Title: Prediction of COVID-19 spread in world using pandemic dataset with application of auto ARIMA and SIR models
Authors: Sunil Gupta; Durgansh Sharma
Addresses: Department of Cybernetics, School of Computer Science and Engineering, University of Petroleum and Energy Studies, Dehradun, India ' Department of Cybernetics, School of Computer Science and Engineering, University of Petroleum and Energy Studies, Dehradun, India
Abstract: COVID-19 has now become the world's highly infectious disease because of the high transmission capability of the coronavirus. This virus has also deeply impacted the global economy. The world situation needs better predication analysis for prevention and decision making. Since then, researchers all over the world are making attempts to predict the likely progression of this pandemic using various mathematical models. The aim of this analysis is to use auto ARIMA model to predict the spread of coronavirus in the world in the next 100 days. We also determine when new confirmed cases, death cases and recovery of COVID-19 would stabilise in top five of the most affected countries. The results obtained from auto ARIMA are then compared with those obtained by applying susceptible infected removed (SIR) model. The comparison of the analytical results and the available results shows that the proposed methods are accurate within a specific range and will prove to be useful for healthcare leaders and decision-makers in near future. The forecasted results suggest the strong need of prevention and environmental measures to be taken rapidly in order to fight with COVID-19.
Keywords: COVID-19; prediction; auto ARIMA; SIR model.
International Journal of Critical Infrastructures, 2022 Vol.18 No.2, pp.148 - 158
Received: 10 Aug 2020
Accepted: 01 Sep 2020
Published online: 09 Jun 2022 *