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

This paper introduces Single Valued Refined Neutrosophic Set (SVRNS) which is a generalized version of the neutrosophic set. It consists of six membership functions based on imaginary and indeterminate aspect and hence, is more sensitive to real-world problems. Membership functions defined as complex (imaginary), a falsity tending towards complex and truth tending towards complex are used to handle the imaginary concept in addition to existing memberships in the Single Valued Neutrosophic Set (SVNS). Several properties of this set were also discussed. The study of imaginative pretend play of children in the age group from 1 to 10 years was taken for analysis using SVRNS, since it is a field which has an ample number of imaginary aspects involved. SVRNS will be more apt in representing these data when compared to other neutrosophic sets. Machine learning algorithms such as K-means, parallel axes coordinate, etc., were applied and visualized for a real-world application concerned with child psychology. The proposed algorithms help in analysing the mental abilities of a child on the basis of imaginative play. These algorithms aid in establishing a correlation between several determinants of imaginative play and a child’s mental abilities, and thus help in drawing logical conclusions based on it. A brief comparison of the several algorithms used is also provided.

School of Computer Science and Engineering

Vellore Campus

VIT Unitversity

Fulltext

Symmetry

Study of Imaginative Play in Children Using Single-Valued Refined Neutrosophic Sets

In the last decade, opinion mining and sentiment analysis have been the subject of fascinating interdisciplinary research. Alongside the evolution of social media networks, the sheer volume of social media text available for sentiment analysis has increased multi-fold, leading to a formidable corpus. Sentiment analysis of tweets have been carried out to gauge public opinion on breaking news, various policies, legislations, personalities and social movements. Fuzzy logic has been used in the sentiment analysis of twitter data, whereas neutrosophy which factors in the concept of indeterminacy has not been used to analyse tweets. In this paper, the concept of multi refined neutrosophic set (MRNS) with two positive, three indeterminate and two negative memberships is proposed. Single valued neutrosophic set (SVNS), triple refined indeterminate neutrosophic set (TRINS) and MRNS have been used in the sentiment analysis of tweets on ten different topics. Eight of these topics chosen for sentiment analysis are related to Indian scenario and two topics to international scenario. A comparative analysis of the methods show that the approach with MRNS provides better refinement to the indeterminacy present in the data. © 2019 Elsevier B.V.

VIT School for Agricultural Innovations and Advanced Learning

World University root node

Computers in Industry

Sentiment analysis of tweets using refined neutrosophic sets

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

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.

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

As recent development of technology, it enables patients to get treatment remotely from doctors through audio conversation. The fourth highest number of death every year is caused by diabetics. Almost 50% to 80% of patients can avoid diabetics if the cause is found at the early stage. In this paper, we propose a new methodology to detect Diabetes at an early stage and recommend few attributes in which the patient needs to be careful in order to avoid diabetics. The proposed methodology makes use of fuzzy logic and kNN classifier to find out the caution attributes and recommends them as soon as possible. The proposed algorithm detects the audio signals from patients or clinical labs to process the data. We implemented our proposed methodology on Pima Indian dataset and compared with existing algorithms and the result shows that our algorithm outperforms existing algorithms. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

International Journal of Speech Technology

Remote diagnosis of diabetics patient through speech engine and fuzzy based machine learning algorithm

Purpose: Erythemato-squamous disease (ESD) is one of the complex diseases related to the dermatology field. Due to common morphological features, the diagnosis of ESDs become stringent and leads to inconsistency. Besides, diagnosis has been done on the basis of inculcated visible symptoms pertinent with the expertise of the physician. Hence, ontology construction for ESD is essential to ensure credibility, consistency, to resolve lack of time, labor and competence and to diminish human error. Design/methodology/approach: This paper presents the design of an automatic ontology framework through data mining techniques and subsequently depicts the diagnosis of ESD using the available knowledge- and rule-based system. Findings: The rule language (Semantic Web Rule Language) and rule engine (Jess and Drools) have been integrated to explore the severity of the ESD and foresee the most appropriate class to be suggested. Social implications: In this paper, the authors identify the efficiency of the rule engine and investigate the performance of the computational techniques in predicting ESD using three different measures. Originality/value: Primarily, the approach assesses transfer time for total number of axioms exported to rule engine (Jess and Drools) while the other approach measures the number of inferred axioms (process time) using the rule engine while the third measure calculates the time to translate the inferred axioms to OWL knowledge (execution time). © 2020, Emerald Publishing Limited.

International Journal of Intelligent Unmanned Systems

A comparative study on the performance of rule engines in automated ontology learning: a case study with erythemato-squamous disease (ESD)

Erythemato-squamous disease (ESD) is one of the complex diseases in the dermatology field, the diagnosis of which is challenging, due to common morphological features and often leads to inconsistent results. Besides, diagnosis has been done on the basis of inculcated visible symptoms pertinent with the expertise of the physician. Hence, ontology construction for prediction of erythemato-squamous disease through data mining techniques was believed to yield a clear representation of the relationships between the disease, symptoms and course of treatment. However, the classification accuracy required to be high in order to obtain a precise ontology. This required identifying the correct set of optimal features required to predict ESD. This paper proposes the Gain based Relative-Non-Redundant Attribute selection approach for diagnosis of ESD. This methodology yielded 98.1% classification accuracy with Adaboost algorithm that executed J48 as the base classifier. The feature selection approach revealed an optimal feature set comprising of 19 selected features. Copyright © 2020 Inderscience Enterprises Ltd.

International Journal of Business Intelligence and Data Mining

An automated ontology learning for benchmarking classifier models through gain-based relative-non-redundant feature selection: A case-study with erythemato-squamous disease