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

Internet made a big revolution in the real world and thus poses so many challenges to the researchers by generating an enormous amount of data. The data generated contains an enormous amount of unwanted information. Before processing with such a dataset, the important features present in the dataset must be retrieved. The feature selection process is important because the performance of a model built for the purpose of classification, prediction or clustering depends mainly on the number of relevant features present in the dataset. In this proposed work, the real coded genetic algorithm is used to find the important features by considering the fuzzy rough degree of dependency as its fitness function for finding out optimum features for agricultural dataset, iris dataset and Pima Indian diabetes dataset. The experimental results show that the proposed work produces relevant features by maintaining classification accuracy. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021

Department of Digital Communications

School of Information Technology and Engineering

Vellore Campus

Department of Computational Intelligence

School of Computer Science and Engineering

Lecture Notes in Networks and Systems

A Comparative Study of Genetic Algorithm and Neural Network Computing Techniques over Feature Selection

Digitalization accumulates data in a short period. Smart agriculture for crop identification for cultivation is a common problem in agriculture for agronomists. The generated data due to digitalization does not provide any useful information unless some meaningful information is retrieved from it. Therefore from the existing information system, prediction of decision for unseen associations of attribute values is of challenging. This paper presents a model that hybridizes a fuzzy rough set, real-coded genetic algorithm, and linear regression. The model works in two phases. In the initial phase, the fuzzy rough set is used to remove superfluous attributes whereas, in the second phase, a real-coded genetic algorithm is used to predict the decision values of unseen instances by making use of linear regression. The proposed model is analyzed for its viability using agricultural information system obtained from Krishi Vigyan Kendra of Thiruvannamalai district of Tamilnadu, India. Further, the accuracy of the proposed model is compared with existing techniques. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC part of Springer Nature.

Multimedia Tools and Applications

An integrated fuzzy rough set and real coded genetic algorithm approach for crop identification in smart agriculture

An extensive amount of data are generated from the electronic world each day. Possessing useful knowledge from this data is challenging, and it became a prime area of current research. Much research has been carried out in these directions initiating from statistical techniques to intelligent computing and further to hybridized computing. The foremost objective of this article is making a comparative study between statistical, rough computing, and hybridized computing approaches. Financial bankruptcy dataset of Polish companies is considered for comparative analysis. Results show that rough hybridization of the binary-coded genetic algorithm provides an accuracy of 98.3% and it is better as compared to other descriptive and rough computing techniques. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

An extensive study of statistical, rough, and hybridized rough computing in bankruptcy prediction

Passwords are a very important sensitive aspect in computer security. Password is the important identitiy in authenticating any individual in different domains. It plays a vital role in accessing any device or any software. Users around the world are consistently told about the necessity of a strong password to protect their access with unauthorized users. In this paper, we propose a comparative analysis of soft computing techniques such as Back propagation neural network (BPN), Logistic regression (LR), Hopfield neural network (HNN), Brain state in a box (BSB) and associative memory network (BAM), Convolution neural network (CNN) system for strong password classification. The dataset contains only a single attribute of passwords with 3 classes as weak, medium and strong. The experimental results analysis shows that for such a datset, the simple logistic regression model yields better output when compared with Convolution Neural networks, Back propagation neural network, Logistic regression, Hopfield neural network, Brain state in a box and Bidirectional Associative Memory. It can be concluded that logistic regression is adapted for such an application and also plays as a better prediction system for such a dataset. © 2020 IEEE.

World University root node

International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2020

A Comparative Analysis of Soft computing techniques for Password Strength Classification

Internet made a drastic change in the way data are collected. There has been huge and huge collections of data. All these data serve no purpose unless some useful information is mined from it. Prediction of future instances will be major research problem. In this work, we adapt a rough and real coded genetic algorithm-based prediction system for prediction of future instances. We adapt rough set in this work because of uncertainties present in the data. Additionally, it is used to eliminate the unwanted attributes. Real coded genetic algorithm is used to predict the values for the unknown instances by making use of multiple linear regression. The model is experimented over agriculture data obtained from Tiruvannamalai district of Tamil Nadu. The experimental results show the viability of proposed research. © 2017, King Fahd University of Petroleum &amp; Minerals.

