Maharaja Engineering College

Coronavirus (COVID-19) is a viral disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The spread of COVID-19 seems to have a detrimental effect on the global economy and health. A positive chest X-ray of infected patients is a crucial step in the battle against COVID-19. Early results suggest that abnormalities exist in chest X-rays of patients suggestive of COVID-19. This has led to the introduction of a variety of deep learning systems and studies have shown that the accuracy of COVID-19 patient detection through the use of chest X-rays is strongly optimistic. Deep learning networks like convolutional neural networks (CNNs) need a substantial amount of training data. Because the outbreak is recent, it is difficult to gather a significant number of radiographic images in such a short time. Therefore, in this research, we present a method to generate synthetic chest X-ray (CXR) images by developing an Auxiliary Classifier Generative Adversarial Network (ACGAN) based model called CovidGAN. In addition, we demonstrate that the synthetic images produced from CovidGAN can be utilized to enhance the performance of CNN for COVID-19 detection. Classification using CNN alone yielded 85% accuracy. By adding synthetic images produced by CovidGAN,the accuracy increased to 95%. We hope this method will speed up COVID-19 detection and lead to more robust systems of radiology.

In the present business situation during the COVID-19 pandemic, employee engagement has become one of the utmost prominent primacies for human resource managers and practitioners in organizations due to lockdown. The paper is to determine the engagement of employees by various companies during coronavirus pandemic. Organizations nowadays are constantly developing innovative and effective means to engage the employees during this tough time. This paper is a conceptual paper that is based on various research papers, articles, blogs, online newspapers, and reports of World Health Organization. During this pandemic situation, organizations are evolving many engagement activities like online family engagement practices, virtual learning and development, online team building activities, webinars with industry experts, online conduct weekly alignment sessions, team meet-ups over video conference for lunch, short online game sessions, virtual challenges and competitions, online courses, appreciation sessions, communication exercises, live sessions for new-skill training, online counseling sessions, recognition and acknowledgment session, webinars dealing with anxiety and stress, providing online guidance for exercise and meditation, social interactions in a virtual office, classrooms training modules digitally, e-learning modules, and many more creative learning sessions. Work-from-home regime engagement activities are very fruitful for employees as well as for organizations. Those organizations doing these kinds of engagement activities for their employees are learning new skills and developing themselves. Employees are feeling committed to the organization and stay motivated during this tough time of COVID-19 pandemic.

Gold nanoparticles (GNPs) have generated keen interest among researchers in recent years due to their excellent physicochemical properties. In general, GNPs are biocompatible, amenable to desired functionalization, non-corroding, and exhibit size and shape dependent optical and electronic properties. These excellent properties of GNPs exhibit their tremendous potential for use in diverse biomedical applications. Herein, we have evaluated the recent advancements of GNPs to highlight their exceptional potential in the biomedical field. Special focus has been given to emerging biomedical applications including bio-imaging, site specific drug/gene delivery, nano-sensing, diagnostics, photon induced therapeutics, and theranostics. We have also elaborated on the basics, presented a historical preview, and discussed the synthesis strategies, functionalization methods, stabilization techniques, and key properties of GNPs. Lastly, we have concluded this article with key findings and unaddressed challenges. Overall, this review is a complete package to understand the importance and achievements of GNPs in the biomedical field.

In this paper, an analytical model for a p-n-p-n tunnel field-effect transistor (TFET) working as a biosensor for label-free biomolecule detection purposes is developed and verified with device simulation results. The model provides a generalized solution for the device electrostatics and electrical characteristics of the p-n-p-n-TFET-based sensor and also incorporates the two important properties possessed by a biomolecule, i.e., its dielectric constant and charge. Furthermore, the sensitivity of the TFET-based biosensor has been compared with that of a conventional FET-based counterpart in terms of threshold voltage ( <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sub> ) shift, variation in the on-current ( <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">on</sub> ) level, and <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">on</sub> / <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">off</sub> ratio. It has been shown that the TFET-based sensor shows a large deviation in the current level, and thus, change in <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">on</sub> can also be considered as a suitable sensing parameter. Moreover, the impacts of device parameters (channel thickness and cavity length), process variability, and process-induced damage on the sensitivity of the biosensor have also been discussed.

Graphical presentation form synthesis to application of nanocellulose.

