ABSTRACT
This contribution proposes a numerical scheme for solving fractional parabolic partial differential equations (PDEs). One of the advantages of using the proposed scheme is its applicability for fractional and integer order derivatives. The scheme can be useful to get conditions for obtaining a positive solution to epidemic disease models. A COVID-19 mathematical model is constructed, and linear local stability conditions for the model are obtained;afterward, a fractional diffusive epidemic model is constructed. The numerical scheme is constructed by employing the fractional Taylor series approach. The proposed fractional scheme is second-order accurate in space and time and unconditionally stable for parabolic PDEs. In addition to this, convergence conditions are obtained by employing a proposed numerical scheme for the fractional differential equation of susceptible individuals. The scheme is also compared with existing numerical schemes, including the non-standard finite difference method. From theoretical analysis and graphical illustration, it is found that the proposed scheme is more accurate than the so-called existing non-standard finite difference method, which is a method with notably good boundedness and positivity properties.
ABSTRACT
The outbreak of Covid-19 and the enforcement of lockdown, social distancing, and other precautionary measures lead to a global increase in online shopping. The increasing significance of online shopping and extensive use of e-commerce has increased competition between companies for online selling. Highlights that online reviews play a significant role in boosting a business or slandering it. Product review is an essential factor in customers' decision-making, leading to an intense topic known as fraudulent or fake reviews detection. Given these reviews' power over a business, the treacherous acts of giving false reviews for personal gains have increased with time. In our research, we proposed a fake review detection model by using Text Classification and techniques related to Machine Learning. We used classifiers such as Support Vector Machine, K-Nearest Neighbor, and logistic regression (SKL), using a bigram model that detects fraudulent reviews based on the number of pronouns, verbs, and sentiments. Our proposed methodology for detecting fake online reviews outperforms on the yelp dataset and the TripAdvisor dataset compared to other state-of-the-art techniques with 95% and 89.03% accuracy.
ABSTRACT
In late 2019, a novel strain of coronavirus (2019-nCoV) named as severe respiratory syndrome coronavirus 2 (SARS-CoV-2) emerged in Wuhan, a city in China, through some zoonotic reservoir, most probably a bat, and spread throughout the world. There have been around 22,213,869 reported cases of COVID-19 and almost 781,677 deaths worldwide according to the data updated by World Health Organization till 20 August 2020. It transmitted via droplets from an infected person to a healthy person in a very short duration of time. After the completion of the incubation period, which ranges from 2 to 14 days, the person experiences pneumonia-like symptoms such as fever, sore throat, cough, breathlessness, malaise, fatigue, and multi-organ dysfunction, etc. The main receptor of SARS-CoV-2 is angiotensin-converting enzyme 2 which binds with the spike (S) protein of the virus and helps it in attachment and entry to the host cells. COVID-19 is diagnosed by molecular testing of respiratory secretions and CT scan analysis. Because of the absence of any approved treatment options for COVID-19, a number of research studies are being carried out to find out any combination of already approved drugs or new lead compounds using in silico docking and screening strategies. © 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group on behalf of the University of Bahrain.
ABSTRACT
The ongoing pandemic of Corona-Virus (COVID-19) induced by the coming forth category of SARS-CoV-2, has terrified the worldwide human health. Primarily, COVID-19 challenges can be categorized into (a) way of epidemic prevention and blocking transmission, (b) live monitoring of infected / suspected persons (c) FDA approved vaccine. Leading to said COVID-19 (a), (b) challenges, digit technologies such Artificial Intelligence, Big data analytics and Internet of Things (IoT), can play a vital role in epidemic prevention and blocking COVID-19 transmission. In this study, we have proposed a smart edge surveillance system that is effective in remote monitoring, advance warning and detection of a person's fever, heart beat rate, cardiac conditions and some of the radiological features to detect the infected (suspicious) person using wearable smart gadgets. The proposed framework provides a continually updated map/pattern of communication chain of COVID-19 infected persons that may span around in our national community. The health and societal impact of suggested research is to help public health authorities, researchers and clinicians contain and manage this disease through smart edge surveillance systems. The proposed model will help to detect and track the contagious person. Moreover, it will also keep the patient's data record for analysis and decision making using edge computing. © 2020 IEEE.