Active Learning-Based Estimation of COVID-19 Pandemic: A Synergetic Case Study in Selective Regions Population

ABSTRACT

The rapid spread of the coronavirus disease 2019 (COVID-19) epidemic poses a threat to human civilization. This infectious outbreak induced a global menace, resulting in day-to-day community and social services standstill. Countries like China and Italy are positioned at an alarming stage of this pandemic, and India is also testifying a rapid outbreak of the COVID-19.This unprecedented scenario warrants the formulation of a robust mechanism to estimate the misfortunes of this pandemic in these three countries to assist governments in countermeasuring the COVID-19 catastrophe. In the light of fast varying fatality data rendered by the World Health Organization (WHO), a spectrum of case-based fatality assessments for the COVID-19 is presented that differs considerably in measurements. This publication elucidates the scope of the curve-fitting methods in terms of the goodness-of-fit statistics and support vector machine-based regression (SVR) in estimating the misfortunes of COVID-19 in China, Italy, and India in a given time frame. Consequently, we achieved a reasonably small root mean squared error (RMSE) for the SVR method in predicting the adversities induced by this global pandemic in China and India. In contrast, conventional regression offers a better estimate to sketch the outbreak pattern in Italy. © 2022, Springer Nature Switzerland AG.