Prediction of COVID-19 Cases Using Constructed Features by Grammatical Evolution

A widely used method that constructs features with the incorporation of so-called grammatical evolution is proposed here to predict COVID-19 cases as well mortality rate. The creates new artificial from original ones using a genetic algorithm and guided by BNF grammar. After are generated, data set modified based on these features, an neural network applied data, results reported. From comparative experiments done, it clear feature construction has advantage over other machine-learning methods for predicting pandemic elements.