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

Department of Database Systems

In this paper we have proposed a priority based Erlang service distribution with k-phases for cloud computing architecture. The multiple users from the public cloud entering into two serially connected M/M/s and M/Ek/1 (Erlang service queue) queues are served based on the non-pre-emptive priority discipline. We have assumed each user of different priority class i, (i ≥ 2) desired to wait until the current user is being served if priority of the service is similar, as per FCFS policy. If the servers are free, users can enter into the M/M/s queue, then enter into the M/Ek/1 queue with probability φ and leave the system after service completion or leave the system with probability (1 – φ) without entering into the ESQ. We have obtained waiting time for both the queues in the cloud system and shown numerically the total waiting time is lower than the existing system. Copyright © 2019 Inderscience Enterprises Ltd.

World University root node

School of Computer Science and Engineering

Vellore Campus

International Journal of Internet Technology and Secured Transactions

Performance analysis of cloud computing using series of queues with Erlang service

Detection and classification of vulnerable road users (VRUs) is one of the most crucial blocks in vision based navigation systems used in Advanced Driver Assistance Systems. This paper seeks to evaluate the performance of object classification algorithm, You Only Look Once i.e. YOLO v3 algorithm for the purpose of detection of a major subclass of VRUs i.e. cyclists and pedestrians using the Tsinghua - Daimler dataset. The YOLO v3 algorithm used here requires less computational resources and hence promises a real time performance when compared to its predecessors. The model has been trained using the training images in the mentioned benchmark and have been tested for the test images available for the same. The average IoU for all the truth objects is calculated and the precision recall graph for different thresholds was plotted. © Science and Information Organization.

Department of Communication Engineering

School of Electronics Engineering

Fulltext

International Journal of Advanced Computer Science and Applications

Vulnerable Road User Detection using YOLO v3

In recent decades Machine learning and Data Science are providing best ways to analyze and solve various problems. In fact, those Machine Learning algorithms gives the best and optimized solutions. These methods are playing key role in providing efficient solutions for the health care problems like predicting the diseases in early stage, and even some automated systems run by Machine Learning Algorithms are prescribing medicines based on the patient’s symptoms. Diabetes is one among the chronic diseases from past years, which leads to the damage of patients eyes, nerves, heart and kidneys etc., In this project we are going to create a pipeline in which the data collected from the source is undergone through some preprocessing techniques and the Machine Learning Algorithms like SVM, KNN, Gradient Boasting, logistic regression and Random Forest are used to classify whether the patient is diabetic or not and the accuracy of these algorithms was measured by using some Evaluation methods like Train/Test Split. Finally, these data will be visualized by using Visualization Tools. © BEIESP.

International Journal of Recent Technology and Engineering

Visualizing the clinical data of diabetes using data science and machine learning algorithms

Cluster computing enables high performance parallel computing by clustering two or three microprocessors, for example, RasberryPi. This paper highlights the different terms that are confused with cluster computing and uses Apache spark which is implemented on Scalar to perform an operation. Forming a cluster of computers is nothing but joining CPUs or Microprocessors that results in a single computer. This in turn increases the efficiency of the whole process. Dual core CPUs are less faster than QuadCore CPUs. Quad core CPUs helps in 4k video editing, graphics processing with seamless rendering. But the Dual core system does it with less render speed and sometimes causes the computer to crash. In this paper, we analyze the methodology of cluster computing, how it is done and provide technologies that helps one to improve their programs throughput through cluster computing. We also provide a minified understanding of the various concepts involved in high power computing and try to solve the ambiguities, the common ones. Copyright © 2019 American Scientific Publishers All rights reserved.

Department of Software Systems

Journal of Computational and Theoretical Nanoscience

Performance Analysis of Data Processing Using High Performance Distributed Computer Clusters

With the growth in the present digital era, the Internet is the prime source of knowledge. This situation is depleted by phishers and they have drafted various websites which steals userâs information and misuse it. Though it is hard to locate a phishing site, various features of the phishing site helps in uncovering its mask. This paper discusses several features to identify a phishing site. Using data mining techniques like classification and association rule mining many explorations are performed to prove the notion. Similarly, the impact of various features considered for analysis is studied too.

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

Evaluation of Features to Identify a Phishing Website Using Data Analysis Techniques

The goal of this work is to build an algorithm to automatically detect and segment ships in satellite images. A number of factors can make ship detection and segmentation a challenging task. Some of these factors include flaws in image quality like uneven brightness, obstruction, and also the fact that there are many images which have similar shape, color and texture. Another problem is that objects like islands, ports, whales etc look quite similar to ships. The algorithm had to be extremely accurate because lives and billions of dollars in energy infrastructure is at stake. In this paper we have used a custom MASK R CNN with backbone as ResNet 50 trained using MS COCO weights. Using mask shape of size 14*14, the algorithm is able to detect and segment ships with a Mean Average Precision of 0.605. The model takes approximately 30 seconds to segment 30 images. Hence this model can be used for real time maritime applications. © 2019, IJSTR.

