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

The grid denotes the electric grid which consists of communication lines, control stations, transformers, and distributors that aids in supplying power from the electrical plant to the consumers. Presently, the electric grid constitutes humongous power production units which generates millions of megawatts of power distributed across several demographic regions. There is a dire need to efficiently manage this power supplied to the various consumer domains such as industries, smart cities, household and organizations. In this regard, a smart grid with intelligent systems is being deployed to cater the dynamic power requirements. A smart grid system follows the Cyber-Physical Systems (CPS) model, in which Information Technology (IT) infrastructure is integrated with physical systems. In the scenario of the smart grid embedded with CPS, the Machine Learning (ML) module is the IT aspect and the power dissipation units are the physical entities. In this research, a novel Multidirectional Long Short-Term Memory (MLSTM) technique is being proposed to predict the stability of the smart grid network. The results obtained are evaluated against other popular Deep Learning approaches such as Gated Recurrent Units (GRU), traditional LSTM and Recurrent Neural Networks (RNN). The experimental results prove that the MLSTM approach outperforms the other ML approaches.

Department of Software and Systems Engineering

School of Information Technology and Engineering

Vellore Campus

IEEE ACCESS

A Multidirectional LSTM Model for Predicting the Stability of a Smart Grid

As digitization increases, the need to automate various entities becomes crucial for development. The data generated by the IoT devices need to be processed accurately and in a secure manner. The basis for the success of such a scenario requires blockchain as a means of unalterable data storage to improve the overall security and trust in the system. By providing trust in an automated system, with real-time data updates to all stakeholders, an improved form of implementation takes the stage and can help reduce the stress of adaptability to complete automated systems. This research focuses on a use case with respect to the real time Internet of Things (IoT) network which is deployed at the beach of Chicago Park District. This real time data which is collected from various sensors is then used to design a predictive model using Deep Neural Networks for estimating the battery life of IoT sensors that is deployed at the beach. This proposed model could help the government to plan for placing orders of replaceable batteries before time so that there can be an uninterrupted service. Since this data is sensitive and requires to be secured, the predicted battery life value is stored in blockchain which would be a tamper-proof record of the data. © 2020 IEEE.

World University root node

Department of Information Technology

2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings

A Framework for Prediction and Storage of Battery Life in IoT Devices using DNN and Blockchain

The growing demand of digital technologies are increasing the quality of human life at an unprecedented rate, but at the same time managing e-waste from these digital technologies are emerging as one of the biggest challenges for most of the industrial and government bodies. Collection of E-waste causes various problems such as environmental effluence, resource scarcity and it also results in developing various health hazards to human population. In this paper, we propose a framework using wireless sensor network and augmented reality to detect and mark the various high pollutant zone, which would save people from being exposed to hazardous environment. © Springer Nature Switzerland AG 2020.

Department of Multimedia

School of Design

Lecture Notes on Data Engineering and Communications Technologies

Managing and Monitoring E-Waste Using Augmented Reality in India

The current situation of COVID-19 demands novel solutions to boost healthcare services and economic growth. A full-fledged solution that can help the government and people retain their normal lifestyle and improve the economy is crucial. By bringing into the picture a unique incentive-based approach, the strain of government and the people can be greatly reduced. By providing incentives for actions such as voluntary testing, isolation, etc., the government can better plan strategies for fighting the situation while people in need can benefit from the incentive offered. This idea of combining strength to battle against the virus can bring out newer possibilities that can give an upper hand in this war. As the unpredictable future develops, sharing and maintaining COVID related data of every user could be the needed trigger to kick start the economy and blockchain paves the way for this solution with decentralization and immutability of data. © 2020 IEEE.

