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

According to the World Health Organization (WHO) report, 438 million peoples are affected by diabetics in the upcoming year of 2030. Due to the seriousness of the diabetics’ disease, it has to be predicted in the earlier stage but the minimum symptoms of diabetic failure to predict in earlier stage. So, the automatic and earlier diabetic prediction system needs to be created for eliminating the serious factors in medical field. There are several earlier diabetic prediction system is created with the help of hybridized machine learning techniques but they are difficult to process the huge dimension of data as well as consume more time for predicting diabetic related features. For overcoming the above issues, in this paper introduces the swarm intelligent redundancy relevance (RR) along with convolution trained compositional pattern neural network for predicting the diabetic disease. Initially, the diabetic data has been collected from Pima Indian Diabetic dataset, the dimensionality of data is reduced by swarm intelligence RR techniques, the selected features are trained by layers of convolution networks that helps to speed up the diabetic prediction process. Finally, diabetic classification process is done by compositional pattern neural network and the efficiency is evaluated using MATLAB based experimental results. © 2019, IUPESM and Springer-Verlag GmbH Germany, part of Springer Nature.

School of Computer Science and Engineering

Vellore Campus

Department of Information Security

Health and Technology

Hybrid swarm intelligent redundancy relevance (RR) with convolution trained compositional pattern neural network expert system for diagnosis of diabetes

Diabetes Mellitus disease is said to occur when there is not proper generation of insulin in the body which is needed for proper regulation of glucose in the body. This health disorder leads to whole degradation of several organs including the heart, kidneys, eyes, nerves. Hence diabetes disease diagnosis by means of accurate prediction is vital. When such disease related data is given as input to several machine learning techniques it becomes an important classification problem. The purpose of the work done in this paper is to compare several classic machine learning algorithms including decision tree, logistic regression and ensemble methods to identify the more accurate classification algorithm for better prediction of the diabetes mellitus disease. This in turn would help for better and effective treatment.

World University root node

Journal of Computational and Theoretical Nanoscience

Comparative Study of Machine Learning Algorithms on Prediction of Diabetes Mellitus Disease

In the present paper, the contributions of dislocations and grain boundaries to the broadening of diffraction line profile have been delineated. Contribution of each factor is studied on single as well as poly crystalline ‘virtual samples’ containing different dislocation configurations generated by molecular dynamics and evaluating the simulated X-ray diffraction line profiles of these samples. Individual contributions to diffraction line profiles by different sample features, such as domain size, dislocations, grain boundaries, have been isolated by deconvoluting the evaluated diffraction line profiles. The diffraction line profiles exhibited significant asymmetry and peak splitting in the case of dislocations with predominantly edge character. It has been shown that splitting of diffraction peaks carries information about the magnitude of Burger's vectors of the dislocations. Application of the variance method based on single peak fitting and Wilkens method based on whole powder pattern fitting of line profile analysis on the computed diffraction line profiles, showed that while accurate domain size estimation was possible, there was an under estimation of dislocation density at the high dislocation density and small grain size regime considered in the present study. © 2019 Elsevier B.V.

Computational Materials Science

Influence of dislocations and grain boundaries on diffraction line profiles of nano-crystalline materials: A numerical study

This paper presents a new Density-Peaks and Self-Organizing Generative Adversarial Networks (DP-SO-GAN) for clustering mixed datasets. Many clustering methods depend on the assumption that datasets contain either categorical or numerical attributes. Nevertheless, in real-time, most of the applications include mixed categorical and numerical attributes. In medicine, the clustering of cardiovascular disease is an essential task. The clustering of such data attributes is a vital and challenging issue. First, we transform mixed data attributes such as categorical attributes using a one-hot encoding technique and numerical attributes using normalization techniques. The converted characteristics are input to a Self-Organizing Generative Adversarial Networks (SO-GAN) to learn the feature map. Second, we train two kernel networks, such as the generator and discriminator, and each one holds a trivial amount of convolution kernels. Last, we propose an enhanced density peaks clustering algorithm and computing similarity measure between the data objects in the feature representation. The clustering accuracy for the cardiovascular disease dataset results in 88.32% with a standard deviation of 0.1 and is relatively higher than that of other existing algorithms. The training time for hand-written digits datasets over 300 epochs is 3148.26 ​s. Experiment results obtained on a set of five datasets demonstrate the merits of the proposed method, especially in terms of the stability and efficiency of network training. The computational complexity of the proposed method in terms of floating-point operations is reduced by around 18% as compared with the classical generative adversarial networks. © 2020 Elsevier B.V.

