that finds its place in smart kitchens. The smart refrigerator is capable of sensing and monitoring its contents and is also able to remotely notify the user about scarce products via SMS (Short Message Service) and email using a GSM module. It also facilitates the purchase of scarce items by providing a link of the online website for purchase of that particular item. This assessment is done with the help of LDR and micro switches employed as pressure sensors (quantity management), odor sensor (quality management) and RFID (shelf life management). The overall food management is done based on coding done using Keil software for the same purpose.

An Intuitive Architecture for Next Generation Digital Personal Assistants

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Mehul Jain | Utkarsh Bhatia

Abstract

Current voice-based digital assistants despite their claims of being intelligent, lack abilities that a true personal assistant must possess like extendable skill set, dynamic adaptation and high context awareness. In this paper, we highlight some design and implementation requirements that must be met in order for the development of next generation digital personal assistants and propose a general architectural backbone that can be used to make headway for such personalized speechoperated assistive technology. In particular, we confer about issues of extensibility of the skill set used by the digital assistant, hypothesis generation and evaluation, extensive user adaptation, and redundant representations handling in the design. Further, we briefly discuss the research and development directions that are undertaken to tackle challenges put by such a system. We then consider a scenario and illustrate the data flow in our architecture.

An Investigation on Nearest Neighbor Search Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th August 2017

Upinder Kaur | (Dr.) Pushpa R Suri

Abstract

The goal of Nearest Neighbour (NN) search is to find the objects in a dataset A that are closest to a query point q. Existing algorithms presume that the dataset is indexed by an R-tree and searching a query point q in a large volume of a dataset, is a tedious task that effects the quality and usefulness of the NNQ processing algorithms which determined by the time as well as space complexity. The simplest solution to the NNS problem is to compute the distance from the query point to every other point in the database. However, due to these complexities issue, the various research techniques have been proposed. It is a technique which has applications in various fields such as pattern recognition, moving object recognition etc. In this paper, a comprehensive analysis on data structures, processing techniques and variety of algorithms in this field is done along with different way to categorize the NNS techniques is presented. This different category such as weighted, additive, reductional, continuous, reverse, principal axis, which are analyzed and compared in this paper. Complexity of different data structures used in different NNS algorithms is also discussed.

An Investigation on Nearest Neighbor Search Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th August 2017

Upinder Kaur | (Dr.) Pushpa R Suri

Abstract

The goal of Nearest Neighbour (NN) search is to find the objects in a dataset A that are closest to a query point q. Existing algorithms presume that the dataset is indexed by an R-tree and searching a query point q in a large volume of a dataset, is a tedious task that effects the quality and usefulness of the NNQ processing algorithms which determined by the time as well as space complexity. The simplest solution to the NNS problem is to compute the distance from the query point to every other point in the database. However, due to these complexities issue, the various research techniques have been proposed. It is a technique which has applications in various fields such as pattern recognition, moving object recognition etc. In this paper, a comprehensive analysis on data structures, processing techniques and variety of algorithms in this field is done along with different way to categorize the NNS techniques is presented. This different category such as weighted, additive, reductional, continuous, reverse, principal axis, which are analyzed and compared in this paper. Complexity of different data structures used in different NNS algorithms is also discussed.

An IoT-Cloud Based ECG Telemonitoring System for Smart Healthcare

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

Raguvaasan .S | Balamurugan .S, R.Lakshmi Devi, Dr.V.Kalaivani

Abstract

Internet of Things (IoT) promises to revolutionize the health-care sector through remote, continuous, and non-invasive monitoring of patients. An IoT platform for prediction of Cardiovascular Diseases using a Signal Quality Aware-IoT-enabled ECG telemetry system, intervals detection application has been presented that contains a Processing signal and alert physician for emergency through Android application. It is helpful for the physician to analysis the heart disease as easy and accurate. We are developing a continuous ECG monitoring system by which people can check their ECG signal even at their home, identify any problem in heart or identify cardiovascular diseases and alert the physician for emergency. The size of system is small and it requires less maintenance and operational cost

An Overview of Text Mining and Its Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th May 2018

M.Kalpana | Dr.S.Nagaprasad, Dr.Manju Khari

Abstract

In KDD data Mining step is generally involved with the pattern detection in numeric knowledge, however fairly often necessary (e.g., important to business) data is hold on within the kind of text. Unlike numeric knowledge, text is usually unstructured, and troublesome to handle. Text mining normally incorporates of the analysis of text documents with the extraction of key phrases, concepts, etc. and also the training of the text practice therein way for additional analysis with lot of data Mining approaches. In explorative knowledge Analysis, some initial information is understood regarding the info, however data mining might facilitate in a very a lot of in-depth information regarding the info. Seeking information from huge knowledge is one amongst the primary attributes of knowledge mining. Manual data investigation about for an only some periods currently, however it creates a bottleneck for big data analysis. Variety of information retrieval techniques measure developed to extract this huge quantity of knowledge. Previous studies on data processing specialized in structured knowledge, like relative and transactional knowledge. Conversely, in certainty, a substantial section of the data is hold on in text databases that consist of enormous collections of documents from varied sources, like news articles, books, digital libraries and web content.

An Unsolicited Heart Stroke Alert System for Humans

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th January 2018

S. Jeyadevan | Surya prakash.S, Sujay.S, Shivashankar.S, Sheela.L

Abstract

Health care for the elderly is one of the promising application fields of IoT. Among them, detecting and preventing indoor heatstroke conditions is a crucial issue. We propose a method for monitoring the indoor environment, detecting any risky conditions, and then effectively warning them to the elderly. Since elderly people have different physical weaknesses such as low vision and poor hearing, we designed and developed a system for alerting the elderly through multi-sensory information presentation. It can convey risky situations to the elderly via visual, auditory, and tactile stimuli.

Analysis and Implementation of Lossless Image Compression for Various Formatting Images

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

T.Vaitheeswari | Dr.R.Shenbagavalli, M.Revathi

Abstract

Digital image compression is a method of image data reduction to save storage space. Image compression is the process of reducing the size of the image that will enhance images sharing, image transmission and easy storage of the image. There are two types of image compression techniques. In Lossy compression, the compressed image is not equal to the original image; it means the quality of compressed image is less than the original image. In Lossless compression the compressed image is exactly equal to the original image. In this work, the analysis of different format of images have been implemented using the Lossless image compression techniques such as Huffman coding, EZW and SPIHT. Huffman encoding technique basically works on the rule of probability distribution. The principle is to reduce the size of the image by removing redundancies. Less number of bits is used to encode the image. Huffman encoding method is used in JPEG image. Set partitioning in hierarchical trees (SPIHT) is a waveletbased image compression technique. It gives good image compression ratios and image quality. EZW method is based on progressive encoding to compress an image. Experimental result was carried out on four types of image format such as .bmp, .jpg, .png, .tif. The Performance metrics such as Peak signal-to-noise ratio (PSNR), Compression Ratio (CR), Mean square error (MSE), Bits per pixel (BPP) were measured for each format of images

Analysis and Implementing the NTRU and Braid Group Cryptosystem Algorithms in IoT Devices

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

M.Jeyanthi | S.Parameswaran

Abstract

In this paper we give an overview of public-key cryptographic schemes based on non-commutative groups with special consideration to braid groups and we have to analysis several commonly used light weight algorithm public key-exchange protocols with the aim of establishing the best algorithms for lightweight cryptography in critical infrastructure and emergency scenarios. Most of the method currently in use are based on arithmetic over finite field. The potential advent of quantum computer is very troubling because all of these cryptosystem are easily broken by such machine. Braid group based on non-commutative algebraic structure over infinite field .Braid group have certain properties that make them easily amenable to digital computation. The main contributions of this paper are: 1.Performance analysis of several state-of-the-art public-key cryptographic algorithms like NTRU Encryption, Braid groups etc. In order to find those that are most suitable for low power computing platforms 2.Implementing security framework based on the analyses public-key key-exchange cryptographic algorithms in IOT devices. Internet of Things (IoT) enables physical things to communicate, compute and take decisions based on any network activity. *This calls for a secure solution for communication among heterogeneous devices. *In heterogeneous environment motive of each user in IoT can be different in form of communication and computation and is difficult to be judged

Analysis and Prediction of Chronic Kidney Disease using Data Mining Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th September 2017

Tabassum S | Mamatha Bai B G, Jharna Majumdar

Abstract

Data Mining in Healthcare has become a present trend for obtaining accurate results of medical diagnosis, Chronic Kidney Disease (CKD) has become an international fitness problem and is a place of concern. It is a situation where kidneys turn out to be damaged and cannot filter toxic wastes within the frame. By using Data Mining Techniques, researchers have the scope to predict the Chronic Kidney Disease. This helps doctors to diagnose and suggest the treatment at an early stage. It also helps the patients to know about their health condition at an earlier stage and follow necessary diet and prescriptions.

Analysis and Retrieval of Leaf Images Based On Feature Extraction Method

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

M.Rajeshwari | Dr.R.Shenbagavalli

Abstract

Image processing is a method to perform some operations on an image in order to extract some useful information. Feature Extraction is one of the significant techniques in image processing. In this Paper, the analysis was processed in three steps. First, the leaf images were preprocessed using Median Filter and transformed into LBP (Local Binary Pattern).Second, the retrieval was performed using feature extraction methods such as GLCM (Gray Level Co-occurrence Matrix), CGLCM (Color Gray Level Co-occurrence Matrix), Shape and Hybrid. In each method, various statistical measurements like Contrast, Correlation, Energy, Homogeneity, Entropy, Area, Perimeter, and Eccentricity were calculated. The KNN classification algorithm was used to retrieve the relevant images. The dataset was collected by capturing some 10 types of leaves using Digital Camera. Each type contains 10 images and used for analysis. Finally, the Performance measurement such as Precision and Recall were measured for each extraction method. The Hybrid extraction method produces the better result than the individual method. This analysis is used to identify the medicinal leaves and its use from the large collection of Database

Analysis of BER and Out-Of-Band Interference Enhanced Using ICTF Approach for PAPR Reduction

International Journal of Engineering Research in Computer Science and Engineering, Available online 25th November 2017

Srikanth.B | Naveen Kumar G S

Abstract

PAPR reduction in OFDM modulation scheme attains attention because of its high application ability. Tremendous work carried out in literature to solve the issue of PAPR but none can meet the desired result. Iterative companding transform and filtering is implemented in this work which achieves reliable trade-off between PAPR reduction and BER performance. Low OUTOF- BAND interference is another significant approach of proposed work. Simulation results show good performance and reliable efficiency over traditional state of methods

Analysis of Classification Methods for Diagnosis of Pulmonary Nodules in CT Images

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th June 2017

Capt. Dr. S.Santhosh Baboo | E.Iyyapparaj

Abstract

The main aim of this work is to propose a novel Computer-aided detection (CAD) system based on a Contextual clustering combined with region growing for assisting radiologists in early identification of lung cancer from computed tomography(CT) scans. Instead of using conventional thresholding approach, this proposed work uses Contextual Clustering which yields a more accurate segmentation of the lungs from the chest volume. Following segmentation GLCM features are extracted which are then classified using three different classifiers namely Random forest, SVM and k-NN.

Analysis of Cognitive Skill level of Students by Fuzzy FP Tree Growth Association to identify Frequent Pattern Mining

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th April 2018

D. Kalpanadevi | Dr. M. Mayilvaganan

Abstract

In this research, focuses on using fuzzy partition method and triangular membership function of quantitative value for each transaction item, for the generation of more realistic association using fuzzy intervals among quantitative attribute. Secondly, to implement Frequent Pattern Tree growth for deal with the process of data mining to analyze the frequent pattern item. The performance of cognitive skill of knowledge can be analyzed by the categories of logical Reasoning, Numerical Ability, and Perceptual Speed of ability and relates with parents’ education, Standard of Medium study gender and specialty.

Analysis of Data Using Hadoop and Mapreduce

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Bharti Kalra | Dr. Anuranjan Misra, Dr. D. K. Chauhan

Abstract

We are in the world of technology, where data is moving around all the time. This data is becoming bigdata when it comes in huge volume and data can be structured, unstructured or semi-structured. hadoop is the technology to analysis the big data. The objective of this paper is to analysis the data that is collected from the open source using the hadoop and mapreduce programming model.

Analysis of Density-Based Spatial Clustering In Data Mining

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

C.Vinothini | Dr V.Lakshmi Praba

Abstract

Data mining involves the association rule learning, classification, summarization, regression, anomaly detection and clustering. Clustering is a data mining technique to group the related data into a cluster and unrelated data into different clusters. Based on the recently described cluster models, there are a lot of clustering that can be applied to a data set in order to partitionate the information. DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is the most well-known density-based clustering algorithm. The aim is to identify dense regions, which can be measured by the number of objects nearest to a given point. Unlike K-Means, DBSCAN does not require the number of clusters as a parameter. It infers the number of clusters on its data, and it can detect clusters of arbitrary shape. Density-based clustering algorithms try to find clusters based on the density of data points in a region. For the experimental work, we have used the milk data set. The results were analyzed and practically tested under MATLAB tools

Analysis of Machine Learning Algorithms over Different Data Sets in R Programming

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th February 2018

R Askshara | S Kranthi Reddy

Abstract

From last two decades, onwards Machine Learning algorithms are used in many areas like the Banking sector, online sites, social network sites, Health sector etc. By applying Machine learning algorithms on past data of the organization, one can take certain decision for the benefits of organization. This paper mainly focuses on explaining the concept and applying different Machine Learning algorithms in R programming over different datasets.

Analysis of Noise in Phase Stepping Interferometry

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd March 2018

Kamal Rani | Vikas,Ajay Shankar

Abstract

In Optical Interferometric Sensors, it is important to precisely monitor changes in fringes which give change in phase information of a signal. The detection of a change in phase provides information on measurable physical parameters like the change in displacement, temperature, strain, etc. These parameters may change with respect to time, therefore; it is needed to monitor continuously changes in phase. The stepping interferometer technique is one of the most widely used techniques for phase detection. During this technique, the phase is continuously modified with known step size and therefore the detector integrates the intensity at every point over a range of phases. The various algorithms have been reported like 3-point, 4-point and much more for measuring phase shift with their own advantages and disadvantages. The various system errors like quantization of the detector signal, miscalibration of the phase shifter, detector nonlinearities, aberrations in optics measuring device, vibrations and air turbulence can affect the phase measurement. In this paper, the effect of such noises on phase detection has been analyzed to provide the least error on the measurement of phase information with high-speed measurements. It has been observed that 4-point & 5-point methods have less effect on noises interface during phase detection with noise interface 1-5% in the detected signal.

Analysis of Noise in Phase Stepping Interferometry Mobile AD - HOC Networks – Issues and Challenges

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th March 2018

Prakhar Agrawal | Subhadra Rajpoot

Abstract

This paper presents the mobile ad-hoc network’s which is also termed as (MANET’s) are less mobile networks that have no fixed routers. All nodes are able for movement and it can be connected dynamically in a proper way by using radio waves.This paper focuses on the Mobile ad – hoc networks (MANET’s), it’s classification and characteristics. This paper also focuses on the issues and challenges that are given by Mobile ad – hoc networks (MANET’s)

Analysis of Priority Scheduling Algorithm on the Basis of FCFS & SJF for Similar Priority Jobs

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Chandra Shekar N | Karthik V

Abstract

Scheduling is one of the most important activities of the process manager which take decision to choose which of the process in the ready queue will be assigned to the CPU. There are different types of scheduling algorithms available for taking decision. One of them is Priority Scheduling Algorithm, which is based on the priority assigned to each process. In priority scheduling the Processes are executed on the basis of priority, the process having highest priority is executed first. In case of similar priority FCFS is used. In this paper, the priority scheduling algorithm is used in such a way that, in case of similar priority SJF algorithm is used instead of FCFS and average waiting time and average turnaround time is calculated. The comparative analysis is performed on the SJF based priority scheduling and FCFS based priority scheduling to compare the average waiting time and average turnaround time

Analysis of Priority Scheduling Algorithm on the Basis of FCFS & SJF for Similar Priority Jobs

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Chandra Shekar N | Karthik V

Abstract

Scheduling is one of the most important activities of the process manager which take decision to choose which of the process in the ready queue will be assigned to the CPU. There are different types of scheduling algorithms available for taking decision. One of them is Priority Scheduling Algorithm, which is based on the priority assigned to each process. In priority scheduling the Processes are executed on the basis of priority, the process having highest priority is executed first. In case of similar priority FCFS is used. In this paper, the priority scheduling algorithm is used in such a way that, in case of similar priority SJF algorithm is used instead of FCFS and average waiting time and average turnaround time is calculated. The comparative analysis is performed on the SJF based priority scheduling and FCFS based priority scheduling to compare the average waiting time and average turnaround time

Analysis of Soil using Spectral Signatures

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th October 2017

Mrs. Chitra. M. Gaikwad | Prof. Dr. S. N. Kakarwal

Abstract

Soil contains organic matter, clay and particles of rock. The composition of soil varies physically as well as chemically which is important for plant growth. The traditional techniques to measure soil contents are time consuming while remote sensing provides efficient techniques for mapping these contents. The visible infrared, near infrared and short wave infra red bands of electromagnetic spectrum are used to study the soil without destructing its properties. In this paper we present the study of soil spectral signatures. The study of soil is carried out using spectral signatures obtained by using ASD field spectrometer. The association between the spectral data and the soil contents is carried out. The soil samples were collected from Shendra and Chikhalthana in Aurangabad district Maharashtra state (India). Principal component analysis is applied to these spectra for classification purpose.

Analysis of various Computing Techniques for Diagnosis of Sleep Disorders

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th February 2018

Vijay Kumar Garg | R. K. Bansal

Abstract

This paper is based on the analysis of various soft computing techniques for the diagnosis of sleep disorders especially sleep apnea, insomnia, parasomnia and snoring on the basis of following three performance parameters: accuracy, sensitivity and specificity. Many techniques and methods are adopted by researchers to implement and diagnose these sleep disorders. The current traditional technique used to diagnose these sleep disorders is polysomnography which is costly and requires human specialists and done in unique labs. Subsequently, there is a need of a more comfortable and less expensive technique to detect such types of disorders. As of late analysts concentrated on signal processing and pattern recognition as substitute modes to reveal them. The following research is focused on the detection of sleep disorders using ECG signals by applying Tunable Q-Factor wavelet transform (TQWT) and accuracy achieved by this method is 94.2%.

Analysis on Cryptographic Algorithms for Effective Secure Implementation of Cryptosystem in Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

S.Rajan | Dr.D.S.Mahendran, Dr.S.John Peter

Abstract

Security plays an important role in all types of computer system from standalone PC to computer system in the cloud. Security can be achieved through cryptographic algorithms. Cryptographic algorithms are categorized as symmetric and asymmetric based on the type of keys used. In pubic Cloud, Data is send through an insecure channel such as internet and stored in a Datacenter which is located far away from the user. So, context effective cryptographic algorithms are needed in the public cloud for transmitting, storing and handling key management. To ensure security, good and context effective cryptographic algorithm should be identified through cryptanalysis. In this paper different cryptographic algorithms are analyzed for efficiency based on computer system used to run algorithm, memory requirement, computational cost and performance

Analytics of Pollution Smart City Data using New Pattern Mining Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th January 2018

Monika Saxena | Dr. C.K. Jha

Abstract

Pattern mining algorithms are used to mine the useful data from the massive amount of IOT data. Mostly used data mining algorithms are classification, clustering, association rule and regression in which the classification and regression come under supervised learning and other two in unsupervised learning. The objective is to review different techniques applied for mining the pattern by using classification, clustering, and other algorithms. By applying parallel data mining algorithm in map-reduce framework. We have also implemented the algorithm for mining the frequent pattern from the datasets. Apriori and FP Growth algorithm have been implemented practically on the market basket dataset. As per the result, we have concluded that Apriori is better than FP Growth in terms of the time stamp. And FP Growth is better than Apriori in terms of large datasets. This paper represents the problems occur in this type of methods with little bit solution of them by a new modified algorithm.

Analyzing Internet DNS (SEC) Traffic with ?R? For Resolving Platform Optimization

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

J Uma Mahesh | Harekrishna Allu , N Chandrakanth

Abstract

This paper proposes to use data mining methods implemented via R in order to analyze the Domain Name System (DNS) traffic and to develop innovative techniques for balancing the DNS traffic according to Fully Qualified Domain Names (FQDN) rather than according to the Internet Protocol (IP) addresses. With DNS traffic doubling every year and the deployment of its secure extension DNSSEC, DNS resolving platforms require more and more CPU and memory resources. After characterizing the DNS(SEC) traffic thanks to reduction in dimension and clustering methods implemented with R functions and packages, we propose techniques to balance the DNS traffic among the DNS platform servers based on the FQDN. Several methods are considered to build the FQDN-based routing table: K- means clustering algorithm, mixed integer linear programming, and a heuristic scheme. These load balancing approaches are run, and evaluated with R on real DNS traffic data extracted from an operational network of an Internet Service Provider. They result in reducing the platform CPU resources by 30% with a difference of less than 2% CPU between the servers of a platform.

Analyzing Internet DNS (SEC) Traffic with ―R‖ For Resolving Platform Optimization

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Uma Mahesh | Harekrishna Allu ,N Chandrakanth

Abstract

This paper proposes to use data mining methods implemented via R in order to analyze the Domain Name System (DNS) traffic and to develop innovative techniques for balancing the DNS traffic according to Fully Qualified Domain Names (FQDN) rather than according to the Internet Protocol (IP) addresses. With DNS traffic doubling every year and the deployment of its secure extension DNSSEC, DNS resolving platforms require more and more CPU and memory resources. After characterizing the DNS(SEC) traffic thanks to reduction in dimension and clustering methods implemented with R functions and packages, we propose techniques to balance the DNS traffic among the DNS platform servers based on the FQDN. Several methods are considered to build the FQDN-based routing table: K- means clustering algorithm, mixed integer linear programming, and a heuristic scheme. These load balancing approaches are run, and evaluated with R on real DNS traffic data extracted from an operational network of an Internet Service Provider. They result in reducing the platform CPU resources by 30% with a difference of less than 2% CPU between the servers of a platform.

Analyzing Sentiments in One Go: A Supervised Joint Topic Modeling Approach

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd May 2018

P.Anand Kumar | Sk.Aseef, S.Siva Kumar, V.Preetham Adithya, I.Rohith

Abstract

In this work, we tend to concentrate on modeling user-generated review and overall rating pairs, and aim to spot linguistics aspects and aspect-level sentiments from review knowledge yet on predict overall sentiments of reviews. We tend to propose a unique probabilistic supervised joint facet and sentiment model (SJASM) to subsume the issues in one go beneath a unified framework. SJASM represents every review document within the kind of opinion pairs, and might at the same time model facet terms and corresponding opinion words of the review for hidden facet and sentiment detection. It additionally leverages sentimental overall ratings, which frequently comes with on-line reviews, as management knowledge, and might infer the linguistics aspects and aspect-level sentiments that don't seem to be solely substantive however additionally prognosticative of overall sentiments of reviews. Moreover, we tend to additionally develop economical reasoning technique for parameter estimation of SJASM supported folded chemist sampling. we tend to assess SJASM extensively on real-world review knowledge, and experimental results demonstrate that the planned model outperforms seven well-established baseline strategies for sentiment analysis tasks.

Analyzing tweets for Real-Time Event Detection and Development of Earthquake Reporting System

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Sumanth V | Aman A. Saxena, Jeevan B, P. Vinay, [Vageesha N. J.

Abstract

Twitter, a popular micro blogging service, has received much attention recently. An important characteristic of Twitter is its real-time nature. For example, when an earthquake occurs, people make many Twitter posts (tweets) related to the earthquake, which enables detection of earthquake occurrence promptly, simply by observing the tweets. As described in this paper, we investigate the real-time inter- action of events such as earthquakes, in Twitter, and pro- pose an algorithm to monitor tweets and to detect a target event. To detect a target event, we devise a classifier of tweets based on features such as the keywords in a tweet, the number of words, and their context. Subsequently, we produce a probabilistic spatiotemporal model for the tar- get event that can find the center and the trajectory of the event location. We consider each Twitter user as a sensor and apply Kalman filtering and particle filtering, which are widely used for location estimation in ubiquitous/pervasive computing. The particle filter works better than other com- pared methods in estimating the centers of earthquakes and the trajectories of typhoons. As an application, we construct an earthquake reporting system in Japan. Because of the numerous earthquakes and the large number of Twitter users throughout the country, we can detect an earth- quake by monitoring tweets with high probability (96% of earthquakes of Japan Meteorological Agency (JMA) seismic intensity scale 3 or more are detected). Our system detects earthquakes promptly and sends e-mails to registered users. Notification is delivered much faster than the announcements that are broadcast by the JMA.

Android Enabled Waste Management System

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

P.Anbumani | G.S.Lakshmi Kant, N.Loganathan, S.Jeevaraj

Abstract

With rapid urbanization, industrialization and population growth in India, waste management is becoming the key challenge for state governments and local municipal bodies. It will seriously affect the society and the quality of life of people. Waste collection is one of the important services provided by corporations that require huge investment and execution of this operation is high-priced. The garbage containers that are placed at public places are found to be overflowing frequently due to increase in the daily waste disposal. In this research, Android enabled waste management system using GSM network is proposed to determine filled status of the garbage container and whenever the level of the garbage reaches the threshold limit it provides the communication link between coordinator and the server

Android Speech Recognition Based Voice Command Notice Board

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th July 2017

Manikandan J | Sunaina K Bari, Dimple Prasad Hari, Suchithra P, Chaithra N C

Abstract

In this paper, the development of simple and low cost Android based wireless notice board is presented. The proposed system uses either Bluetooth or Wi -Fi based wireless serial data communication. For this purpose Android based application programs for Bluetooth and Wi-Fi communication between Android based personal digital assistant devices and remote wireless display board are used. At receiver end, a low cost microcontroller board (Arduino Uno) is programmed to receive and display messages in any of the above communication mode. Using the developed system, two different applications for displaying messages on a remote digital notice board and wireless person calling has been implemented. The developed system will therefore aims in wirelessly sharing the information with intended users and also helps in saving the time and the cost for paper and printing hardware.

Android-based College Fees Payment Application

International Journal of Engineering Research in Computer Science and Engineering, Available online 18th July 2018

Rachitha M V | A Aishwarya, Chandra Mouli Gupta, Eshan Kumar, Manish Parasher

Abstract

The primary focus of this research paper is to propose a mobile solution for college fee’s payment system. Students of the colleges have been paying all their fees such as tuition fees, hostel fees, mess fees and other college-relevant fees manually while waiting in the long queues which waste not only student’s precious time but also the college management’s time. Due to this, colleges have to maintain all the information regarding the fees manually into their databases. This paper proposes to build an android application that will give the students a freedom to pay their fees from anywhere, anytime, 24x7. Although college can provide a particular time constraint for that. This android application serves as a more reliable and effective means of paying college fees and removing all forms of delay and stress that is involved in the manual system of college fees processing

Anomaly Detection in Blockchain Using Clustering Protocol

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th January 2018

Rachana Kumari | Monica Catherine

Abstract

With the growth of technology, everyday new technologies are evolving. Blockchain is one such technology. Blockchain is a revolutionary technology which has proved its potential of being used in numerous fields like digital money or crypto-currency, IoT, Product tracing, Smart Contracts etc. Blockchain is a distributed database which allows to share or process data between multiple parties over a network of non-trusted users securely. One of the biggest advantages of blockchain is that it is fully decentralized i.e. there is no central authority which is governing it. However, it has its own set of disadvantages also. Some of these problems are its complexity, network size, large energy consumption etc. But one key problem is that there is no way to find the anomalous node i.e. nodes which are malicious. In any Blockchain network, there are two types of nodes, the one which behaves normally i.e. the honest node. But some nodes may try to cheat in the network or may have some illegal interest I.e. malicious nodes. If someone tries to monitor this node behaviour manually, it will take tremendous time and effort and is nearly impossible. So, this paper introduces a novel solution for the above mentioned problem. The problem can be solved by clustering the nodes of the network. For this, we will propose an algorithm which will help us in clustering the blockchain and then further for analysing the malicious activity of the nodes, if any performed. In this, we will divide the whole network into clusters of nodes or data points depending or based on some similar traits that they may have. Therefore the aim of our project is to segregate groups having similar traits from the blockchain network and then cluster them so that to identify the malicious node or illegal behaviour.

Anomaly Detection in Policy Authorization Activity Logs

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th December 2017

Zahedeh Zamanian | Ali Feizollah, Nor Badrul Anuar, Laiha Binti Mat Kiah

Abstract

Security in corporations is a crucial issue. As number of users in these corporation increases, the chance for having intruder also increases. It is important to develop effective methods to deal with such threat. Luckily, users leave electric footprint behind, as log files. Analyzing these log files results in examining users’ activity and detecting an intruder. Recent works have proposed methods for detecting intruders inside corporations. However, these methods are complex for today’s corporation. In this work, we proposed a lightweight and effective method to detect an intruder inside corporations using log files. The dataset in this work was provided from NextLabs, one of high-profile companies in information security. The experiment using random forest algorithm shows that this method detects intruders with 97.18% accuracy.

Anomaly Detection in Policy Authorization Activity Logs

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th December 2017

Zahedeh Zamanian | Ali Feizollah, Nor Badrul Anuar, Miss Laiha Binti Mat Kiah

Abstract

Security in corporations is a crucial issue. As number of users in these corporation increases, the chance of having intruder also increases. It is important to develop effective methods to deal with such threat. Luckily, users leave an electric footprint behind, as log files. Analyzing these log files results in examining users’ activity and detecting an intruder. Recent works have proposed methods for detecting intruders inside corporations. However, these methods are complex for today’s corporation. In this work, we proposed a lightweight and effective method to detect an intruder inside corporations using log files. The dataset in this work was provided from NextLabs, one of the high-profile companies in information security. The experiment using random forest algorithm shows that this method detects intruders with 97.18% accuracy

Ant Colony Optimization Based OD-PRRP for Wireless Sensor Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th May 2018

Dr.M.Rajeshwari | C.Manjunath

Abstract

WSNs are composed of hundreds or thousands of sensor nodes which are deployed either inside the phenomena to be observed or very close to it. These sensor nodes are responsible for collecting & processing and routing data either to other sensor nodes or directly to a base station (BS). In most of the applications, sensor nodes are deployed in a random & uncontrolled manner. These uncontrolled deployment methods cause the random distribution of nodes, i.e., node density is not uniform in the area under consideration. In WSNs, for which designing of protocols is application specific, focus on a single isolated technique cannot lead to optimum levels of energy efficiency, scalability and improved network lifetime. Consequently, exploring several energy efficient and scalable mechanisms that address several different characteristics of the network can help in contributing significant improvements in the various network performance metrics (energy efficiency, scalability, load balancing, network lifetime, overheads, delay, and throughput). The other goal of the paper is to propose an application of computational intelligence-based approaches such as Ant colony optimization which manages WSN characteristics.

ANTI ASSAULT

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th October 2017

J.Vaishnavi |  Eesita Sen, M.K.Liza

Abstract

These days physical attacks, harassments and molestations are the common practices that are being done very frequently across the globe. Safety is a prerequisite but not handy. So to bring it in the hands of the needy Anti Assault is being developed. The basic ideology behind this app is to protect victim who is subjected to different types of attacks or assault. It will be a very helpful app in future to instantly escape from danger and also catch hold the crime practiser.

AODV with Reliable and Energy Efficient Route Maintenance Phase

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

Rakesh Kumar | Manas Kumar Mishra

Abstract

AODV is a much popular reactive protocol for Mobile Ad hoc Network. But the performance of AODV is comparable in the highly mobile network due to frequent route breaks. In this paper, we proposed a modified AODV protocol with reliable and energy efficient route maintenance phase. So that in case of link failure a reliable and energy efficient backup route is selected for data packet transmission. It overall increases the packet delivery ration in a highly mobile network as well as increase the throughput and network lifetime. We simulate our proposal on discrete network simulator NS2. The result shows that our proposed approach improves the performance of AODV in terms of packet delivery ratio and network lifetime. Our approach also provides the good QoS parameters when primary route fails.

Application of Classification Algorithms for Disease Diagnosis Using Big Data Analytics

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th January 2018

Shobana.V | Dr.K.Nandhini

Abstract

A numerous amount of data is generated in the healthcare sector and mining of those data yields good results. It will also be helpful in diagnosing a particular disorder or a disease and also helps in predicting the future of the disease occurrence. Various classification algorithms in data mining have been used in research to predict a particular disease. Classification is used to find out in which group each data instance is related within a given datas et. It classifies the data into different classes based on some conditions There are many classification algorithms which includes C4.5, ID3, k-nearest neighbor, Naive Bayes, SVM, and ANN etc., which are used for classification. There are three forms of classification approaches, namely Statistics, Machine Learning and Neural Network for classification. The main objective of this study is to provide a compact source of reference for the researchers who want to use decision tree which is an important tool of data mining technology in their area of work. With this aim in mind, we compared widely used decision tree algorithms to classify types of disease and compared their performances according to six performance metrics (ACC(%), MAE, PRE, REC, FME, and Kappa Statistic). We hope that this study can provide a useful overview of the current work in this field and highlight how to apply decision tree algorithms as a tool of data mining technology. While considering these approaches this paper provides an inclusive survey of different classification algorithms of decision trees and their features and limitations.

Application of Deep learning Techniques to Natural Language Processing

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th October 2017

Sonam Gandotra | Bhavna Arora

Abstract

Deep learning refers to artificial neural networks comprising of multiple layers. The deep learning algorithms automate the representation of abstract features by composing simple representations from raw data at one level to complex representations at the higher. These algorithms have improved the current state of art results and bought new insights to the current data. In this paper, the deep neural architectures and their application on NLP have been discussed. The paper also evaluates the various approaches to train the data. Various classifications of deep neural nets are also an integral part of the paper. On the basis of architecture and transfer of information from input to output layers via hidden layers, deep neural nets have been broadly classified and elaborated. Brief comparisons of the various techniques used in deep neural networks on various parameters are evaluated and have been presented.

Application of Metaheuristic Algorithms for Optimal Allocation of DGs in Radial Distribution System

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

Srinivas Nagaballi | Vijay.S.Kale

Abstract

Metaheuristic algorithms form an important part of an area of Artificial Intelligence (AI). These algorithms are being used to find optimal solutions to a variety of problems in electrical engineering such as allocation of Distributed Generation (DG), coordination of relays, unit commitment etc. This paper presents the application of AI-based optimization algorithms to find the optimal location and sizing of DG in the radial distribution system (RDS). The problem is formulated to minimize real power loss and improve voltage stability in RDS and it is solved using metaheuristic algorithms viz. Particle Swarm Optimization algorithm (PSO), Modified teaching learning-based optimization algorithm (MTLBO) and Jaya algorithm. The results obtained using these algorithms are also compared with those obtained with the conventional analytical method. IEEE 33-bus RDS is considered as a test system. Simulation studies were carried out using MATLAB software. The novel feature of the paper is the application of recent Jaya algorithm to the optimization problem.

Application of Vectors

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th December 2017

Manjula S | Mukul Shukla, Priyam Kumar S

Abstract

This presentation deals with the day to day life application of vectors. Vectors are one the technique that an individual deals from the beginning of their educations. Navigating a person to go to a particular location is a type of vector application. Identifying someone located on the earth in terms of latitudes and longitude can also compare to the height of sea level is a form of vector. We are also going to discuss the various ways in which an individual can apply vector in their routine without their own remembrance. In this presentation, we give a brief idea about the uses of vector-like different cases of rain umbrella, projectile application and relative velocity concepts in our surroundings.

Applications of Computational Linguistics to Language Studies: An Overview

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Sakthi Vel S. | 

Abstract

Computational Linguistics is the scientific study of human languages. It is one of the most relevant interdisciplinary field of Linguistics and Computer science. Intelligent Natural Language Processing (NLP) is based on the science called Computational Linguistics (CL). It is closely connected with General Linguistics and Applied Linguistics. Computational linguistics might be considered as a synonym of automatic processing of natural language, since the main task of computational linguistics is to construct computer programs to process Text/Speech in natural languages [4]. The paper attempts to provide an introductory view about computational linguistics and its various applications to language studies. The paper has three sections. The first section deals with introduction to computational linguistics, its major divisions (applied and theoretical) and some fundamental ideas about the topic. Second section deals with structure of computational linguistics -a tree diagram representation. The third section describes the various applications of computational linguistics in close association with language studies. Finally the paper summed up with conclusion and list of references.

Applications of Internet of Things

International Journal of Engineering Research in Computer Science and Engineering, Available online 24th May 2018

Srinidhi C.N | Meghana M, Dinesh kumar G.M, Dr Anuradha S.G

Abstract

IOT (Internet Of Things) is defined as connecting things to the internet and that connections are used to provide some kind of useful remote monitoring or control to those things. In the past decade, over a billion sensors are connected to various devices providing continuous monitoring. Sensors and actuators embedded in physical objects are connected through wireless networks. The intention of the review paper is to highlight the significance of IOT in our daily lives and the impact of it on our surroundings.

Applying Map Reduction Technique with Genetic Algorithm Approach to Solve Travelling Salesman Problem

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th October 2017

Rajni |  Sunita Rani

Abstract

Travelling salesman problem is a very old mathematical problem. It models a scenario where a salesman has many cities to visit in shortest possible time. Given the distance among the cities, he must calculate the shortest route. Researchers have been working with Travelling Salesman problem for over centuries. Many models have been introduced to solve this legendary mathematical problem. In this Research Work, genetic algorithm is used to solve Travelling Salesman Problem. Genetic algorithm is a technique used for estimating computer models based on methods adapted from the field of genetics in biology. To use this technique, one encodes possible model behaviors into ''genes". We designed a new crossover technique to increase the efficiency of crossover operator of GA for TSP. We also apply map reduce algorithm to efficiently solve the TSP.

Approach of intelligent agent in Cloud resource management

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th February 2018

Manoj Sharma | Dr. Manoj Kumar Sharma, Dr. S. Srinivasan

Abstract

Rapid technological developments in Information Technology (IT) and ubiquitous Internet access are causing serious challenges in service provisioning and resource management landscapes. Cloud computing is proving to be a reliable technology to address these challenges. Service provisioning in the Cloud relies on Service Level Agreements (SLAs) representing a contract signed between the customer and the service provider including non-functional requirements of the service specified as Quality of Service (QoS) and penalties in case of violations. Flexible and reliable management of resources and SLA agreements are of paramount importance to both Cloud providers and consumers. On the one hand, providers have to prevent SLA violations to avoid penalties and on the other hand, they have to ensure high resource utilization to prevent costly maintenance of unused resources In this paper, we propose a novel Cloud management infrastructure, which is based on holistic monitoring techniques and mechanisms for low-level resource metrics to high-level SLA mapping, application scheduling and deployment, and the ability to monitor multiple application executing on the same host.

Artificial Intelligence

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th December 2017

Gyanendra Kumar | Anil Kumar, Guru Prasad, Harsha M

Abstract

This paper reviews the meaning of artificial intelligence and its various advantages and disadvantages including its applications. It also considers the current progress of this technology in the real world and discusses the applications of AI in the fields of heavy industries, gaming, aviation, weather forecasting, expert systems with the focus being on expert systems. The paper concludes by analysing the future potential of Artificial Intelligence.

Artificial Neural Networks for Intelligent Communication Systems: A Study

International Journal of Engineering Research in Computer Science and Engineering, Available online 28th February 2018

S.Pattanayak | Piu Das

Abstract

The paper is a study of the application of Artificial Neural Networks for problem solving and optimizing the performance in different communication systems. Artificial neural networks are being used for spectrum sensing, pattern recognition and many applications in wireless communication. The main objective is to reduce the complex analysis of a communication system. This paper gives the state of the art of research of Artificial Neural Networks making the communication systems adaptive and smart.

