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

Neutrosophy is the study of neutralities, which is an extension of discussing the truth of opinions. Neutrosophiclogic can be applied to any field, to provide the solution for indeterminacy problem. Many of the real-world datahave a problem of inconsistency, indeterminacy and incompleteness. Fuzzy sets provide a solution for uncertainties,and intuitionistic fuzzy sets handle incomplete information, but both concepts failed to handle indeterminateinformation. To handle this complicated situation, researchers require a powerful mathematical tool, naming,neutrosophic sets, which is a generalised concept of fuzzy and intuitionistic fuzzy sets. Neutrosophic sets providea solution for both incomplete and indeterminate information. It has mainly three degrees of membership suchas truth, indeterminacy and falsity. Boolean values are obtained from the three degrees of membership by cut relationmethod. Data items which contrast from other objects by their qualities are outliers. The weighted density outlierdetection method based on rough entropy calculates weights of each object and attribute. From the obtained weightedvalues, the threshold value is fixed to determine outliers. Experimental analysis of the proposed method hasbeen carried out with neutrosophic movie dataset to detect outliers and also compared with existing methods to proveits performance.

World University root node

School of Computer Science and Engineering

Vellore Campus

Fulltext

CAAI Transactions on Intelligence Technology

Outlier detection in neutrosophic sets by using rough entropy based weighted density method

Likert scale is the most widely used psychometric scale for obtaining feedback. The major disadvantage of Likert scale is information distortion and information loss problem that arise due to its ordinal nature and closed format. Real-world responses are mostly inconsistent, imprecise and indeterminate depending on the customers’ emotions. To capture the responses realistically, the concept of neutrosophy (study of neutralities and indeterminacy) is used. Indeterminate Likert scale based on neutrosophy is introduced in this paper. Clustering according to customer feedback is an effective way of classifying customers and targeting them accordingly. Clustering algorithm for feedback obtained using indeterminate Likert scaling is proposed in this paper. While dealing real-world scenarios, indeterminate Likert scaling is better in capturing the responses accurately. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

VIT School for Agricultural Innovations and Advanced Learning

Soft Computing

Indeterminate Likert scale: feedback based on neutrosophy, its distance measures and clustering algorithm

Neutrosophic components (NC) under addition and product form different algebraic structures over different intervals. In this paper authors for the first time define the usual product and sum operations on NC. Here four different NC are defined using the four different intervals: (0, 1), [0, 1), (0, 1] and [0, 1]. In the neutrosophic components we assume the truth value or the false value or the indeterminate value to be from the intervals (0, 1) or [0, 1) or (0, 1] or [0, 1]. All the operations defined on these neutrosophic components on the four intervals are symmetric. In all the four cases the NC collection happens to be a semigroup under product. All of them are torsion free semigroups or weakly torsion free semigroups. The NC defined on the interval [0, 1) happens to be a group under addition modulo 1. Further it is proved the NC defined on the interval [0, 1) is an infinite commutative ring under addition modulo 1 and usual product with infinite number of zero divisors and the ring has no unit element. We define multiset NC semigroup using the four intervals. Finally, we define n-multiplicity multiset NC semigroup for finite n and these two structures are semigroups under + modulo 1 and(M(S),+,×) and(n-M(S),+,×)are NC multiset semirings. Several interesting properties are discussed about these structures. © 2020 by the authors.

Symmetry

Neutrosophic components semigroups and multiset neutrosophic components semigroups

Mobile edge computing (MEC) becomes popular as it offers cloud services and functionalities to the edge devices, to enhance the quality of service (QoS) of end-users by offloading their computationally intensive tasks. At the same time, the rise in the number of internet of things (IoT) objectives poses considerable cybersecurity issues owing to the latest rise in the existence of attacks. Presently, the development of deep learning and hardware technologies offers a way to detect the present traffic condition, data offloading, and cyber-attacks in edge networks. The utilization of DL models finds helpful in several domains in which the MEC provides the decisive beneficiary of the approach for traffic prediction and attack detection since a large quantity of data generated by IoT devices enables deep models to learn better than shallow approaches. In this view, this paper presents a new DL based traffic prediction with a data offloading mechanism with cyber-attack detection (DLTPDO-CD) technique. The proposed model involves three major processes traffic prediction, data offloading, and attack detection. Initially, bidirectional long short term memory (BiLSTM) based traffic prediction to enable the proficient data offloading process. Then, the adaptive sampling cross entropy (ASCE) technique is executed to maximize the network throughput by making decisions related to offloading users to the WiFi system. Finally, a deep belief network (DBN) optimized by a barnacles mating optimizer (BMO) algorithm called BMO-DBN is applied as a detection tool for cyberattacks in MEC. Extensive simulation is carried out to ensure the proficient performance of the DLTPDO-CD model. The experimental outcome stated the superiority of the presented model over the compared methods under different dimensions. © 2019 IEEE Computer Society. All rights reserved.

