Analysis and Prediction of COVID-19 Using SIR, SEIQR, and Machine Learning Models: Australia, Italy, and UK Cases

The novel coronavirus disease, also known as COVID-19, is a disease outbreak that was first identified in Wuhan, Central Chinese city. In this report, short analysis focusing on Australia, Italy, and UK conducted. includes confirmed recovered cases deaths, the growth rate Australia compared with Italy UK, trend of different Australian regions. Mathematical approaches based susceptible, infected, (SIR) exposed, quarantined, (SEIQR) models are proposed to predict epidemiology above-mentioned countries. Since performance classic forms SIR SEIQR depends parameter settings, some optimization algorithms, namely Broyden–Fletcher–Goldfarb–Shanno (BFGS), conjugate gradients (CG), limited memory bound constrained BFGS (L-BFGS-B), Nelder–Mead, optimize parameters predictive capabilities models. results optimized were those two well-known machine learning i.e., Prophet algorithm logistic function. demonstrate behaviors these algorithms countries well better improved Moreover, found provide prediction than function, for cases. Therefore, it seems suitable data an increasing context pandemic. Optimization model yielded significant improvement accuracy Despite availability several predictions pandemic, there no single would be optimal all