COVID-19 Time Series Forecasting - Twenty Days Ahead

Kathleen C M de Carvalho; João Paulo Vicente; João Paulo Teixeira

doi:10.1016/j.procs.2021.12.105

COVID-19 Time Series Forecasting - Twenty Days Ahead

Procedia Comput Sci. 2022:196:1021-1027. doi: 10.1016/j.procs.2021.12.105. Epub 2022 Jan 10.

Authors

Kathleen C M de Carvalho^{1

2}, João Paulo Vicente^{1

2}, João Paulo Teixeira¹

Affiliations

¹ Research Centre in Digitalization and Intelligent Robotics (CEDRI), Instituto Politecnico de Bragança, Braganca, Portugal.
² Federal University of Technology - Paraná (UTFPR), Cornélio Procópio, 86300-000, Brazil.

Abstract

The new Coronavirus, responsible for the COVID-19 disease, is the most discussed topic in the current days, and the forecast numbers of new cases and deaths are the most important source of data in governmental decision-making. The present work presents a prediction model with two different approaches concerning the input data, by using Artificial Neural Networks (ANN). The use of a substantial mitigation procedure adopted (mandatory use of masks) was experimented as an input to the network, in order to evaluate the improvement in the results. The ANN forecasting model was demonstrated to predict with higher accuracy within the next twenty days using the information about the mandatory use of face masks. The final results showed that the twenty days ahead forecasting was made with an error of 24,7% and 1,6% for the number of cumulative cases of infection and deaths for Brazil, and 37,9% and 33,8% for Portuguese time series, respectively.

Keywords: Brazil COVID-19 forecasting; COVID-19 time series; Mitigation procedures; Portugal COVID-19 forecasting; Use of face masks.