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 high-performance computing paradigm needs high-speed switching fabrics to meet the heavy traffic generated by their applications. These switching fabrics are efficiently driven by the deployed scheduling algorithms. In this paper, we proposed two scheduling algorithms for input queued switches whose operations are based on ranking procedures. At first, we proposed a Simple 2-Bit (S2B) scheme which uses binary ranking procedure and queue size for scheduling the packets. Here, the Virtual Output Queue (VOQ) set with maximum number of empty queues receives higher rank than other VOQ’s. Through simulation, we showed S2B has better throughput performance than Highest Ranking First (HRF) arbitration under uniform, and non-uniform traffic patterns. To further improve the throughput-delay performance, an Enhanced 2-Bit (E2B) approach is proposed. This approach adopts an integer representation for rank, which is the number of empty queues in a VOQ set. The simulation result shows E2B outperforms S2B and HRF scheduling algorithms with maximum throughput-delay performance. Furthermore, the algorithms are simulated under hotspot traffic and E2B proves to be more efficient.

Department of Database Systems

School of Computer Science and Engineering

Vellore Campus

Fulltext

Computers, Materials & Continua

High Throughput Scheduling Algorithms for Input Queued Packet Switches

This paper focuses to solve two important problems faced in this digital era. The first problem is handling large amount of digital data. Digital sectors are finding difficulty in handling repetitive works and standardization of process. Our University is a eco-friendly, digital university each and every work of our students are maintained digitally. So for a course instructor to open, view, correct and finding plagiarism in the assignment or homework submitted by students is a tough task. So in this paper this tough task is simplified by applying Robotic Process Automation (RPA). The process of downloading and reading the students’ digital document is automated. The second problem is the plagiarism. There has been a massive threat in the academic and technological integrity of innovation in the name of paraphrasing. In a survey conducted by Donald McCabe of Rutgers University over 70 percent of students admit to paraphrasing and copying of others work. They have also fabricated bibliography. This problem can be addressed using the state-of-the-art document similarity deep learning neural networks. In this paper, we propose the design and implementation of a Siamese Neural Network (SNN), Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) to identify paraphrasing, using only features of similarity between words where the dataset is evolutionary and the model keeps learning with incremental sources of the document’s plagiarism. This paper will also provide the Tensorflow based implementation of such a model. The proposed system will predict the similarity between documents and predict the plagiarism percentage.

Department of Analytics

Solid State Technology

Plagiarism Detection using Attention based Text Similarity

Sequence alignment is a problem in bioinformatics that involves arranging sequences of proteins, RNA or DNA so that similar regions between two or more sequences may be determined. The Smith-Waterman algorithm is a key algorithm for aligning sequences. This paper uses the OpenMP application-programming interface along with the Single-Instruction Multiple-Data (SIMD) instructions. Advanced Vector Instructions 2 (AVX2) is used to implement the SIMD paradigm. It utilizes both fine-level and coarse-level parallelism to improve resource utilization without requiring support from multiple nodes in a distributed memory system. The algorithm shows a multifold decrease in execution time in comparison to an implementation that is sequentially executed. © 2020, Springer Nature Singapore Pte Ltd.

World University root node

Communications in Computer and Information Science

Time Improvement of Smith-Waterman Algorithm Using OpenMP and SIMD

An Intrusion Detection System (IDS) identifies whether the input traffic is normal or an intrusive activity. To improve the performance of the IDS this paper proposes a classifier fusion algorithm, based on Weighted Dempster-Shafer theory. The highlight of this classifier fusion algorithm is, it considers the input data also in the final decision process by taking the product of weighted score and anomaly score as the Basic Probability Assignment (BPA) value for Weighted Dempster-Shafer theory. The proposed system has a multiple IDS unit (MIU) with five IDS, each having different algorithms of anomaly-based and misuse-based detection techniques. The selected features of input traffic data are passed to each IDS in the MIU and it gives out five anomaly scores for five attack types. The maximum anomaly score got from the IDS and a new parameter called weighted score is used in the Weighted Dempster-Shafer theory to take the final decision. The weighted score is obtained by passing the maximum anomaly score and the selected input traffic to the Neural Network learner unit. NSL-KDD dataset with 41 features is used to evaluate the performance of the proposed system. The best 27 features out of 41 is selected using Genetic Algorithm to reduce the computation time. The proposed system outperforms in terms of detection rate and false alarm rate when compared with existing fusion methods. © 2019 SERSC.

