TIME-SERIES MODELING OF COVID-19 USING MACHINE LEARNING TECHNIQUES

Minh-Tuan Nguyen; Van-The Than

Minh-Tuan Nguyen Hung Yen University of Technology and Education
Van-The Than Hung Yen University of Technology and Education

Keywords: COVID-19, Machine Learning, Nonlinear Autoregressive, Long Short-term memory

Abstract

The COVID-19 pandemic was first detected in China in late 2019 and then spread around the world. As of July 31st, 2019, more than 17 million cases have been infected, including more than 670,000 deaths worldwide. In the current study, two machine learning models are Nonlinear autoregressive (NAR) and Long short-term memory (LSTM), were developed to forecast outbreaks of COVID-19 globally and some of the most heavily affected countries such as the United State, Brazil, and India based on a public data set provided by the World Health Organization (WHO). A set of metrics evaluated the performance of the forecasting models as the root mean square error (RMSE), the mean absolute error (MAE), the mean absolute percentage error (MAPE), and coefficient of determination (R2) is given to analyze and evaluate the accuracy of the forecasting models. The results showed that both models are suitable for forecasting the spread of COVID-19, and NAR gave a higher performance than LSTM. The forecasting results can be used for policy formulation and precautions in the studied countries.

References

M. Maleki, M. R. Mahmoudi, D. Wraith, and K.-H. Pho, “Time series modelling to forecast the confirmed and recovered cases of COVID-19,” Travel Medicine and Infectious Disease, 2020, pp. 101742.

Z. Ceylan, “Estimation of COVID-19 prevalence in Italy, Spain, and France,” Science of The Total Environment, 2020, pp. 138817.

F. M. Khan and R. Gupta, “Arima and nar based prediction model for time series analysis of covid-19 cases in india,” Journal of Safety Science and Resilience, 2020, vol. 1, pp. 12-18.

P. Melin, J. C. Monica, D. Sanchez, and O. Castillo, “Multiple ensemble neural network models with fuzzy response aggregation for predicting COVID-19 time series: the case of Mexico,” in Healthcare, 2020, pp. 181.

S. F. Ardabili, A. Mosavi, P. Ghamisi, F. Ferdinand, A. R. Varkonyi-Koczy, U. Reuter, et al., “Covid-19 outbreak prediction with machine learning,” Available at SSRN 3580188, 2020.

V. K. R. Chimmula and L. Zhang, “Time series forecasting of COVID-19 transmission in Canada using LSTM networks,” Chaos, Solitons & Fractals, 2020, pp. 109864.

A. Tomar and N. Gupta, “Prediction for the spread of COVID-19 in India and effectiveness of preventive measures,” Science of The Total Environment, 2020, pp. 138762.

N. Zheng, S. Du, J. Wang, H. Zhang, W. Cui, Z. Kang, et al., “Predicting covid-19 in china using hybrid AI model,” IEEE Transactions on Cybernetics, 2020.

J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proceedings of the national academy of sciences, 1982, vol. 79, pp. 2554-2558.

A. K. Palit and D. Popovic, Computational intelligence in time series forecasting: theory and engineering applications: Springer Science & Business Media, 2006.

S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, 1997, vol. 9, pp. 1735-1780.