Assessment of the purity of silk and its mixed fabric using image processing in textile showrooms

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd August 2017

Balaji.V | 

Abstract

In today’s world where there is a lot of interest towards fashionable and expensive clothing ,the quality and purity of the material is expected to be of high standards. Especially when it comes to silk clothing, people always are doubtful about the purity of the material, due to the high costs people invest on such clothing. In this paper we aim at determining the purity of silk clothing by using image processing algorithms .We basically take a microscopic image of the fabric and compare it with a dataset of pure silk fabric images and hence determine the percentage purity in mixed fabric clothing

Attribute Based Encryption for Securing Personal Health Record on Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd May 2018

Deepali A.Gondkar | Nisha.A.Auti, Nilofer U.Sayyed

Abstract

Personal health record (PHR) has emerged as a patient-centric model of health information exchange. A PHR service allows a patient to create, manage, and control her personal health data in one place through the web, which has made the storage, retrieval, and sharing of the medical information more efficient. Especially, each patient is promised the full control of her medical records and can share her health data with a wide range of users, including healthcare providers, family members or friends. The main aim of this research work is to propose a novel framework of secure sharing of personal health records in cloud computing. Considering partially trustworthy cloud servers, we argue that to fully realize the patient-centric concept, patients shall have complete control of their own privacy through encrypting their PHR files to allow fine-grained access.

Audio/Video Compression Using Transformation Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 28th March 2018

Sumiran Dhamaskar | Ameya Wadekar, Malony Alphanso

Abstract

Audio compression is designed to reduce the transmission bandwidth requirement of digital audio streams and storage size of audio files. Audio compression has become one of the basic technologies of the multimedia age to achieve transparent coding of audio and speech signals at the lowest possible data rates. Similarly, Digital Surveillance Systems are becoming increasingly important to commercial and residential security.

Aushadh Nishtha: A Mobile Based Application to ensure Adherence to Medication in Chronic Non-Communicable Diseases

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Dr. Ankur Joshi | Manu Gupta, Dr.Soumitra Sethia

Abstract

Medication adherence is both vital and difficult to achieve in case of non –communicable diseases. The challenges arise because of the requirement of behavioural monitoring and continuous scrutiny of the process. This prerequisite to ensure adherence may be addressed by ICT through asynchronous communication via mobile based application. This manuscript describes the conceptual and operation framework of one of the adherence assurance application developed by the authors and investigates further the future prospects of such application.

Automated Detection of Targets and Retrieve the Corresponding Analytics Using Augmented Reality

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th February 2018

Dr. Suvarna Kumar G | Dr. Sandhya Devi G, Chanakya P

Abstract

Augmented reality is defined as the collection of the digital (or) computer generated information like images, audio, video, 3d models etc. and overlay them over the real time environment. Augmented reality can be thought as a blend between completely synthetic and completely real. Augmented reality provides scope in a wide range of industries like manufacturing, retail, gaming, advertisement, Tourism etc. and brings out new dimensions in the modern digital world. As it overlays the content, it makes the users to enhance the knowledge by providing the content blended with real world. In this application, we integrated augmented reality with data analytics and integrated with a cloud so the virtual content will be generated on the basis of the data present in the database and we used marker-based augmented reality where every marker will be stored in the database with corresponding unique ID. This application can be used in wide range of industries for different business processes but in this paper, we mainly focus on the marketing industry which helps the customer in gaining the knowledge about the products in the market which mainly focus on their prices, customer feedback, quality, and other benefits. This application also focuses on providing better market strategy information for marketing managers who obtain the data about the stocks, sales, customer response about the product etc. In this paper, we also included the reports from the feedback got from different people after the demonstration and finally, we presented the future scope of Augmented Reality in different business processes by integrating with new technologies like cloud, big data, artificial intelligence etc

Automated Generation of a Natural Challenge File for File Carving Algorithms

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th November 2017

K. Srinivas | Dr. T. Venugopal

Abstract

File Carving is a technique of reassembling unordered mixed file fragments, without using files’ metadata such as FAT, for reconstructing the actual files present on the disk. In the areas of data recovery and digital forensics this situation arises. A challenge file consists of number of files, in the form of fragments, mixed in random order. In this paper authors have presented a software system that generates a challenge file by implementing, at user level, a file system which broadly follows FAT file system. This software system uses a large size file to store file fragments just like a kernel level file system uses disk to store files. The kernel level file system fragments the file, as per the availability of free clusters, at the time of creation of the file. By viewing the challenge file as a virtual disk, it consists of the number of virtual clusters. The software system presented in this paper, a user level file system, fragments the file, as per the availability of free clusters, on the virtual disk i.e., the challenge file. This challenge file consists of mixed file fragments of number of user files. The content of the challenge file is a result of software module which broadly follows FAT file system. The challenge file thus generated is, therefore a natural challenge file. This challenge file provides the writers of file carving algorithms a platform to test their algorithms. The designers of file carvers can use the challenge file conveniently as a virtual disk, in place of the actual disk, thus eliminating the need of physical hard disk for testing their algorithms. There are number of other benefits of this approach as outlined in this paper

Automated Mentoring System

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th May 2018

Aparna K S | Ashwini M, Divya H, Anusha, S Sahitya

Abstract

Automation has become a boom for the present and future generation, which helps in efficient documentation of the data digitally for better transparency, centralization of data and for the quick review of the contents as and when required without spending much of the time in searching through loads of book which is an inefficient process. Mentoring is an age-old method which effectively and efficiently transfers the knowledge and skills from an experienced person to inexperienced personnel. This methodology is used in different sectors like industries, educational field for the overall upliftment. Mentoring requires constant meetings and documentation of the progress being noticed. This paper focusses on implementing the automation to the mentoring systems which can be utilized for the effective and efficient the mentoring system in Dept. of CSE, RYMEC. The tool being proposed would also be useful for the students to provide feedback about the facilities being provided by management and so on, which would reduce considerable amount of time compared to the present system in existence.

Automated Tormenting Recognition in light of Semantic-Enhanced Marginalized Stacked Denoisng Auto-Encoder

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th August 2017

Megha Rani Raigonda | Bhavani Namdar

Abstract

Social media now a day is a major communication bridge among peoples almost around the world which helps them to share their day to day activities to the one who is in contact with them in that network; hence it acts as an intermediary among them. As social media have many excellent features for better communication, it does have the many drawbacks which may hurt the intensions of the peoples sometimes due to some weird actions of the users on social media, such as teasing or posting something which hurts the user intensions by using bullying or tormenting words. The major criterion to deal this problem is learning robust representations of texts through text mining concepts in machine learning and NLP. So to prevent this kind of activities on social networks, we are proposing a technique named Semantic-Enhancement for Marginalized Denoising Auto- Encoder(smSDA), which is an extension of the admired machine learning technique Stacked Denoising Auto- Encoder (SDA).

Automatic Brain Tumor Detection using Super pixel zoning and DWT

International Journal of Engineering Research in Computer Science and Engineering, Available online 21st June 2018

S.V.P. Teja | Tusar Kanti Mishra, Vishnu Ganesh Phaniharam

Abstract

Earlier in the diagnosis of a disease; better is the rate of recovery. As far as the pestilent disease like brain tumor is concerned, its early identification may lead to improve the rate of care and thereby benefitting the survival of a patient. Typically, brain tumor detection and analysis starts from the process of brain MRI segmentation. This segmentation partitions the potentially overlapping parts in the internal structure of the brain into brain tissues such as White Matter (WM), Grey Matter (GM) and Cerebro Spinal Fluid (CSF). In this paper, automated brain tumor detection has been proposed for detecting the presence/ absence of brain tumor from brain MR images. Relevant pre-processing is applied to input brain MR images. Firstly, the brain input image is zoned using superpixel zoning and brain tissues are being segmented using discriminative clustering. Secondly, feature extraction is done using level 2 2-D discrete wavelet transform to generate the matrix vectors. AdaBoost with random forests algorithm (ADBRF) is used as its base classifier to classify the given brain MR image into normal or abnormal. Simulation results are compared with the existing methods on BrainWeb brain MRI dataset and it is observed that the proposed scheme outperforms other state of the art methods.

Automatic Conversion of Formal Specification into Code

International Journal of Engineering Research in Computer Science and Engineering, Available online 1st December 2017

Manju Pandey | 

Abstract

This paper proposes an idea. The idea is to first express a requirement specification using a formal method. The second step is to work out an implementation of the specification in the form of running code in a standard contemporary programming language. The other step is to identify frequently occurring patterns in the formal specifications. And then direct the conversion from the formal specification to the running code. Intermediate steps shall include the development of a computer-based tool for expressing the requirement specifications. we require another tool that shall develop the conversion of the specifications expressed this way into running code. The steps and process are explained with a hypothetical example.

Automatic Detection of potholes and humps for controlling the vehicle speed

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

Marimuthu B | Solaiyappan S, N.Gowthami

Abstract

Automatic detection of potholes and humps for alerting vehicle drivers to drive safely. The mobile application used in this system is an additional advantage as it provides timely alerts about potholes and humps. Identification types of surface distress such as potholes and humps to avoid accidents and vehicle damages. Ultrasonic sensors are used to identify the potholes and humps and also to measure the depth and height, respectively. It recorded the geographical location coordinates of the potholes and humps using a Global Positioning System receiver. The sensed-data includes pothole depth, the height of hump, and geographic location, which is stored in the database. This serves as a valuable source of information to the government authorities and vehicle drivers. Once the fault will be rectified the database updated automatically. Alerts are given in the form of an audio.

Automatic Door Locking System

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th October 2017

Dr. Manoj Priyatham | Rashmi.K.G, Meghana.R, Likitha Prakash.K, Rashmitha.H.R

Abstract

In this paper, the access of unauthorized user can be prevented by using integrated home security with a microcontroller technology which is cost effective. Here the registered password in the system will enhance the security level to prevent from unauthorized users. If users forget password then the security provides the capability to change and reset the password. This paper provides strong authentication where we enter the first password for the Bluetooth connection and second password for unlocking the door in the mobile application with the help of driver circuit which is attached to the door can be open and locked automatically by obtaining the signal from microcontroller. The automatic password lock system will give user more secured

Automatic Dual Line Lubrication System Using Programmable Logic Controller

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th June 2018

Sharath S | Dr. Sudarshan Patilkulkarni

Abstract

Lubrication is a technique employed in most of the steel industries that delivers controlled amount of lubricant to multiple points of rollers in order to perform a smooth operation. The manual lubrication system requires more manpower that leads to more downtime in production and maintenance. Meanwhile, the discrete wiring system leads to complication in the wiring. The proposed automatic dual line lubrication system using PLC sends a command to initiate lubrication cycle that pumps the lubricant to the entire first supply line and then signals a changeover valve to the second supply line. The pressure in the supply line is vented out and lubricant in the line is returned to the pump reservoir through lubrication filter. Thus the lubrication is done alternatively in both the lines to the bearings of rollers with a time interval of every 45 minutes. If any fault occurs during the lubrication cycle, the system will generate a fault message in HMI and gives a signal to alarm. Hence it overcomes the constraints that are associated with the manual and discrete wiring lubrication systems

Automatic Follow-up Actions for Medical Treatment

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th August 2017

Mohamed Esoof | Mohamed Raseen

Abstract

A system to automate the follow-up actions for medical treatment is proposed in this paper. This system uses the existing that uses Aadhaar based authentication to access the centrally stored medical records. Diseases can be classified as Communicable diseases and Non-Communicable diseases. They can be classified also as Chronic and Non-chronic. Follow-up and treatment for chronic disease is very important since the disease extends to the complete life. The proposed system is very helpful in chronic disease where patient needs constant and periodic treatment. The proposed system use the same Centralized records but also provides time alerts to the Patient and Doctors automatically when the follow-up time is due.

Automatic Image Annotation-A Proposed Method

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Sayantani Ghosh | Prof. Samir Kumar Bandyopadhyay

Abstract

Medical images play a central role in patient diagnosis, therapy, surgical planning, medical reference, and medical training. With the advent of digital imaging modalities, as well as images digitized from conventional devices, collections of medical images are increasingly being held in digital form. It becomes increasingly expensive to manually annotate medical images. Consequently, automatic medical image annotation becomes important. This paper reviews annotation of medical records.

Automatic Pill Dispenser

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Manjula G | Udaysree P, Ranjitha S, Sangeetha L, Priyanka VJ

Abstract

Earlier, people would live in joint families where atleast one person used to be there at home to take care of aged people. In modern days, people prefer nuclear families where there are no one present to take care of aged people and patients due to their busy working schedule. To overcome this, they need to appoint a caregiver to take care of the patients for their diet, hygiene, medication etc. Payments given to the caregivers will affect their savings. To overcome such problems a model is needed. This model medicates the patients and aged people automatically to inform them regarding medication in time as prescribed by the Doctor. This is done by presetting the prescribed time and comparing it with RTC time. When they are equal, tablets are dispensed. The patient is given sufficient time to take the tablets. If the patient fails, a message is sent to the caregiver informing about the failure. Thus the proposed model is implemented for aged people, patients, bed-ridden and the illiterates to ensure medication at right time and simultaneously notify the caregiver if patient fails to take medications

Automatic Soil Moisture Monitoring System

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Khushal G. Katara | Saket C. Joshi,Harsh L. Bhanushali,Bhavishek S. Panikar

Abstract

Irrigation part in farming has always been an important part for farmers. Manual attempts for the irrigation, such as water supply and keeping the records are quite tedious .In order to make it simple and connected to technology, Soil moisture can be detected by soil moisture sensor. This sensor can detect the moisture level of the soil. This can be done automatic with microcontroller, so that whenever moisture level of soil gets low or soil gets dry, Water can be supplied automatically. The android app will store the records and can control the sensor and water pump. This can cut the manual attempts regarding the irrigation and simplify the efforts for farming with technology. Connecting the irrigation with technology makes it to the “smart irrigation”.

Automatic Vehicle Accident Detection System

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

K.Saranya | P.Kowsalya, G.Nandhini, K.Pooja

Abstract

The quick development of innovation and framework has made our lives less demanding. The appearance of innovation has likewise expanded the movement dangers and the street mischances happen every now and again which causes immense death toll and property as a result of the poor crisis offices. This paper manages impact and risk location for cruisers by means of inertial estimations. The Microcontroller, GPS, Ultrasonic sensor are getting synchronized with the baud rate of 9600. The microcontroller persistently read the incentive from accelerometer. On the off chance that any progressions found in the accelerometer position. It is contrasted with the past position with distinguish the mischance and furthermore sense the auto motor status and in addition the ultrasonic sensor esteem. The above status is valid, at that point read the GPS esteem and send the area to every one of the healing facilities, adjacent emergency vehicle focuses and furthermore for police with respect to the same. In the event that lone the accelerometer position is changed and keeping in mind that the motor status is in off, at that point the GPS area is sent to the close workshop in regards to the puncher and any blame found in the vehicle. The strategy is tried in a simulation environment; the correlation with a benchmark strategy demonstrates the benefits of the proposed approach

Automation of Building Extraction from Satellite Imagery Using Line Segment Detector

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th March 2018

Anupama Mishra | Abhishek kumar, Akhileshwar Pandey

Abstract

This paper focuses on an automatic algorithm for fast building boundary extraction from satellite imagery and it presents an experimental comparison of the bilateral filter (BF) and adaptive bilateral filter (ABF). The study and experimental result prove that outcomes of ABF are much better than outcomes of BF. ABF produces a more promising result than BF. Old and conventional building boundary extraction models are very complex and time-consuming. The proposed procedure of building boundary extraction consists of three main stages: (1) Edge-preserving and smoothing by using adaptive bilateral filter, (2)detection of a line segment using ED Line algorithm, (3) identification of polygonal building boundary by using perceptual grouping technique. Our proposed algorithm is tested on HR (high resolution) Quick Bird satellite images and obtained results are promising and nearly real-time. Hence the experimental results are useful enough with an overall accuracy of 88.24%, which is accurate enough for further image understanding building boundary detection and identification of the target in real time environment and can contribute to solving the problem of identification of unauthorized and illegal building construction on its early stage

Automation System to Measure the Performance of Employee

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th May 2018

Girish Kumar D | Suresh U, Kaushik CH, Naveed J, Giritej N

Abstract

This paper provides an overview of online student feedback system in educational institutions.Subsequently, this paper describes how data from Student Feedback system is used to observe the quality of teaching of lecturer. The online Student Feedback system with data access restrictions can be used by the eligible students after logging into the portal. The authenticated students can provide feedback and the evaluation is based on students’ response in Student Feedback Online system that measured the lecturers’ ability based on the lecturer’s professionalism and teaching methods. Lecturers can see the feedback given for the courses handled by them, HOD can view the feedback handled by him and the feedback of all other lecturers of the department and the Administrator can view the feedback for any lecturers. Consolidated feedback details should be accessible in easily recognizable visual forms like graphs or plots. Keywords: Feedback, system, forms.

Avoiding Intrusion and Privacy Protection for Cloudlet-based Medical Data Sharing

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th August 2017

Karthika.J | Lavanya.S, JayaSankari.J, Mariya sushmitha.T.F, kanimozhi.R

Abstract

The popularity of wearable devices with the development of clouds and cloudlet technology, increased the need to provide better medical care. The process of medical data includes data collection, data storage and data sharing,. In the Traditional healthcare system ,it requires the delivery of medical data to the cloud, which involves users’ integrated information and causes communication energy consumption. Practically, medical data sharing is a critical and most challenging issue. The functions of cloudlet include privacy protection, data sharing and intrusion detection. In the stage of data collection, we first utilize Number Theory Research Unit (NTRU) method to encrypt user’s body data collected by wearable devices. Those data will be transmitted to nearby cloudlet in an energy efficient fashion. Secondly, a new trust model to help users to select trustable partners who want to share stored data in the cloudlet. Thirdly, we divide users’ medical data stored in remote cloud of hospital into three parts, and give them proper protection. Lastly , to protect the healthcare system from malicious attacks, we develop a novel collaborative intrusion detection system method based on cloudlet mesh.

―SIRASTRANA‖-A Smart Helmet for Air Quality and Hazardous Event Detection for the Mining Industry

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Raghavendra Rao B | Karthik NS, NA Poojitha, Divya L, Nandini N

Abstract

A smart helmet has been developed that is able to detect hazardous events in the mines industry. In the development of helmet, we have considered the three main types of hazard such as air quality, helmet removal, and collision (miners are struck by an object). The first is the concentration level of the hazardous gases such as CO, SO2, NO2, and particulate matter. The second hazardous event was classified as a miner removing the mining helmet off their head. An IR sensor was developed unsuccessfully but an off-the-shelf IR sensor was then used to successfully determine when the helmet is on the miner’s head. The third hazardous event is defined as an event where miners are struck by an object against the head with a force exceeding a value of 1000 on the HIC (Head Injury Criteria). An accelerometer was used to measure the acceleration of the head and the HIC was calculated in software. This paper presents the undertaken design detailing solutions to issues raised in previous research. Main objective to give the correct and clean breathing averment at any hazardous or toxic environment

“An automated brain tumour detection and severity analysis using ANN”

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Prof. Vrushali Borase | Prof. Gayatri Naik, Prof. Vaishali Londhe

Abstract

A Brain Cancer is very serious disease causing deaths of many individuals. The detection and classification system must be available so that it can be diagnosed at early stages. Cancer classification has been one of the most challenging tasks in clinical diagnosis. At present cancer classification is done mainly by looking through the cells’ morphological differences, which do not always give a clear distinction of cancer subtypes. Unfortunately, this may have a significant impact on the final outcome of whether a patient could be cured effectively or not. This paper deals with such a system which uses computer based procedures to detect tumour blocks and classify the type of tumour using Artificial Neural Network Algorithm for MRI images of different patients. Different image processing techniques such as image segmentation, image enhancement and feature extraction are used for detection of the brain tumour in the MRI images of the cancer affected patients. Detecting Brain tumour using Image Processing techniques involves four stages namely Image Pre-Processing, Image segmentation, Feature Extraction, and Classification. Image processing and neural network techniques are used to improve the performance of detecting and classifying brain tumour in MRI images. MRI scan images are taken for this project to process it.This work presents the artificial neural network approach. It is used to classify the type of tumor in MRI images. The whole system worked in two modes firstly Training/Learning mode and secondly Testing/Recognition mode finally gets a classified output. This paper gives an overview of image segmentation technique based on Particle Swarm Optimization (PSO). PSO is one of the latest and emerging digital image segmentation techniques inspired from the nature. After segmentation features are extracted and submitted to a kernel support vector machine (KSVM).

“Data Storage on Fingernail”

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th December 2017

Mimitha Charan Raj | Vijay G.H, Akshitha

Abstract

Recently, there have been rapid developments in the field of information technology, resulting in the need to generate, store, and transport a large amount of information while ensuring data security, an important issue in today's digital age. To meet future demands in information technology, femtosecond laser pulse processing offers a powerful tool for developing new high-capacity devices because it allows fabrication of three-dimensional (3-D) structures inside a wide range of transparent materials. In particular, multilayered 3-D optical bit recording is a promising technique for next-generation computing systems because it offers a large recording capacity by stacking many recording layers without increasing the recording density per layer. Our goal is to realize optical data storage in a human fingernail for highly secure data transportation that does not suffer from problems such as theft, forgery, or loss of recording media

“Digibin”-a smart way of sorting solid waste

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th July 2017

Dr. B Shadaksharappa | Mrs.V.K Shalini, Meenakshi Allagi,Pallavi V Naik,Bhavya C P, K Harshitha

Abstract

Waste Management is the pervasive problem. Nowadays and rising continuously with rise in urbanization. Waste is always the mixture of different types of material. The main goal of this project is to design and develop a sorting system that is portable and also sorts the waste automatically. It’s an eco-friendly automatic system. With the Proliferation of Internet of Things (IOT) Devices as Such as Smart phones and Sensors, this Project describes the effective management of solid waste using embedded system. The solar panel and H-bridge are used by the motor to make the system portable. The moving system stops when a non-living obstacle arrives and takes a turn. Otherwise gets the inputs from the waste dumped by the person which is detected by the sensor. The sensor sends a signal to micro-controller where it decides the type of waste (biodegradable and nonbiodegradable) and separates it automatically and moves forward. Here the IOT module is used to control and monitor the waste. The system consist of mobile app which receives a message when the dustbin is full (3kg) makes the system to alert and the information is sent to the authority who own the and it resend the meesge to the bin for automatic disposal to the dump site. It even includes database of wastage collection on the particular day.

“Dustless Environment”Using NEAGH Device

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Neesu Dubey | Neha Jha, Pragati Katiyar, Ramesha T.H, T.K Pradeep Kumar

Abstract

Dust can be more than just a nuisance – it can be killer. Dust is simply small particles in the air. Often these particles are too small to be seen but deals with the major problem that is irritation in the eyes, coughing, sneezing, hay fever, asthma attacks etc. This project used to automatically clean dust particles from the road of the city. The system will be fitted on any vehicle, where DC motor used to collect the dust particles from the road and store it in a container. When the container is filled, then the system will give an alert

“EDUSCIENZA”-Smart Learning using Augmented Reality

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Dr. B. Shadaksharappa | Suraj S, Spoorthi S, Navyashree R, Nithin Kishore K

Abstract

Augmented reality (AR) is precisely a direct or an indirect real-world view of an environment whose components are augmented by computer-generated information, ideally across multiple sensory modalities. Augmented reality is a reality in which is enhanced digitally with the help of virtual objects that appear to be in our field of vision. The primary task of augmented reality is that it brings components of the digital world into a person's imagination of the real world and does so not as a simple display of data, but through the integration of immersive sensations that are perceived as natural parts of an environment. In our project, AR has been used to guarantee a standard curriculum using Text, Graphics, Video, and Audio which is superimposed into a student's real-time environment. Almost anything can be done with augmented reality, one can create the application that helps students do practical experiments all at one place. The application will be mainly used for students in the learning process at any place with the app installed on their phone that makes students learn efficiently and practically. Students can learn by carrying out interaction through virtual objects and learning materials and help students actively interact in the lab performing different experiments to increase their understanding and to make them learn rather than reading

“HEAD MOVEMENT” Controlled System to Assist the Physically Challenged Using IoT

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Reji Thomas | Anoop Daewoo M, VK Manasa, Aishwarya M, Rakesh Kumar Yadav G

Abstract

“Silla de-ruedas” This project describes the design of a simple, wheel chair using head movement system. Heart rate of the subject is measured from the thumb finger using IRD (Infra-Red Device sensors). This instrument employs a simple Opto electronic sensor, conveniently strapped on the finger, to give continuous indication of the pulse digits. The Pulse monitor works both on battery or mains supply. It is ideal for continuous monitoring in operation theatres, I.C. units, biomedical/human engineering studies and sports medicine.This project uses AT89S52 MCU as its controller. By reading all the values of temperature and heart rate will be displayed on LCD. Temperature and heart beat values will be taken and updated in the web server using IoT module interfaced to the controller. This project uses regulated 5V, 500mA power supply. 7805 three terminal voltage regulator is used for voltage regulation. Bridge type full wave rectifier is used to rectify the ac out put of secondary of 230/12V step down transformer

“Hybrid technique of Image Encryption to Enhance Security”

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Kalyani D. Kadukar | Prof.R. Krishna

Abstract

The aim of this project is related to novel scheme for separable reversible data hiding in encrypted image is proposed, which consists of image encryption, data embedding and data-extraction/image-recovery ,3D chaos generation,3D histogram equalization, row rotation, column rotation and XOR operation phases. Additional message are embed into some cover media, such as military or medical images, in a reversible manner so that the original cover content can be perfectly restored after extraction of the hidden message is called reversible data hiding. Separable reversible data hiding, the name its self indicates that it is a separable reversible data technique .That is it is reversible data technique but which is separable. The separable means which is able to separate .The separation of activities i.e. extraction of original cover image and extraction of payload is done in this method. This separation requires some basic cause to occur. In separable data hiding key explained by Xinpeng Zhang the separation exists according to keys. Digital images has increased rapidly on the Internet. Security becomes increasingly important for many applications, confidential transmission, video surveillance, military and medical applications. The transmission of images is a daily routine and it is necessary to find an efficient way to transmit them over networks

“Implementation of file level and block level deduplication and detecting attacks in cloud environment.”

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Prof. Samita Mokal | Prof. Nilima Nikam, Prof. Vaishali Londhe

Abstract

In cloud computing, security and storage space management techniques are most important factors for improving the performance of cloud computing. Secure deduplication is a technique for eliminating duplicate copies of storage data, and provides security to them. To reduce storage space and upload bandwidth in cloud storage deduplication has been a well-known technique.. The basic idea in this paper is that we can eliminate duplicate copies of storage data and limit the damage of stolen data if we decrease the value of that stolen information to the attacker. This paper makes the first attempt to formally address the problem of achieving efficient and reliable key management in secure deduplication. we propose Sekey, User Behavior Profiling and Decoys technology. Sekey new construction in which users do not need to manage any keys on their own but instead securely distribute the convergent key shares across multiple servers for insider attacker. As a proof of concept, we implement Sekey using the Ramp secret sharing scheme and demonstrate that Sekey incurs limited overhead in realistic environments. User profiling and decoys, then, serve two purposes. First one is validating whether data access is authorized when abnormal information access is detected, and second one is that confusing the attacker with bogus information. We posit that the combination of these security features will provide unprecedented levels of security for the deduplication in insider and outsider attacker..

“Malicious Misbehavior Activity Detection Using Probabilistic Threat Propagation in Network Security”

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Tejaswini S. Akulwar | Associate Prof. P. S. Kulkarni

Abstract

A PTP approach in network security for misbehavior detection system present a method for detecting malicious misbehavior activity within networks. Along with the detection, it also blocks the malicious system within the network and adds it to Blacklist. Malicious node defined as a compromised machine within the network that performs the task provided by i.e. it does not forward the legitimate message to another node in the network or sends some other message to a neighbor node. This system is based on Probabilistic threat propagation. This scheme is used in graph analysis for community detection. The proposed system enhances the prior community detection work by propagating threat probabilities across graph nodes. To demonstrate Probabilistic Threat Propagation (PTP) considers the task of detecting malicious node in the network. Proposed System also shows the relationship between PTP and loopy belief propagation

“Samarthyam”-Advance Footstep Power Generation

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Bindu Madavi | Sandhya A S, Sahana T S, Pooja B N, Priya J

Abstract

‘Samarthyam’- The buzz for power. The man has needed and used energy at an increasing rate for his sustenance and wellbeing ever since he came on the earth a few million years ago. Due to this a lot of energy resources have been exhausted and wasted. Proposal for the utilization of waste energy of foot power with human locomotion is very much relevant and important for highly populated countries like India and China where the roads, railway stations, bus stands, temples, etc. are all overcrowded and millions of people move around the clock. The project advanced footstep power generator system is used to generate power from human footsteps. The system allows for a platform for placing footsteps. It uses Piezo sensors to generate the power. The Footstep Power Generation System is eco-friendly, it reduces waste of energy, it is of less maintenance cost, it is of ultralow noise and wide dynamic and temperature range. This project is used for street lighting, mobile charging. It can be used in power failure situations. The application areas of this project involve public areas like temples, streets, metros, railway stations. This entire system will be integrated with software for displaying the amount of power generation with the help of IOT technology

“Security privacy preserving for content leaks”

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Shradha V. Raghorte | Dr . Rahila Sheikh

Abstract

The information leak of sensitive data on systems has a serious threat to organization data security. Statistics show that the improper encryption on files and communications due to human errors is one of the leading causes of information loss. So there a need tools to identify the exposure of sensitive data by monitoring the content in storage and transmission. However, detecting the exposure of sensitive data information is challenging due to data transformation in the content. Transformations result in highly unpredictable leak patterns. In this paper, it is utilize sequence alignment techniques used for detecting complex data-leak patterns. This algorithm is designed for detecting long and inexact sensitive data patterns. This detection is paired with a comparable sampling algorithm, which allows one to compare the similarity of two separately sampled sequences. The system achieves good detection accuracy in recognizing transformed leaks. It implement a parallelized version of our algorithms in graphics processing unit to achieves high analysis data. In the case of collective privacy preservation, organizations have to cope with some interesting conflicts. For instance, when personal information undergoes analysis processes that produce new facts about users' shopping patterns, hobbies, or preferences, these facts could be used in recommender systems to predict or affect their future shopping patterns. In general, this scenario is beneficial to both users and organizations. However, when organizations share data in a collaborative project, the goal is not only to protect personally identifiable information but also sensitive knowledge represented by some strategic patterns.

Back Propagation Algorithm Based Approach to Recognize and Categorize the DC Fault in PV Module

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd May 2018

Sujit Kumar | Vikramaditya Dave

Abstract

In the present era, the role of solar photovoltaic (PV) in the distributed generation has become inevitable and it is also the need of the hour. Addition of distributed generations (DGs) in the utility grid demand for decent power quality, secure operation and islanding protection of the grid interconnection. In order to maintain the quality of the power, one needs to accelerate the procedure of finding the fault, reduce the downtime and bring the system back to normal condition. Many diagnostic approaches were proposed in the past to identify the PV faults but they are old school methods and sometimes become unmanageable particularly in case of multiple faults and critical PV system. In this paper recognition and categorization of all possible DC faults of a grid-connected PV system using an artificial neural network (ANN), an artificial intelligence technique is presented. The simulation of ANN was done over 100 kW solar PV system connected to an 11 kV grid. Five inputs were fed to the ANN namely, PV voltage (Vpv), current (IPV) and power (P) (PV array parameters) and irradiance (G) and module temperature (T) (environmental data). Also, there were 5 output nodes as a DC fault indicator namely, Short-Circuit; Open-Circuit, Degradation, Shading and Charging Module. The optimized neural network architecture comprised of 5 neurons in the input layer, 20 neurons in the hidden layer and 5 neurons in the output layer. The hyperbolic tangent sigmoid transfer function was used as an activation function for the hidden as well as output layers. The ANN network was trained with over 1000 samples using back propagation algorithm with the accuracy of 0.01. To achieve the set error goal of 0.01 the ANN performance converges within the 1000 epochs. The neural network was tested for additional 1040 samples which were not included in the training data. The results of the tested data were obtained with the accuracy of 99%. It is found that the proposed system has proved its best with the accuracy of 99% for the practical applications when compared with the other artificial intelligence techniques like the fuzzy system, expert knowledge, etc.

Bad Road Tracker

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th October 2017

Varsha Singh | Noor Allema

Abstract

This brief paper describes the uses and concepts of enables the user to track all the roads which are not suitable to travel. It gives the shortest and most comfort path to travel. This application can be used by taxi drivers and by common people.

Batch Normalization and Its Optimization Techniques: Review

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th September 2017

Niveditha Kumaran | Ashlesha Vaidya

Abstract

— Batch normalization is a boon to the training of a deep neural network. It acts as a panacea to the problem of internal covariate shift and facilitates the usage of higher learning rates. It also accounts for the inclusion of saturating non-linear functions, while excluding the need of drop outs for regularisation. However, mini-batch normalization is not self-sufficient and comes with a few limitations such as inability to deal with non-i.i.d inputs and decreased efficiency with a batch size of one. In this paper, we explore normalization, the need for its optimization, and evaluate the optimization technique provided by researchers.

Battery Consumption on Smartphones: A survey

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th January 2018

Farooq Ahmad Mir | Dr. Khalid Mohiuddin

Abstract

Smartphones began as the new significant device to many. A cell phone can combine some or all functionalities of several different devices which include a secretive notebook, mobile, private reformation console, song player, walkie-talkie, and/or GPS. Most of the technologies listed on top of that may be actuated as mandatory, one smartphone is commonly on. Seeing that a smartphone will perform activities within the background even at some purpose in idle mode and since it's restricted to battery life, it'll be essential to understanding what really happens within the background and the way it affects the approach to life of the battery and, therefore, a way to improve it. For this termination, we have analyzed two telephone structures, in particular in search of how the recruitment of force varies according to past historical applications and the type of network connection. For example, we show you that you can increase the power of an iPhone up to 59% while you transmit the song in Wi-Fi instead of 3G, we show that network programs going for walks within the history can lessen the electricity efficiency of an iPhone with the aid of up to 72% when in comparison to real idle kingdom. Our focus commentary sheds light on eating up the battery existence of a smartphone and led us to offer optimization strategies to increase the battery lifestyles.

Behavior and appearance cram of Android Robot for HRI

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th September 2017

R.Priya | 

Abstract

Human–robot interaction is the study of interactions between humans and robots. Human–robot interaction(HRI) is a multidisciplinary field with aid from human–computer interaction, design, robotics, artificial intelligence, natural language understanding, and social sciences. This is basic setback in robot development is its appearance and behavior. Namely, not only the performance but also the look of a robot influences human-robot interaction. However, there is no approach to overcome this problem. In order to utter this problem, we propose an android robot that has similar appearance as humans and several actuators generating micro behaviors.

Behavior and appearance cram of Android Robot for HRI

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

R.Priya | 

Abstract

Human–robot interaction is the study of interactions between humans and robots. Human–robot interaction(HRI) is a multidisciplinary field with aid from human–computer interaction, design, robotics, artificial intelligence, natural language understanding, and social sciences. This is basic setback in robot development is its appearance and behavior. Namely, not only the performance but also the look of a robot influences human-robot interaction. However, there is no approach to overcome this problem. In order to utter this problem, we propose an android robot that has similar appearance as humans and several actuators generating micro behaviors.

Behavioral model to obtain profit with guaranteed quality of service in cloud computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th April 2018

Anjali C.Tak | S.R.Ghungrad

Abstract

As an effective and efficient way to provide our customers with IT resources and services, Cloud Computing is gaining in popularity. From a cloud provider perspective, profit is the most important consideration and is determined by configuring a cloud service platform based on market demand. However, a one-time leasing system is often used to configure the cloud platform, which cannot guarantee the quality of the service. However, it results in severe resource losses. In this article, the dual sourcing system is pre-designed by short-term rentals and long-term lease agreements are combined to target existing issues. This dual-leased system can effectively guarantee the quality of service provided by all applications and greatly reduce resource wastage. Second, the service system is considered to be a queuing model of M / M / m + D, and performance metrics that affect the benefits of our dual lease system, such as average load, requested ratio, temporary server requirements, and more. Third, the problem of maximizing profits is that the formula for the dual lease plan and the optimal configuration of the cloud platform are obtained by solving the problem. These maximize profit Finally, this is calculated to compare the benefits of our service plan with a one-time rental plan. Experimental results show that our system provides not only service quality for all applications but it also gets more profit than the latter system.

Bi-Clustering Mining to Discover Effective Technical Trading Patterns

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd May 2018

Mayuri Patil | Sarita Patil

Abstract

Past database of financial market prices are used to forecast the trend of prospect prices. The developed financial entity technical patterns that contain a permutation of indicators from historical economic data series. Calculation of technical indicators is done based on historical data. The take price forecast system uses a descriptive two-step reasoning approach. This work inventively put forward the use of biclustering mining to determine out patterns are regarded as trading rules and can be categorized as three trading actions (Buy, Sell and No Action) based on support value. K nearest neighborhood (K-NN) procedure (Updated Version) for categorization is applied to trading days in the testing period. Our work offers a practical and efficient algorithm and mathematical system for determining a trading rule which can be used to take informed decision while trading

Big Data Analysis On Gene Mutation Detection For Bacterial Diseases

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Sharath Kumar S | Sanil A Jain,Veeresh Shenoy S, Vinith G,M Ravi Krishna

Abstract

Big data and analytics is a method of examining a lot of datasets to uncover hidden patterns, market trends, and other useful business information. In a human body, the gene will generate a significant amount of data; the real challenge here is to find, collect, analyze and manage information so that we can avoid the occurrence of the illness and be healthier. Nowadays many people are losing their lives because of bacterial diseases like MRSA, CRE, etc. So we are trying to collect the data sets of a particular disease and analyze it by detecting gene mutation, which helps people to find which gene is the actual cause of the particular disease. Here we will be finding which mutation is responsible for that drug resistance. This drug resistant gene will be found out in a large population. A mutation is the permanent change of the nucleotide sequence of an organism, genetic elements, virus or extrachromosomal DNA. Errors during DNA replication results in the mutation which further undergoes error-prone repair. Through genetic recombination, mutations can involve the duplication of vast sections of DNA

Big Data Analytics Based Approach to Tax Evasion Detection

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th March 2018

Yashashwita Shukla | Neena Sidhu, Akshita Jain, T.B. Patil, S.T. Sawant-Patil

Abstract

Tax evasion is the illegal underpayment or non-payment of tax to the government. Detecting these illegal tax evasion activities is an important as well as challenging issue for the tax administration system of any country and the biggest challenge is the increasing volume of tax data. In this paper, we propose a system that can help to characterize and detect the probable tax evaders using the information in their tax payment through big data analysis techniques. After pre-processing the available tax data, K-mean clustering algorithm is applied to form clusters of taxpayers with similar behaviour. Then decision trees are used to classify each cluster into tax payers with and without fraud and patterns in their associated behaviour are detected. Using these characteristics and patterns, the artificial neural network is trained and potential fraudsters could be detected based on the information available. This system will help detect tax fraudsters and enhance knowledge on their patterns of fraud which will be helpful in the prevention of fraud.

Big Data Analytics Evaluation

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th February 2018

Mudassir Khan | 

Abstract

In this age of technological and advanced world big data is prominent as a world new currency. The term big data is not a framework, language and Technology. Actually Big data is nothing but a problem statement. In the current era number of IOT enable devices is using data in huge amount. The data is coming from different datasets at an enormous amount. As data is increasing exponentially every year, the traditional system to store and process the data become incapable to handle it. The existing technologies are not capable to handle the big data. In this digital world, the data is generated automatically by the online interactions of big data applications. The Big data is used in the evaluation of emerging form of information. In the last two years data is growing at an enormous speed exponentially as compare to last twenty years. In this current era human life is totally dependable on IOT. This paper presents the overall changes in big data analytics evaluation growth in the recent years. The innovations in the technology and greater affordability of digital devices with internet made a new world of data are called big data. The data captured by enterprises such ad rise of IOT and multimedia has produce an overwhelming of data in either structured or un-structured format. It is a fact that data that is too big to process is also too big to transfer anywhere. So it is just an analytical program which needs to be moved (not the data) and this is only possible with cloud computing.

