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

Computer Science

Cloudbursts are weather phenomena with very high rain intensity and can result in flash floods causing large scale destruction and are extremely complex to forecast. The main aim of this research is to develop a model which would be capable of predicting cloudbursts by forecasting rain intensity. A model, combination of machine learning models with Markov Chain process, capable of forecasting rainfall intensity and in turn cloudbursts, has been proposed in this paper. The model uses Markov chain technique, in which prediction has been done based on the weather data from the past seven days. This proposed model has been implemented in two different ways, assigned each day of the previous seven days with (i) constant weights (ii) incremental weights, with closer days being considered more important. The results of the proposed model have been verified with the PRISM data set and the results have been tabulated. This result of the research shows that a multilayer perceptron with Markov chain process using incremental weights works better quantitatively.

World University root node

School of Computer Science and Engineering

Chennai Campus

Nowcasting - Rain Intensity Prediction Using Machine Learning Models with Markov Chain Process

There is great demand for VANETs in recent times. VANETs enable vehicular communication with the advent of latest trends in communication like 5G technology, software-defined networks, and fog and edge computing. Novel applications are evolving in recent times on VANETs with the proliferation of internet of things. Real test bed implementation is not always feasible with various limitations like expenditure and manpower and requires more time to experiment with the new facets of VANETs. Hence, the researchers should be aware of the variety of simulation tools that are capable of running VANET simulations. Simulation is a powerful tool in developing any critical/complex system that constitutes minimum cost and effort. The simulation tools of VANETs should support multiple mobility models, real-world communication protocols, and traffic modeling scenarios. This chapter gives a clear view on available tools and their characteristics on VANETs for research purposes. &nbsp;

Modelling and Simulation of Fast-Moving Ad-Hoc Networks (FANETs and VANETs)

A Review of Various Modeling Software for VANETs: Simulation and Emulation Tools

Vehicular ad hoc networks (VANETs) are a type of ad hoc networks where the node movements are high and there will be instant communication between the vehicles (nodes). In tis chapter, the authors propose a real-time simulation of vehicular ad hoc networks using simulation of urban mobility (SUMO) in two cases: 1) user-defined road structure and 2) roads designed through open street maps. In both these cases, cars, buses, trucks, pedestrians, and bicycles will be running in the roads. Most of the vehicles will be following the Euro emission norms. Later these cars will be modelled as nodes in a network and analyse the various network performance metrics like throughput and packet delivery ratio were computed.

Real-Time Traffic Simulation of Vehicular Ad hoc Networks

Description:In the event of a disastrous event leading to the loss of communication networks, ad-hoc networks are a potent wireless communication resource because of their unique features including being quickly deployable and having a distributed nature, large coverage area, reduced cost, and more. Flying ad-hoc networks (FANETS) and vehicular ad-hoc networks (VANETS) are the future technology and can solve many problems in e-commerce delivery through drones, agriculture, vaccine delivery, and more. The unique characteristics of these networks and special requirements have created new challenges for the research community in recent decades.Modelling and Simulation of Fast-Moving Ad-Hoc Networks (FANETs and VANETs) enhances the modelling and simulation aspects of FANETS and VANETS and understands the protocols in mac layer and network layers for fast-moving ad-hoc networks. It presents simulations run using various simulation tools and measures the performance metrics of ad-hoc networks. Covering topics such as emulation tools, secure communication, and modelling software, this premier reference source is an excellent resource for computer scientists, IT specialists, business leaders and managers, supply chain and logistics management, libraries, students, government officials, international organizations, law enforcement, engineers, agriculturalists, researchers, and academicians.

Modelling and Simulation of Fast-Moving Ad-Hoc Networks (FANETs and VANETs)

Transactions on Emerging Telecommunications Technologies

Similarity-based clustering and data aggregation with independent component analysis in wireless sensor networks

In deep learning the most significant breakthrough in the field of image recognition, object detection language processing was done by Convolutional Neural Network (CNN). Rapid growth in data and neural networks the performance of the DNN algorithms depends on the computation power and the storage capacity of the devices.MethodsIn this paper, the convolutional neural network used for various image applications was studied and its acceleration in the various platforms like CPU, GPU, TPU was done. The neural network structure and the computing power and characteristics of the GPU, TPU was analyzed and summarized, the effect of these on accelerating the tasks is also explained. Cross-platform comparison of the CNN was done using three image applications the face mask detection (object detection/Computer Vision), Virus Detection in Plants (Image Classification: agriculture sector), and Pneumonia detection from X-ray Images (Image Classification/medical field).ResultsThe CNN implementation was done and a comprehensive comparison was done on the platforms to identify the performance, throughput, bottlenecks, and training time. The CNN layer-wise execution in GPU and TPU is explained with layer-wise analysis. The impact of the fully connected layer and convolutional layer on the network is analyzed. The challenges faced during the acceleration process were discussed and future works are identified