An Incentive Based Approach for COVID-19 planning using Blockchain Technology

The smart applications dominating the planet in the present day and age, have innovatively progressed to deploy Internet of Things (IoT) based systems and related infrastructures in all spectrums of life. Since, variety of applications are being developed using this IoT paradigm, there is an immense necessity for storing data, processing them to get meaningful information and render suitable services to the end-users. The “thing” in this decade is not only a smart sensor or a device; it can be any physical or household object, a smart device or a mobile. With the ever increasing rise in population and smart device usage in every sphere of life, when all of such “thing”s generates data, there is a chance of huge data traffic in the internet. This could be handled only by integrating “Internet of Everything (IoE)” paradigm with a completely diversified technology — Cloud Computing. In order to handle this heavy flow of data traffic and process the same to generate meaningful information, various services in the global environment are utilized. Hence the primary focus revolves in integrating these two diversified paradigm shifts to develop intelligent information processing systems. Energy Efficient Cloud Based Internet of Everything (EECloudIoE) architecture is proposed in this study, which acts as an initial step in integrating these two wide areas thereby providing valuable services to the end users. The utilization of energy is optimized by clustering the various IoT network using Wind Driven Optimization Algorithm. Next, an optimized Cluster Head (CH) is chosen for each cluster, using Firefly Algorithm resulting in reduced data traffic in comparison to other non-clustering schemes. The proposed clustering of IoE is further compared with the widely used state of the art techniques like Artificial Bee Colony (ABC) algorithm, Genetic Algorithm (GA) and Adaptive Gravitational Search algorithm (AGSA). The results justify the superiority of the proposed methodology outperforming the existing approaches with an increased life-time and reduction in traffic. © 2020 Elsevier Inc.

Fulltext

Journal of Parallel and Distributed Computing

Load balancing of energy cloud using wind driven and firefly algorithms in internet of everything

Background: Congestion can happen in WSNs while congregating the information and sending it towards the sink. It leads to increased packet delay, indiscriminate packet loss, severe fidelity degradation and wasted node energy. Objective: The aim of the proposed work is to suppress congestion using a dynamic weight assignment scheme, where each sensor node transmits the data in accordance to the weight assigned to it, thus ensuring priority fairness and minimizing packet loss. The proposed congestion control technique shall boost the overall performance of the system by supporting assured delivery of high importance events to sinks. Methods: Weights are assigned to each record based on two things, the delay in sending and receiving, and the change in value of the variables passed by the nodes. If the difference in timestamp is below a threshold (alpha) and the difference in the values is above a threshold (Beta), it gets a weight of W1, which is like a high priority data record. Similarly, if the difference in timestamp is above a threshold (gamma) and the values passed by the nodes have changed a negligible amount, that record is assigned a weight of W3, which is the least priority. Results: From the analysis, it is inferred that proposed method had a higher throughput and the throughput was equally distributed among all the participating nodes. Conclusion: The proposed method endeavours to avoid congestion by implementing an effective queuing mechanism to reinforce definitive wireless communication. © 2020 Bentham Science Publishers.

Department of Database Systems

School of Computer Science and Engineering

Recent Advances in Computer Science and Communications

A Weighted Assignment Approach Using Recommendation Routing for Congestion Control in Wireless Sensor Networks-WEAR

Massive Open Online Courses (MOOC) has gained a huge popularity amongst the current generation students mainly because of its open nature and its ubiquity. MOOC made it possible for thousands of aspiring learners to learn from their favorite Universities. Though this online learning platform has its advantages, many studies have proved that these massive courses are suffering from tremendous rates in students’ dropouts. This study surveys the major causes of dropouts and would try to link the MOOC failures with the learners’ stress levels. The study also proposes a framework which could be used while designing MOOC courses and will help MOOC providers to personalize the content delivery according to the online learners’ stress levels.

International Journal of Innovative Technology and Exploring Engineering Regular Issue

Framework for Personalizing Mooc Courses based on Learners’ Stress Levels Towards Increased Course Completion Rates

The main objective to use wireless sensor network (WSN) is to collect data across various nodes and send the collected data to sink for processing. This is typically the scenario in any real time application of WSN. In this paper, the authors review various existing methods in data aggregation, list out the research challenges faced by the researchers and propose solutions for each method. © Research India Publications.

International Journal of Applied Engineering Research

Challenges in data aggregation in wireless sensor network-a review

The main objective to use wireless sensor network (WSN) is to collect data from various nodes and send this data to sink for processing. This is typically the scenario in any real time application of WSN. The proposed paper discusses the issues in routing for data aggregation with respect to QOS metrics. The paper presents literary on various existing solutions for these issues highlighting the key features, pros and cons, compares the results and performance of protocols with respect to QoS metrics and pitches the research challenges to be solved. © Research India Publications.

Analysis of routing mechanisms using QoS metrics in data aggregation for wireless sensor network–A survey

Storage networking technology has enjoyed strong growth in recent years, but security concerns and threats facing networked data have grown equally fast. Today, there are many potential threats that are targeted at storage networks, including data modification, destruction and theft, DoS attacks, malware, hardware theft and unauthorized access, among others. In order for a Storage Area Network (SAN) to be secure, each of these threats must be individually addressed. In this paper, we present a comparative study by implementing different security methods in IP storage network.