Department of Digital Communications

School of Information Technology and Engineering

International Journal of Advanced Science and Technology

Network attack detection using weighted Dempster-Shafer evidence theory

Much is being said about the use of artificial intelligence to assist in the financial markets but there is a surprising lack of actual data supporting one trading algorithm over another. While there are numerous research that explore the possibilities of machine learning and deep learning techniques for stock market prediction, due to the lack of inter-domain expertise (people who are experts in both data science and finance), most of these projects use relatively elementary methods and fail to account for many underlying constraints. This paper aims to create a stock market investment aide which predicts the price action of stock market instruments using neural networks that learn time series patterns in the historical price data, correlates the prediction with the sentiment score of the market for that day and thereby give the investor/trader a buy or sell signal. The model developed has been successful in predicting price action of the NIFTY50 index with an accuracy of 89 percent. The prediction aided with the correlation from the sentiment analysis can give the investor an added confidence while making investment decisions on the stock market.

VIT Unitversity

International Journal of Recent Technology and Engineering Regular Issue

Predicting Indian Stock Prices through Sentiment Score and Data Mining Techniques

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.

International Journal of Recent Technology and Engineering 2

Parallel and Serial Graph Coloring Implementations with Tabu Search Method

International Journal of Intelligent Internet of Things Computing

Performance evaluation on internet of things protocols to identify a suitable one for millions of tiny internet nodes

Day-by-day, the desideratum for high speed internet connectivity increases and consequently, high performance switches are imminent. These switches require efficient schedulers to reach its maximum potential. In this paper, a high performance scheduler is proposed for buffered crossbar switches to work under multicast traffic. The scheduler is able to reduce the starvation effect and thereby achieves maximum throughput with minimum delay than existing algorithms. Copyright © 2018 Inderscience Enterprises Ltd.

International Journal of Information Systems and Change Management

High performance scheduler for multicast switches

Need for high speed internet connectivity has lead to a substantial research in switching systems. Buffered crossbar switches have received a lot of attention from both research and industrial communities due of its flexibility and scalability. Designing a scheduling algorithm for buffered crossbar switches without starvation is a major challenge as of now. In this paper, we proposed a Delay based Prioritized Queue with Round-robin Scheduler (D-PQRS) which uses no speedup. Simulation result shows that DPQRS reduces the starvation considerably with maximum throughput and minimum delay comparable to PQRS and LQF-RR.

International Journal of Engineering, Transactions A: Basics

Starvation free scheduler for buffered crossbar switches

The increasing demand for higher data rates on the internet requires routers that deliver high performance for high-speed connections. Nowadays high speed routers use the buffered crossbar switches, which have been the interest for research and commercialisation. In this paper, a study is made on the importance of buffered crossbar switches and their scheduling algorithms. Performance analysis is made for various buffered crossbar switch scheduling algorithms using non-uniform traffic patterns. © 2015 Inderscience Enterprises Ltd.

International Journal of Information and Computer Security

Performance analysis of buffered crossbar switch scheduling algorithms

Need for high speed internet connectivity has led to a substantial research in switching systems. Buffered crossbar switches have received a lot of attention from both research and industrial communities due to their flexibility and scalability. Designing a scheduling algorithm for buffered crossbar switches without starvation is a major challenge as of now. In this paper, we propose a Delay based Prioritized Queue with Round-robin Scheduler (D-PQRS) which uses no speedup. Simulation result shows that DPQRS reduces the starvation considerably with maximum throughput and minimum delay comparable to PQRS and LQF-RR.

Starvation free Scheduler for buffered crossbar switches

The objective of the paper is to compare the different Wavelet based Image Compression algorithms. SPIHT, WDR, and ASWDR algorithm are involved in the comparison process. These are some recent algorithms, which produce some lowest errors per compression rate and highest perceptual quality. Finally, the results are compared using all the above algorithms. © 2009 IEEE.

ACT 2009 - International Conference on Advances in Computing, Control and Telecommunication Technologies

Wavelet based image compression: A comparative study

In this paper, we proposed a method to rank the professional colleges. Ranking the colleges is a mandatory process for the sake of students, to identify the best college in each discipline. We employ the fuzzy repertory table (FRT) technique to acquire the necessary domain knowledge of colleges from which the ranking is made. A sample of 4 colleges is taken into consideration and accessing similarity is made over it. Distinction matrix is created based on the similarities of colleges from which the ranking has been made. © 2009 IEEE.

ARTCom 2009 - International Conference on Advances in Recent Technologies in Communication and Computing

Fuzzy based framework for professional college rankings

In this paper, a method is proposed for predicting software maintainability. Prediction of maintainability of a product is done by using its code complexity. Here a sample of 4 products is taken into consideration and both the absolute and relative complexity assessment are made over it. The process of measuring the code complexity is done at testing phase. We employ the fuzzy repertory table (FRT) technique to acquire the necessary domain knowledge of testers from which the software complexity analysis is made. Regression analysis is then used to predict maintainability from the product's code complexity. © 2008 IEEE.