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 Software Systems

Although hypoxia is a critical factor that can drive the progression of various diseases, the mechanism underlying hypoxia itself remains unclear. Recently, m6A has been proposed as an important factor driving hypoxia. Despite successful analyses, potential genes were not selected with statistical significance but were selected based solely on fold changes. Because the number of genes is large while the number of samples is small, it was impossible to select genes using conventional feature selection methods with statistical significance. In this study, we applied the recently proposed principal component analysis (PCA), tensor decomposition (TD), and kernel tensor decomposition (KTD)-based unsupervised feature extraction (FE) to a hypoxia data set. We found that PCA, TD, and KTD-based unsupervised FE could successfully identify a limited number of genes associated with altered gene expression and m6A profiles, as well as the enrichment of hypoxia-related biological terms, with improved statistical significance.

School of Computer Science and Engineering

Vellore Campus

World University root node

Fulltext

Scientific reports

Identification of genes associated with altered gene expression and m6A profiles during hypoxia using tensor decomposition based unsupervised feature extraction

In recent years, oceanic based research is gradually growing across the globe. Most researchers in this field aim at resolving the major challenges of Underwater Acoustic Sensor Networks like limited bandwidth, high propagation delay, 3D topology, media access control, routing, resource utilization, and power constraint neglecting spectrum utilization. However, most UAN designs consider the acoustic communication in underwater as a single network and only a very few consider the existence of other multiple acoustic systems in the ocean. Both the natural acoustic systems and artificial acoustic systems in the ocean use the acoustic means of communication leading to a heavily overcrowded spectrum. Despite the oversharing of channels the spectrum is still temporally and spatially underutilized. Unlike cognitive radio, spectrum allocation in cognitive acoustics is highly challenging due to the unique features of the underwater channel and the acoustic systems. The increasing intervention of anthropogenic activities in the oceans has resulted in an overshared, scarce, and inefficiently utilized spectrum. As an effort to calm down these adverse impacts, an underwater cognitive acoustic network-based spectrum decision strategy is proposed in this paper to aid in efficient spectrum utilization and allocation by multiple acoustic systems in the underwater environment. The proposed strategy is aimed at an environmentally friendly spectrum utilization model with much emphasis given to the primary users, the marine species. This paper considers all possible marine species and not just limit it to marine mammals. Finally, the scope of this paper is to provide an in-depth view of cognitive acoustics in UASN that can pay way for environmentally safe underwater research and marine habitat conservation in the future. © 2020 Elsevier Ltd

Applied Acoustics

An underwater cognitive acoustic network strategy for efficient spectrum utilization

Automatic analysis of Electrocardiogram (ECG) signals plays an important role in the medical field to deal with various crucial cardiac conditions. Currently, the detection of cardiomyopathy and arrhythmias considered a challenging task. Machine learning-based techniques have gained a huge attraction to classify these patterns, but most of the existing works have focused on arrhythmia classification. The researchers don't contribute much work towards, the cardiac disease case where Cardiomyopathy induced arrhythmia based classification. This work presents a novel approach to classify cardiomyopathy and cardiomyopathy with arrhythmia using a Convolutional Neural Network (CNN) based model. Along with classification, this work combines a pre-fall alert generation based on the heart rate conditions. The existing CNN models suffer from computational complexity; hence, this work incorporates the Long Short-Term Memory (LSTM) layer and developed CNN–LSTM based architecture. The proposed model is implanted on MIT-BIH data where these two classes segregated with the help of expert clinicians. In order to show the robust performance of the proposed model, the performance of CNN–LSTM has compared with state-of-art classifiers such as decision tree, support vector machine, and neural network. The comparative study shows that the proposed classification methods achieved significant improvement in the classification accuracy rate. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.

Evolutionary Intelligence

Cardiomyopathy -induced arrhythmia classification and pre-fall alert generation using Convolutional Neural Network and Long Short-Term Memory model

Wireless Sensor Networks are developed as a vital tool for monitoring diverse real time applications such as environmental monitoring factors, health care, wide area surveillance, and many more. Though the advantages of WSNs are plenty, the present challenge is to gain effective control over the depleting battery power and the network lifetime. Recent researches have proved that the energy consumption can be minimized if effective clustering mechanisms are incorporated. This paper proposes HOCK and HECK - novel energy efficient clustering algorithms to increase the network lifetime for homogeneous and heterogeneous environments, respectively. Both these algorithms are built using Krill herd and Cuckoo search. While the optimal cluster centroid positions are computed using the Krill herd algorithm, and the Cuckoo search is applied to select the optimal cluster heads. The performance of the HOCK algorithm is evaluated by varying base station locations and node density. To evaluate the HECK algorithm, two and three level heterogeneity are considered. The simulation results show that the proposed protocol is more effective in improving the network lifetime of WSNs compared to other existing methods such as GAECH, Hybrid HSAPSO, and ESO-LEACH. © 2021, Springer-Verlag GmbH Germany, part of Springer Nature.

Department of Analytics

A hybrid approach to energy efficient clustering and routing in wireless sensor networks

Internet of Things (IoT) in the current era is liable for its drastic transforming impact on human life, especially in the agricultural sector. IoT has transformed conventional agriculture into smart agriculture making agriculture more feasible in recent days. In this paper, it is proposed to develop a smart agricultural solution for using technologies like Arduino, IoT and Wireless Sensor Network. The developed system prototype uses IoT to perform three main functions namely, self/smart irrigation, crop productivity estimation and alerts cattle grazing. It also provides easy accessibility of the sensed information using an Android-based application and Bluetooth for short-range communication. The features of this paper include monitoring temperature, moisture level, detecting presence of inflammable gases and an emergency alert notification to alert any decline in crop health and cattle grazing directly to the farmer's smartphone using Android app and Bluetooth. The desirable yielding conditions of a crop are programmed in the android app and compared with the sensed information. With the difference in levels the crop yield is estimated beforehand. A complete health monitoring system is developed using Arduino to perform a periodic check on the growth of the crop and its yielding conditions. Because of its feasibility, energy efficiency and cost-effectiveness, the system can be used in water-deficient agricultural lands with less human intervention. © 2021 World Scientific Publishing Co.

