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

VIT Unitversity

Department of Information Security

School of Computer Science and Engineering

Vellore Campus

Fulltext

Procedia Computer Science

Intrusion Detection in Computer Networks using Lazy Learning Algorithm

Diabetes Mellitus has turned into a noteworthy general wellbeing issue in India. Most recent measurements on diabetes uncover that 63 million individuals in India are experiencing diabetes, and this figure is probably going to go up to 80 million by 2025. Given the rise of big data as a socio-technical phenomenon, there are various complications in analyzing big data and its related data handling issues. This chapter examines Hadoop, an open source structure that permits the disseminated handling for huge datasets on group of PCs and thus finally produces better results with the deployment of Iterative MapReduce. The goal of this chapter is to dissect and extricate the enhanced performance of data analysis in distributed environment. Iterative MapReduce (i-MapReduce) plays a major role in optimizing the analytics performance. Implementation is done on Cloudera Hadoop introduced on top of Hortonworks Data Platform (HDP) Sandbox. © 2018, IGI Global. All rights reserved.

World University root node

Big Data Analytics for Satellite Image Processing and Remote Sensing

Iterative MapReduce: I-MapReduce on medical dataset using Hadoop

Today total populace is seven billion or more, and it will be nine billion by 2050. Over 53% are ladies who are encountering broadened circumstance from destined to death. Being ladies, they face challenges in treatment decision and henceforth ladies are ignored and secluded from performing social duty regarding the purpose of purported defenseless ladies’ wellbeing. In numerous created nations lady's wellbeing, training, sustenance and financial power have shown that ladies are as yet substandard compared to men. Ladies live in rustic territories, are in charge of a hugepart of the residential work without temperate effect examination that is done in provincial regions. Ladies in urban communities can't progress encourage in assembling work. In this paper, savagery against ladies (VAW) and furthermore unique medical problems of ladies have been discussed. Also wplanned skeleton of an easy to use gateway named Women Empowerment which will contain distinctive laws identified with VAW and furthermore contains diverse wellbeing tips for ladies, which will help the provincial and also urban ladies. It incorporates crisis call framework, which will be dynamic by the casualty ladies when they are in threat. © IAEME Publication

Department of Database Systems

International Journal of Civil Engineering and Technology

Women abandon system

International Journal of Intelligent Engineering and Systems

Student Performance Prediction Model Based on Lion-Wolf Neural Network

In the recent days the Delay and Disruption tolerant Network (DTN) have gaining popularity in a bigger way. However,the technology have imposes many challenges in the area of routing,transportation,resource management,security etc. So,the researchers are taking keen interest in exploring the challenges and issues involved in DTN along with some solutions for the same. DTN has the capability of interconnecting the heterogeneous devices in a specific area and hence imposes greater challenges and issues. This paper provides an overview of the Delay and Disruption Tolerant Network (DTN). Definition,architectural information and the application of DTN is the primary focus of this article. Some existing research and future trend in this area is also discussed in the work. © 2016,International Journal of Pharmacy and Technology. All rights reserved.

International Journal of Pharmacy and Technology

Delay and disruption tolerant network: The technology and it’s scope

The higher education system in India is curious about the success of students in education during their study. These educational institutions are adopting several methodologies to improve the quality of education and to improve the success rate of students each year. This is used as a primary objective in improving the academic excellence of a student in his/her higher educational level. The main aim of the study is to create a model that classifies the instances correctly to predict the performance of students using PAFT methodology. The PAFT methodology consists of several attribute of a student modeled into a three-tier model that is collected based on several level testing done on a particular student. The three tier model involves his complete academic details, his/her creative and other interpersonal skills and finally the level of interest towards the present educational approach. To classify the instances correctly, Genetic algorithm is modified in its mutation level with NAND gate. The proposed classifier eliminates the regression fit problem during the selection stage with the help of Tobit regression evaluation of each individual. The classifier is also compared with other techniques like genetic-OR, genetic-AND, Multi-Layer Preceptor and artificial neural network. This classifier optimizes correctly the attributes given as an input for its processing and better learning. The PAFT methodology combined with a genetic - NAND algorithm proves successful in terms of its classification rate. This could be inferred finally that this could be utilized in institutions in determining the performance and success ratio of students as a part of their knowledge management system. Also, this model could also be used for predicting the improvement level of students for the fore coming students based on the collected data set. © 2016, Institute of Integrative Omics and Applied Biotechnology. All rights reserved.