Fulltext

PeerJ ComputerScience

Effect of neural network structure in accelerating performance and accuracy of a convolutional neural network with GPU/TPU for image analytics

Online judge systems that enable the automatic evaluation of predictive models face the problem of choosing the best model among those with near equal accuracy measures. In such scenarios, interpreting competitive models may provide a better insight towards robustness. Sentiment analysis is a well- explored domain with many available approaches and libraries. Despite this, it is context-sensitive and poses many challenges to the research community and thus deems fit to our analysis. Selecting a model with the highest accuracy may not be satisfactory, especially when the decision margins are too narrow. Our comparative study on models with similar accuracies and f1-scores but distinct underlying architectures incorporate custom metrics and evaluation methods to assess their performance on a sentiment analysis task. We have proposed to include human judgment in an online judge system using a feedback acquisition mechanism, presenting explanations for model decisions on selected test cases. Our initial experimental findings indicate that evaluating model robustness by incorporating a well-defined human feedback mechanism, using model agnostic approaches encourages online judge systems to make explainable decisions. The p-value associated with a paired t-Test on the feedback collected for model preference indicates a significant preference for the model supported by our metrics.

2021 Smart Technologies, Communication and Robotics (STCR)

Comparing Deep Sentiment Models using Quantified Local Explanations

Our society has undergone a massive technological revolution over the past decade and electronic appliances have now become ubiquitous. The increase in production of electronic products and the growing inherent need to own the latest technology available has led to a significant increase in the amount of E-waste produced each year. India generated 3.2 million tonnes of E-waste in 2020, with metropolitan cities like Mumbai, Delhi and Bangalore leading the list. Proper management and recycling of E-wastes are critical for the sustainability of any modern city today. While industrial and commercial collection of E-wastes has been in the spotlight, solutions for collection of E-wastes from individual households are limited. This article proposes the implementation of a mobile robot that identifies common electronic wastes based on transfer learning and serves as an attachment to existing municipality garbage trucks. The robot moves around, identifies electronic wastes and performs segregation of the identified material via its arm-based lift and storage mechanism. A convolutional neural network–based identification system has been employed for categorising the E-wastes and yields 96% accuracy. This is a first of its kind attempt, especially in India, to collect and segregate E-wastes from homes and individuals. The system will relieve unskilled labour from the hazardous process while providing a 20% decrease in costs over a 5-year period. The application of this article aims to provide a viable mobile solution for E-waste collection from households with minimal human intervention.

Waste Management and Research: The Journal for Sustainable Economy

Application of artificial intelligence to enhance collection of E-waste: A potential solution for household WEEE collection and segregation in India

Modern ages have perceived an exemplar swing in warehousing electronic health records (EHRs) on cloud settings with the catholic solicitation of mobile healthcare systems, where mobile devices are assimilated by means of cloud computing to assist medicinal data interactions amid patients and surgeons. The distribution of EHRs has prodigious optimistic connotation for investigation of disease and doctors’ diagnosis. This radical model empowers healthcare amenities with truncated operating charge, high flexibility, as well as EHRs accessibility. It is of paramount significance to hitch therapeutic evidence sprinkled through healthcare establishments to provision exhaustive data investigation and accomplish custom-made healthcare. Nevertheless, this newfangled archetype also nurtures apprehensions about data privacy in addition to network security for healthcare schemes. Exactly how to steadfastly stake data among mobile consumers while pledging sophisticated security echelons in cloud is a perplexing concern. Blockchain, by means of a public ledger pigeonholed through its transparency, tamper-evidence, decentralization, unforgeability, verifiability, as well as anonymity can support in forming a secure healthcare scheme. Existing works primarily recompense devotion to centralized in addition to Blockchain-based mechanisms. Nonetheless, they could not acclimatize to the snowballing volume of global medical records and agonize from multifaceted application encounters, singly. In this paper, the authors recommend a Diagonal Digital Signature Algorithm (DDSA) with Merkle Patricia Hash Trie (MPHT) algorithm which is an innovative EHRs sharing framework that exploits Blockchain to expedite secure medical record sharing amid dissimilar patients and surgeons. The pragmatic outcomes illustrate that our scheme affords an operative elucidation for unswerving data interactions on cloud while conserving delicate medical records in contrast to impending intimidations. This work completely works for the Architecture of data can be shared in secured way in the IoT-based health care applications. In the proposed secure data sharing scheme for smart medical applications, the amount of exponential and bilinear mapping procedures in the course of decryption is habitually proportional to the complexity of access control policy. The scheme assessment along with the security investigation also exhibit the performance enhancements in light-weight access control; slightest network latency, transmission delay and file loss rate; with extraordinary security as well as data privacy, paralleled to the prevailing record sharing schemes.