Arabian Journal for Science and Engineering

A Framework for Prediction Using Rough Set and Real Coded Genetic Algorithm

This article describes how agriculture is the main occupation of India, and how the economy depends on agricultural production. Most of the land in India is dedicated to agriculture and people depend on the production of agricultural products. Therefore, forecasting the accuracy of future events based on extracted patterns plays a vital role in improving agricultural productivity. By considering the availability of micronutrients and macronutrients of the soil and water in a particular place, the growth of a plant is determined. This helps people to determine the crops to be cultivated at a certain place. In this article, the forecasting is carried out using rough sets and genetic algorithms. Rough sets are used to produce the decision rules whereas genetic algorithms are used to refine the rules and improve classification accuracy. Accuracy of the classification rules is analyzed using different selection methods and crossover operators. Results show that genetic algorithms with a roulette wheel selection and single point crossover provides better performance when compared with other existing techniques.

International Journal of Fuzzy System Applications

A Rule Based Classification for Vegetable Production Using Rough Set and Genetic Algorithm

RBCs stand for red blood cells (also known as erythrocytes), are the most common type of blood cells. They are the basic means of delivering oxygen, in the vertebrates to different cells and tissues. Hemoglobin is a protein in the RBCs, which carries oxygen and gives blood its red color. The normal range of RBCs in men is approximately 4.7 to 6.1 million cells per microliter and the normal range of RBCs in women is approximately 4.2 to 5.4 million cells per microliter. For a person to be eligible to donate blood, he/she should have the minimum number of RBCs in their blood for donation. This is only possible when the minimum duration between two donations is 3 months, be- cause it takes RBC about three months to develop completely. Many equipment have been developed or installed in hospitals for reducing energy consumption and increasing the efficiency. But even after installing these energy efficient devices in hospitals, it has been found out that these devices face a number of difficulties or obstacles. Thus, this paper focuses in developing an energy efficient software for blood transfusion that can function without interfering with any obstacles and thus giving accurate results.

VIT Unitversity

Department of Control and Automation

School of Electrical Engineering

Fulltext

MATEC Web of Conferences

Energy Efficient Blood Transfusion System

The modern day rule generation by association rule mining (a-priori algorithm) and optimization of the same using genetic algorithms is rather a complex process. The crux of optimization problem is the complexity and accuracy of the methods used to either mine interesting rules or to extract interesting rules from the ones generated initially. This paper has been written with a simple agenda of unifying many elegant and useful techniques to create a less complex yet accurate algorithm for rule optimization and also reduce the computation time. © 2016,International Journal of Pharmacy and Technology. All rights reserved.

International Journal of Pharmacy and Technology

Hybridization of soft computing technique with apriori for association rule mining

Hybridization of different soft computing techniques is very useful in solving real world problems. Soft computing techniques like rough set theory and fuzzy sets are used to handle uncertain or vague information present in the real world data. Hybridizing the soft computing techniques yield better result than the stand alone techniques. Hybridizing these techniques serves different purpose like attribute subset selection, improving classification accuracy, prediction and many more. Data mining concepts are useful in extracting knowledge from the large data set. The usages of some of the soft computing concepts hybridized with data mining concepts used for classification and attribute reduction are also focused and the future work of each concept is highlighted. Comparative analysis made with the survey work is focused which focuses on scalability, robustness, efficiency and accuracy of different classifiers. © 2016, International Journal of Pharmacy and Technology. All Rights Reserved.

