Genetic Optimization of Ensemble Neural Network Architectures for Prediction of COVID-19 Confirmed and Death Cases

Mónica, Julio C.; Melin, Patricia; Sánchez, Daniela

In this work a genetic algorithm for ensemble neural network architecture optimization applied to COVID-19 time series prediction is proposed. The main objective of this paper is to show the results of the optimized number of neurons in two hidden layers of an ensemble artificial neural network used for time series prediction using a real genetic algorithm. The time series dataset used in this work is the confirmed and death cases of COVID-19 of 12 states of Mexico (and information about the whole country). Being the COVID-19 the pandemic that has been affecting many lives in Mexico, for this reason, this work seeks to find a prediction for confirmed and death cases in this country.