Big data Analytics of Medicare Disabled Patients with Hepatitis Disease

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th February 2018

N. Navaneetha | R. Sasi Rekha, L. Prashanti

Abstract

In the growing era of technology, concentration is on the analysis of a large amount of structured and unstructured data. The processing applications are inadequate to deal with these data are termed as BigData since in large amounts. In this work, an initial stage for analysing medical informatics using Rstudio by R programming is attempted by two algorithms. The biomedical data is used because they are concerned with the real-time usage and is an open access journal aiming to facilitate the presentation, validation, use, and re-use of datasets, and can be modifiable with focus on publishing biomedical datasets that can serve as a source for simulation and computational modelling of diseases and biological processes. Random forest technique and support vector machine (SVM) techniques are used to derive features from the database and are able to differentiate various disease supports. The aim of this paper is to provide a comparison between the various techniques that are involved in the field of sorting the data and analysing them in large numbers. For this, the process of data mining is used. Data mining is the process of extracting valuable information from a large set of databases. The latter technique produces more appropriate results that have less deviation from the reference taken from the hepatitis profile. By this method, one can get the lead vision of the results that are produced by medical science. Therefore the SVM technique can be implemented practically in the medical field.

Big Data and Analysis of Data Transfers for Research Networks Using NetSage

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th April 2018

Dr. A P Nirmala | Siddhant Kumar Sahu

Abstract

NetSage is to develop a unified, open, privacy-aware network measurement, and visualization service to address the needs of monitoring today’s high-speed international research networks. NetSage collects data on both backbone links and exchange points, which can be as much as 1Tb per month. This puts a significant strain on hardware, not only in terms storage needs to hold multi-year historical data, but also in terms of processor and memory needs to analyze the data to understand network behaviors.

Big Data and Its Privacy Issues

International Journal of Engineering Research in Computer Science and Engineering, Available online 10th November 2017

P.Latha | Dr. P.Niranjan

Abstract

With the recent growth in knowledge, networking and cost reduction in storage devices, today we are inundated with huge amount of data. The data is collect from various sources and wide variety of application areas. Study was performed on these data by means of precisely developed models. Big data is a straight term used to explain the exponential increase and convenience of structured and unstructured data. In upcoming big data will be essential to big business as well as society like internet capacity. Resolutions that were before build on belief or on conceptual models of reality can now be done based on the composed and store data itself. Big Data study is now used in almost all phase of our society, marketing, banking, communication services, and research. The big data stage has shown the ways for vast opportunities in health care system, science, economic decision, educational system and novel forms of community interaction and activity. But this opportunity also results in challenge in the area of confidentiality and safety. Big data utilize huge quantity of data that may be available in the cloud and it may require data giving out distributed across several servers. It is found that the increase progress of big data also intensify the fear to information security. This paper spotlight on the big data and its privacy issues associated to it.

Big Data – Technologies, Challenges and Future Scope

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

B.V.Hemalatha | R.Vijayalatha

Abstract

Big Data has gained much attention from the academia and the IT industry. In the digital and computing world, information is generated and collected at a rate that rapidly exceeds the boundary range. The term, ‘Big Data’ has been coined to refer to the gargantuan bulk of data that cannot be dealt with by traditional data-handling techniques. A huge repository of terabytes of data is generated each day from modern information systems and digital technologies such as Internet of Things and cloud computing. Analysis of these massive data requires a lot of efforts at multiple levels to extract knowledge for decision making. Therefore, big data analysis is a current area of research and development. The utilization of Big Data Analytics after integrating it with digital capabilities to secure business growth and its visualization to make it comprehensible to the technically apprenticed business analyzers has been discussed in depth. Aside this, the incorporation of Big Data in order to improve population health, for the betterment of finance, telecom industry, food industry and for fraud detection and sentiment analysis have been delineated. The challenges that are hindering the growth of Big Data Analytics are accounted for in depth in the paper

Big Data Based Security Analytics for Protecting Virtualized Infrastructures in Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

J.Yamuna | 

Abstract

In this Paper Virtualized infrastructure in cloud computing has become an attractive target for cyber attackers to launch advanced attacks. This paper proposes a novel big data-based security analytics approach to detecting advanced attacks on virtualized infrastructures. Network logs, as well as user application logs collected periodically from the guest virtual machines (VMs), are stored in the Hadoop Distributed File System (HDFS). Then, extraction of attack features is performed through graphbased event correlation and Map Reduce parser based identification of potential attack paths. Next, determination of attack presence is performed through two-step machine learning, namely, logistic regression is applied to calculate attack's conditional probabilities with respect to the attributes, and belief propagation is applied to calculate the belief in the existence of an attack based on them. Experiments are conducted to evaluate the proposed approach using well-known malware as well as in comparison with existing security techniques for virtualized infrastructure

Big Data Concepts, Challenges and Solution in Hadoop Ecosystem

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd October 2017

Dr. Ujjwal Agarwal | 

Abstract

Data becomes big data when its volume, variety, and velocity exceed the abilities of our systems architecture and algorithm. This paper discusses about three major sources of big data: machine generated data, people generated data and organization generated data, 6V’s of Big Data: volume, velocity, variety, valence, veracity and value along with we discussed the different variety of data: structured, semi-structured and un-structured data like sensor, images, PDF, CSV, JSON, RDMS, database, table data etc. out of which approximately 5% of available data is in structured form rest other data is in either unstructured or semi structured. Big data is facing lots of challenges due to volume, variety and other complexity in the data. Hadoop is the platform where we can find all our solution related to big data to store process and analysis purpose. The main objective of this paper to describe how Hadoop can solve different challenges of Big data by using HDFS (Hadoop distributed file System), Map Reduce and Hadoop Ecosystem components like Hive, Sqoop, HBase, Pig, spark, Flume, Kafka etc.

Big Data management in Manufacturing Industries for Internet of Things

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Sabitha M.S | Dr.S.Viayalakshmi ,R.M.Rathikaa Sre

Abstract

In the current scenario, enormous technology improvements are happening in the field of Network communication, cloud computing, Big Data and IoT. Information technology is bringing a new business paradigm by introducing Internet of Technology (IoT). Nowadays adoption of IoT and Cloud computing has become mandatory for the Modern enterprises. The biggest challenge in front of us is handling the IoT generated Big Data. Big Data provides an opportunity to find the insights from the machine generated data that converts the business environments into more agile and it answers the questions which were considered beyond our reach before. This paper focuses on the requirement of IoT and Big Data in the modern enterprises.

Big Data-An Emerging and Innovative Technology: Survey

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Keerthana R | Nandini N,Karthik N S, Divya L ,Mrs Sheela devi

Abstract

This paper is a review of the big data concept, its dimensions, its architecture comparison between the earlier concept and the latest, the storage possible i.e. the databases and origin of big data. The relational database, having rigid schema, has been prevailing since a long time but it is difficult to store the unstructured data in relational database. The unstructured data has mainly text nature or is in the form of logs. Here comes the concept of No SQL databases. Big Data is small data with large data size

Biological Wastewater Treatment Principles

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Ms.P.Sunitha | Prof.D.Usharani, Mr.K.Ravi Kishore, Ms.D.Sucharitha

Abstract

Natural receiving waters including rivers, streams, and tidal areas sustain a background population of microorganisms including bacteria, fungi, and algae. These organisms require energy for respiration and organic carbon food sources in order to synthesize new cells using the following general equation: In the above equation, the microbes occur naturally and consume organic food sources that are naturally present in the water. Some of the carbon matter in the food is biodegraded to release energy that drives the reaction. Energy is released through the biodegradation process by combining part of the organic food source's carbon compounds with oxygen. The by products of this reaction are additional microbial cells and carbon dioxide. Nutrients, primarily nitrogen and phosphorus, complete the reaction and are needed as part of the building blocks used to form new microbial cell tissue. In a clean water environment, the amounts of available organic food supplies are limited. This places a restriction on how fast the above reactions proceeds and also on how many microbes are able to grow. In general, the population of microbes in a clean water environment is restricted to a low background level by the limited amount of organic food that is present. While periodic fluctuations in the food supply may cause brief periods of population swings or declines, the number of microbes in the ecosystem will achieve an equilibrium condition over time that is based on the steady state amount of organic food present. If an artificial organic food supply is allowed to enter the ecosystem, the number of microbes that can be sustained will increase in response to the added food. If the amount of additional food is large, the population of microbes may increase exponentially and will continue to grow up to the point that the amount of food again becomes limiting for the elevated population. Raw sewage contains a high organic carbon content that provides an excellent supply of food for waterborne microbes. If raw sewage is discharged into receiving water, the bacteria population will become elevated in response to the new addition of food. This causes the above biodegradation reaction to proceed rapidly and, in the process, to create larger amounts of new microbes and carbon dioxide. This requires that more oxygen be available for use by the microbes. If sufficient extra food is added by the sewage discharge, the population of microorganisms and the resulting oxygen consumption may proceed so rapidly that all of the receiving water's oxygen is depleted.

Biometric security based on respiration

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd August 2017

Mr. Shiv Kumar | Dr. Arvind Kumar Sharma, Dr Anil Midda

Abstract

Validation is a major issue to any trust situated processing framework and furthermore a basic part in numerous security conventions. Performing confirmation is famously troublesome. After some customary techniques bio-measurements has been generally utilized and embraced as a promising confirmation strategy because of its favorable circumstances over some current strategies, especially, its imperviousness to misfortunes caused by robbery of passwords and savvy cards."Bio measurements" infers "life estimation" however the term related with the usage of exceptional physiological qualities to recognize a person. It's another approach to confirm validness. Bio-measurements uses natural qualities or behavioral elements to perceive a person. In genuine a Bio-measurements framework is an example ID framework that utilizations different examples, for example, iris designs, retina outline and natural qualities like fingerprints, facial geometry, voice acknowledgment and hand acknowledgment et cetera. Bio-metric acknowledgment framework gives probability to confirm one's personality just by deciding "who these individuals are" rather than "what these individuals have or might be recalled". The very actuality that makes it truly fascinating is that the different security codes like the security passwords and the PIN number could be exchanged among individuals yet the physical qualities can't be. As illustrations portable PCs have a unique finger impression sensor coordinated; banks are beginning to utilize bio-metric information too the attendances in some MNCs are likewise in view of bio-metric framework to maintain a strategic distance from unapproved individual's entrance. In any case, bio-measurements presents its own difficulties, for example, being basic once bargained. Be that as it may, the bio-metric security framework is one of the most secure security frameworks till the date. This paper introduces another sort of biometric security framework in light of human breath.

Biometric template protection techniques: A brief survey

International Journal of Engineering Research in Computer Science and Engineering, Available online 21st July 2017

Shilpa N L | Dr. R Aparna

Abstract

One of the natural and reliable solutions to user authentication problem is biometric recognition. Non universality, intra-class variation etc. are some problems in Unimodal biometric system. Therefore multimodal biometric systems are used to overcome these problems and to increase the level of security. The aim of this paper is to summarize the common attacks against biometric systems (fake biometrics, template modification etc.) and discuss techniques that can be used to counter them. The features that extracted from the biometric samples considered a critical part of biometric system which is called biometric template. Template security schemes are dependent on the overall performance parameters of the system and must be computationally hard to avoid modality reconstruction. This paper also summarizes different biometric template protection schemes (salting, visual cryptography etc.) and discusses their advantages and limitations

Blind Guider – A Smart Blind Stick

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Akshay Santosh Jadhav | Pooja Chandrakant Jadhav, Vrushikesh Madhukar Patil

Abstract

To provide innovative idea in order to enhance the leaving of visually disabled. Just to add more independent action in their lives. The visual identifier helps to detect and identify the obstacle via Ultrasonic sensors and will provide a voice message, distance between the person and an obstacle, where the distance is calculated through the ultrasonic sensor. Additive feature to the previous version which indicated with vibration is the distance calculation and the voice. Thus making movement process much easier. This is a kind of venture which will totally change the way of living of a blind people. It will provide awareness of every single thing around them. The innovative project will guide visually disabled while crossing roads and daily activities nearby areas visiting new places with ease as normal people. Sensor will alert about the presence of obstacles and provide the exact location through GPS as well. Also the IR sensor are used to detect change in level for detection of stairs.

Booster in High Dimensional Data Classification

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd May 2018

G. Madhavi | P. Uthejaswini, N. Bhanuja, M. Ramya, PK. Venkateswar Lal

Abstract

Classification issues in high dimensional knowledge with a little range of observations have become additional common especially in microarray knowledge. Throughout the last twenty years, voluminous economical classification models and have choice (FS) algorithms are planned for higher prediction accuracies. However, the results of associate degree FS rule supported the prediction accuracy are unstable over the variations within the coaching set, particularly in high dimensional knowledge. This paper proposes a brand new analysis live Q-statistic that comes with the steadiness of the chosen feature set additionally to the prediction accuracy. Then, we have a tendency to propose the Booster of associate degree FS rule that reinforces the worth of the Q-statistic of the rule applied. Empirical studies supported artificial knowledge and fourteen microarray knowledge sets show that Booster boosts not solely the worth of the Q-statistic however additionally the prediction accuracy of the rule applied unless the information set is in and of itself tough to predict with the given rule.

Brain Controlled Chess Based on Virtual Reality Control for Paralyzed Patients

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Sindhura Rao | Ashwini S,Kusuma Mohanchandra

Abstract

In this paper, we introduce a game in which the player plays chess by using a brain-computer interface (BCI). The BCI analyzes the steady-state visual evoked potential (SSVEP) responses recorded with electroencephalography (EEG) on the player’s scalp. The single three command control game is specifically designed around an SSVEP-BCI and validated in several EEG setups while using a neurosky headset. As a final step in the validation of the game, a random experiment on a broad audience was conducted with the Neurosky headset in a real-world setting.

Brain Gate: An Assistive Prosthetic Technology

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

Preethi.V | Hemalatha.R, Suganthi.N

Abstract

Brain Gate is a brain implant system developed by the Bio-Tech company Cyber kinetics conjunction with the Department of Neuroscience at Brown University. The device was designed to help those who have lost control of their limbs or other bodily functions such as patients with spinal cord injury. The computer chip, which is implanted into the brain, monitors brain activity in the patient and converts the intention of the user into computer commands. Brain continues to send neural signals required for all voluntary actions even in paralyzed patients but due to spinal cord injuries or some kind of stroke, the relay of signals is disrupted from reaching the corresponding destinations. This Brain Gate Neural Interface system fetches these neural signals through fiber optic cables, feed them to neural signal processing software which uses appropriate decoder algorithms to interpret the brain neural signals and execute the corresponding commands with the help of robotic arms. Currently the chip uses 100 hair-thin electrodes that are targeted to the neurons in specific areas of the brain, for example, the area that controls arm movement. This Brain Gate technology is moving towards passing the neural signals through electrical nerve wires implanted inside human body thus eliminating the use of robots

Brain Tumor Detection using Image Segmentation

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Siddhi N. Nerurkar | 

Abstract

Image segmentation is a process of partitioning a digital image into N regions. In today’s world, Brain tumor detection using image segmentation is fundamental but challenging problem in field of computer vision and image processing due to the diverse image content, image noise, non-uniform object texture and other factors. Accurate detection of size and location of brain tumor plays a vital role in the diagnosis of brain tumor. There are many image segmentation methods available for medical image analysis but the Region based and Clustering techniques are efficient, fast and accurate. This paper presents the two efficient image segmentation algorithms i.e. K-means and region growing techniques for brain MRI images and compare the two algorithms and determine the best one.

Brain Wave Monitoring By Using Open Source Tools

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

A. H. Pudale | Komal Chandiram Jeswani, Priyanka Omprakash Tapadiya, Sonali Madhukar Kadam, Rama Sambhaji Kambl

Abstract

People have no control over their mental state which may change depending on the circumstances. Therefore monitoring these changes is really important in case of a person suffering from depression, or mental disorder. We aim at developing an android application that will monitor the brain waves and provide an appropriate mental condition depending on the values of the waves obtained. We are developing an android application using android studio and interfacing it with arduino board and EEG sensors using bluetooth. Existing system makes use of this technique just for moving objects depending on the value of the waves. Also existing system monitors the mental condition by using facial expressions, heart rate, body temperature and gestures. There does not exists any application which will allow the users to see their mental condition not in the form of just graph but also actual condition after analysing these graph values. In our project we directly attach the sensors to the head so that we get correct brainwaves. So, that we can monitor and provide an appropriate graph and estimated result.

Brief Survey of Different Techniques for Prediction of Groundwater Level and Groundwater Quality

International Journal of Engineering Research in Computer Science and Engineering, Available online 21st November 2017

Ajinkya P. Chatur | R. V. Mante, Amol R. Dhakne

Abstract

Data analysis is a stream which uses concepts from statistics and computer science to clean the data and then to find some useful information out of it. In order, to access useful information, various algorithms of machine learning can be used. Such algorithms can further be used for prediction of future data to some extent. So this paper is focused on the survey of different methods and algorithms to analyze the patterns of groundwater level. After the analysis of their methods and their accuracies, it is concluded that CBA method can best describe the trends in groundwater and various factors affecting it.

Broadband Wireless Communication Using 5G Technology

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th June 2018

Sunita Arun Chavan | Aarti Suresh Varpe, Dr.K.Vikram

Abstract

The objective of this paper is comprehensive study related to 5G technology of mobile communication. Existing research work in mobile communication is related to 5G technology. In 5G, researches are related to the development of World Wide Wireless Web (WWWW), Dynamic Adhoc Wireless Networks (DAWN) and Real Wireless Communication. The most important technologies for 5G technologies are 802.11 Wireless Local Area Networks (WLAN) and 802.16 Wireless Metropolitan Area Networks (WMAN), Ad-hoc Wireless Personal Area Network (WPAN) and Wireless networks for digital communication. 4G technology will include several standards under a common umbrella, similar to 3G, but with IEEE 802.xx wireless mobile networks integrated from the commencement. The major contribution of this paper is the key provisions of 5G (Fifth Generation) technology of mobile communication, which is seen as consumer oriented. In 5G technology, the mobile consumer has given utmost priority compared to others. 5G Technology stands for 5th Generation Mobile Technology. 5G technology is to make use of mobile phones within very high bandwidth. The consumer never experienced the utmost valued technology as 5G.The 5G technologies include all types of advanced features which make 5G technology most dominant technology in near future.

BUGS in Silicon

International Journal of Engineering Research in Computer Science and Engineering, Available online 25th January 2018

Dr. Latika Kharb | Permil Garg

Abstract

In a computing system, a processor refers to an electronic circuit which performs operations on some external data which is stored in usual memory or some other data stream like Hard-disk, Flash-drive, etc. The market leaders in manufacturing CPU’s are Intel, AMD and ARM. MMX, SSE, SSE2, SSE3, SSE 4, SSE 4.1, SSE 4a, SSE4.2, SSE5, x86-64, AMD-V, Intel-VTx, AVX, AVX2, AVX-512, AES, SHA, FMA3, FMA4, F16C, XOP, 3D-NOW are the major instruction set present in today’s CPU’s. In this paper, we will discuss literature study on available processors and emphasized on Bugs in processors that are top marketers today.

Build Minimal Docker Container Using Golang

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd April 2018

Biradar Sangam.M | R.Shekhar

Abstract

Docker container is developed in Go Programming language. Container internal is encapsulated from Linux kernel feature i.e. namespaces and cgroup. Namespace isolation allows a server to isolate a process so that can’t see certain portion of overall system. Control groups as name its control the process, memory and CPU. It will track used memory. Container shares the same host kernel but they have their own virtualized network adapter and file system. Container allow for efficient application deployment and management. Go language is provide system programming support to the container. Container is the lightweight and portable encapsulation of an environment in which to run application. Container is created from images. It has all binaries and dependencies need to run application. Containerization is the new way to build, ship and deploy applications.

Building an Intrusion Detection System Using a Filter-Based Feature Selection Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd February 2018

B. Avanthi | N.Srinivas

Abstract

Redundant and irrelevant features in data have caused a long-term problem in network traffic classification. These features not only slow down the process of classification but also prevent a classifier from making accurate decisions, especially when coping with big data. In this paper, we propose a mutual information based algorithm that analytically selects the optimal feature for classification. This mutual information based feature selection algorithm can handle linearly and nonlinearly dependent data features. Its effectiveness is evaluated in the cases of network intrusion detection. An Intrusion Detection System (IDS), named Least Square Support Vector Machine based IDS (LSSVM-IDS), is built using the features selected by our proposed feature selection algorithm. The performance of LSSVM-IDS is evaluated using three intrusion detection evaluation datasets, namely KDD Cup 99, NSL-KDD and Kyoto 2006+ dataset. The evaluation results show that our feature selection algorithm contributes more critical features for LSSVM-IDS to achieve better accuracy and lower computational cost compared with the state-of-the-art methods.

Captcha as a Graphical Password Authentication System (CaRP)

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Archi Gaikwad | Bijal Parekh, Medha Kona , Shweta Bramhane

Abstract

We face many security breaching issues for our desktop applications and online services. Many internet applications commonly use text based passwords for authentication. Text based passwords are prone to many attacks such as online guessing attacks , relay attacks ,shoulder surfing and are usually hard to remember. Graphical password proves to be a much better alternative to overcome these attacks. This paper introduces the use of Captcha as Graphical Password- CaRP to enhance the security at the time of login. CaRP is the combination of both graphical password and captcha technology. This system allows the user to select different visual login schemes. CaRP is one of the reasonable solutions that provides added security

Cat Swarm Optimization based Localization Algorithm for Wireless Sensor Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st January 2018

Nitin Jain | Sushila Madan,Sanjay Kumar Malik

Abstract

In Present time, Wireless sensor networks (WSNs) can be applied in many different applications areas. It is a network of sensor nodes whose primary work is to collect the data from sensing field and process these data. Hence, in WSNs, localization problem can be occurred due to lack of information about the accurate positions of sensor nodes. The localization algorithms divide into range free and range-based algorithms. Due to hardware limitations of WSNs devices, range-free localization algorithms are more widely adopted to determine the position of nodes in sensor fields. But, these algorithms have the tendency of error during the computation of nodes positions. DV-hop is one of the popular range-free localization algorithms that can widely be adopted in WSNs and works on the concept of hop distance estimation. In this paper, an improved version of DV-hop localization algorithm is proposed based on cat swarm optimization algorithm, called CSO DV-Hop algorithm. The main concern of the integration of CSO algorithm with the DV-Hop algorithm is to reduce the localization error of DV-Hop algorithm. The simulation results reveal that proposed algorithm enhances the location accuracy in comparison to other algorithms being compared.

Causes of Replacing Geographical Traditional Mapping into New World Digital Mapping through Geospatial Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 10th January 2018

Surender Kumar | 

Abstract

Geographical traditional mapping means graphically representation of the earth’s surface features on a flat surface or plain paper. This mapping technique used from prehistoric depiction of hunting and fishing. This old cartographic technique prepares maps for different purpose which is very helpful in any kind of discoveries, innovations and developments. But after a long period these maps becomes referenced data because, in our dynamic world, many aspects of land cover and land use things on the earth are constantly changing over time to time. These analogue mapping such as Topo sheets, wall maps, atlas.etc is facing problems of spatial-temporal changes caused by natural and human activities. They don’t match the current condition of any area because they are out of date. We can’t modify these changing aspects on analogue or paper maps. To solve this mapping problem, geospatial techniques such as remote sensing, geographical information system, and global positioning system has been indispensable in digital mapping using data of aerial photographs, satellite imageries with very fine resolution. Using this data, digital maps are prepared with the help of new generation computer which has the quality of large data collecting, storing, manipulating, analyzing, displaying, and querying of geographically related information. Digital mapping monitor land use and land cover change, which has been seen in various fields such as meteorology, geology, forestry, hydrology, oceanography, environmental management, agriculture etc. and we can easily update this change in maps. That’s why digital mapping replaced geographical traditional analog mapping.

CDA Generation and Integration for Health Information Exchange Based on Cloud Computing System

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

A.Soniya | Dr.V.Sireesha, M.Harshitha, G.Sai Harshitha, B.HariChandana

Abstract

Successful deployment of Electronic Health Record helps improve patient safety and quality of care, but it has the prerequisite of interoperability between Health Information Exchange at different hospitals. The Clinical Document Architecture (CDA) developed by HL7 is a core document standard to ensure such interoperability, and propagation of this document format is critical for interoperability. Unfortunately, hospitals are reluctant to adopt interoperable HIS due to its deployment cost except for in a handful country. A problem arises even when more hospitals start using the CDA document format because the data scattered in different documents are hard to manage. In this paper, we describe our CDA document generation and integration Open API service based on cloud computing, through which hospitals are enabled to conveniently generate CDA documents without having to purchase proprietary software. Our CDA document integration system integrates multiple CDA documents per patient into a single CDA document and physicians and patients can browse the clinical data in chronological order. Our system of CDA document generation and integration is based on cloud computing and the service is offered in Open API. Developers using different platforms thus can useour system to enhance interoperability.

Challenges and Issues in Big Data Era- A Survey

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Shony KM | Navaneeth Krishnan K,Daniel F Netto

Abstract

Big Data analytics have significant promises in this era of information explosion. Cloud computing, ecommerce , social networking etc. are enhancing importance of big data. However, there are a number of challenges that must be overcome to realize its true potential. Big Data analytic systems use cluster computing infrastructures that are more reliable and available as compare to traditional security analytics technologies. Big data absolutely has the potential to change the way governments, organizations, and academic institutions conduct business and make discoveries, and it is likely to change how everyone lives their day-to-day lives. This will constitute its future scope.

Chaotic Based Image Cryptography Using Wavelet Transform

International Journal of Engineering Research in Computer Science and Engineering, Available online 28th March 2018

Dr. P Shanthi | 

Abstract

The main objective of the paper is to enhance the security of the images using chaotic map with wavelet transform. Chaos-based image encryption method is one of the most efficient methods which is used to hide visual information during transmission. This paper presents a new image encryption method based on Arnold cat map with Wavelet Transform, in which, chaotic maps will change the pixels of the plain-image to encrypt that. Finally, the encrypted image will be decrypted to remake the plain-image. To evaluate the efficiency of this method, it has been implemented with MATLAB and also has been measured by doing some tests as analysis of Peak signal-to-noise ratio and adding salt & pepper noise. Simulation results show that the proposed image encryption method has high accuracy while it is resistant to salt & pepper noise

Characterisation of Jute, Areca and Glass Reinforced Polymer Composite

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Muhsin M P | Abee Narayan , Arjun Vijaykumar P,Aboobacker Siddiq KV,Channakeshava R

Abstract

Composite material market is exponentially growing and finding its application in almost every walks of life. Here we prepared three composites of different stacking sequences and fibre reinforcement for our experiment. We have used areca, jute and glass fibres for making a composite with epoxy as resin. Our composites had ten layers of fibre of different stacking sequence for every specimen. Hand layup technique was used for preparing the material. Compression moulding was done on the stacked laminates and the final product was measured to be 30x30x3 mm. the composite then was converted different specimens as per ASTM standards. The tensile and flexural test was done for every combination of specimen and in three different combinations jute+glassfibre reinforced matrix was found to have more tensile and flexural properties. Graphical results were obtained for the tests and analysed and final result was drafted.

Circularly Polarized 2 Element Rectangular Dielectric Resonator Antenna Array

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th April 2018

Khudkhudiya Heema | Dr.Yagnesh Shukla, Prof. Renuka Makwana

Abstract

Circularly-polarized (CP) rectangular Dielectric Resonator Antenna (DRA) array is designed on 5.8GHz. Initially, a single element DRA is designed by feeding with two orthogonal microstrip lines to obtain circular polarization. The gain of the proposed DRA array is 5.11dBi obtained over the 5.8GHz. This DRA can be used for WLAN.

Classification of Emotion using Different No. of MFCCs

International Journal of Engineering Research in Computer Science and Engineering, Available online 28th March 2018

Pramod Mehra | Parag Jain

Abstract

In this paper, the spectral features are separated from speech and used to perceive the feelings from speech. As Speech has been utilized as a vital method of correspondence since the time immemorial. Feelings are a basic piece of normal speech correspondence. The vast majority of the present speech frameworks can process studio recorded nonpartisan speech with more prominent precision. Hence, a need is felt to refresh speech preparing frameworks with the ability to process feelings. The part of feeling handling makes the current speech frameworks more practical and significant. In this work, spectral highlights are extricated from speech to perform feeling grouping. mel recurrence cepstral coefficients and their subsidiaries (speed and increasing speed coefficients) are investigated as highlights. Gaussian blend models are proposed as classifiers. The feelings considered in this examination are outrage, satisfaction, unbiased, pity and astonishment. The speech feeling database utilized as a part of this work is semi-common in nature, which has been gathered from the exchanges of performing artists/on-screen characters.

Classification of Time Series Trajectories Based on Shape Features using SVM

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Gajanan S. Gawde | Jyoti D. Pawar

Abstract

Classification of time series trajectories is a non trivial problem and few researchers have contributed to this field. Time series trajectories such as Character trajectories, ECG trajectories, Stock Exchange Trajectories need to be classified accurately in order to improve the performance of system. The classification of time\ series trajectories is carried out using different techniques such as Neural networks, Support vector machines, Fourier Transforms and Bayesian Network. Most of the existing classification techniques work on simple features such as co-ordinates, distance, and velocity. These techniques are not able to consider shape features of trajectories and classify the test trajectories. Shape of the time series trajectory is an important feature and can be used in the classification method. A support vector machine is better classification technique compared to the existing techniques. In this paper, we have proposed our novel classification method to classify time series trajectories using SVM with shape as the feature vector for classification purpose. Thorough experimental study was carried out on proposed technique with different datasets. Experimental results shows that SVM technique is better compared to Neural Network, Fourier Transform, Bayesian Network. SVM with shape features is efficient compared to SVM without shape features. We have tested SVM with different kernel functions. Our experimental results show that RBF SVM with shape features method is efficient compared with Linear and Non Linear kernels.

Classification of YouTube Data based on Sentiment Analysis

International Journal of Engineering Research in Computer Science and Engineering, Available online 18th July 2018

Shaila S.G | Prasanna MSM, Kishore Mohit

Abstract

Nowadays, Big data and Data mining have attracted a great deal of attention in the information industry, due to the wide availability of huge amounts of data and the urgent need for turning such data into useful knowledge through predictive models. Corporate companies are using social media for improving their businesses, the data mining and analysis are very important in these days. Thus, Interaction and review are established with the customers and the concept, characteristics & need for Big Data & different offerings available in the market to explore unstructured large data. The paper deals with analysis of YouTube Data. The analysis is done using users Sentiments features such as Views, Comments, Likes, and Dislikes. We used the Linear Regression classification approach to classify the YouTube Data. The experimental results are given accurate results which illustrated that it is influential practice and a key enabler for the social business. The insights gained from the user generated online contents and collaboration with customers is critical for success in the age of social media

Classifying Tamil Audio Signals According To Speakers Using Combined MFCC and LPC Method

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th April 2018

J.Rexy | Dr.P.Velmani, Dr.T.C.Rajakumar

Abstract

The social network is the main ambassador for information sharing in this digital era. Nowadays social network is being utilized by different level of people in diverse platforms for many reasons.Most of the data which are shared by social media are unstructured data which does not have a predefined format. There are many examples of unstructured data; among those audio plays, a vital role as many audios are being shared in Social Media. Audio data can be utilized to leverage intelligence such as identify the speaker, identifying emotions, identifying the area of talk etc. Since Tamil is one of the longest surviving classical languages in the world and very few researchers are focused on Tamil audio analysis, this paper deals with Tamil audio speaker recognition implemented in Matlab version 13. The basics of speech recognition, feature extraction process, and pattern matching pave the way for identifying and classifying Tamil audios according to speakers are also reviewed. In order to improve the efficiency of the recognition process, during the pre-processing stage, Adaptive Weiner filter is employed for removing unwanted noise from the audio signal. After the pre-processing stage, the retrieved enhanced signal is utilized for feature extraction process which is carried out using combined LPC (Linear Predictive Analysis) and Mel- Frequency Cepstral Coefficients (MFCC). The mfcc coefficients are used as audio classification features to improve the classification accuracy. LPC is one of the most powerful speech analysis techniques and is a useful method for encoding quality speech at a low bit rate. Hence MFCC and LPC could contribute more to extract best features.In order to increase the accuracy rate of training and recognition,MFCC and LPC are combined in feature extraction.The feature extraction process generates feature vectors which are extracted for further processing. The extracted feature vectors are applied to hybrid MLP and SVM machine learning Algorithm to identify the speaker and classify the audios accordingly

Client Gender Prevision based on the E-commerce Information

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th July 2017

Srinivasa R B.E | Deepika M

Abstract

The Demographic property of clients such as gender, age, and education gives important information for e-commerce service providers or specialists in merchandising and personalization of web applications. However, online clients often do not give this type of information due to privacy and security related reasons. In this we proposed a method for previsioning the gender of clients based o0n their catalogue viewing data on e-commerce systems, such as the date and time of access, list of categories and products viewed, etc. We use a machine learning techniques and investigate a number of characteristics derived from catalogue viewing information to prevision the gender of viewers. Experiments were carried out on the datasets. The results 81.2% on balanced accuracy shows that basic characteristics such as viewing time, products/categories characteristics used together with more advanced characteristics such as products/categories sequence and transfer characteristics effectively facilitate gender prevision of clients

Climate Responsive Smart Homes

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Ar.Rashmi Tijare | Ar.Nikhil Wasade

Abstract

Home Automation is a multidisciplinary. It involves almost all branches of science & engineering. While learning in the urban context of residential design it was realized that the standard of living in terms of quality has come down. Quality, not in terms of material and standard of living or technology, but in terms of the feature of space. Further exploring this topic lead to, the Automation of Building parts so as to suit climate of the region and act smartly according to climatic situation. The study further extends and develops a series of modifying and adaptive elements for residential spaces that are responsive to the climate, lifestyle and its effect.

Clock Power Optimizations in VLSI design at advanced technology nodes

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd August 2017

Penugonda Ravikumar | Devanga Ampabathini Susmitha

Abstract

Classification of time series data is one of the popular fields nowadays. Many algorithms exist to get accurate and faster result which speeds up the computation. Nowadays E-Commerce sites are providing many user convenient options like recommendations for the products that they are purchasing which are playing key role in attracting the users to visit their sites. All these are happening based on the classification of data. Home automation is one of the evolving technologies in which data storage is important. It will be convenient if we are able to compare test data with limited trained data by preserving accuracy. Some data such as national security, personal information, bank details must be very confidential which has to be stored very securely. These all comes under time series data and data such as images, weather reports, speeches, and satellites data can be converted into time series data. Classification of normal data can be done by normal methods like nearest neighbor but to classify Time Series data by taking all these above features into consideration is difficult because time series data has to convert into structured format and it has to be sort and compare according to time Some existing algorithms are quite good in classifying Time Series data by satisfying some of these features. There are many algorithms which can classify data of different types quite accurately. But all algorithms might not satisfy all factors. So based on type of data we have to choose appropriate algorithm.

Cloud Based Plant Leaf Disease Detection System Using an Android Application

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

P.Vanaja | E.Pavithra, P.Jotheswaran, N.Kumaresan, N.Sathiyapriya

Abstract

Most of the population in India depends on agriculture and farming. Indian economy directly depends on agricultural production. The proper maintenance of plant growth includes various steps such as to examine the environmental factors and manage water supply for proper cultivation of plants. A traditional way of irrigation is not efficient and unreliable. Around 18% of crop yield is lost worldwide due to pest attack every year. Identification of plant disease is key to preventing the losses in the yield of agriculture product which is difficult to do manually. The project therefore involves a system architecture which allow user to achieve all above activities in real time so that farmers can view their farm details from remote location. It includes- 1.A module placed in a farm that contains various sensors and device for data conversion and transfer such that farm details and environmental factors are monitored and controlled correctly 2.Image processing for disease detection of visually seen symptoms of plant. Using an application the treatment is suggested to reduce the damage levels. The proposed system will thus improve in the productivity and benefit irrigation sector

Cloud Computing - Web Services

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th January 2018

Abhirati Ghosh | 

Abstract

Today's models and systems (in the application approach) are used according to the user's needs, while the rest of the time computing resources remain not used. Such services are characterized by an extremely high level of security and synchronization of files that are continuously exchanged. Cloud computing is an information technology paradigm, a model for enabling ubiquitous access to shared pools of configurable resources, which can be rapidly provisioned with minimal management effort, often over the Internet. A web service is a service offered by an electronic device to another electronic device, communicating with each other via the World Wide Web. This paper links between the two.

Cloud Computing and Semantic web: An Interplay

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th September 2017

Chethan R | Divya D, Kavya H, Prashanth,Vani Saptasagar

Abstract

CLOUD computing is a subversive technology that is changing the way IT hardware and software are designed and purchased. Cloud computing provides abundant benefits including easy access, decreased costs, quick deployment and flexible resource management, etc. It has become highly popular for data owners to outsource their data to public cloud servers while allowing data users to retrieve this data. For privacy concerns, a secure search over encrypted cloud data has motivated several research works under the single owner model. However, most cloud servers in practice do not just serve one owner; instead, they support multiple owners to share the benefits brought by cloud computing. In this paper, we propose Dynamic Secret key generation for multi user in cloud computing. To enable cloud servers to perform secure search without knowing the actual data of both keywords and trapdoors, we systematically construct a novel secure search protocol. To rank the search results and preserve the privacy of relevance scores between keywords and files, we propose a novel additive order and privacy preserving function family. To prevent the attackers from eavesdropping secret keys and pretending to be legal data users submitting searches, we propose a novel dynamic secret key generation protocol and a new data user authentication protocol

Cloud Computing and Semantic web: An Interplay

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th September 2017

Clara Kanmani A | Suma V, N Guruprasad

Abstract

Cloud Computing is internet based computing that provides shared computer processing resources and data to computers and other devices on demand. Semantic web is an extension of the current web in which information is given welldefined meaning, enabling computers and people to work in cooperation. This paper gives a brief picture of how Cloud computing and future web, semantic web technology evolved. However from the extensive literature survey, it is also observed that, these two technologies plays an interplay role with each other in solving complex problems. Furthermore an analysis of where semantic web technology meets cloud computing is carried out and briefly describes how Semantic web technology can be used to address the challenges of cloud computing.

Cloud Computing and Semantic web: An Interplay

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th September 2017

Adivikottu Ramakrishna | Dr.G.P.Saradhi Varma

Abstract

A customer who has issued a Query word question to a web searcher. The Keyword proposals are the most important element of the web search tool. Truthful clients don't know how to express their examination accurately more often than not questions are short and unambiguous. Using that watchwords web file recovers the reports, the proposed Query hold phrase inquiries to the customer, which are semantically noteworthy to the main question and they have results records that contrast with objects near the customer's region. Thus, here propose a weighted Keyword-Query record graph which gets semantic likewise, expel among inquiries and reports. By then, use the outline to propose questions that are shut as far as graph detachment to the primary inquiries. Fragment-based estimation is used to make the structure more flexible, using the proposed take hold of phrases the system again performs watchword controlling. In catchphrase guiding, the system removes all the keep words from the sentence. By then form a candidate question graph, to find the base partition between the segments. Least Crossing tree is used to find the partition between the segments

Cloud Computing with Internet of Things

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th June 2018

Pawale Pooja | More Priyanka, Vidya Dhamdhere

Abstract

Machine learning is a part of computer science that developed from the study of pattern recognition and computational learning concept in artificial intelligence. Machine learning determines the study and construction of algorithms that can absorb from and make guesses on data. The Internet of Things (IoT) is the network of physical objects or "things" rooted with electronics, software, sensors, and network connectivity, which allows these objects to collect and exchange data. Collections of devices will act as systems that can be enhanced in new ways, and systems of systems will share data and perform as an network of data and devices. Machine learning - a term that describes numerous methods to evolving meaning from data - will have to be part of the calculation, but so will outdated professional and data investigation techniques as organizations prepare for the Internet of Things (IoT). This paper will provide an overview of challenges and openings presented by this new model

Cloud Storage Based on Key-Value Store

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th July 2017

Abhishek Pandhare,  | Mayur Patil, AkshayPandure,Yogesh Pawar

Abstract

Nowadays, cloud-based storage services are rapidly growing and becoming an emerging trend in data storage field. There are many problems when designing an efficient storage engine for cloud-based systems with some requirements such as big-file processing, lightweight meta-data, low latency, parallel I/O, deduplication, distributed, high scalability. Keyvalue stores played an important role and showed many advantages when solving those problems. This paper presents about Big File Cloud (BFC) with its algorithms and architecture to handle most of problems in a big-file cloud storage system based on key value store. It is done by proposing low-complicated, fixed-size meta-data design, which supports fast and highly-concurrent, distributed file I/O, several algorithms for resumable upload, download and simple data deduplication method for static data. This research applied the advantages of ZDB - an in-house key value store which was optimized with auto-increment integer keys for solving big-file storage problems efficiently. The results can be used for building scalable distributed data cloud storage that support big-file with size up to several terabytes

Cloud-Based Secure Access

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th February 2018

Chethan Kumar T E | Karthik Venkateswaran

Abstract

Secure Access is one of the prime requirements for any personal or public asset. Enabling access to only designated personnel is the main requirement. All of the current systems are limited by the physical resource to gain access such as Key, Access card or Trusted escort. Cloud-Based Secure access apart from solving the physical resource also solves the problem of Access Card/Medium being misused by unauthorized personnel and additional controlled access can be granted or revoked easily by the asset owner.