Hybridization of soft computing framework-a survey

Many plant growth promoting rhizobacteria (PGPR), biocontrol agents and biofertilizer bacteria are used in agriculture. They are applied to crops by seed or soil application which colonizes in the rhizosphere. Although there are extensive reports on the output (growth, yield, disease resistance, phenotypes, etc) of the combined inoculations of these bacteria the companionship among these bacteria and the relative contribution to overall output is largely unknown. The starting point to unravel this would be to study the bacterial companionship in terms of ability to co-aggregate, stability of co-aggregation and developing molecular evidences for co-colonization in crop roots. Our work mainly aimed at understanding the extent of co-aggregation between Pseudomonas fluorescens and Bacillus subtilis and their co-colonization abilities in plant roots. This was verified by conducting several experiments of co-aggregation and effect of various factors like pH and growth phase, effect of various treatments like urea, protease K, EDTA, heat, thermal stability, sonication and desiccation on the extent of the co-aggregation. Co-aggregation between these two bacteria was found to be pH and growth phase dependent. Protease and EDTA treatment reduced the co-aggregation whereas sonication treatment improved the same. Talc based formulation of the bacteria was prepared separately and used for seed treatment in black gram. The seeds were germinated under laboratory conditions and growth parameters were observed. DNA from roots of germinated seedlings was used as template to amplify bacterial DNA with species specific primers. PCR analysis results indicated that P. fluorescens and B. subtilis are compatible in colonizing black gram. © 2015 Elsevier Ltd.

Department of Biotechnology

School of Bio Sciences and Technology

Biocatalysis and Agricultural Biotechnology

Co-aggregation of Pseudomonas fluorescens and Bacillus subtilis in culture and co-colonization in black gram (Vigna mungo L.) roots

Communication between heterogeneous networks became unavoidable. Clustering simplifies the communication. Cluster head is the leader of the cluster. If the cluster head fails or becomes unreachable an alternative efficient algorithm is required to recover from the failure. This proposes the algorithm which initiates the alternative cluster head selection in a heterogeneous environment. © Research India Publications.

Department of Information Technology

Department of Smart Computing

Department of Software and Systems Engineering

Global Journal of Pure and Applied Mathematics

Self restorative cluster head selection in heterogeneous network

During last few years, the interest in using natural fibers as reinforcement in polymers has increased significantly. Natural fibers are not only strong and lightweight but also relatively very cheap and bio-degradable. In this work, an investigation is carried out on jute fiber, a natural fiber. Jute fiber has gained interest in the composite field due to its superior specific properties compared to manmade synthetic fibers like glass, Kevlar, asbestos, etc. The present work describes the development and characterization of natural fiber based composites consisting of jute fiber as reinforcement and hybrid resin consisting of general purpose resin and cashew nut shell resin as matrix material. The composites are fabricated using hand lay-up technique. The tensile strength is studied using experimental and numerical analysis. The nature of hybrid matrix at different composition is also studied. The commercial Finite Element Analysis software ANSYS is used for numerical study.

Mechanical

School of Mechanical Engineering

Chennai Campus

Applied Mechanics and Materials

Finite Element Analysis of Jute Fibre Made Hybrid Polymer Matrix Composite

Cloud computing is a practical approach to experience direct cost benefits and it has the potential to transform a data centre from a capital-intensive set up to a variable priced environment. Cloud providers trade their services on cloud resources for money. It include separate prices for infrastructure elements, i.e., disk space, CPU, I/O, bandwidth and applications deployed on the infrastructure where the service is prices as static, and provides the user for pay as per the usage. These pricing scheme does not maximize profit for cloud providers. The goal of cloud economy is to optimize user satisfaction and cloud profit. So, we propose a novel scheme that achieves optimal pricing for the services of a cloud cache which is offered by a cloud provider as an integral part of its platform-as-a-service. The goal of such a cloud cache is to provide efficient querying on the back-end data at a low cost and a dynamic pricing scheme for queries executed in the cloud cache. Data caching in a cloud is a key paradigm for improving the performance of web services in terms of both end-user latency and database load. © Research India Publications.

International Journal of Applied Engineering Research

Providing an optimal price demand model by cloud cache

Nowadays, there is a huge amount of data being collected, especially at the age of internet. It is very hard to extract knowledge from this huge amount of data. These data are of no use unless we retrieve knowledge from it. As there is a huge raise in in the volume of data, it is an obvious challenge to reduce the data set and extract useful information from it. This paper mainly focuses on extracting knowledge in the form of rules using rough set by finding the reduced set of data. In rough set theory, the data is represented in the form information system. Discernability matrix is used to find the core and reduct of the attribute. After finding the core and reduct the strength of the attributes is found and the rules are generated. Also the proposed work is validated by taking real time example which extracts knowledge in the form of rules. © Research India Publications.