IIOAB Journal

A novel genetic nand PAFT model for enhancing the student grade performance system in higher educational institutions

Advances in Intelligent Systems and Computing Information Systems Design and Intelligent Applications

Apply of Sum of Difference Method to Predict Placement of Students’ Using Educational Data Mining

International Journal of Computer Applications

Students’ Performance Prediction based on their Academic Record

Data mining is the process of discovering useful patterns and relationships from the data. It facilitates making decision in education field. The quantity of data educational database stores is growing rapidly. Higher educational institute can use this database which holds hidden information. This hidden information is helpful in improving student’s performance in their academics. Successful prediction of student’s performance leads to assure and achieve better quality in higher education system. The performance of student is determined by different attributes. In this paper, the classical techniques and the evolutionary data mining technique called grammar based genetic algorithm (GGA) is used to build a model for predicting the performance of undergraduate students by using their past educational and general record. The result of different classifiers is compared to discover the final prediction model. Further, the result of prediction is analyzed and its relationship with different predictors is studied. This kind of analysis facilitates improvement in a specific area of educational system and also helps studying the various general factors responsible for the performance of student. © Research India Publications.

International Journal of Applied Engineering Research

Mining students’ record to predict their performance in undergraduate degree

Performance of student’s efficiency is a serious problem that happens usually in colleges. There are many techniques to predict their performance. To apply necessary steps for the weak students, the predictions have been helpful for selecting weak students who will be less than average and who can assist the management, so that they can perform well in their next tests. The selection of the best classification algorithm for a given dataset is a very widespread problem and also a complex one. In this work we focus on the accuracy to assess the classification performance. First we compare the accuracy of different classification algorithms used in data mining on multiple datasets and select an algorithm which has high accuracy for all classes to ensemble them with the help of a method by name, weak classifier to get a combination of multiple classifier. Then we measure the accuracy of combination of weak classifiers (Naïve Bayes, OneR and Decision Stump).We present results which display that the combination of multiple classifiers using vote method is more accurate than other single classifiers. There are other techniques also which are used in preprocessing of dataset like re-sampling to produce more accurate results. The results with the re-sampled data set proved to be more efficient and accurate compared to the original dataset. © Research India Publications.

Students performance prediction based on multiple classifiers

International Journal of Data Mining & Knowledge Management Process

Predicting Students' Performance Using ID3 and C4.5 Classification Algorithms

The ability to predict performance of students is very crucial in our present education system. We can use data mining concepts for this purpose. ID3 algorithm is one of the famous algorithms present today to generate decision trees. But this algorithm has a shortcoming that it is inclined to attributes with many values. So , this research aims to overcome this shortcoming of the algorithm by using gain ratio(instead of information gain) as well as by giving weights to each attribute at every decision making point. Several other algorithms like J48 and Naive Bayes classification algorithm are also applied on the dataset. The WEKA tool was used for the analysis of J48 and Naive Bayes algorithms. The results are compared and presented. The dataset used in our study is taken from the School of Computing Sciences and Engineering (SCSE), VIT University.

International Journal of Engineering and Technology

Predicting students' performance using modified ID3 algorithm

An unsupervised competitive learning algorithm based on the classical k-means clustering algorithm is proposed. The proposed learning algorithm called the centroid neural network (CNN) estimates centroids of the related cluster groups in training date. It is based on the observation that synaptic vectors converge to the centroids of clusters as learning proceeds in conventional unsupervised competitive learning algorithms such as SOM or DCL. The centroid, or conditional expectation, can minimize the mean-squared error of the vector quantization. As is the case with SOM or DCL, the synaptic vectors converge to the centroids of clusters as learning proceeds in CNN. However, the CNN finds locally optimal synaptic vectors for each datum presented and consequently converges to the centroids of clusters much faster than conventional algorithms. This centroid neural network can be used for generating the clusters using user data. The data may either image pixels or tables of information. One of the very advantageous features in the CNN algorithm is that the CNN does not require a schedule for learning coefficients. The CNN rather finds its optimal learning coefficient in each representation of data vectors. The CNN can also reward and punish by learning coefficients for winners and losers, respectively. Unlike SOM or DCL, the CNN also does not require the total number of iteration in advance.