Clouds and IoT

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2018

Dr.A.V.Prathap Kumar  | Dr K. Satish Kumar

Abstract

Machine learning is a part of computer science that developed from the study of pattern recognition and Computational learning concept in artificial intelligence. Machine learning determines the study and construction of algorithms that can absorb from and make guesses on data. The Internet of Things (IoT) is the network of physical objects or "things" rooted with electronics, software, sensors, and network connectivity, which allows these objects to collect and exchange data. Collections of devices will act as systems that can be enhanced in new ways, and systems of systems will share data and perform as annetwork of data and devices. Machine learning - a term that describes numerous methods to evolving meaning from data - will have to be part of the calculation, but so will outdatedprofessional and data investigation techniques as organizations prepare for the Internet of Things (IoT). This paper will provide an overview of challenges and openings presented by this new model

Cluster Based Data Centric Trust Management in VANET

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

S.V.Saboji | Bhagyashree K.L

Abstract

Vehicular ad hoc networks (VANETs) require the potential to transform the way people travel through the construction, interoperable wireless communications network that comprises cars, buses, traffic indicators mobiles, and other devices. However, VANETs are susceptible to safety threats due to increasing requirement on communication computing and control technologies In this paper an challenges has been made for create new cluster model for efficient communication among the VANET nodes this paper emphases on data centric trust management system to provide consistent communication between the nodes prevents the malicious nodes, RSU aided scheme help to generate the trust values. Simulation shows the effectively analyze data provided in VANET and correctly establish trust on data.

Clustering Based Crop Diversification Model Using K-Means Algorithm in Indian Punjab Region

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th May 2018

RadhikaSethi | Sikander Singh Cheema

Abstract

A major area of research in Indian Punjab is in crop diversification. Crop Diversification means cropping system to agricultural production on same farm to increase biological stability of the farm. Then present studies and attempt to focus on the systematic review of the literature about the crop diversification and role of clustering in crop diversification. The finding showed that clustering provide better crop diversification. We will also consider possible future work to provide different clustering techniques to gain most of the knowledge in crop diversification.

Clustering of Labeled And Unlabeled Data By Integrating Pre And Post Clustering Approaches

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Mr.Asadi Srinivasulu | Dr.Ch.D.V.Subbarao,I. Muralikrishna

Abstract

Clustering is the process of organizing objects into groups whose members are similar in some way or differ significantly from other objects. There are two approaches viz., pre-clustering and post-clustering. Pre-clustering is an unsupervised learning that assigns labels to objects in unlabeled data. The important pre-clustering approaches that we have considered are Dark Block Extraction (DBE), Cluster Count Extraction (CCE) and Co-VAT (Visual Assessment of Cluster Tendency). The present work focuses on pre-clustering approach. The limitations of these pre-clustering algorithms are i) DBE can’t handle the large data ii) CCE suffers because of perplexing iii) Co-VAT works with only rectangular data. Our work proposes Extended Dark Block Extraction (EDBE), Extended Cluster Count Extraction (ECCE) and Extended co-VAT to overcome the above said limitations. The following five steps results after integrating pre and post clustering approaches. They are 1) Extracting a VAT image of an input dissimilarity matrix. 2) Performing image segmentation on the VAT image to obtain a binary image, followed by directional morphological filtering. 3) Applying a distance transform to the filtered binary image and smoothing the pixel values on the main diagonal axis of the image to form a smoothening signal. 4) Applying first-order derivative and fast fourier transformation on smoothened signal for detecting major peaks and valleys. 5) Now post-clustering approach i.e. k-means algorithm is applied to the major peaks and valleys in-order to obtain refined clusters. The proposed algorithms viz., EDBE, ECCE and Extended Co-VAT uses VAT as well as the combination of several image processing techniques are applied on various real world data sets like IRIS, WINE and Image Data sets. These extended approaches use Reordered Dissimilarity Image (RDI) that highlights potential clusters as a set of 'Dark blocks' along the diagonal of the image. The simulation results show that EDBE, ECCE, Extended co-VAT outperform DBE, CCE and co-VAT in terms of time-complexity and accuracy of labeled and unlabeled data.

Collaborative Filtering-Based Recommendation of on-line Social option

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th May 2018

P.Rangamma | Dr.V.Sireesha, S.Yamini, V.Manusha, V.Manusha

Abstract

Collaborative filtering, on-line social networks (OSNs), recommender systems (RSs), social option

Collective Activity Recognition Using Nave Bayes Classifiers

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Salini. S | Prof.V.S. Mahalle

Abstract

Collective activity recognizing is the action of collecting the individual persons activity and it is distinguished as an atomic activity in isolation. In this paper, our work is based on the object detection and object recognition (ie) tracking is done for a given input video frame. The collective activity computes the class-specific person to person interaction patterns. The multiinteraction response proposed a activity specific pattern for each interaction at the same time Naive bayes classifier is used to track the object and the tracked result is feed back into the recognition part to find category of an object and it is the final result.

Color and Texture Based Image Retrieval Based on Quadtree Segmentation Technique

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Shradha Naik | Prof. Umesh A. Bapat

Abstract

With the increasing demand for need of retrieval of images based on different aspects, properties, characteristics there has been tremendous research going on in the field of Content-based image retrieval (CBIR), also known as query by image content (QBIC). Content here is referred to visual features ie colour, texture, shape, spatial layout of an image which needs to be extracted. This paper proposes a novel approach wherein content based image retrieval is based on color and texture primarily implementing color histogram for color based and gabor filter for texture based retrieval. Colour histogram comprises of two colour models(RGB and HSV). For texture based, Frequency and orientation representations of Gabor filters are similar to those of the human visual system, and they have been found to be particularly appropriate for representing and discriminating texture well . Main aim of this paper is to implement a new technique that is quadtree segmentation on query and database images and then apply feature extraction ie color histogram on all images and match the query and database images using similarity criteria. Similarity metric used in this paper is Euclidean distance. Quad tree is a segmentation technique which divides image into homogeneous blocks. Hence the name Quadhistogram is a new revised technique to implement colour based retrieval under local colour histogram which divides the images into homogeneous blocks and then compute histogram of each block

Color based Wavelet and Curvelet Transform Image Retrieval

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

D.Saratha | R.Kanagaselvi

Abstract

The system proposes new approach in extension with local color and Fast curvelet transform and entropy measurement in RGB Space. Discrete curvelet transform is one of the most powerful approaches in capturing edge curves in an image. The project presents the robust object recognition using texture and directional feature extraction. The system proposes texture descriptors such as Fast Discrete Curvelet Transform (FDCT) based entropy feature which represents better texture and edges and Local Directional Pattern (LDP) which provides textural details about all eight directions. By using these methods, the category recognition system will be developed for application to image retrieval which proves Low computational complexity and high compatibility.The tests are performed more than 12 seat stamp regular scene and shading surface picture databases, for example, Corel-1k, MIT-VisTex, USPTex, Hued Brodatz, et cetera.

Color Image Denoising Methods Based on Modified Mean-Median (MMM) Method

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th December 2017

Gourav Dhakad | Hitesh Gupta, Vijay Trivedi

Abstract

Image enhancement techniques are best solution for improving the visual appearance of images to a human viewer. It also preserves the structure features of the image. Enhancement of the noisy image data without losing any significant information is very challenging. In this paper we have introduced the modified mean median based method for removing impulse noise effectively while preserving details of the image. The proposed filter would be better than many of the existing filters such as the median filter and its variant and other fuzzy filters. The advantages of these method are that it reduces Impulse noise in a grayscale image as well as the color image (low-level impulse noise),It preserves edge sharpness, It does not introduce blurring artifacts or new colors artifacts in comparison to other states of the art methods.

Combating Mind Wandering in The Area of Academics

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Tanu Varshney | Priyanka Chaudhary, Priyanka Tripathi , Neha Tyagi

Abstract

This paper presents how the wandering mind is linked to the field of academics. We are also going to talk about how can we interpolate memory test in reducing mind wandering. We also mention here the strategies to train our brain. Here we devise the measures to combat mind wandering during studies i.e. Learning Mental Self-Regulation for improved concentration and arranging factors that you can immediately control your mind. Also we will focus on two applications that can be built to study mind wandering.

Combined Economic Load and Emission Dispatch using Cuckoo Search Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

MCV Suresh | Dr. Shaik Rafi Kiran

Abstract

This paper presents an application of cuckoo search algorithm for multi-objective optimization problem in power system. Considering the environmental impacts that grow from the emissions produced by fossil-fuelled power plant, the economic dispatch that minimizes only the total fuel cost can no longer be considered as single objective. Application of cuckoo Search algorithm in this paper is based on mathematical modelling to solve economic, emission and combined economic and emissions dispatch problems by a single equivalent objective function. cuckoo search algorithm has been applied to two realistic systems at different load condition. Results obtained with proposed method are compared with other techniques presented in literature. Cuckoo Search algorithm is easy to implement and much superior to other algorithms in terms of accuracy and efficiency.

Comparative Analysis of Heart Disease Dataset using KNN and Decision Tree Classification

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th August 2017

Bhavini Bhatia | Vamika Razdan

Abstract

There are huge amount of data in the medical industry which requires prediction and analysis so that right decisions can be made and help in proper analysis. As the data is large and the decision made by the doctor may not be accurate which may result in failure in some cases and can sometimes put someone's life at stake. Data mining in healthcare is an intelligent diagnostic tool. Heart disease is the leading cause of death in the world over the past 10 years.29.2% of deaths are due to Cardiovascular Diseases(CVD). Researchers have been using several data mining techniques to help healthcare professionals in the diagnosis of heart disease. Decision Tree is one of the successful data mining techniques used. However, most researchers have applied KNN . Number of experiments has been conducted to compare the performance of predictive data mining technique on the same dataset and the outcome reveals that Decision Tree outperforms other predictive methods like KNN, Neural Networks.This research paper intends to provide the knowledge that which data mining technique gives better accuracy and should be used in Heart Disease analysis.

Comparative Analysis of Outlier Detection Methods

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th May 2018

Mahvish Fatima | Jitendra Kurmi

Abstract

This paper presents different types of outlier detection methods. There are many factors which generate outliers it can be a measurement error, instrumentation error etc. No matter whatever is the reason outliers can be identified using these methods effectively. The experiment was conducted on SPSS tool. The comparative analysis of these methods was performed successfully. The aim of this paper was to analyze the methods of outlier detection from the research point of view. Furthermore, we find out the impact of different methods on the dataset containing outliers.

Comparative Study of Big Ten Information Security Management System Standards

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th February 2018

Mr. Mohd Tajammul | Dr. Rafat Praveen

Abstract

Data is a very critical element of any corporation in the modern age of information. Its protection is the main concern of an organization. Current scenario does not indicate that data is fully protected and also there does not exist any single mechanism which can make data cent percent secure. Security breaches that are leakage of sensitive information leverage a bad effect on the market of cloud computing. It produces a barrier before organizations to adopt cloud computing. In this paper, the effect of security standards on the data protection and also on the market of cloud computing has been uncovered. Finally, a comparative study of ten security standards namely PRINCE2, COSO, ISO27001, BS7799, OPM3, PCI-DSS, CMMI, SOA, ITIL and COBIT has been discussed.

Comparative Study of Management Information System and Decision Support System

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th April 2018

Dr. Arun Mohan Sherry | Mayur Desai

Abstract

Management information systems (MIS) is an organized, diverse and automated information system that is concerned with the process of gathering, storing and transferring relevant information to support the management operations of an organization. The data is distributed among the various departments in an organization. MIS work in online mode with an average processing speed.Generally, it is used by low-level management.Decision support system is the powerful tool that assists corporate executives, administrators and other senior officials in making the decision regarding the problem. This paper focuses on understanding the concept of IS, DSS, MIS, the MIS model, Comparison of MIS and DSS, decision-making system and majorly the role of MIS in decision making.

Comparision of K-Means and Knn Algorithm in Data Mining

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th February 2018

S.R.Kalaiselvi | C. Karpagam

Abstract

Data mining is the procedure for analyzing data from the different perspective and shortening it into helpful information. It can be used to increase income, minimize the costs. Data mining software is one of the analytical tools for analyzing data. It allows users to examine data from many different proportions, classify it, and review the relationships identified. Theoretically, data mining is the process of ruling correlations or patterns among dozens of fields in huge relational databases. Nowadays, organizations are accumulating vast and growing amounts of data in different formats and different databases. A data mining algorithm is a set of calculations which creates a data mining model from data. To build a model, the algorithm first analyzes the data and it looks for the particular type of pattern. These algorithms use the outcome of the analyzed data to define the most favorable parameters for creating the mining model. K-means is the unsupervised learning algorithm and it is an incremental approach to clustering data dynamically adds one cluster center at a time through a deterministic global search procedure. It is a simple and easy way to classify a given data set through a certain number of clusters. The k-Nearest Neighbors algorithm (or k-NN for short) is a non-parametric method used for classification and regression. In k-NN algorithm, neighbors are taken from a set of objects for which the class (for k-NN classification) otherwise the object property value (for k-NN regression) is identified. This can be considered of as the training set for the algorithm, though no explicit training step is necessary.

Comparison of Keyword Search and Ranked keyword Search in Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Kavya H | Prashanth Putta P, Chethan R, Divya D,Vani Saptasagar

Abstract

Cloud computing otherwise known as on demand computing. It provides the services over the internet. It has the provision of facilitating users to store and access their data in and from cloud server by sitting anywhere and on any device. Storing data in cloud server also opens up so many security threats as data is accessed over internet and client has no direct control over data once uploaded into cloud server. We first implement a basic idea for the Single Keyword Search Over Encrypted Data And then Multi-keyword Ranked. Search over Encrypted cloud data (MRSE) based on secure inner product computation and efficient similarity measure of coordinate matching, i.e., as many matches as possible, in order to capture the relevance of data documents to the search query, then we give two significantly improved MRSE schemes to achieve various stringent privacy requirements in two different threat models. Assignment of anonymous ID to the user to provide more security to the data on cloud server is done. To improve the search experience of the data search service, further extension of the two schemes to support more Search semantics is done.

Comparison of Leaf Recognition using Multi-layer Perceptron and Support Vector Machine

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

Juby George | Gladston Raj S

Abstract

Identification of leaves from digital images using various automatic pattern recognition algorithms results in performance degradations. Here, various leaf features are been extracted and exposed to Multi-layer Perceptron and Support Vector Machine. The leaf images are taken from the Columbia Dataset and that are preprocessed to get the region of interest (ROI). The shape, color and vein features are then extracted from the selected ROI. The prominent features are then found out by using Principal Component Analysis (PCA). The reduced feature sets are supplied to these algorithms for identification. Total 150 samples were taken from this dataset spreads over 10 different leaf species. Multilayer Perceptron and Support vector machine are trained with 104 leaf images and are been tested and validated using 23 leaf images each. A comparison is made between the performances of these two learning methods and found that the leaf recognition accuracy of the support vector machine is better than that of Multilayer Perceptron algorithm

Comparison of various clustering algorithm with proposed clustering algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th August 2018

RadhikaSethi |  Sikander Singh Cheema

Abstract

Division of data into similar groups of objects called clustering. Each group is called a cluster. A comparison between all the clustering algorithms i.e. K-means, Exception Maximization, Hierarchical, Density-Based, Farthest First, SOM are thought about on the bases of the size of the informational collection, the number of clusters and time taken to Shape groups.

Compendious and Optimized Succinct Data Structures for Big Data Store

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

Vinesh kumar | Dr Amit Asthana, Sunil Kumar, Dr. Sunil Kumar

Abstract

Data Representation in memory is one of the tasks in Big Data. Data structures include several types of tree data structures through the system can access accurate and efficient data in Big Data. Succinct data structures can play important role in data representation while data is processed in RAM memory for Big Data. Choosing a data structure for Data representation is a very difficult problem in Big Data. We proposed some solution of problems of data representation in Big Data. Data mining in Big Data can be utilized to take a decision by Data processing. We know the functions and rules for query processing. We have to either change method of data processing or we can change the way of data representation in memory. In this paper, different kind of tree data structures is presented for data representation in RAM of a computer system for Big Data by using succinct data structures. Data mining is often required in Big Data. Data must be processed in parallel or steaming manner. In this paper, we first compare all data structures by the table and then we proposed succinct data structures those are very popular now. Each tree presented for Data representation has different time and space complexities.

Compensation of Reactive Power With Fuzzy Based Control of PV Solar Farm as Pv-Statcom during Day and Night

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th December 2017

G. Poorna | T. Vinay Kumar

Abstract

In this paper, we are implementing a concept of the photovoltaic (PV) solar farm inverter as STATCOM, called PV- STATCOM using fuzzy controller is proposed in this paper, for improving stable power transfer limits of the interconnected transmission system. During daytime, the inverter capacity left after real power production is used. During night time it utilizes the entire solar farm inverter capacity. And during various operating conditions system has different real and reactive power flow which is required to be controlled to enhance the system power transfer capability, transient stability and reduce the losses in the system. For this purpose, the recent trend is the use of FACTS control devices. Here we are using the fuzzy controller when compared to other controllers for the better performance. Therefore, the fuzzy controller is the most suitable for the human decision-making mechanism, providing the operation of an electronic system with decisions of experts. The main aim of the LCL filter is to reduce high-order harmonics on the output side; however poor design may cause a distortion increase. Power transfer increases are also demonstrated in the same power system for 1) two solar farms operating as PV-STATCOMs and 2) a solar farm as PV- STATCOM and an inverter-based wind farm with similar STATCOM controls. By using the fuzzy controller for a nonlinear system allows for a reduction of uncertain effects in the system control and improves the efficiency. By using the simulation results we can analyze the proposed method.

Computer Graphics in Movie Making

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th May 2018

Abhilash V | Padmini S, Sirisha P, Dr Anuradha S G

Abstract

Entertainment has the higher appeal when compared to other areas .Computer Graphics is the reason behind this popularity .Earlier movies used to be low-key in terms of graphics, but after adapting to CGI, cinema has changed completely .The movies that we watch today are testimony to the revolution of graphics in movie industry .This paper reviews the application of graphics in entertainment industry.

Computer Network Routing using Swarm Intelligence

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd March 2018

Dr. Mirza Waseem Hussain | M Mubasher Hassan

Abstract

With the revolution in computing, particularly in telecommunication there has been a considerable amount of research how to include phenomenon in nature for network routing particularly Swarm Intelligence in telecommunication routing. Various algorithms have been proposed time to time by various researchers for performing efficient routing in wired and wireless adhoc networks. This paper provides overview of novel routing algorithms inspired by communicative and evaluative methods and procedures of Social Insects like Ants and Bees

Computer vision based fall detection for elderly person using HOG descriptor and HAAR feature extractor

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd May 2018

Devisahay Mishra | Namrata Mukta, Swarna Rana, Payal Karnawat

Abstract

In this paper, an image based fall detection system for elder person who alone at home is introduced. It is novel computer vision based fall detection system using deep learning method to analyse posture in smart home environment. First, background subtraction is employed to extract the foreground human body. Then global local features of human body postures are extracted by HOG (Histogram of Oriented Gradient) and HAAR extractor. After deep learning classifier applied for posture classification. After that certain rules are set to detect falls. Experimental result indicate that the proposed method can realizes human fall detection.

Conditional Identity-Based Broadcast Proxy Re-Encryption and It’s Application to Cloud Email

International Journal of Engineering Research in Computer Science and Engineering, Available online 23rd January 2018

A.Soumya | D.Kiran Kumar, N. Srinivas

Abstract

Recently, various PRE. Contingent (CPRE), character primarily based PRE and speak PRE (BPRE), had been contingent for adaptable programs. By becoming a member of ’CPRE’, ‘IPRE’ and’ BPRE’, this paper proposes an adaptable primitive alluded to restrictive character primarily based communicate PRE (CIBPRE) and construe its semantic safety. CIBPRE grants a sender to encode a message to various leasers through making sense of these beneficiaries' identities, and the sender can allow a re-encryption [4] key to a middle person with the reason that he can trade over the fundamental ciphertext into each unique each other game plan of contingent recipients. the different one to another arrangement of contingent beneficiaries. further, the re-encryption [5] key can be akin to a condition to such a quantity that lone the coordinating ciphertexts may be re-scrambled, which enables the first sender to implement get to govern over his far-off ciphertexts in a high-quality-grained manner. We advocate an effective CIBPRE conspire with provable protection. In the instantiated conspire, the underlying ciphertext, the re-scrambled ciphertext and re-encryption input are all consistent length, and parameters to produce a re-encryption key are freed from first creditors of any underlying ciphertext. At long last, we exhibit a use of our CIBPRE to cozy cloud electronic mail framework worthwhile over current comfortable electronic mail frameworks in mild of Pretty Good Privacy convention or character based totally encryption.

Congestion control mechanism using Traffic Aware Dynamic Routing (TADR) algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th March 2018

S.Pavithra | R.Bavani, J.Uma Sawmiya, Dr.K.Vimaladevi

Abstract

Traffic-Aware Dynamic Routing(TADR) algorithm is proposed to route the packets around congestion areas and scatter the excessive packets along multiple paths consisting of idle and underloaded nodes. Utilizing the concept of potential in classical physics, TADR algorithm is designed for constructing hybrid virtual potential field using depth and normalized queue length to force the packets to steer clear of obstacles

Conjunctive catchword scan with Designated analyser and timing enabled proxy re-encryption method for e-health clouds

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Koustuba A | Lakshmi N,Leelavathi S, Salma Arifa Farzana, Ravindra Prasad S

Abstract

An electronic health (e-health) record framework is a novel requisition that will achieve incredible comfort in health awareness. The protections and security of the delicate data aid the major worries of the users, which will thwart further improvement and broadly reception of the frameworks. The searchable Encryption (SE) plan will be a innovation organization with fuse security protection moreover ideal operability capacities together, which plays a fundamental part in the e-health record framework. In this paper, we present a novel cryptographic primitive named as conjunctive Catchword scan with designated analyzer and timing enabled proxy re-encryption capacity, which is a sort of a time-dependent SE plan. It could empower patients to represent fractional entry privileges to others to perform search operation over their records within a restricted time period. The period of the time for the delegatee to search and decrypt the delegator’s encrypted documents could be regulated. Moreover, the delegatee could be naturally denied of access power after a specified time. It can be backing the conjunctive keywords search and Oppose keyword guessing strike. We define a system model and a security model for proposed plan to indicate that it is an effective plan demonstrated secure in the standard model.

Conjunctive Keyword Search with Designated Tester and Timing Enabled Proxy Re-Encryption Function for E-Health Clouds

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th January 2018

G.Hema | Dr.K.Sreenivasa Rao, N.Srinivas

Abstract

An electronic health (e-health) record system is a novel application that will bring great convenience in healthcare. The privacy and security of the sensitive personal information are the major concerns of the users, which could hinder further development and widespread adoption of the systems. The searchable encryption (SE) scheme is a technology to incorporate security protection and favorable operability functions together, which can play an important role in the e-health record system. In this paper, we introduce a novel cryptographic primitive named as conjunctive keyword search with designated tester and timing enabled proxy re-encryption function (Re-dtPECK), which is a kind of a time-dependent SE scheme. It could enable patients [1] to delegate partial access rights to others to operate search functions over their records in a limited time period. The length of the time period for the delegatee to search and decrypt the delegator’s encrypted documents can be controlled. Moreover, the delegatee could be automatically deprived of the access and search authority after a specified period of effective time. It can also support the conjunctive keywords search and resist the keyword guessing attacks. By the solution, only the designated tester is able to test the existence of certain keywords. We formulate a system model and a security model for the proposed Re-dtPECK scheme to show that it is an efficient scheme proved secure in the standard model. The comparison and extensive simulations demonstrate that it has a low computation and storage overhead

Constant-size cipher text in Cloud computing”

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Mr. Kulkarni O.S | Miss. Jasud D.S,Miss. Gunde P.R,Mr.Chavan A.B,Mr. Patil R.M.

Abstract

Cloud computing refers to the practice of transitioning computer services such as computation or data storage to multiple redundant offsite locations available on the Internet, which allows application software to be operated using internetenabled devices. Clouds can be classified as public, private, and hybrid. Cloud computing and storage solutions provide users and enterprises with various capabilities to store and process their data in third-party data centers. It relies on sharing of resources to achieve coherence and economies of scale, similar to a utility (like the electricity grid) over a network. At the foundation of cloud computing is the broader concept of converged infrastructure and shared services. Since the cloud computing environment is distributed and un trusted, data owners have to encrypt outsourced data to enforce confidentiality. To achieve practicable access control of encrypted data in a un trusted environment is an urgent issue that needs to be solved. Attribute-Based Encryption (ABE) is a promising scheme suitable for access control in cloud storage systems. This system proposes a hierarchical attribute-based access control scheme with constant-size cipher text.

Content Based Image Retrieval: An Overview of Architecture, Challenges and Issues

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th December 2017

K. Bharathi | Dr. Miryala Chandra Mohan

Abstract

The objective of this paper is to present a brief overview of existing Content-Based Image Retrieval (CBIR) technique. The CBIR method is used to retrieve relevant images from the database based on the query image submitted by the user. The retrieval of images from a database relies purely on the image features such as color, shape and object identification using texture(s) in the query image. Apart from CBIR architecture and its existing methods, the paper presents the issues and challenges of CBIR system that needs to be addressed along with the future scope.

Content Management

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th May 2018

C H Rajatha | Karthik Kumar H M, Lokesh Chowdary K, Srivennala K, Swetha Ramana, Dr. Anuradha S G

Abstract

Storing and maintaining data is of higher importance these days. Manual handling of data becomes a tedious task, hence this paper proposes a system where in allocation of project and its related task can be done through a dedicated website. This website will let the end-user to allocate guides, create groups, issue circulars and also lets the staff to update marks on-line without any hassle.

Content-Based Image Retrieval Using Local Orientation Gradient XoR Patterns

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th February 2018

A. HariPrasad Reddy | N. SubhashChandra

Abstract

This paper presents a novel feature extraction method, local orientation gradient XoR patterns (LOGXoRP) for image indexing and retrieval. The LOGXoRP encodes the exclusive OR (XoR) operation between the centre pixel and its surrounding neighbours of quantized orientation and gradient values. Whereas local binary patterns (LBP) and local gradient patterns (LGP) encode the relationship between the grey values of the center pixel and its neighbours. We show that the LOGXoRP can extract effective texture (edge) features as compared to LBP and LGP. The performance of the proposed method is tested by conducting two experiments on Corel-5K and Corel-10K databases. The results after being investigated the proposed method shows a significant improvement in terms of their evaluation measures as compared to LBP, LGP and other existing state-of-art techniques on respective databases.

Content-Based Image Retrieval Using Local Orientation Gradient XoR Patterns

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th February 2018

A. HariPrasad Reddy | N. SubhashChandra

Abstract

This paper presents a novel feature extraction method, local orientation gradient XoR patterns (LOGXoRP) for image indexing and retrieval. The LOGXoRP encodes the exclusive OR (XoR) operation between the centre pixel and its surrounding neighbours of quantized orientation and gradient values. Whereas local binary patterns (LBP) and local gradient patterns (LGP) encode the relationship between the grey values of the center pixel and its neighbours. We show that the LOGXoRP can extract effective texture (edge) features as compared to LBP and LGP. The performance of the proposed method is tested by conducting two experiments on Corel-5K and Corel-10K databases. The results after being investigated the proposed method shows a significant improvement in terms of their evaluation measures as compared to LBP, LGP and other existing state-of-art techniques on respective databases.

Context Aware Personalised Travel Sequence Recommendation using Data Mining

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd August 2017

Ashitha S | R.Karthika

Abstract

A tailored travel sequence proposal from mutually supportive travelogues and community-contributed photos has been implemented through the project. Topical Package Space containing delegate tags, the Distributions of Cost etc. is excavated to overpass the lexis breach connecting user voyage predilection and trek courses. Famed directions are positioned higher by identifying its analogy amongst User Package and Route Package. Subsequently apex titled routes is optimized with auxiliary approaches with catalogues on alike users online.

Control of Wheel Chair and Home Automation Using Mobile Application

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th May 2018

Md Zakirulla | Ambika, Anusha A3, Bindu shree E, Chaitna K

Abstract

It is difficult for the people who are aged and having physical disabilities to move about and to operate house hold appliances without any external help. The proposed project based on Bluetooth technology is targeted for above mentioned people. It enables them to move independently from one place to another place without any external aid and at the same time it also helps them to operate house hold electric appliances using wireless communication. The wide spread prevailing loss of limbs is day-to-day scenario due to wars, accidents, age and health problems [2]. The proposed system is prototype wheel chair that can be commanded by patient itself. The main advantage is to design a wheelchair that will be operated using wireless blue technology and will be very easy to operate it with no physical efforts [1]. This paper analysis the motion technology through android mobile application with an inbuilt Bluetooth module. The Signals from the Bluetooth module are controlled by the microcontroller

Convolutional Neural Networks for 3d Brain MRI Classification

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th May 2018

Arpit Chaudhary | Prateek Prince Thakur, Devang Kulshreshtha, Vibhav Prakash Singh, Rajeev Srivastava

Abstract

In the recent years there have been a number of studies that applied deep learn-ing algorithms to neuroimaging data. Pipelines used in those studies mostly require multiple processing steps for feature extraction, although modern ad-vancements in deep learning for image classi cation can provide a powerful framework for automatic feature generation and more straightforward analy-sis. In this report, we show how similar performance can be achieved skipping these feature extraction steps with the 3D convolutional neural network archi-tectures. An accuracy of 84% has been achieved with a precision of 95%. The performance of the proposed approach outperforms various statistical machine learning based approaches such as SVM, Random Forest, Ada Boost etc.

Copy- Move Forgery Detection Using Passive Technique

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

U. Neha | K. Priyadharshini, M.Priyanka, K.Kiruthika

Abstract

An extensive growth in digital technology has resulted in tampering of image. Image plays an important role in todays digital world. Powerful image editing tools has made it difficult to determine whether the image is authentic or forged. The main objective of this paper is to detect the forgery in which a part of the image is copied and pasted on to same image without the information of the original image. First, the forged image is segmented. With the help of SIFT features, key points are extracted. The matching process of these key points detects the copy move region.

Cost Effective Voice Controlled Home Automation Using IoT

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Abdul Aziz Md | K Harshasri, K Shanmukharao

Abstract

The Internet of Things is emerging technology as the third wave in the development of the internet. Internet of Things (IoT) is expected to have massive impact on consumer products, business, wider culture, but these are still early days. It has potential for very wide applicability to almost all verticals and aspects of business, industries, manufacturing, consumer goods, supply chains, etc. IoT as a whole is very broad area. This paper focuses specifically to design a voice controlled home automation system which makes operating electrical appliances in home through android application and set up the controlling actions in the mobile. The Bluetooth technology devices are used for home automation in a cost effective manner.

Crawler Bot

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th July 2017

Pankaj kumar dubey | Kiran Kumar H, Dhanashekar K, Keerthi R, Shalini K.V

Abstract

Among the many justifications for using robotics, the most important is to shield people from working in dangerous environments and from handling hazardous materials. From dealing with chemicals that are explosive to handling radioactive substances. The main objective of this project is to minimize human causalities in tragedies. This robot is remotely controlled; self powered and has all the controls like normal car which are controlled by a microcontroller unit. A wireless camera has been installed on it, so that it can monitor surroundings remotely when required. An obstacle sensor is used protect the robot from collision.

Credit And Debit Card Transaction Survey Using Map Reduce In Hdfs And Implementing Syferlock To Prevent Fraudulent

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

R.Anbuvizhi | V.Balakumar

Abstract

Big Data is a term that has jumped overnight from its roots. It can be described as an innovative technique and technology to save, distribute, manage, visualize and analyze larger-sized data with extreme velocity and methods to manage unstructured and structure incapable amount of data. Nowadays fraud transactions in real time are increasing, so identifying large-scale patterns across many transactions or detecting anomalous behavior from an individual user can change the fraudulent in online transaction. Thus banks are turning to analytics to predict and prevent fraud in real times. In this project, proposed system deals with Credit and Debit card management to improve its scalability and efficiency in big data environment, it is implemented on (HDFS) Hadoop distributed file system. On the other hand, nowadays fraudulent and web attacker are increased to steel the password. In order to overcome those, proposed system implements SyferLock concept to add more security to Credit card transaction. The changes include a stronger user authentication tool, SyferLock that will require associates to follow a few new steps when logging into the network remotely. SyferLock patented, random number generation authentication solutions provide next generation One-Time Passwords/PINs (OTPs) for secure access to computers, networks and the Internet. SyferLock has engineered an enhanced authentication methodology and system using device-less OTPs that provides users with a simple, more secure way to access information leveraging their existing passwords. It uses a one-time password that expired once used. This added security strengthens the ability to protect the applications and systems.

Crop Field Analyzer

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Athawale Kiran M. | Shikhare Abhilash D., Dhotre Akash S. , Dhawale Sudarshan U

Abstract

A cloud-enabled mobile app plays an essential role in improving farming activities. This paper focuses on using cloud computing and the Wireless Sensors Network (WSNs) technology to enhance the application and its benefits to the field of agriculture. The paper focuses on the Cloud Database as well as Data Mining which gives details of past agriculture work records of farmers. The farmers who have inserted the system and installed the application on their Smartphones can register the application so that they can access as well as upload the data stored on the server and use the system efficiently. Temperature, Humidity and Soil moisture will be the various WSN's used. The main purpose of the sensors are to sense and measure the environmental parameters and data from the fields. The farmer will get the notifications of condition in his field by these sensors. When the water level in the field reduces, the farmer will get notification, so that he can power ON the motor through his Smartphone. The motor will get power OFF automatically when the sufficient water supply is provided in the farm up to the threshold or particular value. The main objective is to minimize the efforts and time of farmer and perform efficient and systematic farming to increase productivity.

Cross-Lingual Opinion Mining using Machine Learning Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th January 2018

Abhiseha J | Sahaana R T, Dharshini K, Menaha R

Abstract

Opinion mining is a type of natural language processing for tracking the mood of the public about a particular product. Opinion mining is also called sentiment analysis that involves building a system to collect and categorize opinions about a product. Opinion mining can be used in several ways such as marketers in success of an ad campaign, new product launch, determine which versions of a product is popular, etc., The main idea of the project is to segregate the reviews as positive, negative and neutral and to give a clear idea about the product to the immigrants of France. The products are criticized and depicted as reviews in C discount, a French website. These reviews are categorized as positive, negative and neutral. But the main disadvantage is these reviews are only in the French language. Thus reviews of other language are analyzed using machine learning techniques and translated into English for easy understanding of immigrants.

Crowd Analysis Using Computer Vision Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th May 2018

Shivashree G | Dr Anuradha S G

Abstract

Crowd analysis involves the interpretation of data gained studying the natural movement of groups or objects. Crowd analysis presents a survey using computer vision techniques covering different aspects such as people tracking, crowd density estimation, event detection, validation, and simulation. It also has wide range of applications such as crowd management, public space design, virtual environment, visual surveillance and intelligent environment. The major challenge in crowd analysis is the generation of ground thruthed images or video sequences, which can be used either for training or validation purposes.

Crowd Analysis using Computer Vision Techniques

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th August 2017

Shivashree G | Dr Anuradha S G

Abstract

Crowd analysis involves the interpretation of data gained studying the natural movement of groups or objects. Crowd analysis presents a survey using computer vision techniques covering different aspects such as people tracking, crowd density estimation, event detection, validation, and simulation. It also has wide range of applications such as crowd management, public space design, virtual environment, visual surveillance and intelligent environment. The major challenge in crowd analysis is the generation of ground thruthed images or video sequences, which can be used either for training or validation purposes

Cryptographic Predicate Encipherment For Multi Receiver In Online Community

International Journal of Engineering Research in Computer Science and Engineering, Available online 1st August 2018

Veda D | Brunda C, Monisha N S, Prakruthi B, Yeshashwini C A

Abstract

Among the users of the web and cloud computing, the online social network is an extremely mainstream service. Since a great deal of data is put away in Online Societal Community stage security endurance on such application is a critical issue. If client scrambles their messages, the online informal organization cannot generate exact advertisements to the user. Thus, to accomplish both protection and precise notice is a basic issue unfortunately online informal organization cannot accomplish both protection safeguarding and exact advertisement simultaneously to the users. In this prospect, the predicate encryption for online informal organization platform is proposed primary multi-receiver. The predicate encryption is utilized which provides shorter cipher text that indeed provides us more privacy/security and reduces the cost of encryption and decryption.

Cryptographically Securing the Data Transfer to Cloud from Mobile Devices Using Csprn Generation

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th December 2017

Sharanya G | Bhargavi KN, Sushma G, Rashmi, Arpitha Vasudev

Abstract

The way we store and share data has been revolutionized with the help of mobile device and its applications. It is now becoming warehouse to store personal information of the user. The data stored here are mostly in encrypted format, resulting in security threats. In this paper, we propose a protocol called CLOAK which is computationally efficient and light in weight for the mobile devices. CLOAK is based on stream cipher that generates and distributes cryptographically secure pseudo-random numbers (CSPRN) with the help of external devices. Here we use the concept of symmetric key cryptography to enhance the security of the protocol. There are three versions of protocol referred as d-CLOAK, s-CLOAK, r-CLOAK, and these protocols differ on the basis of key selection procedure. To secure data at its origin a core encryption/decryption of a CLOAK is performed within the mobile devices. Here deception method is used ensure the security of CSPRN.Using mutual identity verification all messages are exchanged securely between mobile and the server in a CLOAK. We use Android smartphones to evaluate CLOAK, and for generating CSPRN we use Amazon web services.

Current Status: Comparative Analysis Of Optimization Techniques Used In Steganography Schemes

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Samadrita Guha | Dipti Kapoor Sarmah

Abstract

Steganography has been used immensely in various fields to maintain the confidentiality and integrity of messages transferred via the internet. The need to hide messages has increased with the increase of fraudulent activities in the cyber space. To diminish the number of such cyber crimes a number of optimized and advanced steganographic schemes have been invented by researchers. This paper presents a comparative analysis among the various optimization techniques that have been applied to steganography to achieve better results in terms of quality, capacity and security of stego objects. All the results compared in this paper have been obtained from the application of optimization techniques on gray-scale images and 2- Least Significant Bit (2- LSB) substitution method .Optimization techniques compared in this paper include Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Genetic Algorithm (GA) and also hybrid optimization techniques like PSO-GA, PSO-ACO, GA-ACO. This paper also mentions which optimization technique is best suited for spatial domain image steganography, frequency domain image steganography, watermarking and security against steganalysis techniques based on the studies of research work done previously. The limitations of each optimization technique are provided in this work to help researchers decide which technique to apply in a specific steganography scheme to obtain best results.

