European Journal of Molecular & Clinical Medicine

Abstract

In recent years, Artificial Neural Networks (ANN) was widely implemented for
developing predictive and estimation models to estimate the needed parameters. As the
Coronavirus disease 2019 (COVID-19) case numbers are rising internationally as
uncontrolled outbreaks, it is important to better understand what factors promote the super
spreading events. In this paper, the use of Multi-Layer Perceptron (MLP) and Radial Basis
Function (RBF) of ANN for COVID-19 spread and death contributing factors in America
was described. A comparison was made by using a dataset of COVID-19 cases and deaths
reported from 49 states in America during April 2020. Seven covariates used in the network
which are High Temperature, Low Temperature, Average Temperature, Population,
Percentage of Cases over Population, Percentage of Death over Population, and Total
Cases. However, the performance of MLP and RBF networks may be evaluated relatively
similar. It was found that both MLP and RBF proved that the Population, Percentage of
cases over population, and Total cases are the most contributing factors towards COVID-19
spread and death in America particularly.