COVID-19 Forecasting Based on an Improved Interior Search Algorithm and Multilayer Feed-Forward Neural Network

COVID-19 is a novel coronavirus that was emerged in December 2019 within Wuhan, China. As the crisis of its severe, increasing dynamic outbreak all parts globe, forecast maps and analysis confirmed cases (CS) becomes vital excellent changeling task. In this study, new forecasting model presented to analyze CS for coming days based on reported data since 22 January 2020. The proposed model, named ISACL-MFNN, integrates an improved interior search algorithm (ISA) chaotic learning (CL) strategy into multilayer feed-forward neural network (MFNN). ISACL incorporates CL enhance ISA's performance avoid trapping local optima. This methodology intended train by tuning parameters optimal values thus achieving high-accuracy level regarding forecasted results. ISACL-MFNN investigated official World Health Organization (WHO) upcoming days. validated assessed introducing some indices, including mean absolute error (MAE), root square (RMSE), percentage (MAPE) comparisons with other optimization algorithms are presented. most affected countries (i.e., USA, Italy, Spain). experimental simulations illustrate provides promising rather than while candidate countries’