Cyber Security: Computer Viruses

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th December 2017

Govind Kumar Thakur | Vikrant Singh, Bijoy Kumar Gupta, Richa Yadav, Prof. Sanjana Y

Abstract

Computer virus refers to a program which damages computer systems and destroys or erases data files. It has the Capability to copy itself and infect a computer without the permission or knowledge of the owner. The different types of computer viruses are Trojan Horse, Boot Sector Virus, DOS Virus, Worm, Time Bomb and Logical Bomb. Viruses can be spread through email and text message attachments, Internet file downloads, social media scam links, and even your mobile devices and smartphones can become infected with mobile viruses through shady App downloads. Viruses can hide disguised as attachments of socially shareable content such as funny images, greeting cards, or audio and video files. The most common symptoms of computer viruses are Your computer slows down without any reason. Your computer system has the less available memory than it should, Unknown programs or files are being created, Programs or files become missing, Corrupted files, your computer restarts in unusual ways. Some files or programs suddenly don’t work properly, Strange messages, displays, music or sounds, Changed Hard Drive name or Volume name, Hard Drives or Disk Drives are inaccessible.

Cyberbullying Detection in light of Semantic Enhanced Marginalized Denoising Auto-Encoder

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Cyberbullying Detection in light of Semantic Enhanced Marginalized Denoising Auto-Encoder | Rashmi S Shetty, Sushmitha S Siddanagoudar, Vidyashree.G, Asha.N.

Abstract

As a symptom of progressively prevalent online networking, cyberbullying has developed as a difficult issue afflicting kids, youths and youthful grown-ups. Machine learning methods make programmed identification of harassing messages in web-based social networking conceivable, and this could develop a sound and safe web-based social networking condition. In this significant research region, one basic issue is vigorous and discriminative numerical portrayal learning of instant messages. In this paper, we propose another portrayal learning technique to handle this issue. Our strategy named Semantic-Enhanced Marginalized Denoising Auto-Encoder (smSDA) is produced through semantic expansion of the prominent profound learning model stacked denoising autoencoder. The semantic expansion comprises of semantic dropout commotion and sparsity requirements, where the semantic dropout clamor is outlined in light of area learning and the word inserting system. Our proposed strategy can misuse the concealed element structure of tormenting data and take in a hearty and discriminative portrayal of content. Far reaching investigates two open cyberbullying corpora (Twitter and MySpace) are directed, and the outcomes demonstrate that our proposed approaches outflank other standard content portrayal learning strategies.

DAAM: Direct Address Accessing Method for Scalable Forwarding in NDN

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th December 2017

Anjali Kumari | Anurudh Kumar, Ms Devikala K, R.P. Seenivasan, Dr K.Suresh Joseph

Abstract

Named data Networking (NDN) is emerging internet architecture according to today scenario about devices which function in internet of everything environment. NDN-architecture forked from content-centric networking. NDN router works on in path caching although other existing network architecture also having in-path caching mechanism but NDN works with the proper data structure and specialized interest packet handling mechanism which makes unique NDN architecture among several existing network architectures. It stores incoming interest packet address which in form of array of string containing alphanumeric values separated by (‘/’) delimited. While in Flat TCP/IP architecture IP address is used, which is not justifying today internet requirement where data handling is more important than machine and exactly NDN has hit this weakness of TCP/IP module, NDN follow only data address instead of machine address, but string is used for naming which leads to exhaustive memory consumption and extra lookup time for particular interest in table so proposed methodology reduces space complexity and lookup cost (i.e. time complexity). By using the encoding technique which potentially restrict the memory usage. In encoding technique encode the element of a name prefixes with an automatically generated unique number. This paper, based on reduction the lookup up cost and the insertion cost for a request.

Data aggregation And Energy efficient by using COM-LEACH protocol in Wireless Sensor networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th October 2017

Rupali Dahake | Dr. G Prasanna Lakshmi

Abstract

The prediction of air passenger’s mode choice decision to and from airport forms a key analytical component of airport management system. And help to define strategies of Inbound and Outbound process together to minimize congestion at airport terminal. The goal of this proposed model is to perform mode choice analysis by using customized Multinomial Logit Model (MNL) for Indian transport facilities and factors associated with it. The resulting parameters used to perform decision making process for airport expansion and management schema. In addition, it helps to define smart solution for ease congestion at airport terminal

Data aggregation And Energy efficient by using COM-LEACH protocol in Wireless Sensor networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th October 2017

G.Rama Subba Reddy | Dr.S. Balaji

Abstract

The routing protocols that are specifically designed for the applications used by Wireless sensor networks, the limited available power of the sensor nodes has been taken into attention in order to increase lifetime of the networks. This paper presents a new version of leach protocol called COM-LEACH (Compound-Low Energy Adaptive Clustering Hierarchy) which aims to increase network lifetime. We first completely analyzed clustering Routing Protocol LEACH for data aggregation and its deficiencies and proposed COM-LEACH. Here we compose four Leach Architectures and their functionalities to develop new protocol called COM-LEACH. The goal of our work is to design COM-LEACH architecture and protocol that lead to efficient data aggregation and consume less energy.

Data Analysis and Machine Learning using PySpark

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th March 2018

Kavitha C | Athithya J, Dhinesh Kumar K, Mohamad Imran A

Abstract

Data analysis and machine learning have the potential to become an integral part of every existing industry. Using collective data from different sources on a specific topic or issue, an extensive scientific analysis could be done to create models and patterns that enable us to predict future outcomes with a comfortable measure of accuracy. This paper focuses on using the predefined methods available in the PySpark API to conduct data analysis and create an efficient model to predict future outcomes.

Data Compression in Dictionary Based secure Provenance for Wireless Sensor Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th January 2018

Vishwa Prasath T S | Rajasekar P

Abstract

Remote sensor systems are spatially dispersed sensor hubs that monitor the physical or ecological conditions like sound, push waves, the temperature of encompassing and so on, and furthermore send the detected information back to the sink or base station.WSN are utilized as a part of numerous applications like military regions, debacle administration in remote regions, in building keen urban communities and so forth. In this manner security is an essential angle in WSN. These systems can be inclined to different sad assaults or programmers that have the intention to upset the whole system. In a commonplace WSN organize, the minor hubs introduced in various areas since the encompassing condition, send the gathered information to their neighbours, which thusly is sent to a sink hub. The sink hub total the information got from various sensors and send it to the base station for additionally handling and vital activities. The data’s source, also packet and provenance binds with AM-FM sketch and uses secure packet sequence generation technique. Everything is fine here, but the data is not compressed, hence data compression part will be done using Lempel-Ziv method.

Data Gathering and Route Optimization Protocol for Mobile Sink in Wireless Sensor Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th June 2017

B.Bhuvaneshwari | Dr.G.Anna Poorani, V.M.Priyadharshini

Abstract

Wireless sensor networks are the grouping of tiny sensor node collects the information by sensing activeness from the surroundings. The way the sinks are not move freely in the deployed space. The pre-calculated trajectories may not applicable. To avoid this constant sink location updating, by using mobile sinks rather than static for data collection is the proposed system. This project is focusing on moving patterns of the mobile sink to achieve optimized network performance, and also collecting a small area of sensed data in the network.

Data Hiding In Encrypted Images by Reversible Image Transformation

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd January 2018

R.Sivaranjani | R.Kanimozhi, A.Suhasini

Abstract

An information concealing is that the technique by that some information is hidden into a cover media. It will be exhausted audio, video, image, text and film. The mistreatment of Watermark within the encrypted image will satisfy completely different wants on image quality and enormous embedding capability severally. The user encrypts the first compressed image mistreatment associate the encoding key. With associate encrypted image containing further information, and transfer the encrypted information to cloud storage. Outsourced information to the cloud, it is important to shield the privacy of knowledge change the cloud server to simply manage the information. The user will decipher then reveals the information hidden into cover media at an equivalent time with none loss.

Data Integrity Checking in Dynamic Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

R. Vinoth | R.Vimalraj, R. Sathishkumar, R. Sarathkumar

Abstract

Cloud storage is a model of data storage in which the digital data is stored in logical pools, the cloud providers are responsible for keeping data available, accessible with security. A public auditing protocol allows a TPA (Third Party Auditor) to check the integrity protection in cloud computing a formidable task. In fact, the end devices may have low computational capabilities. The trusted third party auditing process should take in no new vulnerabilities towards user data privacy. The proposed work for improving the data integrity and data security by implementing the double encryption algorithm to encrypt the data twice and stored in the cloud server. The trusted third party auditing for the data modification happened on the first level encrypted layer of the file. The first level encryption key would be secure on the user side. In this project work, double encryption approach with public auditing protocol, we can enhance the data privacy preserving in the public cloud without leakage of data.

Data Mining Method using Clustering Mechanisms and Feature assortment for efficient content categorization

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th January 2018

E. Ramesh | Dr. B Tarakeswara Rao

Abstract

Data mining manages the way toward finding data from data. With the wide accessibility of data, there are different applications and requirements for data mining. Data can be of any sort specifically message, pictures, recordings and some more. This work concentrates on the characterization of content data utilizing a semi-regulated grouping calculation. The principle issue in any data mining assignment is the treatment of gigantic data. Immense dimensionality does not demonstrate more data rather it might incorporate irregularities and commotions. To make the data predictable powerful pre-preparing strategies are finished. Notwithstanding this element choice system chooses valuable highlights and evacuates superfluous ones along these lines making the data significant for mining. A semi-managed bunching calculation TESC was utilized as a part of this investigation. It was then changed by actualizing a component determination strategy, record recurrence thresholding by which the tremendous dimensionality issue was tended to. The proposed framework along these lines beats the current strategy. Tests were led on Reuters- 21578 which portrayed better execution with lessened time many-sided quality.

Data Mining on Privacy Protected Data using Naïve Bayes Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Mr. Pankaj Jogi | Mr.Shubham Purankar, Ms. SamikshaPinge,Ms. Urvashi Ingale,Ms. Neha Mahalle,Prof.V.S. Mahalle

Abstract

Data mining has become an essential player in determining future business strategies. Data mining helps identifying patterns and trends from large amount of data, which can be used for reducing cost, increasing revenue and many more. With increased use of various data mining technologies and larger storage devices, amount of data collected and stored is significantly increased. This data contains personal information like credit card details, contact and residential information, etc. All these reasons have made it inevitable to concentrate on privacy of the data. In order to alleviate privacyconcerns, a number of techniques have recently been proposed to perform the data mining in privacy preserving way

Data Mining System Using Multiple Agents For Stock Market Prediction

International Journal of Engineering Research in Computer Science and Engineering, Available online 25th October 2017

Prajyoti P.Sawant Dessai | Megha Ainapurkar

Abstract

Intelligent Agent based distributed data mining system to generate stock market database rules and transfer it to the main controller. The combo of data mining technology with multi-Agent technology is expected to provide efficient roadmap for developing highly configurable software approaches that incorporate knowledge and provide decision making capabilities. This paper has offers the performance of every Agent in detail and the basic thoughts of the mining method adopted. The system achieves the goal of mining data accurately and effectively, and offer the personalized service, and improves the efficiency of the system.

Data Mining Techniques for Online Communities

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th March 2018

Saloni Fathima | A.Rajesh

Abstract

Data mining techniques can be applied to any type of old or new data, each of which can be best dealt with using specific technologies (not requiring all of them).In other words, data mining techniques are limited by data types, data set sizes, and task application environments. Each data set has its own suitable data mining solution. Data mining practitioners often face problems of the unavailability of all training data at the same time and the inability to process a large amount of data due to constraints such as lack of adequate system memory. Once older data mining techniques cannot be applied to new data types or if new data types cannot be converted to traditional data types, new data mining techniques will always need to be explored. The most popular and most basic form of data from the database, data warehouse, orderly data or sequence data, graphics data and text data. In other words, they are joint data, high-dimensional data, longitudinal data, streaming data, web data, numerical data, categorical data, or textual data.

Data Pre-Processing for Web Usage Mining

International Journal of Engineering Research in Computer Science and Engineering, Available online 24th March 2018

K.Kiruthika | T.Jeevitha, S.Kamali Prabha, V.S.BabyPriya

Abstract

Obtaining all the academic input about any individual at one click will be a great comfort. This is the case especially for any college/university or employment agency, getting na authenticated information about the student/candidate is very helpful in making a proper and well informed selection. This application has been developed to support such a requirement. The application will capture all the relevant information about the student on- line and by getting the student to feed the information directly. This also helps in tracking the student performance.

Data Privacy in Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th May 2018

Sree Aswini.J | Kavitha Juliet

Abstract

Cloud Computing provides the services to the users for storing the data moved into the cloud securely. Small and medium organisations are nowadays giving least importance to the IT infrastructure and instead moving their data and information to the cloud. To provide secure access to the data moved into the cloud by Data privacy in cloud. This approach uses the cryptographic ways to encrypt the data which is being stored into the cloud by the owners of the data. The data is secure because the access to the data is being given by the owner any of other users to decrypt the data. Without the owner permitting the access to the data, any other user cannot access the data. So, by using the Data privacy in cloud approach, data uploaded to the cloud is much more secure.

Data Security for Cloud Storage by Using Two-Factor Data

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th April 2018

Nimmaraju Rajesh | 

Abstract

We propose a two-factor data security protection mechanism with factor revocability for cloud storage system. Our system allows a sender to send an encrypted message to a receiver through a cloud storage server. The sender only needs to know the identity of the receiver but no other information (such as its public key or its certificate). The receiver needs to possess two things in order to decrypt the ciphertext. The first thing is his/her secret key stored in the computer. The second thing is a unique personal security device which connects to the computer. It is impossible to decrypt the ciphertext without either piece. More importantly, once the security device is stolen or lost, this device is revoked. It cannot be used to decrypt any ciphertext. This can be done by the cloud server which will immediately execute some algorithms to change the existing ciphertext to be un-decryptable by this device. This process is completely transparent to the sender. Furthermore, the cloud server cannot decrypt any ciphertext at any time. The security and efficiency analysis show that our system is not only secure but also practical

Decentralized Network for Retrieval of Secret Information in Wireless Area Network

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Rachel Evangeline Christian | J. Nagesh Babu

Abstract

In this paper, our proposed system conveys a safe and secure information system with CP-ABE on the decentralized Network in which any number of authorized authorities can man access their own secret keys personally. Our results conveys the way to practice the suggested implementation strongly and effectively to address the secret facts disseminated in the disturbance of wireless area network. Many applications require increased protection of confidential data including access control methods that are cryptographically enforced.

Decentralized Trust Management and Trust Worthiness of Cloud Environments

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Qhubaib Syed | Syed Afzal Ahmed,Syed Abdul Haq

Abstract

Now days, cloud computing an ever green technology used by all segment of areas. To choose best cloud service providers trust is an important factor in growing cloud computing. The highly dynamic nature of cloud system services throws different challenges on privacy, security and availability. The communication between consumers and trust management system involves sensitive information that makes the privacy is an important factor. Protecting cloud services from malicious users is a difficult problem. During this paper we tend to planned a brand new approach Cloud Armor, a reputation-based trust management framework that has a collection of functionalities to deliver trust as a service (TaaS), which incorporates i) a completely unique protocol to prove the believability of trust feedbacks and preserve users’ privacy, ii) An adaptive and strong believability model for measure the believability of trust feedbacks to shield cloud services from malicious users and to check the trait of cloud services, and iii) an accessibility model to manage the provision of the redistributed implementation of the trust management service. The practicability and edges of our approach are valid by an example and experimental studies employing assortment of real-world trust feedbacks on cloud services

Deciphering Business Integration Needs with Cloud Integration

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th January 2018

Garima Srivastava | Jenifer Sam

Abstract

With tons of cloud applications around us, integrating and consuming data from these applications has become the need of the hour. It’s not very difficult anymore to build applications that operate on social networking data or even to build a flashy sentiment analysis app that reads volumes of data from the cloud. To adopt innovations in the cloud, existing enterprise solutions need to be extended or integrated with new cloud applications in various kinds of cloud platforms, primarily public cloud and enterprise/private cloud. However, such an integration becomes quite challenging as it poses its own set of questions with respect to performance, scalability and security. There are certain key integration scenarios to be considered as we strive to build bridges between various on-premise and cloud applications. This paper discusses such possible Integration scenarios and the potential methodologies that can be adopted by organizations for a seamless integration in these scenarios. Experimental study based on various implemented system shows that the proposed approaches can help industries move towards shared computer processing to achieve coherence and economy of scale. These Integration techniques that cater to enterprise needs will increase productivity and help in minimizing cost invested in on-premise maintenance.

Deep Learning- Emerging Science

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

Bugatha Bala Gayatri | 

Abstract

Deep learning, a subfield of machine learning concerned with algorithms is inspired or mimicked both by the structure, function and mechanism of brain and its neural structure called Artificial Neural Networks (ANN). It uses multiple layers of artificial neurons for classification and pattern recognition in its perception, analysis and understanding. Deep learning is a science that is aimed to produce algorithms mimicking and performing activities performed with human intelligence and perception associated with neural mechanisms without human intervention. In deep learning, we develop multiple layers of computations and analysis through algorithms that are embedded into chips as software, which results in better perception and results that are 90%- 100% accurate. This leads to a technology that is more informative, perceptive and efficient in a way, changing the world for better.

Deep Neural Networks for Big Image Data Classification

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

R. Swathi | Dr.R. Seshadri

Abstract

With big data development in biomedical and medical industries, accurate examination of medical data benefits early disease discovery, patient care and group administrations. In any case, the examination accuracy is lessened when the nature of therapeutic information is deficient. Medical imaging plays a vital role in diagnostic healthcare and deals with a high volume of data collection and processing. In this paper, we streamline machine learning algorithms for classification and prediction of chronic disease outbreak in disease-frequent groups. Deep Learning has emerged as another era in machine learning and is applied to various image processing applications. The fundamental motivation behind the work exhibited in this paper is to apply the idea of Deep Learning algorithms to be specific, Convolutional neural networks (CNN) in image classification. This paper presents the classification of images using deep learning algorithms through spark. Classified different types of skin cancers using Convolutional neural networks in distributed environment achieved in less time with more accuracy

Deep Web and Dark Web

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Chandra Shekar N | Sugali Vijay, M Balachandra Reddy

Abstract

the Deep Web refers to any Internet content that, for various reasons, can’t be or isn’t indexed by search engines like Google. Which includes dynamic web pages, blocked sites (like those that ask you to answer a CAPTCHA to access), unlinked sites, private sites (like those that require login credentials), non HTML/-contextual/-scripted content, and limited-access networks

Delay Analysis Wireless Sensor Networks Considering Energy Costs of Sensing and Transmission in Energy Harvesting Nature

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st March 2018

J Rajiv | Sandeep Santosh

Abstract

Wireless sensor nodes lifetime can be enhanced by a means of Energy harvesting (EH). However, the randomness characteristic in the EH process for performing sensing operations and transmitting sensed information to the sink may cause significant delay. We consider the energy costs of both sensing and transmission unlike most existing studies on the delay performance of EH sensor networks, where only the energy consumption of transmission is considered. Specifically, we consider EH sensor that monitors some status property and adopts a harvest-then- use protocol to perform sensing and transmission. To study the delay performance, we consider two complementary metrics and derive their statistics analytically:1) update age— how timely the updated information at the sink by measuring the time taken from when information is obtained by the sensor to when the sensed information is successfully transmitted to the sink and 2) update cycle—how frequently the information at the sink is updated by measuring the time duration between two consecutive successful transmissions. Our results show that the consideration of sensing energy cost leads to an important trade-off between the two metrics: more frequent updates result in less timely information available at the sink.

Design Analysis of Spoke Type BLDC Motor for Spinning Mill Application

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Shamphavi.S | Manimala.R , Prashanthi.R , Kurinjimalar.L

Abstract

To design a motor that would overcome the drawbacks of the conventional spinning motor and to evaluate the characteristics of the chosen motor with the help of software packages from Infolytica. The motor which is currently used is three phase Totally Enclosed Fan Cooled Squirrel Cage Induction Motor (TEFCSCIM).The motor employed in the spinning machine undergoes partial loads during most of its operating hours.It is noted that the motor efficiency and power factor are poor in the case of partial load. Heat, Sound and Slip of the motor are few factors to be considered for the change in design. The objective of this project is to design a Permanent Magnet Brushless Direct Current (PMBLDC) Motor which would eliminate the above complications. Initially the design has to be analytically arrived and the same has to be scrutinized through the software packages from Infolytica.Critical key parameters such as speed, average and cogging torque has to be accounted in the analysis. Generally, the cogging torque increases with increase in average torque and hence there is a need to modify the rotor parameters such that the former remains low for significant increase in the latter. The software analysis and comparison will be followed by the final design of the spinning motor. We concentrate mainly on the effects of temperature. Temperature is of main concern because more cool the motor is, more efficient it is.

Design and Develop a Monitoring System on Embedded Platform for Finding the Driver Drowsiness Using ARM Microcontroller

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th February 2018

S. Rama Kishore | M. Amru

Abstract

The principle thought behind this work is to build up a nonintrusive system which can recognize the weakness of the driver and issue an advantageous forewarning [3]. Since endless accidents happen in light of the driver tiredness [1]. Thus this system will be useful in averting numerous mischances, and subsequently spare cash and decrease individual enduring [2]. In this paper, the location of eye state and head posture of the driver is to screen and the driver mindfulness in autos. This venture is to screen the driver's eye and head developments by utilizing webcam. This implanted venture is to outline and build up a minimal effort highlight which depends on installed stage for finding the driver sleepiness [5]. In particular, our system incorporates a webcam set on the directing section which is proficient to catch the eye developments and head developments of the Driver [4]. In the event that the driver is not focusing out and about ahead and a perilous circumstance is identified, the system will caution the driver by giving the notice sounds as the voice [6]. Our Embedded System utilizes ARM miniaturized scale controller has an element of picture preparing procedure and in addition Analog to Digital Conversion. Picture handling is any type of flag preparing for which the information is a picture, for example, a photo or video outline; the yield of picture preparing might be either a picture or an arrangement of qualities or parameters identified with the picture

Design and Development of RF energy sensing Circuit Using ADS software

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th June 2017

V. Sai Kiran | P. Vinay Kumar,Yogesh Kumar Choukiker

Abstract

This article mainly focuses on study of RF energy Sensor circuit. We are surrounded with enormous Radio frequency signals, mostly varying in the range of 1 GHz to 3.5 GHz. An RF energy sensing Circuit has been designed, In Advanced Digital Simulation software, to detect the level of signal at a particular frequency and converting RF energy into voltage levels. In order to restrict our circuit to a particular frequency, we have designed a Helical Antenna as a receiver which can send RF power to designed circuit. This antenna is designed with particular dimensions such that it has minimum reflection coefficient at desired frequency, allowing only a particular frequency to reach RF sensing circuit.

Design and Development of Wireless Sensor Node for Anti-Poaching Of Valuable Trees

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th May 2018

Mallikarjun N | Shilpa N, Renuka D, Sindhu T, Sridevi malipatil

Abstract

Sensor for the forest department using For many days we are reading in the newspapers about smuggling of trees like sandalwood, ’sag wan’ etc.In many states of India, like the jungles of Karnataka and Tamilnadu notorious smuggler “virrappan” did the smuggling of such trees in the past years.Inorder to overcome this smuggling of trees we use wireless sensor network (WSN) technology which is a modernistic addition in the field of radio network. In this case we use MEMS technology to monitor these kinds of peculiar trees and also use of vibration renewable energy source of solar energy. Here we can also save the forests and wild animals from forest fire.

Design and Developmentof Token Generate Toll for Future Phone Technologies

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th August 2017

Shreekant | Salotagi,Shridevi Kembhavi,Zarinabegam K Mundargi

Abstract

“Design and Development of Token Generate Toll for future Phone Technologies” project summarizes the various key areas and technologies This Project gives a brief history about to Generate the Token resource files in different languages with respect to default language as US English from TMS sheet. The generic requirements for “Tool” that will be used in LG Android Platform for generation of Token resource files in XML format. It takes TMS sheet and UK English as a reference tokens and generates token resource files in XML format in more than 40 languages. This Project is implemented by using C++ Language on Qt Platform (Tool).. It also gives a good representation of the organizational and the interconnectivity (communication) of the various Languages between Country to country, Engineering and Services Departments. This project mainly deals with creating XML files for generating resources in different languages. Main window of this project contains GUI components like Progress bar, Token Table, Settings and Help Menu. GUI Window display supports horizontal and vertical scroll bars to view the contents. Token Table is the list of Input and output tokens displayed in the GUI display window. Settings menu shows the Tool version name and the Release Date. Help Menu shows the information about the tool components usage. Parses the XML files and extracts the tokens from the resource files. The extracted tokens will be stored in a buffer

Design and Implementation of IoT Enabled Wireless Sensor Network Applications

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th May 2018

Aditya. M | Meghana Reddy. P, Nayana. B, Aishwarya H.M, Dr. Veeragangadhara Swamy T.M

Abstract

This paper is an advanced solution for monitoring various climatic parameters at a particular place and makes the information visible anywhere in the world. The technology behind this is Internet of Things. The IoT allows objects to be sensed or controlled remotely across existing network infrastructure, creating opportunities for more direct integration of the physical world into computer-based systems, and resulting in accuracy, economic benefit and improved efficiency in addition to reduced human intervention. The main goal is to monitor and report the temperature, humidity, light intensity and moisture content in any location i.e. agricultural fields, high temperature zones in industries, cold storages and other locations.

Design and Implementation of 6lowpan Using Coap in Internet of Things

International Journal of Engineering Research in Computer Science and Engineering, Available online 21st December 2017

M.V.R Jyothisree | Dr.S.Sreekanth, Dr. D.Shravani

Abstract

IPv6-enabled low-power wireless personal area networks of smart objects (6LoWPANs) play an important part in the Internet of Things (IoT), especially on account of the Internet integration (IPv6), energy consumption (low-power), and ubiquitous availability (wireless). This paper presents our experience of designing and implementing 6LoWPANs for developing IoT applications. The performance evaluation provides a comprehensive analysis of several communication aspects between 6LoWPANs and regular IPv6 networks such as energy consumption, network performance, and service communication.

Design and Implementation of a Smart Parking System using IoT Technology

International Journal of Engineering Research in Computer Science and Engineering, Available online 18th July 2018

Narayana Swamy J C | Sahana Satyanarayana, Lokesh Babu S, Trishank Sharma

Abstract

With the rapid increase in the number of vehicles in urban areas, drivers waste a lot of time and fuel to find an appropriate parking spot in a commercial parking lot. Moreover, approximately 30% of urban congestion is created by drivers cruising for packing space. This paper aims at providing a low-cost solution to this problem by creating a Smart Parking Space using the technology of IoT and an inexpensive processor - NodeMCU. This amalgamation of embedded systems, connectivity and application will provide the user with the information of available parking spaces in a parking lot and also allows the user to reserve a parking space in the lot within the timestamp over the MQTT protocol. A Smart Parking Technology, as such, will help optimize space usage, improve the efficiency of the parking operations and help the smoother flow of vehicles. Further, this paper proposes a completely automated and smart parking space without much human intervention by including fire alarms, temperature and humidity sensors, water sensors for avoiding waterlogging and light sensors for automatic control of lights. On the whole, this paper focuses on designing smart parking system, beneficial to both the users and provider in terms of time, fuel and infrastructure.

Design and Implementation of External Sorting as a Novel Tool for efficient processing of gas holders Details

International Journal of Engineering Research in Computer Science and Engineering, Available online 1st November 2017

S. Hrushikesava Raju | Dr.M.Nagabhushana Rao

Abstract

The importance of external sorting and its proposed methodology is discussed. The proposed methodology is refined in such a way that incurs few input, output costs, number of disk accesses, number of runs and other parameters compared to other existing methodologies. The proposed methodology is transformed as a tool with specific features in order to process huge gas details located to a particular area. The information stored on external devices requires external sorting technique which arranges the information in a particular manner according to the user option requirement. To do this, the features are assumed as facilities that may be used to process the information according to area selected. The results obtained using this novel tool is specified against existing literature methodologies. The comparison also be done among these approaches against this tool. This novel tool is applicable to the application in which gas holder’s details are stored and this tool’s features such as Esorting, results, and filtering to be applied over that data which output the reports to the user to use them efficiently

Design and Implementation of Logic Gates Using Quantum Computing Technique

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th February 2018

G Divya | K Ravi Kiran

Abstract

Reversible computing is a model of processing where the computational process to some extent is reversible. A necessary condition for reversibility is that there should be one to one mapping between input and output. It is generally considered an unconventional form of computing. There are two major types of reversibility that are of particular interest for this purpose: physical reversibility and logical reversibility. A process is said to be physically reversible if it results in no increase in physical entropy. These circuits are also referred to as charge recovery logic or adiabatic computing

Design and Implementation of Real time Wireless Sensor Networks based multi patient health care monitoring system

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd September 2017

G.Veera Pandu | Dr.Ch. Santhi Rani

Abstract

- In a hospital health care monitoring system it is necessary to constantly monitor the patient’s physiological parameters. For example a pregnant woman parameters such as blood pressure (BP) and heart rate of the woman and heart rate and movements of fetal to control their health condition. This paper presents a monitoring system that has the capability to monitor physiological parameters from multiple patient bodies. In the proposed system, a coordinator node has attached on patient body to collect all the signals from the wireless sensors and sends them to the base station. The attached sensors on patient’s body form a wireless body sensor network (WBSN) and they are able to sense the heart rate, blood pressure and so on. This system can detect the abnormal conditions, issue an alarm to the patient and send a SMS/E-mail to the physician. Also, the proposed system consists of several wireless relay nodes which are responsible for relaying the data sent by the coordinator node and forward them to the base station. The main advantage of this system in comparison to previous systems is to reduce the energy consumption to prolong the network lifetime, speed up and extend the communication coverage to increase the freedom for enhance patient quality of life. We have developed this system in multi-patient architecture for hospital healthcare and compared it with the other existing networks based on multi-hop relay node in terms of coverage, energy consumption and speed

Design and Implementation of Student Feedback System at Education System

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th May 2018

Nikhil H.M | Varada Sunitkumar, Shruti S Basapur, R. Vinil Shah

Abstract

The main aim and objective was to plan and program web application for any domain. We have to apply the best software engineering practice for web application. As a web application developer, I was asked to develop an “Student Feedback System” using PHP and MySQl. This system is generally used by four kinds of users Student, Faculty, Head of departments, Admin. The application should evaluate the answers given by the students based on the feedback which will be given by the range. 1 – 10 and grade has to be generated to all the staff members of a particular department. These feedback report was checked by the HOD’s. He can view overall grades and view the grades obtained to the lecturers and give this report to the principal and he can give counselling to the college staff. “By using this online system, we make it better and quick way.”

Design of an Energy Aware Multicast Routing Protocol with Optimal QoS Support over IoT Networks – EAMRO

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th March 2018

J. Jayabharathi | Dr. R. Saminathan, Dr. S. Saravanan

Abstract

Researches in field of QoS and energy supportive approaches in IoT networks nodes primarily focus on node inter connectivity and packet transmission, packet collision during transmission and optimize network lifetime. Majority of QoS and energy supportive algorithms in IoT networks focus on providing route management and effective data transmissions, supportive energy dissipation on the transmission route. EAMRO, the proposed algorithm lead to maximal node utilization, as well as decrease on node energy used during transmission on selected route. Consistent demand on QoS and controlled energy consumption is always felt by researching community. This paper proposes an energy controlled QoS support routing scheme EAMRO for IoT node location systems where demand for services are high. EAMRO suggests an optimal energy identification approach for selection of a data transmission route, along with route identification based on ratio of energy identified and its corresponding distance to destination node as location aware to solve the problem. Providing optimal QoS is controlled by assigning a least transmission power to the nodes where each node is aware of location information and hence able to adjust their transmission power accordingly. EAMRO is simulated using cup carbon simulator whose performance shows minimal energy consumption of sensor nodes compared to RPL.

Design of Credit Approval System using Artificial Neural Network: A Case Study

International Journal of Engineering Research in Computer Science and Engineering, Available online 7th September 2017

Anupam Shukla | Apoorva Mishra, Sanjeev Sharma

Abstract

An enormous amount of images or videos are collected from laptops, mobiles, storage devices during the investigation by Police or intelligence agencies or digital forensic team. These collected images/videos to be analyzed to ascertain the source device that was used to capture these during the investigation. An every camera has its fingerprint in the form of Photo Response Non- Uniformity (PRNU) noise. Because it has universality and generality nature, it is unique and hence plays a very vital role in the source camera identification. PRNU is a sensor pattern noise which contains noise components, and other information hence many techniques have been proposed for the extraction of the PRNU. In this paper, a Discrete Cosine Transform (DCT) method is used for extracting the noise, and Weighted Averaging technique for PRNU estimation. Finally, the distance function is used for comparing g the difference between the Query image PRNU and the stored image PRNU. We conducted the experiments its results are verified against the different cameras, and it is giving 93% accuracy

Design of FPGA Logic Architectures using Hybrid/LUT Multiplexer

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd November 2017

Pallavi Mamidala | V.Sowmya

Abstract

Hybrid configurable logic block architectures for field-programmable gate arrays that contain a mixture of lookup tables and hardened multiplexers are evaluated toward the goal of higher logic density and area reduction. Multiple hybrid configurable logic block architectures, both nonfracturable and fracturable with varying MUX:LUT logic element ratios are evaluated across two benchmark suites (VTR and CHStone) using a custom tool flow consisting of LegUp-HLS, Odin-II front-end synthesis, ABC logic synthesis and technology mapping, and VPR for packing, placement, routing, and architecture exploration. VPR is used to model the new hybrid configurable logic block and verify post place and route implementation. In this paper experimentally, we show that for nonfracturable architectures, without any mapped optimizations, we naturally save up to∼8% area post place and route. For fracturable architectures, experiments show that only marginal gains are seen after place-and-route up to∼2%. For both nonfracturable and fracturable architectures, we see minimal impact on timing performance for the architectures with best areaefficiency.

Design of High-Speed Multiplier Architecture Based on Vedic Mathematics

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Chaitanya CVS | Sundaresan C, P R Venkateswaran, Keerthana Prasad, V Siva Ramakrishna

Abstract

High speed and efficient multipliers are essential components in today’s computational circuits like digital signal processing, algorithms for cryptography and high performance processors. Invariably, almost all processing units will contain hardware multipliers based on some algorithm that fits the application requirement. Tremendous advances in VLSI technology over the past several years resulted in an increased need for high speed multipliers and compelled the designers to go for trade-offs among speed, power consumption and area. Amongst various methods of multiplication, Vedic multipliers are gaining ground due to their expected improvement in performance. A novel multiplier design for high speed VLSI applications using Urdhva-Tiryagbhyamsutra of Vedic Multiplication has been presented in this paper. The multiplier architecture is implemented using Verilog coding and synthesise during Cadence RTL Compiler. Physical design is implemented using Cadence Encounter RTL-to-GDSII System using standard 180nm technology. The proposed multiplier architecture is compared with the conventional multiplier and the results show significant improvement in speed and power dissipation

Design of Power and Area Efficient Approximate Multipliers

International Journal of Engineering Research in Computer Science and Engineering, Available online 21st November 2017

Dhanavath Kiran Kumar Naik | 

Abstract

Approximate computing can decrease the design complexity with an increase in performance and power efficiency for error resilient applications. This brief deals with a new design approach for approximation of multipliers. The partial products of the multiplier are altered to introduce varying probability terms. Logic complexity of approximation is varied for the accumulation of altered partial products based on their probability. The proposed approximation is utilized in two variants of 16-bit multipliers. Synthesis results reveal that two proposed multipliers achieve power savings of 72% and 38%, respectively, compared to an exact multiplier. They have better accuracy when contrasted with existing estimated multipliers. Mean relative blunder figures are as low as 7.6% and 0.02% for the proposed inexact multipliers, which are superior to the past works. Execution of the proposed multipliers is assessed with a picture handling application, where one of the proposed models accomplishes the most astounding pinnacle flag to commotion proportion.

Design of PV Systems with Fuzzy Control of both Active and Reactive Power during Unbalanced Grid Voltage

International Journal of Engineering Research in Computer Science and Engineering, Available online 18th November 2017

K.Srinivas | D. Chandrashekar, B.Saritha

Abstract

The proposed reactive power control is intended to regulate the maximum and minimum phase voltages at the point of common coupling within the limits established in grid codes for continuous operation. This paper presents a control strategy for a grid connected photovoltaic (PV) system aiming to regulate the active and reactive power injected to the electric system during asymmetrical voltage faults. Fuzzy controller is advance controller which is mostly suitable for the human decision making mechanism which also provided the operation of an electronic system with the expert decision. The active power reference is obtained from a Maximum Power Point Tracking (MPPT) algorithm. The proposed control strategy generates the required reference currents to be imposed by the grid-tied inverter from the desired active and reactive power and the measured supply voltage. In unbalanced voltage sags, positive and negative sequence reactive powers are combined to flexibly raise and equalize the phase voltages; maximum phase voltage is regulated below the upper limit and the minimum phase voltage just above the lower limit. The scheme is validated for a single stage PV system where the inverter currents are regulated via predictive control. By utilizing the fuzzy controller for a nonlinear system which allow the reduction for the uncertain effect in the system which control and perfectly improve the efficiency. Results showing the performance of the strategy are presented during unbalanced voltage sags and swells.

Design of Sanitation System in a Village

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th July 2017

Jyothi Sulochana | K Hemavathi ,P Kalamani ,Lorate Shiny

Abstract

This project is an attempt to develop the mobile networks to have a wireless voice call happening without the help of the towers. Our main aim is to remove the towers in the communication process. The towers have been hazardous to many birds and animals. This project uses the Raspberry Pi boards with the inbuilt wi-fi on board. The Raspberry Pi with the wi-fi is used for the prototype, which would be used to develop a voice call application which would transfer the voice through the wifi communication. It is proposed to develop this technology to be able to access only till the distance of 30 meters which is the distance limit of the wi-fi communication. It would be possible to move this communication to be expanded by the use of the Wimax technology which would be able to communicate in the range of kilometers. This project uses two Raspberry Pi kits with Wi-fi inbuilt on it and would be able to communicate by developing the voice call application and would be able to use the audio jack on the kit. A hardware implementation would be developed and the results would be analyzed for performance.

Design of Suspicious User Profile Identification system Using ACO Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th February 2018

Asha | Dr. Balkishan

Abstract

The aim of this paper is to design a system for the identification of suspicious user profiles using Ant Colony Optimization algorithm. The communication technologies and their advancements have greatly influenced our daily lives. The technologies like social networking websites, blogs, chat forums, instant messengers and many more are leading various fascinating trends in today’s world. Unfortunately, the increase in suspicious activities is one of the major causes due to the misuse of the technology. The internet is loaded with very large amount of data. Some people make use of the technology to spread rumours, to spread violence, bully other people, spread hate messages or even perform criminal activities like financial frauds etc. and thus increasing the amount of suspicious content over the internet. In this paper, textual data from social networking websites is considered to detect the suspicious user profiles. A suspicious user profile (SUP) detection system is proposed which considers the text based data as input and retrieves the suspicious user profile based on the extracted features.

Design of Wireless Sensor Network for Hydroponic System

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th April 2018

Patel Nirav | Dr. Y. B. Shukla, Nilofar A. Shekh

Abstract

Cultivation, adding up to an important aspect in GDP (Gross Domestic Produce), has been affected tremendously over the past few decades due to the use of chemicals. Due to rapid urbanization and industrialization, arable land under cultivation is decreasing enormously. Hydroponics is a method of growing plants purely using water and nutrients, without soil.The system facilitates the growth of multiple crops under AVR controller. Necessary supplements for the crops are provided based on the inputs obtained from the pH sensor and Temperature sensor and also Humidity sensor are used and also solenoid valve and relay are used in system

Designing a Secure Exam Management System (SEMS) for M-Learning Environment

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

ShivaKumara | Dr.Sai Madhavi D, H.V.Yerrinand, Sunil Kumar, R.Gopal Y.V

Abstract

The Secure exam management system is a Mobile Learning process. However, enforcing exam security in open environments where each student has his/her own mobile/tablet device connected to a Wi-Fi network through which it is further connected to the Internet can be one of the most challenging tasks. By using Internet or WiFi Connections students can easily exchange information during exam time. In m-learning environments where the Students mobile/tablet devices that can be connected to an Internet browsing or e-book reading, as well as for the sake of exams. Using student’s mobile devices as exam stations offers the advantage of low cost, more exam takers at the time, and no need for a wired network. Thus, a dynamic security policy is needed in this case with an appropriate enforcing mechanism.

