COVID-19 Pandemic: A Comparative Prediction Using Machine Learning

Rifat Sadik; Md Latifur Reza; Abdullah Al Noman; Shamim Al Mamun; M Shamim Kaiser; Muhammad Arifur Rahman

doi:10.61797/ijaaiml.v1i1.44

Rifat Sadik Department of Computer Science and Engineering, Jahangirnagar University, Dhaka, Bangladesh
Md Latifur Reza Department of Computer Science and Engineering, Jahangirnagar University, Dhaka, Bangladesh
Abdullah Al Noman Department of Computer Science and Engineering, Jahangirnagar University, Dhaka, Bangladesh
Shamim Al Mamun Institute of Information Technology, Jahangirnagar University, Dhaka, Bangladesh
M Shamim Kaiser Institute of Information Technology, Jahangirnagar University, Dhaka, Bangladesh
Muhammad Arifur Rahman Associate Professor, Department of Physics, Jahangirnagar University, Dhaka, Bangladesh

DOI: https://doi.org/10.61797/ijaaiml.v1i1.44

Keywords: Pandemic, COVID-19, Machine learning, SIR, PR, MLP, LSTM

Abstract

Coronavirus Disease 2019 or COVID-19 is an infectious disease which is declared as a pandemic by the World Health Organization (WHO) have a noxious effect on the entire human civilization. Each and every day the number of infected people is going higher and higher and so the death toll. Many of country Italy, UK, USA was affected badly, yet since the identification of the first case, after a certain number of days, the scenario of infection rate has been reduced significantly. However, a country like Bangladesh couldn't keep the infection rate down. A number of algorithms have been proposed to forecast the scenario in terms of the number of infection, recovery and death toll. Here, in this work, we present a comprehensive comparison based on Machine Learning to predict the outbreak of COVID-19 in Bangladesh. Among Several Machine Learning algorithms, here we used Polynomial Regression (PR) and Multilayer Perception (MLP) and Long Short Term Memory (LSTM) algorithm and epidemiological model Susceptible, Infected and Recovered (SIR), projected comparative outcomes.