The recent advancements in Internet of Things (IoT), cloud computing, and Artificial Intelligence (AI) transformed the conventional healthcare system into smart healthcare. By incorporating key technologies such as IoT and AI, medical services can be improved. The convergence of IoT and AI offers different opportunities in healthcare sector. In this view, the current research article presents a new AI and IoT convergence-based disease diagnosis model for smart healthcare system. The major goal of this article is to design a disease diagnosis model for heart disease and diabetes using AI and IoT convergence techniques. The presented model encompasses different stages namely, data acquisition, preprocessing, classification, and parameter tuning. IoT devices such as wearables and sensors permit seamless data collection while AI techniques utilize the data in disease diagnosis. The proposed method uses Crow Search Optimization algorithm-based Cascaded Long Short Term Memory (CSO-CLSTM) model for disease diagnosis. In order to achieve better classification of the medical data, CSO is applied to tune both `weights' and `bias' parameters of CLSTM model. Besides, isolation Forest (iForest) technique is employed in this research work to remove the outliers. The application of CSO helps in considerable improvement in the diagnostic outcomes of CLSTM model. The performance of CSO-LSTM model was validated using healthcare data. During the experimentation, the presented CSO-LSTM model accomplished the maximum accuracies of 96.16% and 97.26% in diagnosing heart disease and diabetes respectively. Therefore, the proposed CSO-LSTM model can be employed as an appropriate disease diagnosis tool for smart healthcare systems.

In medical imaging, segmentation plays a vital role towards the interpretation of X-ray images where salient features are extracted with the help of image segmentation. Without undergoing surgery, clinicians employ various modalities ranging from X-rays and CT-Scans to ultrasonography, and other imaging techniques to visualise and examine interior human body organ and structures. To ensure appropriate convergence, training a deep convolutional neural network (CNN) from scratch is tough since it requires more computational time, a big amount of labelled training data and a considerable degree of experience. Fine-tuning a CNN that has been pre-trained using, for instance, a huge set of labelled medical datasets, is a viable alternative. In this paper, a comparative study was done using pre-trained models such as VGG-19 and ResNet-50 as against training from scratch. To reduce overfitting, data augmentation and dropout regularization was used. With a recall of 92.03%, our analysis showed that the pre-trained models with proper finetuning was comparable with Iyke-Net, a CNN trained from scratch.

The aim of this paper is to develop a hybrid model of a powerful Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) for recognition of handwritten digit from MNIST dataset. The proposed hybrid model combines the key properties of both the classifiers. In the proposed hybrid model, CNN works as an automatic feature extractor and SVM works as a binary classifier. The MNIST dataset of handwritten digits is used for training and testing the algorithm adopted in the proposed model. The MNIST dataset consists of handwritten digits images which are diverse and highly distorted. The receptive field of CNN helps in automatically extracting the most distinguishable features from these handwritten digits. The experimental results demonstrate the effectiveness of the proposed framework by achieving a recognition accuracy of 99.28% over MNIST handwritten digits dataset.

The research develops a theoretical model that highlights the determinants of adoption of online teaching at the time of the outbreak of COVID 19. Empirical data was gathered from 643 school teachers by means of an online survey. The proposed conceptual framework was investigated empirically by means of confirmatory factor analysis (CFA) and structural equation modelling (SEM). The findings of the study revealed performance expectancy, and facilitating conditions had a positive impact on behavioural intention as well as attitude. However, effort expectancy failed to drive teachers' adoption to online teaching. On the other hand, social influence had insignificant relationship with attitude but significant relationship with behavioural intention. Attitude had a significant impact on behavioural intention as well as actual use. This study contributes to the literature by presenting and validating a theory-driven framework that accentuates the factors influencing online teaching during outbreak of a pandemic.

At present times, the real-time requirement on the multiaccess healthcare monitoring system, information mining, and efficient disease diagnosis of health conditions is a difficult process. The recent advances in information technology and the internet of medical things (IoMT) have fostered extensive utilization of the smart system. A complex, 24/7 healthcare service is needed for effective and trustworthy monitoring of patients on a daily basis. To accomplish this need, edge computing and cloud platforms are highly required to satisfy the requirements of smart healthcare systems. This paper presents a new effective training scheme for the deep neural network (DNN), called ETS-DNN model in edge computing enabled IoMT system. The proposed ETS-DNN intends to facilitate timely data collection and processing to make timely decisions using the patterns that exist in the data. Initially, the IoMT devices sense the patient's data and transfer the captured data to edge computing, which executes the ETS-DNN model to diagnose it. The proposed ETS-DNN model incorporates a Hybrid Modified Water Wave Optimization (HMWWO) technique to tune the parameters of the DNN structure, which comprises of several autoencoder layers cascaded to a softmax (SM) layer. The SM classification layer is placed at the end of the DNN to perform the classification task. The HMWWO algorithm integrates the MWWO technique with limited memory Broyden-Fletcher-Goldfarb-Shannon (L-BFGS). Once the ETS-DNN model generates the report in edge computing, then it will be sent to the cloud server, which is then forwarded to the healthcare professionals, hospital database, and concerned patients. The proposed ETS-DNN model intends to facilitate timely data collection and processing to identify the patterns exist in the data. An extensive set of experimental analysis takes place and the results are investigated under several aspects. The simulation outcome pointed out the superior characteristics of the ETS-DNN model over the compared methods.

