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

Body mass index (BMI) is used widely as an indicator in general health. Determination of BMI using non-intrusive measurements are of interest and recent advancements in the availability of digital imaging sensors have paved the way for performing quick and automatic measurements. In this work, we consider automatic computation of BMI using correlation features from face images. We show that using face detection based facial fiducial points analysis provides good BMI prediction. Experimental results on comparing the correlation coefficients of facial ratios along with the colour feature has higher significance in BMI of a person. © 2020 - IOS Press and the authors. All rights reserved.

VIT Unitversity

Department of Software Systems

School of Computer Science and Engineering

Vellore Campus

World University root node

Technology and Health Care

Automatic body mass index detection using correlation of face visual cues

In this paper, a CBIR system based on multiple features of the images is proposed to retrieve similar images from the database of textile industry. Multiple feature technique includes well-structured union of various color, shape, and texture features. Nowadays, most of the CBIR systems use query-by-example where image is given as a query to the system which extracts the most relevant image from the database having similar features as that of query image. As classifying the category in which a particular image belongs is one of the traditional concerns in image retrieval, a lot of approaches are used for classifying large datasets of images. As traditional CBIR techniques fail for some real-world applications where user wants the desired result in the first go. Support vector machine is a learning model which when used with retrieval process finds appropriate images more often. Also, it is useful even when the size of the dataset is not so large. Using SVM classifier, the CBIR system can retrieve more relevant images from the databases. In this paper, the capability of SVM on classification of images is evaluated. © Springer Nature Singapore Pte Ltd. 2020.

Frontiers in Intelligent Computing: Theory and Applications Advances in Intelligent Systems and Computing

Content-Based Image Retrieval for Textile Dataset and Classification of Fabric Type Using SVM

Government now-a-days are looking forward to achieve “Energy for All” standards. Countries are committing themselves to reduce carbon emissions. Recently, every IT industry giants, who typically own and operate huge Data Centers (DC) are looking forward to achieve “100% usage of green energy to power their datacenters, contribute to the utility grid in equivalence to their electrical power consumptions”. Electrification and gradual decarbonisation still continue as significant, global concern. Hence it is pretty clear that need for MicroGrid (MG) based facilities is actually a mandatory. But intermittent-characteristic (unreliability/unavailability) of Renewable-Energy (RE) generating sources (like Solar Panels, Wind Turbines) regularly hinder both the stake holders-Government and IT industry from accomplishing such social and economic initiatives. Hence SmartMicroGrid (SMG) connected with utility grid are envisioned to support powering industries inorder to avoid future power outages. Interconnected industry4.0 factories where, actually the smart-management interms of two-way power supply and two-way communication network is foreseen. They are highly dependent on modern, integrated, Information and Communication technologies (IoT sensors, Fog and Cloud computing etc.). In this paper we have focussed on two objectives. Firstly our objective is to identify, optimum renewable-generation-capacities inorder to minimise investment cost of a microgrid. Secondly our objective is to maximize usage of more clean energy for applications running on FogMicroDataCenter (fogMDC), powered by microgrids and controlled by Sofware Defined Networking (SDN). We have used realistic meteorological data of Tamil nadu, India for our proposed work. To the best of our knowledge, this is the first work proposed for two different scenarios, performance modelling and economic modelling aiding MG powered FogMDCs. Proposed economic modelling work is related to finding, the optimum sizing of distributed energy resources and financial cost. Proposed performance modelling is about, the clean energy usages in micro grid powered fogMDC for operations, supported by SDN for efficient distributed Virtual Machine (VM) based resource utilization to guarantee QoS in time sensitive IoT applications. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

Computer Science

Chennai Campus

Wireless Networks

Sustainability modelling and green energy optimisation in microgrid powered distributed FogMicroDataCenters in rural area

The freedom of movement for people in urban cities in the twenty-first century is curtailed due to traffic congestion and parking problems. It has brought out the need for development of smart cities through incorporation of Internet of Things and other technologies in the planning of cities. Chennai, a city in India with a population size of 9.1 million and a vehicle pool of more than 3.7 million units, is in dire need of intelligent solutions to its traffic and transportation issues. Sustainable and practical city planning not only requires considering increased air pollution, longer travel duration, accidents, but also with frustration among travelers. Hence, smart city planning measures are incomplete if parking space issues are ignored. In this paper, we address the parking space problem and how they can be tackled in smart cities in the interest of both government and travelers. Based on the Stackelberg game model, our proposed scheme considers a game between the public authority and the travelers. The government with the help of its policies can influence the decisions taken by the travelers. In this study, we work upon proposing two utility function—one for traveler and one for government. The utility function of the government aims to maximize the public transit usage while maintaining flow of travelers to urban city centers in Chennai. City center refers to an urban center such as a shopping mall, heritage site, or government building. The utility function of an individual traveler aims to minimize travel duration, cost of travel, and other inconveniences. A trade-off demand of the players is sought using variable parking space. A small version of the game is envisioned for urban reality-based scenarios like strong center, weak center, weak transit system, strong transit system, respectively. Consequently, on the basis of the results, optimized parking space allotment is obtained and we infer that reducing parking space works more promisingly in a strong urban center scenario. The solution provided in our paper can be collaborated with existing smart parking systems for optimal results. Conclusions inferred can be applied by the government towards development of practical, efficient, and sustainable parking schemes. © 2020, Springer Nature Singapore Pte Ltd.