Designing a User Interface in HCI for predicting the performance task using Keystroke Level Model and Cognitive Complexity Theory

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

D. Kalpanadevi | Dr. M. Mayilvaganan

Abstract

In this research focuses on Human computer Interface system gives the better performance of the student usability based on Keystroke Level model and cognitive complexity theory. A task performance can be measured by the goal factor of evaluating the user interaction when the response to the question. To conduct laboratory test by user interface design to determines the exact task in the test plan, based on the cognitive model with usability metrics. Usability testing can be processed by the suggestion of evaluating usability metrics under in terms of effectiveness, efficiency and satisfaction.

Detecting Better Keyword Query Suggestion Based on Location Using Weighted Keyword Document The graph on Partition Based Algorithm.

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th December 2017

Chethan R | Divya D, Kavya H, Prashanth,Vani Saptasagar

Abstract

CLOUD computing is a subversive technology that is changing the way IT hardware and software are designed and purchased. Cloud computing provides abundant benefits including easy access, decreased costs, quick deployment and flexible resource management, etc. It has become highly popular for data owners to outsource their data to public cloud servers while allowing data users to retrieve this data. For privacy concerns, a secure search over encrypted cloud data has motivated several research works under the single owner model. However, most cloud servers in practice do not just serve one owner; instead, they support multiple owners to share the benefits brought by cloud computing. In this paper, we propose Dynamic Secret key generation for multi user in cloud computing. To enable cloud servers to perform secure search without knowing the actual data of both keywords and trapdoors, we systematically construct a novel secure search protocol. To rank the search results and preserve the privacy of relevance scores between keywords and files, we propose a novel additive order and privacy preserving function family. To prevent the attackers from eavesdropping secret keys and pretending to be legal data users submitting searches, we propose a novel dynamic secret key generation protocol and a new data user authentication protocol

Detecting Better Keyword Query Suggestion Based on Location Using Weighted Keyword Document The graph on Partition Based Algorithm.

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th December 2017

Clara Kanmani A | Suma V, N Guruprasad

Abstract

Cloud Computing is internet based computing that provides shared computer processing resources and data to computers and other devices on demand. Semantic web is an extension of the current web in which information is given welldefined meaning, enabling computers and people to work in cooperation. This paper gives a brief picture of how Cloud computing and future web, semantic web technology evolved. However from the extensive literature survey, it is also observed that, these two technologies plays an interplay role with each other in solving complex problems. Furthermore an analysis of where semantic web technology meets cloud computing is carried out and briefly describes how Semantic web technology can be used to address the challenges of cloud computing.

Detecting Better Keyword Query Suggestion Based on Location Using Weighted Keyword Document The graph on Partition Based Algorithm.

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th December 2017

Adivikottu Ramakrishna | Dr.G.P.Saradhi Varma

Abstract

A customer who has issued a Query word question to a web searcher. The Keyword proposals are the most important element of the web search tool. Truthful clients don't know how to express their examination accurately more often than not questions are short and unambiguous. Using that watchwords web file recovers the reports, the proposed Query hold phrase inquiries to the customer, which are semantically noteworthy to the main question and they have results records that contrast with objects near the customer's region. Thus, here propose a weighted Keyword-Query record graph which gets semantic likewise, expel among inquiries and reports. By then, use the outline to propose questions that are shut as far as graph detachment to the primary inquiries. Fragment-based estimation is used to make the structure more flexible, using the proposed take hold of phrases the system again performs watchword controlling. In catchphrase guiding, the system removes all the keep words from the sentence. By then form a candidate question graph, to find the base partition between the segments. Least Crossing tree is used to find the partition between the segments

Detecting Botnets with Tight Command and Control

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd May 2018

T N Prakash | K .Nagendar Rao, Y.Harikrishna, P.Pujith Kumar

Abstract

Systems try to discover botnets by examining traffic content for IRC commands or by fitting honeynets. Our approach for detective work botnets is to look at flow characteristics reminiscent of information measure, duration, and packet temporal arrangement trying to find proof of botnet command and management activity. we've got made associate degree design that initial eliminates traffic that's unlikely to be a region of a botnet, classifies the remaining traffic into a bunch that's possible to be a part of a botnet, then correlates the possible traffic to search out common communications patterns that might counsel the activity of a botnet. Our results show that botnet proof is extracted from a traffic trace containing virtually nine million

Detecting Mobile Malicious Webpages in Real Time

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

G. Ashok Kumar  | A. Venu Gopal, I. Abhilash balu, M. M. V. Vamsi

Abstract

Mobile specific webpages disagree considerably from their desktop counterparts in content, layout and practicality. consequently, existing techniques to noticemalicious websites area unit unlikely to figure for such webpages. during this paper, we have a tendency to style and implement knock cold, a mechanism that distinguishes between malicious and benign mobile webpages. knock cold makes this determination supported static options of a webpage starting from the amount of iframes to the presence of identified dishonorable phone numbers. First, we have a tendency to by experimentation demonstrate the requirement for mobile specific techniques so establish a spread of recent static options that extremely correlate with mobile malicious webpages.We then apply knock cold to a dataset of over 350,000 identified benign and malicious mobile webpages and demonstrate ninetieth accuracy in classification. Moreover, we have a tendency to discover, characterize and report variety of webpages lost by Google Safe Browsing and VirusTotal, however detected by knock cold. Finally, we have a tendency to build a browser extension exploitationknock cold to guard users from malicious mobile websites in time period. In doing thus, we offer the primary static analysis technique to notice malicious mobile webpages

Detecting Node Failures in Mobile Wireless Networks: A Probabilistic Approach

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Dr Sai Madhavi D | Sumalatha Gouda

Abstract

Detecting node failures in mobile wireless networks is very challenging because the network topology can be highly dynamic dynamic, the network may not be always connected, and the resources are limited. In this paper, we take a probabilistic approach and propose two node failure detection schemes that systematically combine localized monitoring, location estimation and node collaboration. Extensive simulation results in both connected and disconnected networks demonstrate that our schemes achieve high failure detection rates (close to an upper bound) and low false positive rates, and incur low communication overhead. Compared to approaches that use centralized monitoring, our approach has up to 80% lower communication overhead, and only slightly lower detection rates and slightly higher false positive rates. In addition, our approach has the advantage that it is applicable to both connected and disconnected networks while centralized monitoring is only applicable to connected networks

Detecting Node Failures in Mobile Wireless Networks: A Probabilistic Approach

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Dr Sai Madhavi D | Sumalatha Gouda

Abstract

Detecting node failures in mobile wireless networks is very challenging because the network topology can be highly dynamic dynamic, the network may not be always connected, and the resources are limited. In this paper, we take a probabilistic approach and propose two node failure detection schemes that systematically combine localized monitoring, location estimation and node collaboration. Extensive simulation results in both connected and disconnected networks demonstrate that our schemes achieve high failure detection rates (close to an upper bound) and low false positive rates, and incur low communication overhead. Compared to approaches that use centralized monitoring, our approach has up to 80% lower communication overhead, and only slightly lower detection rates and slightly higher false positive rates. In addition, our approach has the advantage that it is applicable to both connected and disconnected networks while centralized monitoring is only applicable to connected networks

Detecting Stress Based on Social Interactions in Social Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

K.Maheswari | K.Soundari, K.T.Sanjiv, S.Rama priya

Abstract

Mental pressure is undermining individuals' wellbeing. It is non-unimportant to distinguish pressure opportune for proactive care. With the prominence of web-based social networking, individuals are accustomed to imparting their day by day exercises and associating to companions via web-based networking media stages, making it doable to use online interpersonal organization information for push discovery. It is find that clients push state is firmly identified with that of his/her companions in online networking, and a huge scale dataset from certifiable social stages is utilized to deliberately ponder the relationship of clients' pressure states and social collaborations. It is first characterized an arrangement of stress-related literary, visual, and social properties from different angles, and after that propose a novel half breed display – a factor diagram demonstrate joined with Convolutional Neural System to use tweet substance and social connection data for stretch location. In this paper, we find that clients push state is firmly identified with that of his/her companions in online networking. To examine the connection of clients push states and social cooperations with the prominence of online networking , individuals are accustomed to imparting their day by day exercises and collaborating to companions via web-based networking media stage to characterize an arrangement of stress related literary visual and social traits from different perspectives

Detection and Analysis of Influence by Renowned Leaders in Online Social Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th September 2017

Sr.SujathaYeruva | 

Abstract

Social networks (SNs) are part and parcel of human life: inhabitants progress, influence and are influenced by their acquaintances. The quantity of knowledge accessible on SNs is gigantic with the advent of World Wide Web, allowing the qualitative exploration of information. Social network analysis (SNA) has been gaining thought from divergent areas like social science, economics, psychology, biology. The swift rise of the net SN sites and their publically procurable knowledge attaining API’s has crystallized the prosperity of SNA analysis. Tracing potent users and their influence is one among the trendiest topics of SNA. Contemporary exploration of associations among the members of a SN reveals that through direct contacts individuals influence indirect ones. Substantive data concerning the prestigious users and also the ability to predict them could also be leveraged for many applications. This analysis work employs Pareto Front function to mark the outstanding leaders that is followed by an empirical analysis of the results of their dependable influence

Detection and Diagnosis of Diseases in Cotton Leaf Using Knowledge Based Expert System

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Miss.Sonali Borikar | Miss.Pallavi Khedekar,Miss.Darshana Jangam, Miss.Pallavi Paratwar, Mr.Ketan Bodhe

Abstract

The economy of India is based on agriculture as it is the backbone of the rural livelihood security system. The cotton is mostly used by world and grown in more than 100 countries accounting for 40% than any other fiber of the world fiber market. As managing diseases in cotton crop is a challenging task and cotton crop production in India is important.This propose system focuses on maximizing the cotton crop production, this is the main purpose of this project. Sometimes farmers identify diseases by their experiences with the naked eyes and due to incorrect identification, there will be the possibility incorrect control measurement. By using this propose system farmers can identify cotton crop diseases in early stages & also they are known to the particular diseases of cotton crop. The system is specially proposed for the controlling the diseases in cotton plant. Here the system is consisting of the Knowledge Based Expert System and the inference engine. The inference engine applied logical rules to the knowledge base and obtain the result for detection of diseases.

Detection and mitigation of Black hole attack in MANET using Artificial intelligence technique

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th November 2017

Saurabh Kumar | Anjani Garg

Abstract

MANET (Mobile ad hoc network) is a self-governing network that comprises of moveable nodes that communicates with each other through wireless links. To find the route from source to destination, different routing protocols named as proactive, reactive and hybrid routing protocols are used. In the proposed work, AODV (Ad-hoc on demand) routing protocol is used. It is a packet routing protocol which is designed to use in MANET. Every node maintains a routing table that contains information about the destination node. In MANET, normally, numbers of attacks are routing protocol attacks. This research has dealt in detecting and mitigating black hole attack. The black hole attack is one of the well known security threat occurs in MANET. A black hole attack occurs due to malicious nodes that attract the data packet by addressing a false route. In the proposed work, ABC (Artificial Bee Colony) algorithm is used to optimize the route from source to destination. ANN (Artificial Neural network) is used to detect and prevent the network from black hole attack. The simulation is carried out in MATLAB simulator and the performance parameters, namely, throughput, packet delivery ratio, delay are measured..

Detection of Broken Railway Tracks and Obstacles by Ultrasonic Technology

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Manish Dixit | Bitan Paul, Drishant Sharma, Manik Reshi, Jeyadevan S

Abstract

Railways are one of the important transports in India. There is a need for manual checking to detect the crack on railway, even though the inspection is made regularly, sometimes the crack may go unnoticed. Because of this the train accident or derailment may occur. To avoid this situation, we have proposed this railway crack detection system. Here, ultrasonic sensor is used to detect the crack in the railway track. We place both the ultrasonic sensors on the train for obstacle and crack detection. If the crack is detected, notification is shown by LCD to the driver and is send through GSM to the base station, and EPM module is used to halt the train depending on the pressure applied

Detection of Clone Attack in Wireless Sensor Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th June 2017

Vishakha Pawar | Seema Hanchate

Abstract

These Recent trends of wireless communication is Wireless sensor network,this is upcoming technology which has enabled the development of network with huge number of tiny, low power, multitasking sensor nodes. As WSN has broadcast approach, there is a need of security Wireless sensor networks (WSNs) are now used as supporting infrastructure in many applications. Secure communication in WSNs is very important because information sent through these networks can be easily captured or replaced or altered. Clone attack is node replication attack. An adversary can steal a node from the network and altered data from stolen node and can reprogram that node to create a clone of a stolen node. To protect network from clone attack is vital in WSN. The main objective of proposed clone detection protocol is to provide strong protection against clone attacks, high detection probability, low storage requirements with enhanced network lifetime by increasing energy efficiency with distributed detection mechanism.

Detection of Compromised Accounts in Online Social Network

International Journal of Engineering Research in Computer Science and Engineering, Available online 28th March 2018

Sneha Rane | Megha Ainapurkar, Ameya Wadekar

Abstract

Compromised accounts are of a severe risk to the social network users. People nowadays are mostly dependent on Online Social Networks. While some persistent spams feat the relationship between the users by spreading spams. Therefore time to time detection of the compromised accounts is a necessity. In this paper, we will study different social user behaviour and detect the compromised accounts and spam users. Spam behaviour in social networks has a wide range of illegal activities. Such activities need to be evaluated and effect of spam users needs to be reduced. To reduce such effects, we require proper detection strategy. We validate the effectiveness of this behaviour by collecting the clickstream data on a social network website. Social behaviour reflects the user's behaviour online. While a legitimate user coordinates its social behaviour carefully, it is hard for the fake users to pretend to be affected. Different studies are performed in spam behaviour analysis and define a structure for spam account detection.

Detection of Cross Site Scripting Attack and Malicious Obfuscated Javascript Code

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th August 2017

Vrushali S. Bari | Prof. Nitin N. Patil

Abstract

JavaScript is a scripting language. On one hand, it allows developers to create client-side interfaces for web applications. On the other hand, the malicious JavaScript code infects the web user and web browser. In order to detect malicious activities, two methods viz. static and dynamic detection methods have been discussed in the literature. The dynamic analysis method has better capability in detecting malicious activities compared to the static detection method. In this paper, we present a method based on Support Vector Machine (SVM) that would identify the malicious JavaScript code at the beginning itself. In addition, our proposed method supports the analysis of obfuscated code and analyzes the system offline. Further, it analyzes the web pages and identifies the type of attack. However, our focus is on the Cross-Site Scripting (XSS) attack.

Detection of DOS Attacks through Evidence Collection using Dempster-Shafer Theory

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Shradha S. Ippakayal | Geetanjali S. Dhaygude, Vinaya P. Kalyanshetty, Prof. M.N.Ingole

Abstract

MANETs has been experiencing exponential growth in the past decade. Due to their vulnerability to various attack makes extremely prominent for its distributed and independent nature. Among these various DOS attacks black hole, grey hole, and co-operative black hole attack may collapse the network, and this may become a major threat in MANETs. Here we are using Dempster-Shafer evidence based theory to collect various evidences for various nodes in the network against black hole and grey hole attack. For detecting malicious node we used Direct Trust Value (DTV) to detect a single black hole attack. DTV is calculated for each node that exists in the network and then that value is compared against predetermined threshold, if the calculated value is less then predetermined threshold then the node is malicious node.

Detection of Human Face in a Meeting Using Audio Sensitive Camera

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th December 2017

Giridhar N R | Aniketh M, Ashish Kumar Vishwakarma, Ganesh Prateek L, Dr. Jharna Majumdar

Abstract

A meeting outcome is a desired result or product that will be achieved by the end of the meeting. It is also necessary to take note of key points made in the meeting. In this paper, we achieve this goal using an autonomous system. The entire system is built on both hardware and software components. The system is developed on an embedded board containing a video recording camera, audio sensors and a Dynamixel motor. The camera rotates in the direction the sound originates and starts to record. The recorded video is fed to the software part where face detection is done. Face detection is a computer technology that is used to identify human faces in digital images. We make use of three colour models like RGB, HSV and YCbCr to perform skin segmentation to obtain probable regions where the human face is present. We determine the best colour model which is suitable for skin segmentation. From the segmented image obtained from the previous step, Lucas-Kanade Optical Flow Method [6] is used in determining the location of the face in the frame.

Detection of Impurity in Liquids Using Electronic Sensor Based System with Infrared Camera and The Real Time Monitoring of Water Qualityin IoT Environment

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th August 2017

Sanjana U Neralkatte | Nittayashree S, Roja K R, Shilpa K, Sushma G S

Abstract

This paper is based on new enhancement technique for infrared images which integrates the benefits of additive wavelet transformation and homomorphic image processing. The main motive behind this technique is to decompose the images into subbands in an additive fashion and the principle adopted to implement the same is using additive wavelet transform which produces the image as an addition of subbands of the same resolution. Drinking water varies from place to place, depending on the condition of the source water from which it is drawn and the treatment it receives, but it must meet EPA regulation. The traditional method of testing Turbidity, PH & Temperature is to collect samples manually and then send them to laboratory for analysis. However, it has been unable to meet the demands of water quality monitoring today. So a set of Monitoring of Turbidity, PH & Temperature of Water quality has been developed. The system consists of Turbidity, PH & Temperature sensor of water quality testing, single-chip microcontroller data acquisition module, information transmission module, monitoring center and other accessories. Turbidity, PH & Temperature of water are automatically detected under the control of single chip microcontroller all day. The single chip gets the data, and then processes and analyzes them. If the water quality is abnormal, the data will be sent to monitoring center and alert the public at the same time

Detection of outliers in the IoT data using the STCPOD model

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th October 2017

I.Priya Stella Mary | Dr. L. Arockiam

Abstract

The Internet of Things (IoT) is the novel communication paradigm in which the internet is extended from the virtual world to interact with the objects in the physical world. Through this, an immense number of applications can be developed but at the same time, enormous challenges have to be dealt with to reap the benefits of the IoT. One such challenge is outlier detection in Internet of Things. Outlier detection is a process to detect the data that vary from the rest of the data based on a certain quantity. Outlier detection is very essential in Internet of Things to detect unusual behaviours, readings and events. In this paper, a novel STCPOD (Spatially and temporally correlated proximate Outlier Detection model) is proposed to deal with Outlier detection problem in IoT. Experimental results have proved that the proposed method has outperformed the existing STCOD model in terms of accuracy

Detection of Red Lesions For Diabetic Retinopathy In Telemedicine Context

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd August 2017

Kazi Syed Naseeruddin Mustafa | Prof.SushilKumar N. Holambe

Abstract

In this paper we present the Red Lesion Detection for diabetic retinopathy in telemedicine context. The method used in this in this paper is the process of morphological image flooding. The development of an automatic telemedicine system for computer-aided screening and grading of diabetic retinopathy depends on reliable detection of retinal lesions in fundus images Signs of DR include red lesions such as microaneurysms and intraretinal hemorrhages, and white lesions, such as exudates and cottonwool spots. This paper concerns only the red lesions, which are among the first unequivocal signs of DR. Therefore, their detection is critical for a prescreening system

Determining Key Performance Indicators and Envisioning Results Using Data Mining

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th May 2018

Dr. V.B.Narsimha | 

Abstract

Information Systems or databases holds enormous amounts of information/data which can be used for mining to extract the effective patterns which can be further used in making better decisions in business, healthcare, banking and other applications. During this research we tend to build a model which predicts the performance of a Student in a Programming Language named 'Python' based on the different factors like the high school marks, parent's education, nature of environment, faculty approach, difficulty level of subject, etc. During the research, we have applied different feature selection techniques using algorithms like Naive Bayes and Decision Tree and found that Naive Bayes have built a prediction model with accuracy of 82.4%. This model helps to understand about the students who may fail which in turn give a sign to faculty to focus on those students to take active measures in improving their performance.

Developing a GIS Platform for Tourism marketing and promotion In Nigeria: Case Study Of Bauchi State

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Abubakar Siddiq Ango | Abdulsalam Waheed Abdulfatah, Idrissa Djibo

Abstract

Tourism has been noted to be one of the important sectors of the Nigerian economy. Tourism is a highly complex activity which requires tools that aid in an effective decision-making to come to terms with the competing economic, social and environmental demands of sustainable development. Geographic Information System (GIS) is one of such tools. GIS being an information system that is capable of answering questions about where facilities and resources are located represents enormous benefits to the tourism sector of any economy. The power of GIS lies not only in the ability to visualize spatial relationships, but also beyond the space to the holistic view of the world with its many interconnected components and complex relationships. The use of GIS technology could assist Bauchi State government as well as the Nigerian government with better planning of tourism infrastructure, location and dissemination of such infrastructure, production of better quality maps showing tourists sites abound in the country because of the dynamic capability of GIS tools to incorporate changes that occur over time to its database. A GIS database for tourism in Bauchi State was created using some selected roads, tourist attractions and facilities with the aid of base maps and GPS. This paper presents the significant role that GIS can play in tourism development in Bauchi State if a complete database for tourism in the State is designed and developed.

Developing a Neural Network Based Approach for Sentiment Classification

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

M.Karthi | R.Kirubhakaran, S.Vijay, K.K.Yuvaraj kumar, D.Suganya

Abstract

The study of sentimental analysis and opinion mining deals with attitude and emotions. Opinion mining has several challenges. The first challenge is that a word is either positive in one situation or negative in another situation. Therefore, sentiment can be performed using social media messages.. To overcome this problem, social media messages are used which are free of cost and produced in world wide. In this the public concern can be measured using two-step word alignment approach. In the first step, raw reviews are separated into personal reviews and news reviews. In the second step, personal reviews are further classified into personal negative and personal non-negative. In both steps, the trained data is generated automatically using an emotional-oriented, clue-based method and the trained dataset can be tested using machine learning model such as Naïve Bayes. The proposed algorithm will increase the accuracy for epidemic domain

Development of IOT Gateway for Weather Monitoring

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th June 2018

Aniket S. Rokade | Mahadev S. Patil

Abstract

Internet of things is an emerging field in technology. The purpose of this project is to link the internet to the physical devices in the industry like sensors by the Gateway. Industrial IoT concept requires Gateway for secure monitoring of physical components. A microcontroller controls the sensors and transmits data through Gateway by GSM/GPRS module to the internet. The MQTT protocol is used as the Gateway. MQTT increases the security of data which gets the transfer from device to the internet. The result is a continuous sensor monitoring system which can be used to determine weather conditions.

Development of Natural Language Interface to Voice Control Smart Environment

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

D.Sucharitha | Dr.M.Humera Khanam, K.Ravi kishore,G.Divya

Abstract

Development of smart home technology changed the human living conditions greatly. In smart home we can control and automate the lighting, heating, ventilation and air conditioning by voice. System can change the state of devices. For remote monitoring of devices we use Wi-Fi of IOT( Internet of Things).In this paper, we provide a natural language interface to control the smart devices, by speaking in the own language. It uses microphone to collect the speech signals and object recognition technology to locate the target object. Finally, SRM (Speech Recognition Module) can communicate with the central control program by socket.

DGA Based Incipient Fault Diagnosis of Transformer Using AI Technique

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th March 2018

Ashwini D. Vajirabadkar | Sandip M. Apte

Abstract

In this paper, we focus on a Smart Fault Diagnostic Approach (SFDA) based on the integration of the output results of recognized dissolved gas analysis (DGA) techniques. These techniques are Dornenburg method, Electro-technical Commission standard (IEC) Code, the Central Electricity Generating Board (CEGB) Code based on Rogers’ four ratios, Rogers method given in IEEE-C57 standard, and the Duval triangle. The artificial intelligence model will be constructed to monitor the transformer fault conditions. The fault decision of AI model will supply the proposed integrated SFDA. The integration between these DGA approaches will not only improves the fault condition monitoring of the transformers but also overcomes the individual weakness and the differences between the above methods. Toward a better diagnostic scheme, a new SFDA will be developed based on the integration of the most three appropriate DGA methods

Diagnosing Human Diseases using Toe Nail

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

Dr.A.Mercy Rani | M.Kaleeswari, M.Karpagam

Abstract

Digital Image Processing deals with the manipulation of digital images through a digital computer. Digital Image Processing plays a vital role in the medical field. Medical Imaging helps to reveal and analyze the internal structure and external structure of the human parts for easy diagnosis of the diseases. A human Toenail is one of the parts for finding the diseases. The diseases can be detected by extracting its assorted features from the nail. The features such as color, texture, and shape are the basic component to ascertain the affected areas in the nail. In this paper, the proposed system is developed to identify the diseases using toenail color. In this system, the nail images are acquired by the image acquisition and the segmentation technique is applied for feature extraction to extract the affected portion of the toenail. The Hue value is used for identifying the color of the nail. Finally, the result is evaluated and the nail disease is diagnosed based on the nail color

Diagnosis of ADHD using Statistical measures

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th May 2018

E.Radhamani | K.Krishnaveni

Abstract

Diagnosis of ADHD using Statistical measures is proposed in this paper. An ADHD data set with 105 samples based on different ages ranging from 6 to 9 and gender (Male & Female) is collected and classified into noADHD, moderateADHD and highADHD by using statistical parameters like mean and standard deviation. The ADHD may be caused by different factors like age, gender, and brain damage, etc. In this research work, only two factors namely age and gender are taken to find the goodness of fit for the data collected and to examine that whether these parameters have any significance for the cause of ADHD. The Tests of Independence between these variables are carried out by Chi-Square Test and the results are discussed and analyzed. From this test it has been concluded that age has no significance for the cause of ADHD but Gender has significance ie, AGE and ADHD are independent but Gender and ADHD are dependent variables.

Dictionary Learning Arrangement for Multi-Label Image Annotation

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Yogini B. Bhadane | Prof. Nitin N. Patil

Abstract

The passing keywords to images is of huge attention as it allows one to retrieve, directory and recognize big collections of image data. Various systems have been designed for image annotation that gives a realistic presentation on consistent datasets. Here, studied multi-label image annotation with dictionary learning methods. In multi-label image annotation, new (SLED) semantic label embedding dictionary demonstration used, which is solved the problem of annotation, under the softly supervised situation. Several of the consumers have the skill to produce and store images. Peoples did not spend their time for organizing and grouping their particular (private) image collections. So it's difficult for peoples to finding particular (exact) images. Image annotation contains a number of methods that goals to find the link between words and images. The multi-label image annotation system divided into two branches, i.e. the training branch and the testing branch. In training branch, datasets are divided into exclusive groups. In it, Fisher discrimination law used for the train the label of that image. Then co-occurrence labels would offer the context data of that image. This context data adds into the novel dictionary table. In the testing branch, use label propagation and reconstruction coefficient to get the score of each image labe

Digital Image Watermarking Algorithm Using Eigen Values and Singular Value Decomposition for Gray Level Images

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th March 2018

Dr P. Shanthi | 

Abstract

In the current globalized world, the right of ownership is at stake. This is arises due to the easy exchange of data through various channels of communications and lack of authentication. The problem of piracy can be limited to a large extent by using a technique called Digital Watermarking.. The main aim of this paper is to increase robustness by implementing the digital watermarking using Singular Value Decomposition (SVD). In this paper, instead of using the conventional SVD, introduce a new algorithm to directly compute the largest eigenvalue and eigenvector of segmented image blocks. By using this approach, our proposed watermarking scheme has lower computational complexity than various SVD based schemes. Experimental results also showed that our watermarking scheme outperforms several widely used schemes in terms of robustness. Moreover, using the proposed algorithm, we designed a digital image watermarking using eigen values and improved Singular value decomposition from gray level Images, where watermarked images can be verified without using the pre - defined watermark and a secret key.

Digital Image Watermarking Using QR Code

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Sumedha Nishane | Prof. V. M. Umale

Abstract

In this science era with the development of technology and internet, the protection and authentication of data is essential. Watermarking techniques provide solution to this problem. QR code being so versatile because of its structural flexibility that it leads to so many diverse field for research such as increasing data capacity, security applications such as different kinds of watermarking . We have used QR code as cover image and as secret image to protect it from other users. This paper is representing a new watermarking technique with QR code to protect the secret image. In the method described here the image is first encrypted in random matrix, then it is invisibly watermarked in cover image and no information about the secret image and cover image is needed for extraction of secret image, so it more secure.

Digital Signatures using PDF Creator

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th October 2017

G. Swetha | 

Abstract

Digital signatures are useful to show that, the document is approved electronically. It is the proof for the sender’s identity. This paper is about creating digital signatures using PDFCreator. PDFCreator is a tool which converts our documents into PDF format. It creates a virtual printer that prints to PDF files, and allows practically any application to create PDF files by choosing to print from within the application and then printing to the PDFCreator printer. Some other tools for creating digital signatures on PDF documents are iTextSharp, Nova pdf Expert, etc.

Digital Trinket

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

L. Manisha Priya | 

Abstract

This paper describes the use of Trinket in a digital way. Trinket worn for many reasons -- for exquisite, to impress others, or as a symbol of affiliation or commitment. Basically, Trinket embellish the body, and has very little practical purpose. However, researchers are looking to change the way we think about the beads and bobbles we wear. In the next wave of mobile computing devices, our trinket might double as our cell phones, personal digital assistants (PDAs) and GPS receivers. In the next age of computing there will be an explosion of computer parts across our bodies. It can defined as the wireless wearable computers that allow you to communicate by different ways. This paper enlightens on how various computerized Trinket (like ear-rings, bracelet, ring, necklace etc) will work with mobile embedded intelligence. ’Digital Trinket’ can help you solve problems like forgotten passwords and security badges

Digital Watermarking for Developing Trust in Medical Imaging Workflows State of the Art Review

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th May 2018

Jyoti | 

Abstract

Medical images can be intentionally or unintentionally manipulated both within the secure medical system environment and outside, as images are viewed, extracted and transmitted. Many organisations have invested heavily in Picture Archiving and Communication Systems (PACS), which are intended to facilitate data security. However, it is common for images, and records, to be extracted from these for a wide range of accepted practices, such as external second opinion, transmission to another care provider, patient data request, etc. Therefore, confirming trust within medical imaging workflows has become essential. Digital watermarking has been recognised as a promising approach for ensuring the authenticity and integrity of medical images. Authenticity refers to the ability to identify the information origin and prove that the data relates to the right patient. Integrity means the capacity to ensure that the information has not been altered without authorisation. This paper presents a survey of medical images watermarking and offers an evident scene for concerned researchers by analysing the robustness and limitations of various existing approaches. This includes studying the security levels of medical images within PACS system, clarifying the requirements of medical images watermarking and defining the purposes of watermarking approaches when applied to medical images

Digitalization of Medical Prescription and Localization of Healthcare Products

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

R. Ganesan | E. Kughan , R. Sanjay, S. Arun Karthikeyan

Abstract

This project enables the doctors to send prescription digitally to the patients who are not able to visit the doctor in person and also allows the patients to check the availability of medical products in nearby pharmacies. The conventional way practised by doctors is to write the prescription using pen and paper and also the patient may not know about the availability of these medical products in nearby pharmacies. The use of pen and paper for medical prescription is not encouraged because the prescription might get damaged, lost over duration of time and no further automations/computations cannot be done that limits the scope of pervasive healthcare system. During emergency situations, the patient might not get the prescribed medical products due to lack of availability in nearby pharmacies which lead to severe health issues. This project digitalizes the prescription given by the doctors and also guides the patients to the nearby pharmacies which contain the required quantity of medicines and other medical products. Due to this digitalization of medical prescription, the patients suffering from severe ailments might not strain themselves to consult the doctor in person. This project also enables the user to check for the availability of the required medical products in the nearby pharmacies using GPS and Google Maps implemented in Android platform. It uses an ranking algorithm to enhance the quantity of information which is fetched from the database and presented to the patient. The ranking also uses a credit-based system, which weightage to rating given in recent years. The uniqueness of the project is to design low cost pervasive healthcare inventory automation system.

Disease Inference System based on Health-Related Question Answer system

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Paresh Karande | Manoj Khairavkar, Vinayak Lokhande, Khemchand Mahajan , Rupali Umbare

Abstract

Health is one of the expanding subjects used for assessing health condition among patients who suffer from specific ailment or diseases. We aims to model the relationship between the Health variables using integrated model of inference system and linear regression. Linguistic data were collected by a guided interview and fed into the deep sparse inference system to yield Health indices. We next propose a novel significant learning plan to surmise the conceivable maladies given the inquiries of wellbeing seekers. The proposed plan is embodied two key parts. The main part mines the discriminant therapeutic marks from crude elements. The second esteems the crude components and their marks as info hubs in one layer and concealed hubs in the consequent layer, individually. In the interim, it takes in the between relations between these two layers by means of pre-preparing with pseudo-marked information. Taking after that, the shrouded hubs serve as crude components for the more unique mark mining. With incremental and option rehashing of these two segments, our plan manufactures a scantily joined profound construction modelling with three shrouded layers.

Disruptive Technologies

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Chandra Shekar N | K Anjali, A Pavithra

Abstract

the term "disruptive technology" as coined by Christensen (1997) refers to a new technology having lower cost and performance measured by traditional criteria, but having higher ancillary performance. Christensen finds that disruptive technologies may enter and expand emerging market niches, improving with time and ultimately attacking established products in their traditional markets. This conception, while useful, is also limiting in several important ways. By emphasizing only "attack from below" Christensen ignores other discontinuous patterns of change, which may be of equal or greater importance (Utterback, 1994; Acee, 2001). Further, the true importance of disruptive technology, even in Christensen's conception of it is not that it may displace established products. Rather, it is a powerful means for enlarging and broadening markets and providing new functionality. In Christensen's theory of disruptive technology the establishment of a new market segment acts to channel the new product to the leading edge of the market or the early adopters. Once the innovation reaches the early to late majority of users it begins to compete with the established product in its traditional market.

Disruptive Technologies

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Chandra Shekar N | K Anjali, A Pavithra

Abstract

the term "disruptive technology" as coined by Christensen (1997) refers to a new technology having lower cost and performance measured by traditional criteria, but having higher ancillary performance. Christensen finds that disruptive technologies may enter and expand emerging market niches, improving with time and ultimately attacking established products in their traditional markets. This conception, while useful, is also limiting in several important ways. By emphasizing only "attack from below" Christensen ignores other discontinuous patterns of change, which may be of equal or greater importance (Utterback, 1994; Acee, 2001). Further, the true importance of disruptive technology, even in Christensen's conception of it is not that it may displace established products. Rather, it is a powerful means for enlarging and broadening markets and providing new functionality. In Christensen's theory of disruptive technology the establishment of a new market segment acts to channel the new product to the leading edge of the market or the early adopters. Once the innovation reaches the early to late majority of users it begins to compete with the established product in its traditional market

Distinguish DDoS Attacks and Suggesting Some Counter Measures For Distributed P2P Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th November 2017

Gera Jaideep | R.V.Kishore Kumar, Dr.B.V.V.S.Prasad

Abstract

Peer-to-Peer networks became more popular in now days because of its useful delivery services. It utilizes distributed resources to perform some intended activities. Because of its distributed in nature they are widely used in file sharing. For every network there is a common problem that is an attack, it may of many types in those most complicated and highly threatening and hard to detect attack in distributed Peer-to-Peer network is Distributed Denial of Service (DDoS) attack. An attack that interrupts the services to all the users is DDoS attack. Many techniques are in existence to solve the DDoS attack but still hard to respond in short time to flooding based DDoS attacks. The reason is this attack is made by intruders or opponents who use large number of attacking machines by a method of source address spoofing. In this paper we proposed architecture, this designed structure defend and detect DDoS attacks. Here we can resolve this with the help of two important parameters. Time-to-Live (TTL) value and the distance between victims source to victim’s destination. This architecture can take care of agent-based trace back, traffic control and detection of DDoS attack. The proposed methodology can detect and prevent DDoS attacks and ensure Quality of service for real traffic.

Distress Signal Messaging Through Radio Frequency for Mobile

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd May 2018

Pravin R. Pachorkar | Saurabh D. Kale, Ankush S. Wagh, Chandrashekhar U. Dixit, Abdulraheem W. Khan

Abstract

Recently, this has been found that there are network related issues which are occurring in some mountain and hilly areas. There are few outdated technologies that are still in use like cellular network, wired network techniques that could not find proper solution to overcome the issues. We are trying to find the solution for this issue using some latest technologies and small devices that can be used with smartphones. We are focusing on radio frequency techniques to increase the range for conversation in No-Network areas. For this, we are supposed to use radio antennas that will broadcast the signals in forward direction. The device Interface with smartphone through OTG. Where, the signal-receiving device will have same system arrangement for the communication to have taken place between them.

Distributed Data Transfer for Disaster Using Cloud Computing Infrastructure

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

Keerthana R | Lavanya S, Preethi C, Priya S

Abstract

The main objective of this project is to enhance the data storage security and secured data transfer during disaster. To resolve this IaaS (Infrastructure as a Service) methodology will be implemented here. As per survey most of the banking server and data centres are placed in metropolitan cities, most of the metropolitan cities are in sea shore. We proposed the system to find out a solution for safe hand the data centres and banking servers. In this paper, we aimed to achieve the minimum cost benchmark, so we proposed a novel highly cost-effective and practical storage strategy that can automatically decide whether a generated data set should be stored or not at runtime in the cloud. The main focus of this strategy is the local-optimization for the trade off between computation and storage.

Document Sharing Android Project

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Lahiri Kolli | M. Swathi, Kirankumar, K. Shree Krishna, Dr. H Girisha

Abstract

The project is to share the data between the college faculty and the students. The system consists of individual login to faculty and students. The faculty can upload the notifications, e-notes, syllabus, timetable and any other important information through the faculty login. This project will work on android operating system and will be a great system for sharing the information between the documents. Student Faculty Document Sharing Android Project is based upon java technology. This project is designed for the sake of reducing efforts between both the students and the faculty.

Dr. House - Warehouse Manager

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th August 2017

Jayant Benjamin | Milan Dave

Abstract

Dr. House is a website interface which helps user to track, control, monitor and maintain a warehouse. The website interface acquires from two types of IoT devices one for ambience control and the other asset tracking, with the help of http get and post requests. The main USP of Dr.House is it’s online recommendation, which helps user to order good from online retail stores whenever times are urgent and adequate quantity of goods aren’t available

Dustless Environment by Transportation Means

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th July 2017

Gagana G E | Madhushree P, M Vanishree,Veena R,Mr. T K Pradeep Kumar

Abstract

This is an automated system which will be fitted in the Bus for cleaning the dust particle from environment.The proposed technique is intended to facilitate the user to clean the dust particle through vacuum cleaner. In this system Microcontroller is the main unit, which controls the whole process. We are going to use AVR family microcontroller (ATMEGA 8/ ATMEGA 16). Vacuum Cleaner is used for cleaning the dust particle from road, which is connected with microcontroller. There is a container for containing the dust particle. We are going to use IR sensor for detecting the quantity of dust particle in container. IR sensor will be fitted on the top of container. When the container will be filled with dust container, then the sensor will detect it and send information to microcontroller. The sensor will be connected with Microcontroller .There will be one alert system for giving alert when the sensor will detect the quantity of dust. There will be one manual switch, which will be used for opening and closing of the container. Motors will be fitted on the top of container for opening and closing container.solar panels are placed on roof of the bus for power supply

DWT & SVD Based Watermarking Scheme for Copyright Protection In Medical Images

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Ms. Shubhangi D. Mashalkar | Prof. S. S. Shirgan

Abstract

Watermarking is a popular method for copyright protection. This technique seems to be very popular and helpful for protecting the privacy of patients by doing watermarking procedure on medical images. In this watermarking scheme a text image is created which may vary from patient to patient and is embedded on the MRI images to generate a secure image which contain hidden patient data (not visible to naked eyes). Two methods are implemented for watermarking i.e. Discrete Wavelet Transform and Singular Value Decomposition. The PSNR (between original MRI image and generated secure image) and correlation (between patient text information and extracted watermark image) are calculated to check the robustness and capacity of the scheme.