In this paper, an extensive study on the intermodulation distortion and the linearity of gate-material-engineered cylindrical-gate MOSFET (GME CGT MOSFET) has been done, and the influence of technology variations such as channel length and gate material workfunction variations is explored using an ATLAS 3-D device simulator. The simulation results reveal that the GME CGT MOSFET design displays a significant enhancement in the device's linearity and intermodulation distortion performance in terms of the figure-of-merit metrics VIP2, VIP3, IIP3, and IMD3 and the higher order transconductance coefficients <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">gm</i> 1, <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">gm</i> 2, and <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">gm</i> 3. The results are, thus, useful for optimizing the device bias point for RFIC design with higher efficiency and better linearity performance.

Abstract As specified by World Health Organization, the occurrence of skin cancer has been growing over the past decades. At present, 2 to 3 million nonmelanoma skin cancers and 132 000 melanoma skin cancers arise worldwide annually. The detection and classification of skin cancer in early stage of development allow patients to have proper diagnosis and treatment. The goal of this article is to present a novel deep learning internet of health and things (IoHT) driven framework for skin lesion classification in skin images using the concept of transfer learning. In proposed framework, automatic features are extracted from images using different pretrained architectures like VGG19, Inception V3, ResNet50, and SqueezeNet, which are fed into fully connected layer of convolutional neural network for classification of skin benign and malignant cells using dense and max pooling operation. In addition, the proposed system is fully integrated with an IoHT framework and can be used remotely to assist medical specialists in the diagnosis and treatment of skin cancer. It has been observed that performance metric evaluation of proposed framework outperformed other pretrained architectures in term of precision, recall, and accuracy in detection and classification of skin cancer from skin lesion images.

Due to recent developments in highway research and increased utilization of vehicles, there has been significant interest paid on latest, effective, and precise Intelligent Transportation System (ITS). The process of identifying particular objects in an image plays a crucial part in the fields of computer vision or digital image processing. Vehicle License Plate Recognition (VLPR) process is a challenging process because of variations in viewpoint, shape, color, multiple formats and non-uniform illumination conditions at the time of image acquisition. This paper presents an effective deep learning-based VLPR model using optimal K-means (OKM) clustering-based segmentation and Convolutional Neural Network (CNN) based recognition called OKM-CNN model. The proposed OKM-CNN model operates on three main stages namely License Plate (LP) detection, segmentation using OKM clustering technique and license plate number recognition using CNN model. During first stage, LP localization and detection process take place using Improved Bernsen Algorithm (IBA) and Connected Component Analysis (CCA) models. Then, OKM clustering with Krill Herd (KH) algorithm get executed to segment the LP image. Finally, the characters in LP get recognized with the help of CNN model. An extensive experimental investigation was conducted using three datasets namely Stanford Cars, FZU Cars and HumAIn 2019 Challenge dataset. The attained simulation outcome ensured effective performance of the OKM-CNN model over other compared methods in a considerable way.

Home automation is becoming more and more popular day by day due to its numerous advantages. This can be achieved by local networking or by remote control. This paper aims at designing a basic home automation application on Raspberry Pi through reading the subject of E-mail and the algorithm for the same has been developed in python environment which is the default programming environment provided by Raspberry Pi. Results show the efficient implementation of proposed algorithm for home automation. LEDs were used to indicate the switching action.

Load frequency control in modern‐complex‐uncertain power systems (PSs) assumes significance due to their challenging nature of the operation and hence utilisation of robust controllers is indispensable. In the industry, conventional single‐loop controllers may not offer robust behaviour under changed operating conditions. Alternatively, two‐loop cascade fuzzy structured controllers can show significant robust performance in dynamic conditions and best suited in systems having non‐linearities. Hence, a novel optimal cascade fuzzy‐fractional order integral derivative with filter (CF‐FOIDF) controller is utilised for 2‐area thermal and hydrothermal PSs considering various physical constraints from a practical point of view. As physical constraints mandate an energy storage system, hence in this study, batteries of electric vehicles (EVs) are employed to assist power plants to swiftly arrest oscillations in the system frequency following load demands. A combined model of EV fleets is incorporated in the control areas of PSs. Numerous simulations are conducted to authenticate the robustness and excellence of EVs and the suggested control strategy over existing methods.

