Application of machine learning for predicting the spread of COVID-19

TL;DR

This paper explores how machine learning can predict COVID-19 spread and assess the impact of containment measures like quarantine, social distancing, and mask-wearing, enhancing understanding of disease transmission dynamics.

Contribution

It introduces a machine learning approach to predict COVID-19 transmission and evaluate the effectiveness of various containment policies.

Findings

Machine learning accurately predicts COVID-19 spread.

Containment measures significantly reduce transmission.

Policy adherence is crucial for controlling outbreaks.

Abstract

The spread of diseases has been studied for many years, but it receives a particular focus recently due to the outbreak and spread of COVID-19. Studies show that the spread of COVID-19 can be characterized by the Susceptible-Infectious-Recovered-Deceased (SIRD) model with containment coefficients (due to quarantine and keeping social distance). This project aims to apply the machine learning technique to predict the severity of COVID-19 and the effect of quarantine, keeping social distance, working from home, and wearing masks on the transmission of the disease. This work deepens our understanding of disease transmission and reveals the importance of following policies.