Hybrid Machine Learning Model Coupled with School Closure For Forecasting COVID-19 Cases in the Most Affected Countries

Authors : Yıldıran YILMAZ, Selim BUYRUKOĞLU

Pages : 123-131

Doi:10.17350/HJSE19030000222

View : 11 | Download : 7

Publication Date : 2021-06-30

Article Type : Research Paper

Abstract :Coronavirus disease insert ignore into journalissuearticles values(Covid-19); caused millions of confirmed cases and thousands of deaths worldwide since first appeared in China. Forecasting methods are essential to take precautions early and control the spread of this rapidly expanding pandemic. Therefore, in this research, a new customized hybrid model consisting of Back Propagation-Based Artificial Neural Network insert ignore into journalissuearticles values(BP-ANN);, Correlated Additive Model insert ignore into journalissuearticles values(CAM); and Auto-Regressive Integrated Moving Average insert ignore into journalissuearticles values(ARIMA); models were developed to forecast of Covid-19 prevalence in Brazil, US, Russia and India. Covid-19 dataset is obtained from World Health Organization website from 22 January, 2020 to 6 January, 2021. Various parameters were tested to select the best ARIMA models for these countries based on the lowest MAPE values insert ignore into journalissuearticles values(5.21, 11.42, 1.45, 2.72); for Brazil, US, Russia and India, respectively. On the other hand, the proposed BP-ANN model itself provided less satisfactory MAPE values. Finally, the developed new customized hybrid model was achieved to obtain the best MAPE results insert ignore into journalissuearticles values(4.69, 6.4, 0.63, 2.25); for forecasting of Covid-19 prevalence in Brazil, US, Russia and India, respectively. Those results emphasize the validity of our hybrid model. Besides, the proposed prediction models can assist countries in terms of taking important precautions to control the spread of Covid-19 in the world.
Keywords : Covid 19, Neural Network, ARIMA, Time Series, Correlated Additive Model