IEEE Access

Deep learning enabled data offloading with cyber attack detection model in mobile edge computing systems

Internet of Vehicle (IoV) technology is a promising application of Internet of Things (IoT) employed in smart city environment for smart communication. Traffic handling and non-delay tolerant communication services are expected from the communicating vehicles to improve its application efficiency. With the consideration of IoV in healthcare applications, this manuscript introduces a rapid connection aware neighbor selection (RCNS) for improving the efficiency in handling medical information. The selection process is induced by an instantaneous reward based learning algorithm (RLA) for ease of neighbor selection. The multi-attributes of the neighbors in the information transmitting route are estimated with the knowledge of their position. Distance and reward of the neighbors in the transmission direction are assessed using a beacon-assisted vehicle discovery that minimizes the impact of collision. Different from the other neighbor selection schemes, this method is relies on renewed attribute estimated at the time of transmission. This aids the transmitter to decide transmission and modify transmission attributes. The performance of the proposed neighbor selection method is estimated through extensive simulation using the metrics: delay, delivery ratio, selection overhead and outage. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

Department of Analytics

Peer-to-Peer Networking and Applications

A reward based connectivity-aware IoV neighbor selection for improving reliability in healthcare information exchange

Technology development has improved to its extent for mobile monitoring that mainly concentrates on a new trend that named as the Internet of Vehicles (IoV).A large number of researchers and organizations are attracted by this technological development that promises to be huge commercial interest. Several health monitoring devices were developed for the purpose of humans to identify themselves about their health problems and state of the situation about their health. This paper proposes a new architecture design for the healthcare that mainly concentrates on heart diseases using the IoV technology. Here, the continuous health monitoring device is used to monitor heart-related diseases that connected with IoV for obtaining a new way to provide and gather information about their health condition and updated automatically to the IoV based ambulance and the reports are updated to doctors using the same IoV technique. The architecture explains the several protocols that were used for communication, managing and analysis of data and transmitting from vehicle to device. © 2019, IUPESM and Springer-Verlag GmbH Germany, part of Springer Nature.

Health and Technology

A new healthcare architecture using IoV technology for continuous health monitoring system

Driving may be a skill that needs our full attention to safety control the vehicle and reply to event happening on the road. Distracted driving becomes a bigger threat per annum and has been the leading causes of accidents for the past decades. There are 3 forms of distractions i eyes off the road visual, ii mind off the road cognitive, iii fatigue or drowsiness while driving. in step with the study released by National Highway Traffic Safety AdministrationNHTSA and also the Virginia Tech Transportation InstituteVTTI, 80 percent of collision and 65 percent of near collision involve some kind of driver distraction. To deal with these challenges, we introduce a system to observe the motive force in terms of fatigue, distraction and activities. This method deals with automatic driver activity detection supported visual information and MTCNN. We propose an algorithm to trace and analyze drivers eyes PERCOLSpercentage of eyelid closure, heartbeat rate. © 2020 SERSC.

International Journal of Advanced Science and Technology

Detection of driver drowsiness using multi-task cnn framework

Intrusion detection systems assume a noteworthy job in the provision of security in wireless Sensor networks. The existing intrusion detection systems focus only on the detection of the known types of attacks. However, it neglects to recognise the new types of attacks, which are introduced by malicious users leading to vulnerability and information loss in the network. In order to address this challenge, a new intrusion detection system, which detects the known and unknown types of attacks using an intelligent decision tree classification algorithm, has been proposed. For this purpose, a novel feature selection algorithm named dynamic recursive feature selection algorithm, which selects an optimal number of features from the data set is proposed. In addition, an intelligent fuzzy temporal decision tree algorithm is also proposed by extending the decision tree algorithm and integrated with convolution neural networks to detect the intruders effectively. The experimental analysis carried out using KDD cup data set and network trace data set demonstrates the effectiveness of this proposed approach. It proved that the false positive rate, energy consumption, and delay are reduced in the proposed work. In addition, the proposed system increases the network performance through increased packet delivery ratio. © The Institution of Engineering and Technology 2020

Computer Science

Chennai Campus

Department of Information Technology

School of Information Technology and Engineering

IET Communications

Intrusion detection using dynamic feature selection and fuzzy temporal decision tree classification for wireless sensor networks

Opinion mining is an ongoing research area in e-commerce which aims at analyzing the people's opinions, sentiments and emotions. Moreover, the existing e-commerce systems allow the users to share their feedback in the form of textual reviews regarding the products and services. It also allows the consumers to give ratings for products that help in future recommendation of products. In this research work, a computational framework for efficiently predicting the consumer review ratings on the products has been proposed. The proposed framework integrates dimensionality reduction, genetic algorithm, fuzzy c-means and adaptive neuro-fuzzy inference techniques to overcome the limitations of the existing systems. Experiments have been conducted in this work using Amazon dataset consisting of reviews for different products. This system provides better performance and prediction accuracy for review ratings when it is compared with the related work. © 2020 Inderscience Enterprises Ltd.

International Journal of Business Intelligence and Data Mining

Fuzzy-based review rating prediction in e-commerce

This paper seeks to evaluate the performance of the state of the art object classification algorithms for the purpose of cyclist detection using the Tsinghua–Daimler Cyclist Benchmark. This model focuses on detecting cyclists on the road for its use in development of autonomous road vehicles and advanced driver-assistance systems for hybrid vehicles. The Tiny YOLO v2 algorithm is used here and requires less computational resources and higher real-time performance than the YOLO method, which is extremely desirable for the convenience of such autonomous vehicles. The model has been trained using the training images in the mentioned benchmark and has 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. © 2020, Springer Nature Singapore Pte Ltd.