Dynamic cluster Selection based on less energy dissipation in Wireless Sensor Network

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd April 2018

Sharad | Dr. Savita Shiwani, Dr. Manish Suroliya

Abstract

The ever-rising demands for real time transmission requirement has widened up the scope for wireless sensor network. From the conventional use of gathering, processing and transmitting data via network for offline and online analysis, WSN sensing devices are now used in various industries for efficiently monitoring and controlling real time requirements. However, the rapid consumption of energy and its wastage is still a major challenge. Therefore, in this research study, we will propose a new algorithm to select a cluster head in the wireless sensor network as these cluster heads play a very significant role in the reduction of energy consumption while enhancing the lifetime of the whole network

Dynamic Frequency Filtering based on Analysis of Hearing Impairment

International Journal of Engineering Research in Computer Science and Engineering, Available online 12th January 2018

Padmaja Kuruba | Tilak Kumar L

Abstract

Worldwide more than 10% of the people are suffering from Hearing impairment. The statistical report shows more than 20 crores of people are subjected to various levels of hearing problems based on various reasons depending on the surrounding environment. Hearing impairment is seen in all age groups from infants to adults. In this paper, we propose a digital hearing system which mimics the biological ear. The system is designed to produce required sound based on the patient impairment level, using digital signal processing techniques. This involves noise reduction, the frequency selected filtering & amplification and compression such that bouncing of the frequencies is avoided. The proposed work is simulated using MATLAB where the following parameters are tested namely 1) reduction of white Gaussian Noise 2) increase in the gain of specific frequencies 3) dynamic shaping of the signal amplitude to reduce bouncing of the signal.

Dynamic resource allocation for distributed file system in Cloud computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

V.Nithya Priya | K.Mathan Kumar

Abstract

Distributed computing enables clients to utilize assets in view of the requirements of the relating applications. A standout amongst the most critical strategy in the distributed computing is virtualization method which is utilized for multiplexing of assets, servers, and so on. In spite of the fact that an Inter cloud is an interconnected around the world "surge of fogs" that enables each cloud to exploit asset of various fogs, joint efforts among Inter cloud accomplices are mind boggling in light of the way that Inter cloud assets are scattered and controlled by different fogs. "Administrator based disseminated registering" incorporates the improvement of experts for fortifying disclosure, planning, assurance, association, course of action, arranging, work process, and checking of Inter cloud asset. An authority is a PC system that is fit for settling on decisions self-sufficiently and associating with various administrators through support, coordination, and exchange. Using an administrator based approach, traits related with watchful practices of masters, for instance, conveying socially through interest, coordination, and exchange can be joined with fogs. This paper 1) inspects the vitality and good conditions of using an authority perspective for Inter cloud asset appropriation, 2) overviews designate models of administrator based Inter cloud Resource assignment and gives a relationship among these models, 3) contemplates pro based and non-administrator based procedures for undertaking executions in different fogs, and 4) offers pointers to future headings.

Dynamic Secret Key Generation for Multi Data User in Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Chethan R | Divya D, Kavya H, Prashanth,Vani Saptasagar

Abstract

CLOUD computing is a subversive technology that is changing the way IT hardware and software are designed and purchased. Cloud computing provides abundant benefits including easy access, decreased costs, quick deployment and flexible resource management, etc. It has become highly popular for data owners to outsource their data to public cloud servers while allowing data users to retrieve this data. For privacy concerns, a secure search over encrypted cloud data has motivated several research works under the single owner model. However, most cloud servers in practice do not just serve one owner; instead, they support multiple owners to share the benefits brought by cloud computing. In this paper, we propose Dynamic Secret key generation for multi user in cloud computing. To enable cloud servers to perform secure search without knowing the actual data of both keywords and trapdoors, we systematically construct a novel secure search protocol. To rank the search results and preserve the privacy of relevance scores between keywords and files, we propose a novel additive order and privacy preserving function family. To prevent the attackers from eavesdropping secret keys and pretending to be legal data users submitting searches, we propose a novel dynamic secret key generation protocol and a new data user authentication protocol

Dynamic Secret Key Generation for Multi Data User in Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Clara Kanmani A | Suma V, N Guruprasad

Abstract

Cloud Computing is internet based computing that provides shared computer processing resources and data to computers and other devices on demand. Semantic web is an extension of the current web in which information is given welldefined meaning, enabling computers and people to work in cooperation. This paper gives a brief picture of how Cloud computing and future web, semantic web technology evolved. However from the extensive literature survey, it is also observed that, these two technologies plays an interplay role with each other in solving complex problems. Furthermore an analysis of where semantic web technology meets cloud computing is carried out and briefly describes how Semantic web technology can be used to address the challenges of cloud computing.

Dynamic Secret Key Generation for Multi Data User in Cloud Computing

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Adivikottu Ramakrishna | Dr.G.P.Saradhi Varma

Abstract

A customer who has issued a Query word question to a web searcher. The Keyword proposals are the most important element of the web search tool. Truthful clients don't know how to express their examination accurately more often than not questions are short and unambiguous. Using that watchwords web file recovers the reports, the proposed Query hold phrase inquiries to the customer, which are semantically noteworthy to the main question and they have results records that contrast with objects near the customer's region. Thus, here propose a weighted Keyword-Query record graph which gets semantic likewise, expel among inquiries and reports. By then, use the outline to propose questions that are shut as far as graph detachment to the primary inquiries. Fragment-based estimation is used to make the structure more flexible, using the proposed take hold of phrases the system again performs watchword controlling. In catchphrase guiding, the system removes all the keep words from the sentence. By then form a candidate question graph, to find the base partition between the segments. Least Crossing tree is used to find the partition between the segments

DYNAMIC SECURE SYSTEM FOR DETECTING AND ELIMINATING FRAUDULENCE IN CLOUD STORAGE

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Kalaivani A | Ranjith Kumar M , Sabarish M , Sai Kishore R

Abstract

When data is hosted by data owners and made available to clients, security challenges are faced. Thus, we need to audit the data to solve security challenges. Existing remote integrity checking methods can only serve for static archive data. Thus, cannot be applied to the auditing service since the data in the cloud can be dynamically updated. Hence, a dynamic System is desired to ensure that the data are correctly stored in the cloud. In this Paper, we create a monitoring tool that detects fraudulent using link analysis and checks for similar details among multiple databases will be created. As there is no interlinking between different banks database an individual can create many accounts with different identity proofs So that they can do malicious activities in the network. To avoid this we use link analysis for finding similarity link in the entire combined cloud stored database. It uses Joint Threshold Administrative Model (JTAM) for authenticating database storage and handles fault tolerance effectively using the monitoring tool

Dynamic Slicing of Service-Oriented Software

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th March 2018

Kaushik Rana | Jalpa Ramavat, Durga Prasad Mohapatra

Abstract

SoaML (Service oriented architecture Modeling Language) diagrams are the basic modeling artifacts for Service- Oriented Architecture (SOA). These SoaML models can also be used for testing Service-Oriented Software (SOS). Testing can be planned at design phase of software development life cycle. With this context, we present a novel technique to compute dynamic slices for Service-Oriented Software (SOS) based on SoaML Sequence Diagram. In our technique, we first map each message in sequence diagram with the corresponding web service messages. This mapping is observable. After that we construct an intermediate representation of SoaML sequence diagram which we called as Service-Oriented Software Dependence Graph (SOSDG) which is an intermediate representation that needs to be stored and traversed to get dynamic slice as and when web service gets executed. This SOSDG identifies data, control, intra-service and inter- service dependencies from SoaML sequence diagram and from web service execution. For a given slicing criterion our algorithm computes global dynamic slice from SOSDG and identifies the affected service. The novelty of our work lies in computation of global dynamic slice based on SOSDG, it’s dependencies induced within or across organizations and small slices

E-Bin for Waste Segregation

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th July 2017

Reji Thomas | Sukanya B, Ishwarya Lakshmi S,Sushmitha K, Archana M

Abstract

An E-BIN is a cheap, easy to use solution for a segregation system at households, so that it can be sent directly for processing. It is designed to sort the refuse into metallic waste, wet waste and dry waste. This employs parallel resonant impedance sensing mechanism to identify metallic items, and capacitive sensors to distinguish between wet and dry waste. Experimental results show that the segregation of waste into metallic, wet and dry waste has been successfully implemented using the E-BIN. In recent times, garbage disposal has become a huge cause for concern in the world. A voluminous amount of waste that is generated is disposed by means which have an adverse effect on the environment. . In India, rag pickers play an important role in the recycling of urban solid waste. Dependency on the rag-pickers can be diminished if segregation takes place at the source level. Currently there is no system of segregation of dry, wet and metallic wastes at a household level. The purpose of this project is the realization of a compact, low cost and user friendly segregation system for urban households to streamline the waste management procesS

EBV: Expectation based Validation for Vehicle-to- Vehicle Communication using 3DES

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

B.Sam | S.MuthuKumar

Abstract

In vehicular systems, communicate correspondences are basically critical, the same number of security related applications depend on single-bounce guide messages communicate to neighbor vehicles. Be that as it may, it turns into a testing issue to plan a communicate verification conspire for secure vehicle-to-vehicle communication. Particularly when an expansive number of reference points touch base in a brief span, vehicles are powerless against calculation based Denial of Service (DoS) attack that unreasonable signature check depletes their computational assets. In this paper, we propose a proficient communicate confirmation conspire called Expectation based Validation (EBV) to guard against calculation based DoS attack, as well as oppose parcel misfortunes caused by high portability of vehicles. Rather than most existing confirmation conspires, our EBV is a proficient and lightweight plan since it is principally based on symmetric cryptography. To additionally lessen the confirmation delay for some crisis applications, EBV is intended to misuse the sender vehicle's capacity to foresee future reference points ahead of time. What's more, to counteract memory-based DoS attack, EBV just stores abbreviated re-keyed Message Authentication Codes (Macintoshes) of signatures without diminishing security. We dissect the security of our plan and reproduce EBV under changing vehicular system situations. The outcomes show that EBV quick checks very nearly 99% messages with low stockpiling cost in highthickness activity situations as well as in lossy remote conditions

Ecnm: Energy Conscious Native Monitoring In Wireless Sensor Networks – Certain Exploration

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2018

M. Satheesh Kumar | P.RaviKumar

Abstract

Energy consumption is one of the leading constraints of the wireless sensor node and this limitation combined with the typical positioning of large number of nodes have added many challenges to the design and management of wireless sensor network. Wireless sensor network is at this moment receiving substantial consideration due to their unlimited potential, so in the last few years wireless sensor networks have extended attention from both the research group and actual users. A fundamental challenge in the design of WSN is to enhance the network lifetime, as each sensor node of the network is equipped with a limited power battery. Nodes are placed in a hostile or unpractical environment so very difficult to change or recharging the battery. To overcome this challenge, different methods were developed in the last few years using such techniques as network protocols, data fusion algorithms using low power, energy efficient routing, and locating optimal sink position. In this paper, we do certain exploration of Energy Conscious Native Monitoring in Sensor Networks. This deals with Sleep-Wakeup management, further sectioned into three classes On-demand, Scheduled rendezvous and Asynchronous. The result shows that the performance of the network is increased based on the lifetime of the network and packet delivery ratio

Economic Load Dispatch Problem With Valve - Point Effect using Cuckoo Search Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

MCV Suresh | M Jyothsna Devi, K Prathibha

Abstract

This paper proposes application of cuckoo search algorithm for solving economic load dispatch problem. cuckoo search algorithm is based on aggressive reproduction strategy of fascinating birds, cuckoos. The proposed approach has been examined and tested with the numerical results of economic load dispatch problems with three and five generating units with valve point loading without considering prohibited operating zones and ramp rate limits. The results of the proposed cuckoo search algorithm are compared with that of other techniques such as lambda iteration, and ABC. For both the cases, the proposed algorithm outperforms the solution reported for the existing algorithms. In addition, the promising results show the robustness, fast convergence and efficiency of the proposed technique

Effect of Varying Training Images on Performance of Face Recognition: A Study

International Journal of Engineering Research in Computer Science and Engineering, Available online 26th March 2018

Nitin Kumar | Ajay Jaiswal

Abstract

One of the problems in face recognition is the limited number of images per person available for training. In this paper, we investigate the performance of popular feature extraction methods such as Gabor wavelets, Discrete wavelet transform, Multi-view canonical correlation analysis, Linear discriminant analysis, Generalized uncorrelated linear discriminant analysis and Supervised canonical correlation analysis for face recognition with variation in the number of training images per person. The performance is measured in terms of classification accuracy. Experimental results on four publicly available datasets viz., AR, ORL, CMU-PIE and YALE demonstrate that the classification accuracy in general increases with increase in the number of training images per person with few exceptions.

Effective Approach for Inconsistent Probabilistic Graph Database

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

Burru Sivaiah | 

Abstract

The Resource Description Framework (RDF) has been generally utilized to describe resources and their connections as a part of the semantic web. The RDF graph is one of the usually utilized representations for RDF information. In any case, in many real time application such as data extraction or integration, RDF graph incorporated from various information sources may frequently contain uncertain and conflicting data (e.g., uncertain labels or that violate facts/rules), because of the lack of quality of information sources. The formalizing the RDF data by conflicting probabilistic RDF diagrams, which contain the two anomalies and uncertainty. With such a probabilistic diagram model and concentrate on a vital issue in cache based query retrieval management in conflicting probabilistic RDF charts, which recovers sub graphs from conflicting probabilistic RDF graphs that are isomorphic to a given query graph and with excellent scores. In order to efficiently answer QA-gMatch queries, the proposed cache supported to query retrieval system, which can reducing time delay between new search and cache searching time. Finally, demonstrating the efficiency and the effectiveness of the proposed approach through extensive experiments.

Effective Localization Depending on Indoor or Outdoor Context

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

Dr.S.Rajesh | R.Bharath kumar, S.Pavithran, V.Krishna kanth

Abstract

Today, there is the broad utilization of mobile applications that exploit a user’s location. Prominent uses of a location data incorporate geotagging via web-based networking media sites, driver help and route, and questioning adjacent areas of intrigue. Although, the normal client may not understand the high energy expenses of utilizing location services (to be specific the GPS) or may not settle on smart choices in the matter of when to endow or deny the location services—for instance, when indoors. As a result, a system that can make these choices for the user's sake can essentially enhance a cell phone's battery life. In this paper, we exhibit an energy dissipation inspection of the localization methods on present day Android cell phones and propose the indoor localization system that can be activated relying upon whether a user is recognized to be indoors or outdoors. With respect to our analysis and execution of our proposed system, we give exploratory outcomes—observing battery life after some time—and demonstrate that an indoor localization strategy activated by indoor or outdoor setting can enhance cell phone battery life and, possibly, location exactness

Effective Web Search using HAPIT Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

S. Gunasekaran | V.B. Ajith Raghavan, Avinash Nimmagadda, T. Harsh Singhania, R. Anandhan

Abstract

Nowadays, in IT industries several aspects of information retrieval with focus on ranking and user-friendly nature of web search engine are used. This proposed HAPIT work integrates Hubs & Authorities, Page Ranking, HITs, which has several concepts and components of an information retrieval system than existing system. This work also discusses an important theoretical model of IR and how IR systems are evaluated. This work compared with existing case studies of the available search engines and its problems in common. In future, the work is extracted with upcoming trends in search based on image search, location search

Efficient Access and Revocation System for Dynamic Groups in the Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Dr.B R Prasad Babu | Kavya.H, Nimisha Antony,Sneha.P

Abstract

Benefited from cloud computing, users can achieve an effective and economical approach for data sharing among group members in the cloud with the characters of low maintenance and little management cost. Meanwhile, we must provide security guarantees for the sharing data files since they are outsourced. Unfortunately, because of the frequent change of the membership, sharing data while providing privacy-preserving is still a challenging issue, especially for an untrusted cloud due to the collusion attack. Moreover, for existing schemes, the security of key distribution is based on the secure communication channel, however, to have such channel is a strong assumption and is difficult for practice. In this paper, we propose a secure data sharing scheme for dynamic members. First, we propose a secure way for key distribution without any secure communication channels, and the users can securely obtain their private keys from group manager. Second, our scheme can achieve fine-grained access control, any user in the group can use the source in the cloud and revoked users cannot access the cloud again after they are revoked. Third, we can protect the scheme from collusion attack, which means that revoked users cannot get the original data file even if they conspire with the untrusted cloud. In our approach, by leveraging polynomial function, we can achieve a secure user revocation scheme. Finally, our scheme can achieve fine efficiency, which means previous users need not to update their private keys for the situation either a new user joins in the group or a user is revoked from the group.

Efficient Algorithms for Mining Erasable Closed Patterns from Product Datasets

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2018

Nikhil Gumaste | Sunita Nandgave

Abstract

Discovering information from expansive informational collections to use in intelligent systems turns out to be increasingly essential in the Internet period. Pattern mining, classification, text mining, and opinion mining are the topical issues. Among them, pattern mining is a important issue. The issue of mining erasable patterns (EPs) has been proposed as a variation of frequent pattern mining for optimizing the generation plan of production factories. A few algorithms have been proposed for effectively mining EPs. Be that as it may, for extensive limit esteems, many EPs are acquired, prompting substantial memory use. In this manner, it is important to mine a consolidated portrayal of EPs. This paper first defines erasable closed patterns (ECPs), which can represent to the set of EPs without data loss. At that point, a theorem for quick deciding ECPs in view of dPidset structure is proposed and demonstrated. Next, two efficient algorithms [erasable closed patterns mining (ECPat) and dNC_Set based algorithm for erasable closed patterns mining (dNC-ECPM)] for mining ECPs in view of this theorem are proposed

Efficient and Expressive Keyword Search over Encrypted Data in the Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th April 2018

Balne Sridevi | Siddi Sravani

Abstract

In today’s world, there are many new challenges for the security of data and access control when users outsource sensitive data for sharing on third party server known as cloud servers, which are not within the same trusted domain as data owners. The existing technique used to maintain the confidentiality of personal medical record (PMR) against untrusted servers by disclosing data decryption keys only to authorized users. However, in doing so, these solutions inevitably introduce complexity in key management also burden on the data owner in data management well as in key management. The problem of simultaneously achieving security and data confidentiality and ingrainedness of access control still remains unresolved. This paper addresses this challenge 1) Key management, 2) Defining and enforcing access policies based on data attributes, and, 3) Keyword search over the encrypted data. PMR(patient medical record)system users need to deal with complicated key management problem to accomplish fine-grained access control when their PMRs are encrypted using symmetric key cryptography or asymmetric key cryptography.With our scheme multi-authority attribute based access control (MAABAC) we can reduce the key management complexity for owners and users. For this users are divided into the two domains; professional domain and personal domain. To achieve security of PMR, key management, user revocation and efficient keyword search exploiting KP-ABE, Multi-authority attribute based access control(MA-ABAC), and uniquely combining it with techniques of proxy re-encryption.

Efficient Bandwidth and Space Utilization Using Object Based Deduplication on the Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Ms. Uzma madeeha |  Smt. Shabana sultana

Abstract

As cloud computing is mostly used domain now a days, keeping the cloud limitations in mind we try to efficiently utilize the cloud resources by applying basic optimization techniques. Since text data occupy very small space compared to images or multimedia files in general, we come up with some space optimizing and de-duplicating schemes. Instead of traditional techniques of block level de-duplication, we implement a technique where the images are divided into blocks and are given unique hash id and stored in ind ex table. Now instead of sending entire object onto cloud for comparison, we send only index table to check for duplicate entries and eliminate them. This way the bandwidth is very efficiently utilized compared to traditional schemes and also optimizes space utilized in cloud storage systems.

Efficient Central Keyword Based Search Method over Encrypted Data in Cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

A.Ramya | D.Udhaya chandrika, S.Sureka, R.Vinothini

Abstract

Keyword based search is a important aspect, when searching the data in cloud. Keywords may have a certain grammatical relationship among them which reflect the importance of keywords from the user’s perspective intuitively. Proposed system has relationship among query keywords into consideration and designs a keyword weighting algorithm to show the importance of distinction of the keywords. Key word weighting algorithm accurately and efficiently localizes the central keyword that the user is interested in. We can choose the central keyword (not all keywords) of the query to extend. When a user inputs some query keywords, our scheme can effectively and accurately locate and extend the semantics of the central keyword. The returned results should be relevant to both the multiple keywords that the user inputs and the extension keyword. To calculate the relevance scores between keywords and files, we use the widely used TF-IDF rule, where TF (term frequency) denotes the frequency of a given keyword in a document and IDF (inverse document frequency) represents the importance of a keyword. When the data owner updates the dataset, the TFIDF values are also changed. To enable updating, we make a few changes in the trapdoor and index generation by inserting the IDF values into the query vector and the TF values into the index vector, respectively

Efficient Cluster based Communication with Plausibility Checks in VANET

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st July 2018

Manisha.A | Lekshmi.E, Pavithra.K, Muthumanickam.S

Abstract

In a Vehicular Ad Hoc Network (VANET), node trustworthiness in packet forwarding is required for the network to function properly. The trustworthiness of the messages is decided upon using sensors. Only if the event is thought to be prevalent, the trust opinion generator announces this event to the applications. First, a node checks whether the event is in its own detection range. If not the decision is made on either the rule of majority or on the trust levels already assigned to the nodes. In case the event is not prevalent, the proposed algorithm also sends a malicious intent information packet in order to inform the neighbour nodes about the detection of a malicious activity. The proposed algorithm is better equipped to handle such attacks. It can detect at least such attacks if the node is itself in the detection range. It eliminates attacks pertaining to false event generation completely by utilizing the plausibility of data collected through sensors as well as the trust value of the sending nodes. The cluster based attack detection and communication is contributed. This scheme applies the attacker detection mechanism only at cluster head node hence it reduces the overhead.

Efficient Document Classification using Phrases Generated by Semi-Supervised Hierarchical Latent Dirichlet Allocation

International Journal of Engineering Research in Computer Science and Engineering, Available online 18th April 2018

Rohit Agrawal | A.S. Jalal, S.C. Agarwal, Himanshu Sharma

Abstract

There are many models available for document classification like Support vector machine, neural networks and Naive Bayes classifier. These models are based on the Bag of words model. Word’s semantic meaning is not contained by such models. Meanings of the words are better represented by their occurrences and proximity of words in particular document. So, to maintain the proximity of the words, we use a “Bag of Phrases” model. Bag of phrase model is capable to differentiate the power of phrases for document classification. We proposed a novel method to separate phrases from the corpus utilizing the outstanding theme show, Semi-Supervised Hierarchical Latent Dirichlet Allocation (SSHLDA).SSHLDA integrates the phrases in vector space model for document classification. Experiment represents an efficient performance of classifiers with this Bag of Phrases model. The experimental results also show that SSHLDA is better than other related representation models.

Efficient Energy Saver for Multi-hop Wireless Sensor Communication

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th March 2018

S.Jayasri | L.Priya, V.S.Harini, Dr.S.Chakaravarthi

Abstract

A network is a series of points or nodes interconnected by communication paths. The purpose of a network is to enable sharing of files and information between multiple systems. Wireless Sensor Networks usually battery powered, and very energy constrained, the present main challenge is the energy efficiency. Now-a-day’s sensor networks are static, if anyone of the node gets failed, the entire data will be lost. Moreover, all the nodes are active during the communication between only two nodes so that remaining nodes are also using the power. Due to that, power consumption is high and sensor node’s life gets reduced. In the proposed system sensor networks are dynamic and asynchronous. The nodes are placed randomly over the area of interest and their first step is to detect their immediate neighbours. Distributed traffic flow consolidation algorithm is proposed in which only the two nodes in communication are alone active and remaining nodes are in sleep state and remain as deactivated nodes so as to reduce the power consumption.

Efficient Video Watermarking and Image Data Encryption Technique

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th July 2017

Priya Sonawane | Sujata Mane, Priya Barhalikar, Reshma Nazirkar,Prof. Aruna Verma

Abstract

Proposed technique is based on DWT, DCT FFT, and SVD. First video is converted into frames. Apply DWT on each frame that will convert it into four sub-band frequency ranges as LL, LH, HL, and HH. Apply again DWT on LL sub-band then it will divide as LL1, LH1, HL1, and HH1 sub band of LL band. After applying DWT at 2-level, apply SVD in LL1 Sub-band, DCT in LH1 and FFT in HH1 sub-band of LL band. Same process will be applied on watermark symbol/image. Embed both host frame and watermark image with some scaling factor ‘α’. For watermarked video arrange all the decomposed matrices using inverse technique. Watermarked video will be generated. To proof of ownership watermarking extraction process would be follow And for proofing robustness and security level of this watermarked technique watermarked video will be compared with original video And NCC, PSNR, BER value would be calculated

Electronic Healthcare Consultation System (E-consults)

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th December 2017

A.Kodeeswaran | Avinash V, Yuvraj K M, Divyashree R, Prof. Pradeepa C

Abstract

One of the main issues in the modern society is maintaining health and so we make it modernized and self-usable for all people. The aim of this project is to bring healthcare to people in need. People in rural areas can use this system to connect to internet from a centre and answer some questions to get some medical advice and keep their health record clean. If it is minor it suggests medicines or also gives doctor contacts. E health care is a new trend that recently comes in to use with the availability of new electronic and software applications. We are developing a web-based healthcare system in order reach every single person who is in need. A Few software users in this are Java, PHP and MySQL. A brief description of this system, a patient in need logs in through an Id they create. Then the person has to answer a series of questions related to health. The system gathers all the answers, analyses and manipulates and gives a most appropriate answer. It either gives a health issue according to it the person could go ahead or if it thinks it’s more of a serious issue it gives contacts of doctors related to it. This system also holds all the records of that particular logged in patient’s account.

Eliminating Duplicate Data in Cloud Storage with Dynamic Ownership and Security

International Journal of Engineering Research in Computer Science and Engineering, Available online 8th August 2017

Dhananjaya M K | Krishna Mohan Shah, Gaurav Bhusal, Kirti Lata,J Meghana Patel

Abstract

Ever increasing volume of back up data in cloud storage may be a vital challenge. There is a need of data management as back up windows are shrinking due to growth of information. So, to make data management scalable deduplication concept is used. It is a technique of keeping only one unique instance of data copy by detecting identical data copies and eliminating those so that it could improve storage utilization, system performance of storage system. There are different schemes introduced by people. This paper surveys these different deduplication approaches.

Embedded Based Handpicking Robot Using Memes

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th December 2017

Sai Lakshmi | T.Sravan Kumar

Abstract

The primary point of this task is to plan and build up a successful and effective hand picking robot utilizing "MEMS" sensor for the impair individuals. In this undertaking versatile impedance control is proposed for a robot teaming up with a human accomplice, within the sight of obscure movement expectation of the human accomplice and obscure robot progression. Human movement expectation is characterized by the want direction in the appendage model of the human accomplice, which is to a great degree hard to acquire considering the non-straight and time changing property of the appendage display. Neural systems are utilized to adapt to this issue, in light of which an online estimation technique is created. The evaluated movement aim is coordinated into the created impedance control, which influences the robot to take after the given target impedance shows under the proposed strategy and the robot can effectively work together with its human accomplice, which is checked careful exploratory investigations.

Emergency Packet Transmission Using Optimal Backpressure Scheduling

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th April 2018

Rajalakshmi. A  | 

Abstract

The backpressure scheduling scheme has been applied in Internet of Things, which can control the network congestion effectively and increase the network throughput. However, in large-scale Emergency Internet of Things (EIoT), emergency packets may exist because of the urgent events or situations. The traditional backpressure scheduling scheme will explore all the possible routes between the source and destination nodes that cause a superfluous long path for packets. Therefore, the end-to-end delay increases and the real-time performance of emergency packets cannot be guaranteed. To address this shortcoming, this paper proposes EABS, an event-aware backpressure scheduling scheme for EIoT. A backpressure queue model with emergency packets is first devised based on the analysis of the arrival process of different packets. Meanwhile, EABS combines the shortest path with backpressure scheme in the process of next-hop node selecting. The emergency packets are forwarded in the shortest path and avoid the network congestion according to the queue backlog difference. The extensive experiment results verify that EABS can reduce the average end-to-end delay and increase the average forwarding percentage. For the emergency packets, the real-time performance is guaranteed.

Emotion Analysis of Social Media Data

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Sonia Xylina Mashal | Kavita Asnan

Abstract

Emotion analysis in text is a trending field of research that is closely related to Sentiment analysis. With the increase of Internet connectivity, all the human interactions has moved to the social media platforms hence a lot of data can be tapped for research purposes. Emotion analysis is carried to study the writer’s state of mind. In this paper social media data is classified into five emotion categories (happy, sad, anger, fear and surprise) using supervised machine learning techniques(Naïve Bayes and Support Vector Machine).

Empowering open check for secure conveyed information in the cloud

International Journal of Engineering Research in Computer Science and Engineering, Available online 29th November 2017

Manchikatla Srikanth | 

Abstract

Distributed computing gives a sparing and productive answer for imparting information among the cloud users to low support. There is as yet a testing issue, because of the successive difference in the membership for sharing information in a multiproprietor way while saving information and character privacy from an un-put stock in cloud. Here, a safe multi-proprietor information sharing plan, named Mona, for dynamic bunches in the cloud has been proposed. Any cloud client can namelessly share information with others by giving gathering signature and dynamic communicate encryption procedures. In the interim, the capacity overhead and encryption calculation cost of the plan are autonomous with the number of renounced clients.

Encountering Evidence of a Node with Proximity based Mobile Opportunistic Social Network

International Journal of Engineering Research in Computer Science and Engineering, Available online 30th August 2017

Dr.S.Chakaravarthi | D.Saranya, T.Shanmuga Priya

Abstract

The mobile communication are usually done by proximity based mobile opportunistic social network to communicate between the nodes. Usually the nodes are communicated with their real ID to the mobile opportunistic social network (MOSN).In current method, using FaceChange that can support both anonymizing real IDs among neighbour nodes and collecting real IDbased encountering information which also support the fine grained control over the information in encountering evidence. Only when the two nodes disconnect with each other, each node forwards an encrypted encountering evidence to the encountered node to enable encountering information collection. Here, we propose, Advanced extensions for sharing real IDs with the alias name or alias ID between mutually trusted nodes of trusted authority. The efficient encountering evidence collection are done by the exchanging encountering information between the nodes after communication are done. This exchange of information by encountering evidence shows the trustworthiness and validate the use by having the time, real ID, alias name which are in the encrypted form of cipher text with some advanced encryption algorithm and with signatures. The signature with the real ID based play the role for decryption which says about the trustworthiness and validate the user. This helps to verify the trustworthiness of the mutually trusted node of trusted authority and validity of the user nodes from malicious nodes

Encryption Protocol for Securing MANET-L to S

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th July 2017

P.N. Sharath sagar reddy | Manasa.S, Anitha A, Jhansi Rani, Sheela Devi,Sowmya.A.M

Abstract

Mobile ad hoc network are a kind of wireless ad hoc network that usually has a routable networking environment on top of a link layer ad hoc network. The technological growth in the field of wireless technologies provides communication between mobile users. Any invention is to say success, only if it is useful in a meaningful manner. Wireless technology is the one that will help an emergency needy like in any natural disaster, emergency rescue operations, military battle-field etc. With the advent of Mobile Ad-Hoc Networks, an immediate self-configuring network can be created. Being an open network, security is the main concern for MANETs. In such situations to protect the confidentiality of the message to be transmitted, cryptography is the one of the solution. The process of converting the original data into a secret form is known as cryptography. It hides the actual information and sends the encrypted message. At the destination end, the message can be recovered by using decryption. Here we are proposing a new encryption technique named as Letter-Shape Encryption. This method exchanges different shapes for letters in a message to be transmitted. This approach is safe against man in middle attacks.

Energetic Data Mining Law To Identify Frequenty Item Sets over Huge Database via IFCM

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st January 2018

Pragathi Vulpala | 

Abstract

Association Rule Mining is one of the most important tasks in data mining industry, especially in terms of huge database handling strategies; this association rule mining plays a vital role to deal with the commercial and non-commercial data. The main process of association rule mining is to identify the frequent items from the itemset. In past analysis there are several methodologies available to identify the frequent items over the inputting itemset. Most of the researchers and developers commonly used Apriori' and Frequent Pattern-Tree algorithms to identify the frequent items over the itemset. Generally Apriori investigates multiple number of iterations over the huge databases to identify the frequent items over the inputting itemset, globally Apriori law follows the candidate introduction process for identifying the frequent items. The approach of Frequent Pattern-Tree algorithm is different from Apriori law, it investigates the database twice without' includes the generation of candidates. In this proposed system, a new algorithm is proposed to improve the time constraint and accuracy levels of identifying the frequent items over the large itemset database, called Intelligent Frequency Count Model [IFCM]. This algorithm of IFCM uses the scanning method different from the past two terminologies such as multiple scanning and twice scanning schemes, instead of these two concepts, the IFCM performs scanning with one time as well as it belongs with the candidate generation process. So, this methodology is also termed as Hybrid Intelligent Frequency Count Model [HIFCM]. For all the proposed logic, clearly shows that the IFCM provides better results compare to Apriori and Frequent Pattern-Tree process.

Energy Balance of Structural System with Load Sliding

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

Ryo Sasaki | Kuniaki Yamagishi

Abstract

Although the seismic response reduction effect with load sliding (slide effect) is not considered in general structural design, consideration of this effect may contribute to a rational structural design. In the present study, in order to obtain the basic characteristics of the slide effect for an elastoplastic frame, shaking table tests were carried out on a single-story elastoplastic steel frame while varying certain parameters. An analytical model considering the slide effect was constructed, and seismic response analyses of the parameters were also conducted in order to obtain the energy balance in the system.

Energy Efficiency Using Load Balanced Clustering - Dual Data Uploading In Wireless Sensor Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

D.Iswarya | G.Rajeswari

Abstract

In mobile wireless networks, the developing vicinity based applications have prompted the requirement for very compelling and vitality productive neighbor disclosure conventions. The Primary worry in a Wireless Sensor Network is Energy utilization. The primary issue in the system is the point at which the information is sent from hub to sink, the information will be lost because of low vitality of node.The structure utilizes dispersed load adjusted grouping and double information transferring, which is alluded to as LBC-DDU. It comprises of three-layer (I) sensor layer (ii) group head layer, and (iii) portable gatherer (called SenCar layer). At the sensor layer, a disseminated stack adjusted grouping (LBC) calculation is proposed for sensors to self-arrange themselves into bunches. At the bunch head layer, the between group transmission extend is deliberately ensured the network among the bunches. Numerous group heads inside a bunch participate with each other to perform vitality sparing between bunch correspondences

Energy Saving Strategy in Cognitive Radio Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

S.Swathy | Y.Vanmathi,G.Sindhiya, J. Daphney Joann

Abstract

In recent years, the development of intellectual, adaptive wireless devices termed cognitive radios, composed with the introduction of secondary spectrum licensing, has led to a new hypothesis in transportations: cognitive networks. Cognitive networks are wireless networks that consist of several types of users: often a primary user (the primary license-holder of a spectrum band) and secondary users (cognitive radios). These cognitive users employ their cognitive abilities to communicate without spoiling the primary users. The study of cognitive networks is comparatively new and many queries are yet to be responded. In this article we best part some of the recent information theoretic limits, models, and design of these auspicious networks.

Energy Saving Through Home Automation and Data Mining Technique

International Journal of Engineering Research in Computer Science and Engineering, Available online 24th October 2017

Rahul Ramesh Gaikwad | Amol Joglekar

Abstract

we build on electricity to power our appliances, and electronic devices in our home. As we consume more electricity in our homes, our electricity bills rise. Efficient products and energy-saving strategies can help us to save money and energy at home. Therefore there is a need of home automation system which would be a very good choice for energy saving and comfort. In the proposed paper a home automation system is proposed using and integration of Arduino UNO, Raspberry Pi 3 and sensors. The model will be developed using the concepts of data-mining techniques for the analysis so that one can cut the cost of the electricity bill. The system has features like computing, control, and connectivity. The integration of the system with an Android app makes it possible to analyze the data and saves the electrical energy

Engrafting Data Using RDH by Reserving Room before Encryption

International Journal of Engineering Research in Computer Science and Engineering, Available online 17th April 2018

G.Abinaya | Deepanshu Garg, Sarthak Kabra, Shivani Priya, Akanksha Priya

Abstract

There is also a large number of tasks on data covering in the engrafted field. Most of the work on RDH concentrates on the encryption and decryption of the data. This method is by reserving a room before encryption using traditional RDH a technique, and thus it is simple for the data hider to reversible engrafts the data in the engrafted image. The method that we are proposing can accomplish real reversible-ness, and extraction of data and recovery of the picture are free of any fault. Thus the data hider can profit from the additional space Released out in the prior stage to make data hiding method smooth. The stated scheme can take benefit of all regular RDH procedures for definite pictures. It obtains great description without loss of perfect privacy. Furthermore, this new method can obtain actual reversibility, separate data wrenching and an excellent growth on the quality of marked decrypted Pictures. Testing showed that this scheme can secure more than ten times as extensive payloads for the same picture quality as the prior schemes. The data extraction and image recovery can be achieved by examining the block smoothness. After encrypting the entire data of an uncompressed image by a stream cipher, the additional data can be embedded into the image by modifying a small dimension of encrypted data. With an encrypted image containing additional data, first we decrypt it using the encryption solution, and the decrypted version is similar to the original picture. According to the data-hiding key, with the aid of spatial similarity in a natural image, the embedded data can be successfully obtained and the original image can be perfectly revived.

Enhanced Active Feature Selection method for Object Tracking

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

Sandeep G.S | Sunitha M R , Niranjan Murthy C

Abstract

The key idea of Adaptive tracking is how to train an online discriminative classifier which can well separate object from its local background. The classifier is incrementally updated using positive and negative samples extracted from the current frame around the detected object location. If the detection is less accurate thereby leading to visual drift. Recently, the multiple instances learning (MIL) based tracker has been proposed to solve these problems to some degree. It puts samples into the positive and negative bags, and then selects some features with an online boosting method via maximizing the bag likelihood function. Finally, the selected features are combined for classification. In MIL tracker, the features are selected by a likelihood function, which can be less informative to tell the target from complex background. Motivated by the active learning method, in this paper we propose an enhanced active feature selection approach which is able to select more informative features than MIL tracker by using the Fisher information criterion to measure the uncertainty of classification model. More specifically, we propose an online boosting feature selection approach via optimizing the Fisher information criterion, which can yield more robust and efficient real-time object tracking performance. Experimental evaluations on challenging sequences demonstrate the efficiency, accuracy and robustness of the proposed tracker in comparison with state-of-the-arts.

Enhanced Forensics Enabled Cloud through Secured Logging as a Service

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th August 2017

Ms.D.Gomathi | Dr.B.Mukunthan

Abstract

The principle goal of this venture is to build up a secured logging as an administration in cloud engineering. So in the proposed strategy, security and safeguarding techniques are upgraded. The secured logging contains six noteworthy functionalities to guarantee more securities: Correctness, Confidentiality, information logs, Privacy, Preservation and VPS (Virtual intermediary server). The accuracy manages rightness information of the genuine history. Classification manages delicate data not showing amid seek. Information logs manages the information history for distinguishing fitting clients. Security conspire manages document connecting and information get to history. Safeguarding manages upgraded shading code. Lastly VPS manages the intermediary server for virtual information get to. The usage of the above given strategies are appeared in any condition, which manages enormous number of information with different clients. There are very little contrast amongst programmers and interlopers in the cloud design. Programmers are from different systems mean while interlopers are from same systems. Programmers can be kept away from and gatecrashers are can't be dodged. This is on account of gatecrashers may know about the system where they will interrupt. With the goal that secured logging as an administration is much imperative for all sort of cloud server condition so as to give appropriate login to approved client and triggers out the unapproved clients.

