A Comprehensive Exploration of Mathematical Models and Machine Learning Techniques for COVID-19

Abstract

Mathematical modeling has proved to be useful in predicting the spread of infectious diseases and assessing the dynamical behavior of contagious diseases, including COVID-19. Various models aid in forecasting COVID-19 spread, such as SEIR (Susceptible – Exposed – Infected – Recovered), SIR (Susceptible – Infected – Recovered), SIRD (Susceptible – Infected – Recovered – Death), and SIRVD (Susceptible – Infected – Recovered – Vaccinated – Death). With recent technological advancements, forecasting of COVID-19 can also be done using machine learning techniques such as SVM (support vector machine), decision tree, random forest, and linear regression. This chapter delves into the various mathematical models and provides simulations using Python and machine learning techniques for COVID-19. These simulations provide essential insights into the spread of infectious diseases and evaluate which machine learning algorithm performs better using evaluation metrics.