Journal of Information and Knowledge Management

Crop Yield Estimation Using the Internet of Things

The prices in the stock market are dynamic in nature, thereby pretend as a hectic challenge to the sellers and buyers in predicting the trending stocks for the future. To ensure effective prediction of the stock market, the chronological penguin Levenberg-Marquardt-based nonlinear autoregressive network (CPLM-based NARX) is employed, and the prediction is devised on the basis of past and the recent rank of market. Initially, input data are subjected to the features extraction that is based on the technical indicators, such as WILLR, ROCR, MOM, RSI, CCI, ADX, TRIX, MACD, OBV, TSF, ATR and MFI. The technical indicator is adapted for predicting the stock market. The wrapper-enabled feature selection is employed for selecting the highly significant features that are generated using the technical indicators. The highly significant features of the data are fed to the prediction module, which is developed using the NARX model. The NARX model uses the CPLM algorithm that is formed using the integration of the chronological-based penguin search optimization algorithm and the Levenberg-Marquardt algorithm. The prediction using the proposed CPLM-based NARX shows the superior performance in terms of mean absolute percentage error and root mean square error with values of 0.96 and 0.805, respectively. © 2020 The British Computer Society 2020. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Computer Journal

Wrapper-Enabled Feature Selection and CPLM-Based NARX Model for Stock Market Prediction

In WSN, the energy efficiency is a major issue in networks for enhancing the network lifetime. Due to the more data collections and packet transmission this issue becomes even more critical in large sensor networks. In this study, an energy efficient cluster head selection methodology has been proposed for WSN using firefly with dual update process (FFDUP) algorithm. The proposed approach produces maximum energy and prolongs the network lifetime. Subsequently the analysis based on the network sustainability, manner of cluster head distribution, risk mode and trade-off occurred from the proposed FFDUP algorithm is determined and validated by comparing with conventional algorithms such as artificial bee colony (ABC), FABC, firefly (FF) and artificial bee colony-dynamic scout bee (ABC-DS). The simulation results revealed that the proposed algorithm provides superior performance while comparing with the existing algorithm.

International Journal of Advanced Intelligence Paradigms

Energy efficient cluster head selection for wireless sensor network by improved firefly optimisation

Encryption is one of the most critical and mandatory technique to provide security in outsourced data. Message passing is the most unsecure place of transfer of crucial information and these messages passing are made end-to-end encryption to avoid a centralised security agent to access the data. Existing methods of encryption only provide end-to-end encryption which is not feasible for certain situations like implementing authentication. When the end-to-end encryption is made, the messages are always not known to the central authentication agent like CBI, in this paper, we provide a two-side decryption algorithm that can be decrypted by two entities (one receiver and the other is the central authentication agent) thus improving the message passing security by allowing the centralised authentication agent to read the transferring words. We implemented this two-way decryption in trip database dataset, and the experiment results prove that our proposed algorithm improves the security of message passing of electronic medical records in public cloud while comparing with existing encryption algorithms. Thus we made with quantitative research based on the previous techniques compared based on the various types of key generation occurs in the algorithms. © 2021 Inderscience Enterprises Ltd.. All rights reserved.

International Journal of Intelligent Enterprise

Enhancing security by two-way decryption of message passing of EMR in public cloud

Neural networks play a significant role in data classification. Complex-valued Hopfield Neural Network (CHNN) is mostly used in various fields including the image classification. Though CHNN has proven its credibility in the classification task, it has a few issues. Activation function of complex-valued neuron maps to a unit circle in the complex plane affecting the resolution factor, flexibility and compatibility to changes, during adaptation in retrieval systems. The proposed work demonstrates Content-Based Image Retrieval System (CBIR) with Hyperbolic Hopfield Neural Networks (HHNN), an analogue of CHNN for classifying images. Activation function of the Hyperbolic neuron is not cyclic in hyperbolic plane. The images are mathematically represented and indexed using the six basic features. The proposed HHNN classifier is trained, tested and evaluated through extensive experiments considering individual features and four combined features for indexing. The obtained results prove that HHNN guides retrieval process, enhances system performance and minimizes the cost of implementing Neural Network Classifier-based image retrieval system. © 2021 World Scientific Publishing Company.

International Journal of Wavelets, Multiresolution and Information Processing

Hyperbolic Hopfield neural networks for image classification in content-based image retrieval

Formed at the cerebral cortex, neuron cell assemblies are regarded as basic units in cortical representation. Proposed by Hebb, these cell assemblies are regarded as the distributed neural representation of relevant objects, concepts or constellations. Each cell assembly contains a group of neurons having strong mutual excitatory connections. During a stimulus, these cells get activated. This activation either performs a given action or represent a given percept or concept in brain. This theory is in the strongest connection of the problem of concept forming in the brain. The challenge is to model coordinated activity among neurons in brain mathematically. The need of modelling it mathematically enables this paper to give clear view of functionality of Hebbian cell assembly. Therefore this paper proposes a pragmatic approach to Hebbian cell assemblies using mathematical model grounded in lattice based formalism that utilizes Galois connections. During this proposal, the authors also show the connections of the proposal to cognitive model of memory in particularly long-term memory (LTM). © 2021 IGI Global. All rights reserved.