Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

The pervasiveness of interpersonal organizations has made it less demanding than any time in recent memory for clients parts the photographs, recordings, Different communication like audio, video materials anyone in anyplace. Be that as it may, the simple access of client produced media content additionally realizes security concerns. Customary control of connection components, however the solitary connection strategy only through particular bit of substance, can't fulfill the client protection prerequisites in substantial scale media sharing frameworks. Rather, arranging numerous connection for dimensions benefits at mutual video and audio parts are wanted. In unhandy, this adjusts the guideline for interpersonal organizations in data spread. Then again, it concurs the difficult social Websites with their informal organization clients. Propose a versatile media get to control framework to empower such an arrangement in a protected and productive way. The proposed SMAC framework engaged these adaptable encoded message approach quality based encryption calculation just as a complete key administration plot. Here, give normal evidence along with secure for demonstrate the new framework with their security. Moreover, And also lead escalated investigations cell phones to exhibit its productivity.

Department of Information Technology

School of Information Technology and Engineering

Vellore Campus

Department of Software and Systems Engineering

Department of Digital Communications

Department of Smart Computing

VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE International Journal of Innovative Technology and Exploring Engineering

Image Distribution with Scalable Access Control for Privacy in Social Network

In the current network area, cloud service providers offer infinite storage space and computing power for users to manage their data in the cloud. To enjoy these services, individuals or organizations store their private data on cloud servers. However, in the case of security breaches, users’ private data stored in the cloud are no longer safer. When users outsource their data to cloud servers, they expect complete privacy of their data stored in the cloud storage. To enjoy these services, individuals or organizations store their private data on cloud servers. The semantic-based keyword search over encrypted cloud data becomes of paramount importance. Protecting the privacy and data of users has remained a very crucial problem for cloud servers Additionally, the existing approaches only process them as single words, the flexibility of the encryption policy and the description of users’ rights, and it changes from a one-one to one-many scenario during the encryption and decryption phases, calculation method to measure the semantic similarity between compound concepts. Keyword has been widely used in many scenarios, particularly in cloud computing. In this Project in the proposed scheme we use the trusted authority to generate the trapdoor .The generated trapdoor will be send to the user's e-mail ID, the user will search

Department of Computer Applications

Secured Service Chains Tuned Resource Sharing using Nsdp

Several classifiers are prevalent which act as a major drive for almost all supervised machine learning applications. These classifiers, though their objective working looks similar, they vary drastically in their performances. Some of the important factors that cause such variations are the scalability of the dataset, dataset nature, training time estimation, classifying time for the test data, prediction accuracy and the error rate computation. This paper focuses mainly on analyzing the performance of the existing four main classifiers: IF-THEN rule, C4.5 decision trees, naïve Bayes, and SVM classifier. The objective of this research article is to provide the complete statistical performance estimates of the four classifiers to the authenticated cloud users. These users have the access facility in obtaining the essential statistical information about the classifiers in study from the cloud server. Such statistical information might be helpful in choosing the best classifier for their personal or organizational benefits. The classifiers follow the traditional underlying algorithms for classification that is performed in the cloud server. These classifiers are tested on three different datasets namely PIMA, breast-cancer and liver-disorders dataset for performance analysis. The performance analysis indicators used in this research article to summarize the working of the various classifiers are training time, testing time, prediction accuracy and error rate computation. The proposed comparative analysis framework can be used to analyze the performances of the classifiers with respect to any input dataset.

VIT Unitversity

International Journal of E-Health and Medical Communications

Comparative Performance Analysis of Various Classifiers for Cloud E-Health Users

Buying and selling the goods and services through internet called as electronic network known to be E-commerce. Due to the convenience of e-commerce, the number of users are increased. Meanwhile, the people review of product also increased. In e-commerce websites, fake review is often the major problem. Nowadays, it is known to be common that user can write the review for their purchased product. There are many ways that user can write reviews. Using this opportunity, there is a possibility that spammers can leave fake review. Many users determine the quality of product based on user’s reviews. So, the fake review creates lot of problems on product quality, sales, and economic growth. To tackle this problem, we are going to use Naive Bayesian classifier which is very simple and easy technique to classify the product review. Feature extraction can be used to extract the feature .Here we are using dataset for classifying the product reviews. Here our aim is to find fake reviews. By detecting fake reviews the accuracy of e-commerce system can be improved. © IAEME Publication.

World University root node

International Journal of Civil Engineering and Technology

Spam review detection on e-commerce sites

International Journal of Intelligent Engineering and Systems

Hybrid Approach for Data Classification in E-Health Cloud

Mathematics

School of Advanced Sciences

Chennai Campus

Fulltext

Informatics in Medicine Unlocked

Cloud based automated framework for semantic rich ontology construction and similarity computation for E-health applications

In this paper we study about the mixture cloud for duplication. Duplications is more important because now a day’s cloud user are facing a big problem based on the storage space. Now a day’s cloud uses are demanding that to increase the storage space because everyone wants to store their data on the cloud. There are many reasons to store data on the cloud because it is safe, if users want to upload data on cloud is more protected. For solving this problem we proposed hash encryption method for finding duplicate data. If user tries to upload data on cloud but he/she doesn’t know about their file is already stored or not, our proposing system can easily find that the file is already stored or not. In this system users data stored in the public cloud. Before these thing users need to tag and key of the file and these two things are provided by the private cloud. Authentication user can do this only; here user should be authorised, private cloud response to user. If user is not valid it does not give any response to the user. In this system user first select the file get tag and convergent from private cloud and upload a file on cloud, if file is already it shows message that the file is already stores or not if not then file will upload successfully on cloud. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

International Journal of Pharmacy and Technology

A hybrid cloud approach for secure authorized deduplication

A program that infect computers, destroy the data, steal personal information, get some valuable information, we focus on a particular kind of malware that is key logger. A keylogger monitors a user input and keeping a log of all keys that are pressed. There are various tracking techniques such as computer monitoring, software key stroke recorder, key stroke logger, Keyboard sniffer and snoop ware, they can track virtually any running program on a system. Some of the keylogger known as screen scrapers. This takes the snapshot of the screen. It can be defined two category hardware and software keylogger. Hence we are working on software keylogger which are monitoring on windows operating system. In this when a user performing an event (pressing a key) in the windows operating system, the keyboard driver of the operating system translate a key stroke in to a windows message is called "wm_keydown". There are four main methods developing keylogger keyboard state table method, windows keyboard hook method, kernel-based keyboard filtering driver method. in this paper we used a new method getkeystate, that is variation of windows keyboard hook method, which is unique to windows message mechanism. © Research India Publications.

International Journal of Applied Engineering Research

A new approach to cyber security through keylogger

Share market acts as one of the key role for building economy of any developing nation. It is highly complex to determine booms and crashes in the market, so it became one of the interesting and challenging topics for all the business researchers to predict an accurate share value. In this paper we propose an algorithm based on Support Vector Machine (SVM) and k-Nearest Neighbor (k-NN) algorithms to predict next day's closing price share value of a company. Here we take historical data of company i.e. past prices to predict future prices by training them. We use Relief-F feature selection technique used for parameter selection. Performance of SVM and k-NN is calculated using Root mean squared error (RMSE) and Mean absolute percentage error (MAPE). © Research India Publications.