Enhanced Indexing and Scraping for Educational Search Engine using Web Usage Mining

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd May 2018

Ramkrishna R. Gaikwad | Mansi Bhonsle

Abstract

Nowadays the growth of World Wide Web has better a lot with more assumption. Large amount of text, multimedia files, images website documents were present in the web and it is still increasing in its forms. Education Search engine has become an important daily network application tool to search information. Data mining is the form of extracting data present in the internet. We propose an Education Search Engine in two-stage technique, namely Smart Crawler, for efficient gathering deep web interfaces. To achieve more accurate results for a focused crawl, Smart Crawler ranks websites links to prioritize highly relevant result in websites link rankings. In the second stage, Web Usages mining in web scraping is a method for extracting textual characters from screens so that they could be analyzed. Web scraping is the process of collecting information from the World Wide Web. The results showed that the smart crawler and scarper can realize the high-efficient and flexible data collection function, and laid the foundation for Web data mining. This efficiently retrieves web data mining interface from large-scale sites and achieves higher.

Enhanced Multi-Keyword Ranked Search Manipulations via Cloud Virtualization

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

S.Uma Maheswari | p.priya ponnusamy, dr.r.vidhyapriya

Abstract

The enhancement and the fame of cloud computing are increasing nowadays which is driving the data owners to keep their personal and professional data on public cloud servers With the help of data outsourcing the organizations can provide reliable and efficient services to their users. The other advantage of outsourcing the data over cloud servers is for high benefit and lesser cost in managing the data and the data can be accessed from anywhere and at any time. However, for privacy concerns, the data that are highly sensitive should be encrypted before outsourcing. Taking into consideration the huge amount of data users and files that are present in the cloud, it is important that multiple keywords should be allowed in the searching request and retrieve the files relevant to those keywords. There are some methods and solutions offered to provide privacy and security for the data over the cloud server. However, the data that are sensitive should be encrypted and stored before outsourcing. In this paper, a secure scheme called the enhanced multi-keyword ranked search is presented. In the proposed scheme the search takes place as content based search along with ranking. Based on the content, data is searched and retrieved and then the rank is applied. During searching, attacks might be done by SQL injection to dump the database contents by the unauthorized users or attackers. In this project SQL injection is not allowed. The SQL parameterization technique is used to prove that SQL injection is not possible

Enhanced Security Technique of Wireless Sensor Network using Hybrid Cryptography

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th January 2018

K.Sethu Selvam | Dr.S.P.Rajagopalan

Abstract

Wireless sensor network (WSN) is a collection of a sensor which is deployed remotely to sense the complicated area. It is used in various fields like military surveillance, disaster management and etc. Security is the most vital in the network. Cryptography plays an important role in network security. The traditional cryptographic technique can’t be applied to wireless sensor network because of its resource limitation. The proposed model is a hybrid cryptography which is a combination of both symmetric and asymmetric cryptographic techniques. The key is generated with the help of ECC and securely transmitted through ECDH protocol. Confidentiality of data is done through AES, Blowfish and ECC. Hashing technique MD5 is used for Integrity of data. It provides high security in an efficient manner. It requires less memory, energy and computation time.

Enhancement of Digital Images Using Fir Filter

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

Gurjinder Kaur | Rajneesh Kansal

Abstract

Underwater image pre-processing is absolutely necessary due to the quality of images captured under water. When capture such images, quality of images degrade due to many factors like ripples in water, lack of availability of light, organic matter dissolved in water etc and also such images are captured from a very small distance , so the images must be pre-processed before applying any kind of operation on these images. Different filtering techniques are available in the literature for pre-processing of underwater images. The filters used normally improve the image quality, suppress the noise, preserves the edges in an image, enhance and smoothen the image. In this paper comparative analysis of various Filters for such underwater images is presented.

Enhancement of Image Steganography using a Dynamic Symmetric Key by Arithmetic Coding

International Journal of Engineering Research in Computer Science and Engineering, Available online 21st December 2017

Wa'el Ibrahim A. Almazaydeh | H. S. Sheshadri, S.K. Padma

Abstract

This paper is an enhancement of the image Steganography using a dynamic symmetric key algorithm by applying it on the colored images and using the Arithmetic coding algorithm. However, the Peak Signal to Noise Ration (PSNR) algorithm has been used to compare the results.

Enhancement of Security in Cryptographic Systems by Improving Randomness

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th October 2017

Antu Annam Thomas |  Varghese Paul

Abstract

Randomness plays an important role in many of the applications where natural selection process needs to be simulated. The term randomness also finds an important and irreplaceable role in the area of data security and cryptography. There are various traditional random number generators. Multiplicative Congruential Generator (MCG) is one among them. The randomness of the generated sequence is enhanced by the concept of nesting introduced into the algorithm. In this work the traditional MCG is compared with Nested Multiplicative Congruential Generator(NMCG) using statistical and graphical analysis techniques. The most important advantage of NMCG is that the period of the generated sequence is infinity. In the case of MCG the period depends upon the value of multiplicand. The analysis performed also concludes that NMCG is a better random number generator when compared to MC.

Enhancing Map Reduce Performance in Heterogeneous Distributed Environment

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th September 2017

Suyash Mishra | Dr. Anuranjan Mishra

Abstract

Now a day’s size of the data used in today’s enterprises worlds has been growing at exponential rates day by day. This had triggered need to process and analyze the large volumes of data for business decision making quickly as well. MapReduce is considered as a core-processing engine of Hadoop, which is prominently used to cater continuously increasing demands on computing resources imposed by massive data sets. Highly scalable feature of MapReduce processing, allows parallel and distributed processing on multiple computing nodes. This paper talks about various scheduling methodologies and most appropriate one can be used for improving MapReduce processing .Also tried to identify scheduling methods scaling or processing limitations along with the situations wherein they can be best suited. Map Reduce is used majorly for short jobs, which eventually require low response time. The current Hadoop implementation assumes underline computing nodes in a cluster are homogeneous, have same processing capability and memory. Hadoop’s scheduler suffers from severe performance degradation in heterogeneous environments. In heterogeneous environment, Longest Approximate Time to End (LATE) scheduling can be most efficient in comparison to other scheduling .It has been seen in various studies that LATE has improved Hadoop response times by approximately two times in a clusters.

Enhancing the Network Lifetime and Storage Utilization Using Distributed Clone Detection in Wireless Networks

International Journal of Engineering Research in Computer Science and Engineering, Available online 24th May 2018

Choudary Swetha | M Pragathi

Abstract

In this paper, we support an energy-efficient location-conscious clone detection protocol in compactly deployed WSNs that may assurance successful clone assault detection and maintain exceptional network lifetime. In particular, we make the most the province facts of sensors and randomly pick witnesses placed in a ring region to confirm the legitimacy of sensors and to certificate detected clone attacks. The ring structure helps electricity-efficient records forwarding along the path in the direction of the witnesses and the sink. We tentatively prove that the anticipated protocol can obtain one hundred percent clone detection probability with trustful witnesses. In addition, we develop the work by way of reading the clone detection explain with untruthful witnesses and show that the clone detection prospect still strategies 98 percentage when 10 percentages of witnesses are compromised. furthermore, in maximum current clone detection protocols with random witness selection proposal, the required buffer garage of sensors is usually dependent on the node density, i.e., 0 √n, at the same time as in our projected protocol, the specified buffer garage of sensors is impartial of n but a characteristic of The hop period of the network radius h, i.e., 0(h). Widespread simulations display that our planned protocol can accomplish long network lifetime by using efficiently distribute the site visitor’s load crosswise the network.

Enhancing the Privacy Preserving Data Mining Techniques by using Anatomisation with Slicing Approach for Multiple Susceptible Attributes without Loss of Accuracy

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th November 2017

V.K.Saxena | Shashank Pushkar

Abstract

A gigantic quantity of individual health information is accessible in modern decades and dispositioning of any part of this information establishes a huge risk in the field of healthcare. Enduring anonymization methods are only appropriate for single susceptible and low down dimensional data to remain with privacy particularly like generalization and bucketization. We propose an anonymization technique that is an amalgamation of the betterment of anatomization and improved slicing approach observing to the principle of k-anonymity and l-diversity for the reason of dealing with high dimensional data along with multiple susceptible data. The anatomization approach disrupts the correlation detected between the quasi-identifier attributes and susceptible attributes (SA) and turnouts’ two different tables with non-overlapping attributes. Hence, experimental outcomes specify that the suggested method can preserve the privacy of data with various sensitive attributes. The anatomization approach reduces the loss of information and slicing algorithm advices in the correlation preservation and usefulness which gives output in sinking the data dimensionality and information deficiency.

Ensemble Learning Network Traffic model for misuse and anomaly detection

International Journal of Engineering Research in Computer Science and Engineering, Available online 3rd May 2018

Jayashree Patil | Sarita Patil

Abstract

System security is of essential part now days for huge organizations. The Intrusion Detection frameworks (IDS) are getting to be irreplaceable for successful assurance against assaults that are continually changing in size and intricacy. With information honesty, privacy and accessibility, they must be solid, simple to oversee and with low upkeep cost. Different adjustments are being connected to IDS consistently to recognize new assaults and handle them. This paper proposes a semisupervised model based on combination of ensemble classification for network traffic anomaly detection. As most IDS try to perform their task in real time but their performance hinders as they undergo different level of analysis or their reaction to limit the damage of some intrusions by terminating the network connection, a real time is not always achieved. In this research, we are going to implement intrusion detection system (IDS) using anomaly intrusion detection method for misuse as well anomaly detection. The proposed framework is used a classifier, whose information base is demonstrated as a administer, for example, "ifthen" and enhanced by a hereditary calculation. The system is tried on the benchmark KDD'99, NSL KDD and ISCX intrusion dataset and contrasted and other existing methods accessible in the writing. The outcomes are empowering and show the advantages of the proposed approach.

ESPY: A Work Monitoring Solution by Facility Mapping of Smart Cities

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Tejashree S. Dhengre | Rishika S. Dubey, Gopal R. Mishra,Swapnil M. Meshram

Abstract

As per the concept of Smart City to provide efficient urban mobility and affordable housing facility, a lot of construction work has begun at different geographical points to turn this concept into reality. Work monitoring of Construction Company by higher government authorities is necessary to get work done quickly, get daily updates and prevent corruption. For this work Construction Company has Site supervisors who provide weekly or monthly updates but process is manual and time consuming. Also, with lots of Construction going on, citizens face severe problems which requires immediate attention of officials. To have an easy interface between Site Supervisors and higher officials of government and also between common people and government we aim to create an Android Application named “eSPY” which will give facility to Site supervisors to daily report the work progress to authority online or offline along with necessary proofs such as geo-tagged image of work done that day, details of expenditure etc. Citizens can use the App to register complaints regarding construction work at any location causing problems. On the other end, a website will be provided to officials for receiving proper report in specific pre-determined format for saving time and quick action. Officials can view received geo-tagged image or can establish a real time video connection to quickly monitor work at various sites. For establishing the connection between Android application and website, WebRTC as technology is used which will provide easy connectivity, less data and efficient offline support

Evaluating Machine Learning Algorithm on Cross- Site Scripting (XSS) Security Vulnerabilities in Web Applications

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th August 2017

Kishan Babu T D | Dr. Jayanna H S

Abstract

In this paper, the prediction and analysis of cross-site scripting (XSS) security vulnerabilities in web application’s source code is demonstrated. Cross-site scripting (XSS) is a security vulnerability that affects the web applications and it occurs due to improper or lack of sanitization of user inputs. There is no single solution that can effectively mitigate XSS attacks. More research is needed in the area of vulnerability removal from the source code of the applications before deployment. Security inspection and testing require experts in security who think like an attacker and locating vulnerable code locations is a challenging task. Alternatively, there are also vulnerability prediction approaches based on machine learning techniques which showed that static code attributes such as code complexity measures are cheap and useful predictors. The main focus is on prediction of XSS vulnerabilities and extracts the relevant features to classify vulnerable source code file from benign one. Attack prevention and vulnerability detection are the areas focused in this study

Evidence forwarding of a Node in Mobile Opportunistic Social Network with proximity

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th May 2018

Dr.S.Chakaravarthi | D.Saranya

Abstract

Usually, the sending of messages or communication between the nodes are done by proximity based mobile opportunistic social network. When sending the messages from one to another there is the chance of packet loss i.e missing of information. This is usually happened by communication between the nodes are done by real id . In current method, the prevention of message or information are done by FaceChange i.e changing of real id to alias name or id. Here, we use advance method of not only preventing the information while communication but also check the trustworthy ness of the third party authority and verify whether the communication are done between the real node are alias node. This is mainly effective in group communication where we cannot check that the near by node are real node or malicious node or attacker node. Once when we come to know that the attacker node is active it gives the warning or kind of information that which node is attacker node to all other trusted node or communicating node

Evolution of Internet Communication up to IoT

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th December 2017

Vaibhav Bharati | Tanvi Chavan

Abstract

In the current era of connectivity, Internet is playing the major role. This connectivity via internet is radically evolving by creating diverse methodologies. Among all these methodologies of connectivity Internet of Things (IoT) is one of the evolved Internet communications between objects. Objects can be living or non-living things. IoT can flawlessly connect the every real object in world and space media embedded with variety of sensors as per requirement. A large number of Internet connected objects will produce and transfers huge amount of data to make daily life additionally comfortable by providing smart services. This paper includes survey of evolution of various methodologies of the internet communication from wired to wireless to smart communication using IoT. It also focuses on importance of IoT for making life of human being more convenient along with features of technology, issues and future trends in brief. Doubtless, the IoT becomes most popular internet communication methodology in the coming days as it has latent to fetch out many benefits.

Evolving Machine Intelligence toward tomorrow’s Intelligent Network Traffic Control Systems

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th May 2018

Nikitha G | Amitha Sai G, Pooja KP, Manjula Patil, Dr B Sreepathi

Abstract

An effective traffic signal management project that allows for managing 4 way traffic signal management system. The system consists of 4 signals corresponding to each road. We here propose a density based traffic signal scheduling algorithm. The system is designed to manage traffic signal timings based on the density of traffic on its corresponding road. The system represents the traffic strength of a road graphically using traffic judgments. By measuring the traffic lined up on a particular road the signal timings are adjusted to let that particular way clear out and then the next populated one. The entire system works according to an algorithm that allows for smooth and efficient traffic flow across all four ways. It also consists of an emergency override that allows traffic authorities to remotely let go a particular signal in case an ambulance or important vehicle arrives on that way.

Exploring Big Data Analytics for Satellite Imagery Data Using Hadoop Technique

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Ch.Rajya Lakshmi | Dr.K.RammohanRao, Dr.R.RajeswaraRao

Abstract

Now a days Big Data has defined very large amount of data, it includes both structured and unstructured format. The structured data analyzing is very easy task but an unstructured data analyzing is very difficult that can be produced by an individuals (eg. Twitter data)it also gathered by sensors(eg. satellites, videos) which can range from giga bytes, tera bytes and peta bytes. Big Data entitles more and more data that can be analyzed through various analyzing techniques. If the right analytic method is applied to unstructured datasets we can easily analyze and classifying various patterns, But at the same time will consider efficiency and scale of Data. In the real world the major issue of Big Data is early warning predictions is the use of Satellite imagery and Radar Sensor data. In the Satellite imagery data could reach a million derived spatial objects such data querying ,managing and various image patterns classification is very difficult task. So a proper architecture should be proposed to gain knowledge about Big Data for analyzing various Satellite imagery patterns classifications with hadoop technology. In the proposed architecture differentiate various classification methods for various satellite imagery pattern classification methods and also proposing Google’s Map reduce C4.5 Algorithm for effective classification to increase performance of patterns classification and increasingly large volume of Data sets to results both time efficiency and scalabilty. This research is carrying based on NASA Satellite data and Twitter data and also in weather forecasting.

Extending the functionality of Android Clipboard Manager

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Amol D. Gaikwad | Pratik R. Tambekar, Pankaj R. Hatwar,Swapnil R. Ramtekkar

Abstract

Clipboard is a software facility used for short-term data storage and/or data transfer between documents or applications, via Copy and Paste operations. The standard built in clipboard of android operating system store only one item at a time so that it provide speedy access to such content normally android clipboard has disadvantages firstly it store only one item at a time and secondly when you turn off system it clears memory. My goal is to eradicate the problems of standard clipboard of Android OS to developed such App that it contains buffer which is located on System Memory and it is permanent storage need not worry about lost of data. Whatever user copy data that copied is maintained or stored in their respective buffer. When I am going to perform paste operation it will populate all respective copied buffer data you have to just select the desired data that you want to paste it save user time and increase the efficiency.

Extraction Of Object In Multiviews Based On LDA Approach

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2017

Geeravani | Dr. P.Mohanaiah

Abstract

Linear Discriminant Analysis (LDA) is most commonly used as dimensionality reduction technique in the pre-processing step for pattern-classification and machine learning applications. The goal is to project a dataset onto a lower-dimensional space with good class-separability in order avoid over fitting (―curse of dimensionality‖) and also reduce computational costs. Ronald A. Fisher formulated the Linear Discriminant in 1936, and it also has some practical uses as classifier. The original Linear discriminant was described for a 2-class problem, and it was then later generalized as ―multi-class Linear Discriminant Analysis‖ or ―Multiple Discriminant Analysis‖ by C. R. Rao in 1948 The general LDA approach is very similar to a Principal Component Analysis (for more information about the PCA, see the previous article, but in addition to finding the component axes that maximize the variance of our data (PCA), we are additionally interested in the axes that maximize the separation between multiple classes (LDA). So, in a nutshell, often the goal of an LDA is to project a feature space (a dataset n-dimensional samples) onto a smaller subspace kk (where k≤n−1k≤n−1) while maintaining the class-discriminatory information. In general, dimensionality reduction does not only help reducing computational costs for a given classification task, but it can also be helpful to avoid over fitting by minimizing the error in parameter estimation (―curse of dimensionality‖).

Extraction of Superficial and Volumetric Features from 3D Color Images

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th March 2018

A.Arun Kumar | N.Devender

Abstract

The three-D objects in the physical structure connected computer Games area unit hollow plane figure meshes with textures applied to them. On the other side, volumetric data illustration not solely stores the outer surface options for example visualization of 3D MRI/CT known ledge is all about within the elements too. This needs additional video memory. Most of the particular 3D volume data generation particularly by MRI scanners area unit grey-level pictures. In this paper proposed a technique to make colours for grey images.

Extraction of Text from an Image and its Language Translation Using OCR

International Journal of Engineering Research in Computer Science and Engineering, Available online 14th July 2017

G.R.Hemalakshmi | M.Sakthimanimala, J.Salai Ani Muthu

Abstract

In our day to day life the people are facing many problems in understand the languages. For example, if the people move from one state to the other they don’t understand their language at that time this Mobile Application will help them. Existing system, having a separate application for each and every process like camera, Google translator and Optical Character Recognition(OCR) text scanner. But, people expect the application consists of all the three facilities together. So this proposed application provides a new idea to the people to translate the other language text into their known language. This application contains three steps. 1.Take a photo image of the unknown language text which you want to translate(either handwritten or printed material), 2.Tessaract is an open source Optical Character Recognition (OCR) technology, which is used to extract the text from the image then Google API and Bing API is used for translation of language. 3.The translated text is generated in PDF format.

Face Detection and Recognition from Live Video Stream

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd February 2018

Dr. S Govinda Rao, | G Anil Kumar, Y Manoj Kumar

Abstract

Face recognition” is a very active area in the computer vision and Biometric fields as it has been studied vigorously for 25 years and is finally producing applications in security, robotics, human-computer interfaces, digital cameras, and entertainment. ”Face recognition” generally involves two stages. Face detection, where a photo is searched to find the related face, then image processing cleans up the facial image for easier recognition. Since 2002, Face Detection can be performed fairly reliably such as openCV face detector, working in roughly 90-95% of clear photos of a person looking forward at the camera.The OpenCV libraries make it fairly easy to detect a frontal face new in an image or from a video feed. Face Recognition is the process, where that detected and processed face is compared to a database of known faces to decide who that person is. Under face recognition, we can then compare the detected image to a database of real identity of that person

Facebook Vs Linkedin: A Text Mining Approach for Job Preference

International Journal of Engineering Research in Computer Science and Engineering, Available online 6th June 2018

Sarita. Byagar | Dr. Anil Jadhav

Abstract

Social media has become the catchword as every individual is directly or indirectly hooked to these sites. The topical growth of online social networks has enabled job seekers to stay connected and find anticipated jobs through these sites. The amount of textual data generated on these sites is massive which can be mined to find what information they focus on and also discover which site is ideal to the user for job search or job related bustle. The paper is organized as follows: Section 1 is the introduction of social media, social media for jobs and data mining of social media. Section 2 gives a brief review of text mining, Section 3 explains the research questions explored in this paper, the context of the study, Section 4 details its methodological approach i.e procedures. Section 5 discusses the results. Section 6 concludes discussion and conclusion.

Facial Age Estimation with Age Difference

International Journal of Engineering Research in Computer Science and Engineering, Available online 2nd May 2018

Ramasubramanian.SA | Derick Immanuvel.F, Gowtham.J, Bharat Kumar, Sahaya Sakila.V

Abstract

Estimating human age by automation is required mainly for security purposes. But the system getting developed won’t help with the correct output of ages. For increasing the accuracy, the system is developed with Convolutional Neural Networks and estimating KULLBACK LEIBLER DIVERGENCE for finding the entropy loss to enhance the output efficiency. Thus the system is designed for better accuracy with the formulas driven for finding the mean difference between images. It will help to overcome the age difference of the images without age labels and also train a large number of images without labels.

Facial Emotion Detection Based on the Features of Mouth Regions

International Journal of Engineering Research in Computer Science and Engineering, Available online 13th April 2018

G.Kalaivani | Dr.K.Krishnaveni

Abstract

Emotion is a mental state which involves the lot of behaviors, actions, thoughts, and feelings. Emotion recognition is the process of identifying the human emotion, most typically from facial expressions. Different types of facial expressions are Joy, Sadness, Fear, Disgust, Surprise, and Anger. The eyes and mouth (lip) movements will generally exhibit the emotions. The main aim of this research work is to propose a technique to detect the facial emotion from the features of the mouth region. The facial images with different emotions are captured, preprocessed and mouth regions are detected by Viola-Jones algorithm and extracted by means of Bounding Box method. Then Edge detection, region filling, and morphological algorithms are proposed to extract the lips and filled mouth region for which the area of the region is calculated with the help of the number of extracted mouth region pixels. Then Data mining Decision Tree Classifier is applied to classify the emotions based on the area values. The input images of various expressions are taken, results are analyzed and their performances are evaluated

Facial Features Detection Using Regression

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th April 2018

G.Radha Priyadharsini | Dr.K.Krishnaveni

Abstract

Facial Feature Detection is one of the essential techniques in face recognition, face modeling, head pose estimation and facial expression recognition. Emotions may be recognized through the facial features such as eyes, nose, lip movements etc. The objective of the proposed work is to detect the face with these facial features. Cascade Object Detector is initially proposed to identify the face region from the input image. Then Regression based face alignment algorithm is employed for the feature point alignment and registration. By means of the scale-invariant feature transform and regression results, the landmark points for the facial features are estimated inside the template. Delaunay method is used to construct a triangulation that can be utilized to draw the template with the associated points. Finally the facial features are detected along with the boundary points. The WSEFEPv101lo dataset is used for evaluation and analysis. Out of 62 facial images, the facial features of 48 images are accurately detected and due to misalignment of facial landmark points due to facial emotions, 14 images are not detected correctly

Farmer’s Intel

International Journal of Engineering Research in Computer Science and Engineering, Available online 15th May 2018

Mohan Kumara V | Sampath Kumar R, Anusha, Venkatesh, Venkatesh

Abstract

The aim of the system is to develop a system (Application), to help in the field of agriculture. The main objective of this app is to establish interaction between many formers, formers – students or any other agri experts those are interested in solving formers problems. This site acts as best media for direct communication between former and experts.

Fault Tolerance Approach in Distributed Sensor Networks using Genetic Algorithm

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th August 2017

Anagha Nanoti | Prof. R. K. Krishna

Abstract

Nature has always been a great source of inspiration to all kind of researches so far. Genetic Algorithms (GA) were invented to mimic some of processes observed in natural evolution by John Holland in 1970s. GA simulates “survival of fittest” among individuals over consecutive generation for solving optimization problems. In this paper considering Fault tolerance as one of the important issues in Distributed Sensor Networks, the Genetic Algorithm has been proven to be the best. The Distributed Sensor Networks are interconnection of tiny, low cost, low-powered and multi-functional sensor nodes. However these DSNs (sensors) are highly prone to malicious attacks, faults due to energy depletion and sometimes due to link failure. When energy in some of the sensor nodes reduces or gets depleted the implementation of Genetic Algorithm have proven to be the masterpiece for development of healthier network than any other algorithms. As we know prevention is better than cure. This paper aims to prevent the sensor nodes from occurring failure. Thus the main objective of the current work is to generate energy efficient DSNs and a way towards fault tolerance.

Feature Vectors Generation for Mammogram Classification based on 2-D GLCM matrix

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

Shehnaz Begum Sk | T. K. Mishra

Abstract

Earlier is the diagnosis of a disease, better is the rate of recovery. So far as the fatal disease like breast cancer is concerned, it’s early diagnosis may lead to improve the rate of care and thereby survival of a patient. Generally, breast cancer detection and analysis starts from capturing the Mammogram of the effected breast region. In this paper, an automated diagnosis scheme has been proposed for detecting the presence/ absence of breast cancer from such mammograms. Suitable pre-processing is applied to input mammogram images. For the feature extraction, the gray level co-occurrence matrix is framed out of the preprocessed image. The AdaBoost technique has been used for the purpose of feature selection. Classification is carried out with the help of the state-of-the-art Random-forest classifier. For the purpose of validation, the mammography image analysis society (MIAS) database has been taken into consideration. Satisfactory classification rate of 94% is achieved through the proposed scheme.

FiDoop-DP: An Efficient Data Mining Technique on Heterogeneous Clusters

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th September 2017

Juturu Chandana | 

Abstract

Data mining is the analysis step of the “Knowledge discovery in data bases process” [1]. Actually, it is very hard to mine item-sets which are frequently used in the transactions. To identify frequently used item-sets, parallel algorithms which are used for mining were developed. These parallel algorithms were developed to balance the data and to maintain equal partitions of data, among a group of nodes which are to be computed. Because of redundant transactions, there is a significant performance problem of parallel frequent item-sets mining. Therefore, a data partitioning technique has been developed. FiDoop-DP is a kind of data partitioning method which is used to divide the data based on item-sets of the transaction which are brought by the clients or customers. To know better about frequent item-sets i.e., products which are regularly sold together, an algorithm is used for time consumption while running data which is extremely large. This algorithm is named as Equivalence Class clustering and Lattice Traversal algorithm (ECLAT). This ECLAT algorithm is combined with the Map-Reduce functionality, and then it gives better solutions within small amount of time. At the same time ECLAT is combined with Local sensitive hashing technique for better performance of items which are present at locally present in the data nodes. By combining those two techniques, the performance of FiDoop increases. This is known by the time taken to mine frequent item-sets. The main goal of this paper is to mine the itemsets which are prominently used or sold in the market by that it can increase the sales of those products.

Flexibility of the Natural Source of Attribute Based Encryption Based on the Network

International Journal of Engineering Research in Computer Science and Engineering, Available online 4th May 2018

C.Selvalakshmi | M.Karthikeyan

Abstract

Attribute based encryption (ABE) is a famous cryptographic generation to protect the security of users’ data. However, the decryption cost and cipher text size restriction the utility of ABE in exercise. For most present ABE schemes, the decryption price and cipher text size develop linearly with the complexity of access structure. This is unwanted to the gadgets with restrained computing functionality and garage area. Outsourced decryption is taken into consideration as a possible method to lessen the consumer's decryption overhead, which allows a person to outsource a big variety of decryption operations to the cloud provider issuer (CSP). However, outsourced decryption cannot guarantee the correctness of transformation finished by means of the cloud, so it's far vital to test the correctness of outsourced decryption to make certain safety for users’ facts. Current research mainly specializes in verifiability of outsourced decryption for the legal users. It nonetheless stays a hard difficulty that a way to guarantee the correctness of outsourced decryption for unauthorized users. In this paper, we recommend an ABE scheme with verifiable outsourced decryption (called full verifiability for outsourced decryption), that could simultaneously test the correctness for transformed cipher text for the authorized customers and unauthorized customers. The proposed ABE scheme with verifiable outsourced decryption is proved to be selective CPA at ease within the standard version

Fog Computing a Paradigm: Scenarios And Security Issues

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th May 2018

Sai Keerthi.Tulluru | Dr.Anuradha S.G

Abstract

Fog computing is a paradigm that extends cloud computing and services to the edge of the network. Fog computing provides data, storage, and application services to end users. In Fog computing user data is outsourced and user’s control over dated is handed over to fog node, which introduces same security threats as it is in cloud computing. Fog computing is well suited for real time analytics and big data .Security incidents regarding fog computing are posed by the hostile attack and main-in-the-middle attacks

Fog Computing: A platform for Internet of Things (IOT)

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th May 2018

Rashmi KG Matt | Dr.Anuradha S G

Abstract

Fog computing extends the cloud computing paradigm to the edge of the network thus enabling a new breed of applications and services. Fog computing is the appropriate platform for a number of critical Internet of Things namely connected vehicle, smart grid, smart cities, wireless sensors and actuators networks(WSANs).

FOOD HUB A Model for Ordering In Restaurant Based On Qr Code Without Presence Of A Waiter At The Table

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th June 2018

Dr. B. Shadaksharappa | KotraChaithanya, Suresh .J, Mahesh R, Deepak Kumar

Abstract

Communication field has changed rapidly and an appropriate condition has been created to use this capacity in business due to developing technology in the field of information technology and availability of tools to work with this technology especially the arrival of smartphones to market and its expansion which provides the capability of connecting to the internet with desired broadband. In this article, we have tried to design a system to be able to provide more advantages including electronic payment of bills as well as entertainment facilities in the time between ordering and delivering the goods to customers beside previous options by reviewing restaurants that take advantage of the electronic menu using QR code on the customer’s mobile. Moreover, in this new model, there will be the possibility of Internet-based remote ordering and also bill payment will be through bank portal before delivering the good to the customer by allocating QR code to the steady customers and entering their information in the databases such as phone number and exact address

Forecasting Techniques for Time Series Financial Data

International Journal of Engineering Research in Computer Science and Engineering, Available online 5th March 2018

T. Soni Madhulatha | Dr. S. Sameen Fatima

Abstract

This paper focuses on Time Series forecasting techniques to financial time series with an autoregressive integrated moving average (ARIMA) and Seasonal and Trend decomposition using Loess(STL) that estimates nonlinear relationships. The data used are historical currency exchange rates of INR/USD, INR/GBP, INR/EURO and INR/YEN from May 2005 to July 2014 provided by Reserve Bank of India. First, we show the Multivariate Analysis and then perform the forecasting on individual currency. Various plots are used for visualization.

Forest Monitoring System Using Wireless Sensor Network

International Journal of Engineering Research in Computer Science and Engineering, Available online 22nd January 2018

G.Aaroma | B.Clinton David, S.T.Priyanka, P.T.Subasini

Abstract

The Wireless Sensor Network is used in the field of automation, home appliances and security. The proposed system enables the integrated use of Mercury Tilt Sensor, vibration sensor, temperature and humidity sensor, pressure sensor and CO gas sensor incorporated into trees for the sensing of events in the natural environment. The wireless RF module enables the communication between the cluster node, the node and the control centre. This helps monitoring and detection of tree theft and disasters like forest fire protecting the natural environment. This article presents the interface and network topology of the wireless sensor network and their advantages.

Fortify Cloud Computing Security with Federal Identity Management Using Hierarchical Identity- Based Cryptography

International Journal of Engineering Research in Computer Science and Engineering, Available online 9th February 2018

S Venkata Ramanaiah | A. Anil Kumar Reddy, N.Prashanti

Abstract

An ever increasing number of organizations start to give various types of Cloud computing administrations for Internet clients in the meantime these administrations additionally bring some security issues. As of now the larger part of Cloud computing frameworks give computerized personality to clients to get to their administrations, this will bring some burden for a mixture cloud that incorporates various private mists as well as open mists. Today most Cloud computing framework utilize uneven and traditional open key cryptography to give information security and shared authentication. Personality based cryptography has some fascination qualities that appear to fit well the prerequisites of Cloud computing. In this paper, by receiving sustained e-rated personality administration together with various levelled character based cryptography (HIBC), the key conveyance, as well as the shared confirmation, can be streamlined in the cloud.

Framework and Architecture of Internet of Things

International Journal of Engineering Research in Computer Science and Engineering, Available online 20th February 2018

Muzammil Hussain | Dr.Sk Yadav

Abstract

Internet of Things - IoT (Internet of Things) or Internet of Everything characterizes a system of items that consolidates electronic circuits that permit correspondence by means of existing foundation (arrange INTERNET), remote or link for some reasons including observing or remote control. The presence of a web interface through which a man may get to the gear of the house is valuable to expand productivity and spare assets. Both claim homes and additionally organizations, medicinal administrations, plants, state administrations and groups will profit by utilizing associated IoT conditions. These conditions are portrayed by data sharing between gear, gadgets and people help gadgets and the trading of data between these. This exploration diagrams the advantages brought by IoT frameworks received in organizations from various perspectives. We utilize a contextual investigation keeping in mind the end goal to point to genuine encounters and circumstances. A further target of this paper is to propose a model of engineering for the frameworks and inspect their procedure of working by dissecting the innovations used to grow such frameworks and the security issues that can be met.

Framework for Dynamic Resource Allocation and Efficient Scheduling strategies to enable Cloud for HPC Platforms

International Journal of Engineering Research in Computer Science and Engineering, Available online 31st May 2018

Tavhare K.S | Kambale B.S., Hule K.A., Raut Anuradha

Abstract

Resource Scheduling and allocation is extremely important issue in cloud computing. Any computation is applied once there's ample or proportionate resources obtainable. Services square measure provided to the shoppers or finish users with the correct analysis of resources. Infrastructure as a service in cloud grabs a lot of attention in Cloud computing. To utilize resources a lot of with efficiency Associate in Nursing optimized programming rule is employed to deal with cloud programming issues. By deploying virtual machines in acceptable locations to boost the speed of locating best allocation methodology that intern allow most utilization of resources obtainable. The programming resources to beat unbalance in assignment drawback, during this parallel genetic rule idea is employed that is far quicker than ancient genetic rule Cloud computing plays an important role may be a model for sanctionative omnipresent network access to a shared pool of configurable computing resources. Any cloud provides services chiefly 3 ways code as a service (SaaS), platform as a service (PaaS) and infrastructure as a service (IaaS)

Frequent ITEMSET Mining Map Reduce

International Journal of Engineering Research in Computer Science and Engineering, Available online 27th November 2017

Sanchita Sonar | Shweta Kawad, Karishma Murudkar, Prof.Mrs.Sandhya S.Waghere

Abstract

Data mining deals with the extraction of hidden predictive information from large databases. Main task of data mining is to discover action rules to take profitable decisions from huge database. However, with the exposing recent growth of size of data it is challenging to find out patterns of dataset. We have used a scalable approach for discovering action rules. The main goal of this algorithm is to build a mechanism that enables au-tomatic parallelization and data distribution for parallel mining of frequent itemsets on large clusters. We are proposing an algorithm inspired from FiDoop which run in-house Hadoop cluster. We are distributing dataset into number of blocks as each block allotted to each node for mining purpose. In this algorithm, we have pro- posed two parts, first part finds the frequent itemset in the dataset while the second part optimizes the efficiency of output. We also have optimized the mapper which gives high performance.

Future Aspects and Key Challenges of IoT

International Journal of Engineering Research in Computer Science and Engineering, Available online 11th July 2017

Bitan Paul | Manik Reshi, Manish Dixit, Drishant Sharma, Dr. B. Shadaksharappa

Abstract

Embedded industry ensures well laid and efficiently advanced days of transparency in the near future ahead. It’s the need as well as call of the hour that we initiate developing IOT configured products, so as to meet the customer needs. The count of people that IoT expects to connect is estimated to be around 28 billion ―things to the internet by 2020, having diverse gadgets that range from wearable devices like smart watches to automobiles, embedded appliances, and industrial equipments. Several IoT solutions that have been enlarged so far, functionalities of them and also the technology used. Thereby, we conclude the various challenges that need to be focused on to pave the way to betterment of solutions that will aid the society.

Future Internet: ICT, Internet of Things and Smart Education in India

International Journal of Engineering Research in Computer Science and Engineering, Available online 16th November 2017

T.Raghotham Reddy | D.Rajkumar, V.Poorna Chander

Abstract

The Internet is rapidly changing and evolving. In the past and present days the main form of communication on the Internet is human-human. But it will be imagined that future objects will have unique identification and these objects can be addressed so every object connected. The Internet will become Internet of Things in India. The form of communication will extend from human-human, human-machine and machine-machine. This will bring new computing that can occur using a device, in any location and any format and change human life. Now a day’s education system in India following traditional system in some institutions accepting latest technologies making learning more innovative. Educational institutions in India are in a process of introducing innovating teaching and learning for creating smart learning facilities to develop student’s talent. In this paper we discuss overview, architecture of IOT and how academic learning easy and motivating the students using ICT and IOT, introducing them to their subjects with smart learning and interactive. ICT provides a vide range of applications and devices for learning. Whereas IOT provides connecting devices making smart and self controllable.

Future of Cloud Computing In It Field 2020

International Journal of Engineering Research in Computer Science and Engineering, Available online 19th December 2017

Ganapriya R | Monika S, R Nitin Kumar, Srikanth P, Prof Bindu Madavi K.P

Abstract

Many organizations taking their first tentative steps, but by 2020 cloud is going to be a major and permanent part of the enterprise computing infrastructure. Three years from now we are likely to see low power processor crunching many workloads in the cloud and supporting massively federated scalable software architecture.2020 cloud computing is likely to be a standard part of enterprise IT. To get an idea of the type of failures that cloud companies will be forced to deal with. It is helpful to look to supercomputing an area that uses many of the technologies and methods that eventually makes the way into the cloud.

Fuzzy Based Current Source Modular Multilevel Converter and Application as Statcom

International Journal of Engineering Research in Computer Science and Engineering, Available online 21st May 2018

Devender Reddy Konathala | Goparaju Kranthi Kumar, Srikanth.S

Abstract

In this paper a Multilevel current source converters is utilized for the high power applications with high current low and voltage requirements. Therefore we can totally analysis of a current source modular multilevel converter (CSMMC) with its application such as STATCOM. There are different properties of CSMMC which are correlated with the voltage source modular multilevel converter (VSMMC). There are two method for inductor current balancing they are sub module inductance selection method and a sorting based algorithm which are proposed for CSMMC. Moreover for the switching technique we are implementing the carrier phase shifted sinusoidal pulse width modulation. Here the performance of a converter can be analyzed under non-interleaved and interleaved carrier signals during the upper and lower arms. Here we are using the fuzzy controller compared to other controllers i.e. The fuzzy controller is the most suitable for the human decision-making mechanism, providing the operation of an electronic system with decisions of experts. Simulation Results will show that CSMMCs which is corresponding VSMMCs have analogous features. Hence, for the reference of CSMMCs and vice versa we are using the developed VSMMCs. Furthermore, the control satergy for CSMMC which is depend upon the STATCOM are presented and also proven by using simulations. The proposed STATCOM will display that the transient and steady state performance of the system are satisfactory.

Fuzzy Based Feature Selection for Intrusion Detection System

International Journal of Engineering Research in Computer Science and Engineering, Available online 25th November 2017

P.Indira priyadarsini | Ch.Anuradha, P.S.R. Chandra Murty

Abstract

An Intrusion Detection System (IDS) gathers and evaluates information from different locations, and finds potential security risks that include exterior as well as inside of the organization. It contains an enormous volume of data with irrelevant and redundant features which result in longer processing time and poor detection rate. So, feature selection should be empowered as an important characteristic for better performance on massive datasets. Feature selection refines the high dimensional data sets by removing over fitting and curse of dimensionality problems mainly in the domain of machine learning. The perceptive of feature selection lies in increasing the accurateness. In this paper, Fuzzy_Chi_Euc algorithm was given for selecting best features in KDD Cup 99 data set. In this algorithm integration of two filtering methods is done. The fuzzy inference rules are applied for selecting the features. The classification is carried out for fi