Advances in Intelligent Systems and Computing Soft Computing for Problem Solving

Optimization of Parking Lot Area in Smart Cities Using Game Theory

Energy, today, has become one of the most important factors in almost every industry domain. The energy reserves of a country largely influences its growth rate. Particularly in case of the textile industry, this contributes 2% to the world GDP. This paper aims at demonstrating through experimentation, how reinforcement learning, a branch of machine learning, can be adopted to help manage and optimize energy usage in a cotton textile mill. The models explored in this paper are established as nonlinear programming mode with the experiment result showing the performance of the penalty based reinforcement-learning algorithms in comparison with results obtained in [1] per annum. It has been calculated that there is a reduction of approximately 1.3% using Thompson Sampling and UCB algorithms, and 1.26% in energy consumption using random selection. © 2020 IEEE.

2020 International Conference on Innovative Trends in Information Technology, ICITIIT 2020

Investigation of Energy Management and Optimization Using Penalty Based Reinforcement Learning Algorithms for Textile Industry

Internet of things due to its profound capability has been responsible for the innovative transformations in lifestyles of human. We propose a system for the smart office environment using the Internet of things. Our developed system configuration provides a comfort of handling smart office environment using Google Voice Over Protocol and Android-based application. Use of lightweight MQTT protocols, high-frequency RF trans-receivers, Raspberry 2 Z-wave-based long distance controllers makes this system feasibly suitable for wider office areas. For low power consumption, high performance and immediate time-to-time response QoS parameters, the system is equipped with PIR, gas, flame, sound, light, temperature and humidity sensors. We ensure reliable communication with a separate channel for every sensor signals, secured with AES encryption and plug-and-play provisions. Further, mail-based anomaly or emergency alert notification is also incorporated. Finally, we have performed the experiment and also tested the developed system in Android phones and smart wear watch, namely Moto360 Watch. © 2019, Springer Nature Singapore Pte Ltd.

Department of Computational Intelligence

Proceedings of the 2nd International Conference on Data Engineering and Communication Technology Advances in Intelligent Systems and Computing

IoT-Based Smart Office System Architecture Using Smartphones and Smart Wears with MQTT and Razberry

Clustering of clinical documents is the major research area in the field of machine learning and artificial intelligence which aims to acquaint some type of association with the information that helps to highlight huge examples and patterns. The rich corpus of clinical notes consists of several unprocessed data which needs to be mined with appropriate technique to improvise the existing healthcare system. Biomedical information mining is a research strategy to recover, break down and analyze clinical information from a collection of medicinal records. This paper presents a novel approach that utilizes Non-Negative Matrix Factorization Clustering approach to mine the medication names based on age of the patients. Pharmaceutical data from clinical notes is regularly communicated with prescription names and other medication information which needs to be mined based on the similarity between documents so that more accurate extraction of similarity could be accomplished. Even in the wake of being an exceptionally effective solution, clustering is yet not deployed in the major search engines. The basic issue with it is to determine a fast and accurate cluster values even after reducing the complexity of the technique. This paper presents an enhanced multi-viewpoint similarity measure that utilizes many distinct viewpoints to measure similarity between documents so that more accurate extraction of similarity could be accomplished. © 2017 Oriental Scientific Publishing Company.

Department of Information Security

Fulltext

Biomedical and Pharmacology Journal

Enhanced Multi-View Point Non-Negative Matrix Factorization Clustering for Clinical Documents Analysis

In a technological world, every entity both natural and man-made areto be imagined as memory based objects in which information can be stored and queried later. Tracking, monitoring the location, environment status of these objects has been the basis for many real time applications to make fine grained decisions to improve the operational performance. Universities and academic institutions have campuses facilitated by many fixed assets. Adding more complexity to this is the management of the assets, so far it's a labour intensive, time consuming, lack of immediate response problem. We propose a framework, providing smart computing features, to overcome the everlasting worries pertaining in the managerial bodies concerned about their valuable assets in the campus. The proposed framework extracts the benefits from the RFID and cloud computing technologies, to ease and improve the work efficiency of the administrators, librarians and other responsible departments members to ensure that there is no misplacement and missing of assets that are massive in numbers. The framework enables automatic caching, filtering and processing of RFID events (using Hadoop) that are generated in a smarter campus. Proposed framework is implemented at department level and the results we got proved its feasibility for implementing in smarter campus. © Medwell Journals, 2016.