International Journal of Scientific and Technology Research

Real time detection and segmentation of ships in satellite images

This paper studies the imaginative play in young children using a model based on neutrosophic logic, viz, Neutrosophic Cognitive Maps (NCMs). NCMs are constructed with the help of expert opinion to establish relationships between the several concepts related with the imaginative play in children in the age group 1-10 years belonging to socially, economically and educationally backward groups. The NCMs are important in overcoming the hindrance posed by complicated and often imprecise nature of psychological or social data. Data was collected by video recording of children playing and the interpretations given by experts. Fifteen attributes / concepts related with children playing with the same toy were observed and according to experts several concepts were related and for some the relations between concepts were indeterminate, so it was appropriate to use NCMs. These NCMs were built using five expert's opinion and the hidden patterns of them happened to be a fixed point. © 2019.

Neutrosophic Sets and Systems

Study of imaginative play in children using neutrosophic cognitive maps model

One of the well-known property of graph is graph coloring. Any two vertices of a graph are different colors such that they are adjacent to each other. The objective of this paper is to analyse the behavioral performance of Tabu Search method through serial and parallel implementations. We explore both parallel and serial Tabu search algorithm for graph coloring with arbitrary number of nodes.

VIT Unitversity

Department of Analytics

International Journal of Recent Technology and Engineering 2

Parallel and Serial Graph Coloring Implementations with Tabu Search Method

Wireless Sensor Networks (WSNs) is a distributed collection of tiny wireless nodes which forms an ad hoc network dynamically to sense the natural phenomenon and sent it to the control station. Due to the resource constrained nature of WSN, maximizing the nodes life time is main and challenging issue. In this paper, Fitness Function based Routing Protocol (FFBRP) is proposed which provides the optimal routing to increase the life time of nodes in a network. The proposed protocol selects the fitness functions based on the important routing parameters like nodes energy consumption, nodes life time, packet Delivery ratio of nodes, distance between nodes, end to end delay of nodes and routing overhead of nodes. Based on the combination of selected fitness function parameters, the intelligent rules are generated and the optimal routes are discovered to perform energy efficient effective routing in WSN. By doing so, the proposed protocol provides better performance in terms of network life time and has better Quality of Service (QoS) than other existing techniques. The implementation of the proposed scheme is carried out using Network Simulator (NS2) with mannasim framework. Simulation results justifies that, proposed protocol outperforms the existing techniques and has better Packet Delivery Ratio, throughput, network life time, energy consumption, end to end delay and routing overhead. © 2019, Blue Eyes Intelligence Engineering and Sciences Publication. All rights reserved.

Department of Information Technology

School of Information Technology and Engineering

International Journal of Innovative Technology and Exploring Engineering

Energy efficient rule based intelligent routing using fitness functions in wireless sensor networks

The Microarray technology permits simultaneous monitoring of several gene expressions for every sample. But unfortunately, this classification of such samples into the distinct classes has often been found to difficult as the actual number of genes (the features) will to a great extent exceed the actual number of the samples. There is a high dimensionality in gene and its expression data which is a huge challenge in many of the problems of classification. Cloud computing is that popular concept of computing which performs a processing of a data of huge volumes by making use of highly accessible resources that are geographically distributed and accessed by the users based on the policy of pay as per use. In spite of the several steps in that of the B Cell that are now elucidate the last few stages of that of the plasma cell (PC) based differentiation that have not been understood yet. The PCs had generated at the time of primary and humoral immune responses that have started their differentiation within their light zones for the germinal centers of such light zones of that of the lymph nodes or the ones in the red pulp of the spleen having a life span of about few days. The selection of the features will aim at the maintenance of their original features of such data and at this time it will seek at identifying their main features and will weed out all those that are irrelevant for building of a learning model that is impactful. Identifying one global maximum will be Non-deterministic Polynomial (NP)-hard and if the criterion is decomposable or possesses the properties that can make some approximate type of optimization easy. The artificial bee colony (ABC) is that one that is used widely and applied for solving all real world problems. The stochastic diffusion search (SDS) will be an efficient multi-agent global search based technique of optimization applied to that of several problems and here the hybrid ABC with that of the SDS feature selection will be proposed and these images will be grouped as either normal or abnormal PC of the bone marrow that is based on this gene expression data. The support vector machine is that algorithms of supervised learning that is capable of being able to solve the complex problems in classification. This proposed method of gene selection will yield a comparable performance for the classification on being compared to that of the currently existing classifiers providing another new insight in case of feature selection. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.