Open Access
ARTICLE
Real-Time Analysis of COVID-19 Pandemic on Most Populated Countries Worldwide
1 Department of Computer Science and Engineering, Chandigarh University, Punjab, 140301, India
2 Department of Computer Science and Engineering, Bharati Vidyapeeth’s College of Engineering, New Delhi, 110063, India
* Corresponding Author: Akash Gupta. Email:
(This article belongs to the Special Issue: Computer Modelling of Transmission, Spread, Control and Diagnosis of COVID-19)
Computer Modeling in Engineering & Sciences 2020, 125(3), 943-965. https://doi.org/10.32604/cmes.2020.012467
Received 01 July 2020; Accepted 14 September 2020; Issue published 15 December 2020
Abstract
The spread of the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has already taken on pandemic extents, inuencing even more than 200 nations in a couple of months. Although, regulation measures in China have decreased new cases by over 98%, this decrease is not the situation everywhere, and most of the countries still have been affected by it. The objective of this research work is to make a comparative analysis of the top 5 most populated countries namely United States, India, China, Pakistan and Indonesia, from 1st January 2020 to 31st July 2020. This research work also targets to predict an increase in the number of deaths and total infected cases in these five countries. In our research, the performance of the proposed framework is determined by using three Machine Learning (ML) regression algorithms namely Linear Regression (LR), Support Vector Regression (SVR), and Random Forest (RF) Regression. The proposed model is also validated upon the infected and death cases of further dates. The performance of these three algorithms is compared using the Root Mean Square Error (RMSE) metrics. Random Forest algorithm shows best performance as compared to other proposed algorithms, with the lowest RMSE value in the prediction of total infected and total deaths cases for all the top five most populated countries.Keywords
Cite This Article
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.