BACKGROUND: Chemotherapy for cancer is an intense and cyclic treatment associated with number of side-effects. The present study evaluated the effect of chemotherapy on distress, anxiety and depression. PATIENTS AND METHODS: A total of 117 patients were evaluated by using distress inventory for cancer (DIC2) and hospital anxiety and depression scale (HADS). Majority of the patients were taking chemotherapy for solid tumors (52; 44.4%). RESULTS: The mean distress score was 24, 18 (15.38%) were found to have anxiety while 19 (16.23%) had depression. High social status was the only factor found to influence distress while female gender was the only factor found to influence depression in the present study. CONCLUSION: The study highlights high psychological morbidity of cancer patients and influence of gender on depression. Construct of distress as evaluated by DIC 2 may have a possible overlap with anxiety.

Financial fraud is a problem that has proved to be a menace and has a huge impact on the financial industry. Data mining is one of the techniques which has played an important role in credit card fraud detection in transactions which are online. Credit card fraud detection has proved to be a challenge mainly due to the 2 problems that it poses - both the profiles of fraudulent and normal behaviours change and data sets used are highly skewed. The performance of fraud detection is affected by the variables used and the technique used to detect fraud. This paper compares the performance of logistic regression, K-nearest neighbors, random forest, naive bayes, multilayer perceptron, ada boost, quadrant discriminative analysis, pipelining and ensemble learning on the credit card fraud data.

The statistics highlights that physical rehabilitation are required nowadays by increased number of people that are affected by motor impairments caused by accidents or aging. Among the most common causes of disability in adults are strokes or cerebral palsy. To reduce the costs preserving the quality of services new solutions based on current technologies in the area of physiotherapy are emerging. The remote monitoring of physical training sessions could facilitate for physicians and physical therapists' information about training outcome that may be useful to personalize the exercises helping the patients to achieve better rehabilitation results in short period of time process. This research work aims to apply physical rehabilitation monitoring combining Virtual Reality serious games and Wearable Sensor Network to improve the patient engagement during physical rehabilitation and evaluate their evolution. Serious games based on different scenarios of Virtual Reality, allows a patient with motor difficulties to perform exercises in a highly interactive and non-intrusive way, using a set of wearable devices, contributing to their motivational process of rehabilitation. The system implementation, system validation and experimental results are included in the paper.

Abstract Expert, intelligent and robust automatic generation control (AGC) scheme is requisite for stable operation and control of power system (PS) integrated with renewable energy sources (RES) under sudden/random small load disturbances. Large frequency deviations appear if AGC capacity is inept to compensate for the imbalances of generation and demand. In this paper, a cascade‐fractional order ID with filter (C‐I λ D μ N) controller is proposed as an expert supplementary controller to promote AGC recital adequately in electric power systems incorporated with RES like solar, wind and fuel cells. The imperialist competitive algorithm is fruitfully exploited for optimizing the controller parameters. First, a 2‐area reheat thermal system is examined critically and then to authorize the worth of the proposed controller, the study is protracted to a 2‐area multi‐source hydro‐thermal system. The prominent benefits of C‐I λ D μ N controller with/without renewable energy sources consist of its great indolence to large load disturbances and superiority over various optimized classical/fuzzy controllers published recently. The sensitivity study validates the robustness of the recommended controller against ±20% deviations in the system parameters and random step load perturbations.

Just over a decade, perovskite solar cells (PSCs) have been emerged as a next-generation photovoltaic technology due to their skyrocketing power conversion efficiency (PCE), low cost, and easy manufacturing techniques compared to Si solar cells. Several methods and procedures have been developed to fabricate high-quality perovskite films to improve the scalability and commercialize PSCs. Recently, several printing technologies such as blade-coating, slot-die coating, spray coating, flexographic printing, gravure printing, screen printing, and inkjet printing have been found to be very effective in controlling film formation and improving the PCE of over 21%. This review summarizes the intensive research efforts given for these printing techniques to scale up the perovskite films as well as the hole transport layer (HTL), the electron transport layer (ETL), and electrodes for PSCs. In the end, this review presents a description of the future research scope to overcome the challenges being faced in the printing techniques for the commercialization of PSCs.