Chemometrics and Intelligent Laboratory Systems

Clustering algorithm for mixed datasets using density peaks and Self-Organizing Generative Adversarial Networks

Machine learning is a promising domain which is widely used now a days in the field of agriculture. The availability of manpower for agriculture is not enough and skill full farmers are less. Understanding the situation of the crop is not that much easy to detect and prevent the diseases in the crop. It is also widely employed in various agricultural fields such as topsoil management, yield management, water management, disease management and climate conditions. The machine learning models facilitate very fast and optimal decisions. The model of machine learning involves with training and testing to predict the accuracy of the result. The use of machine learning in agriculture helps to increase the productivity and better management on soil classification, disease detection, species management, water management, yield prediction, crop quality and weed detection. This article aims at providing detailed information on various machine learning approaches proposed in the past five years by emphasizing the advantage and disadvantages. It also compares different machine learning algorithms used in the modern agricultural field. © 2020 SCPE.

Scalable Computing

A review on the role of machine learning in agriculture

In this paper we for the first time develop, define and describe a new class of algebraic codes using Neutrosophic Quadruples which uses the notion of known value, and three unknown triplets (T,I,F) where T is the truth value, I is the indeterminate and F is the false value. Using this Neutrosophic Quadruples several researchers have built groups, NQ-semigroups, NQ-vector spaces and NQ-linear algebras. However, so far NQ algebraic codes have not been developed or defined. These NQ-codes have some peculiar properties like the number of message symbols are always fixed as 4-tuples, that is why we call them as Neutrosophic Quadruple codes. Here only the check symbols can vary according to the wishes of the researchers. Further we find conditions for two NQ-Algebraic codewords to be orthogonal. In this paper we study these NQ codes only over the field Z2. However, it can be carried out as a matter of routine in case of any field Zp of characteristics p. © 2020. All Rights Reserved.

Neutrosophic Sets and Systems

Neutrosophic Quadruple Algebraic Codes over Z2 and their Properties

Performing secure and robust embedding and extracting in real time voice streams without deteriorating the voice quality is a great challenge. This paper aims on hiding the secret data bits in the voice packets without modifying any data in the cover thereby improving the embedding transparency and becomes robust against the steganalysis attacks using coverless approach. Initially a hash array is built with the frame size. The cover bit position is identified from the hashing function. The hash array is marked with a flag value to indicate that the particular sample consist of the secret message bit. The hash array is attached with the VoIP samples, at the receiver side the hash table is separated, and the secret bits are extracted based on the hash array. The experimental results conducted on a VoIP prototype proved to be simpler and effective in terms of the computational complexity, undetectability and voice quality at both sender and receiver end. © 2020 Sciendo. All rights reserved.

Department of Software and Systems Engineering

School of Information Technology and Engineering

Fulltext

Cybernetics and Information Technologies

Coverless VoIP steganography using hash and hash

The wireless network technology with its gradual advancements is adapted by many domains like banking, governance, health services, etc., where most of their transactions include customer’s sensitive data. Along with advancement in the network technologies, digital crime is also increased at high rate. This may cause loss of sensitive data through malicious activities in the network. This concern of network security system can be effectively handled through the strong authentication mechanism. It can be observed that multiple authentication mechanisms that are currently used in the wireless digital network are vulnerable towards various advanced malicious techniques. Hence, there is a need to strengthen the existing authentication mechanisms or to design a stronger authentication mechanism. This paper considers the vulnerabilities identified in a two-factor authentication scheme for online medical services proposed by Li et al. and further proposes an enhanced two-factor authentication that overcomes the vulnerabilities analysed from Li et al. mechanism. Copyright © 2020 Inderscience Enterprises Ltd.

International Journal of Internet Manufacturing and Services

An enhanced two factor authentication for e-healthcare system

Mobile ad hoc Network (MANET) consists of a group of mobile nodes and the communication among them is done without any supporting centralised structure. Routing in MANETs is a difficult because of their dynamic features such as high mobility, constrained bandwidth and link failures due to energy loss. The objective of this work is to implement an intelligent routing protocol by selecting efficient nodes for routing the information. To provide good throughput in the network, Ant Colony Optimisation (ACO) based enhanced energy-efficient intelligent routing is proposed. Selecting the best intermediate hop for intelligent routing includes ACO technique which greatly reduces the network delay and link failures by validating the coordinator nodes. Coordinator nodes are picked by validating their metrics and Best Coordinator Nodes (BCN) are selected among them as good intermediate hops for intelligent routing. The performance is evaluated for the proposed protocol and the metrics considered for evaluation are delivery and loss rate of sent data, throughput and lifetime of the network, delay and energy consumption. © 2020 Inderscience Enterprises Ltd.