Forecasting COVID-19 Cases in Indonesia, Malaysia, Philippines, and Vietnam Using ARIMA and LSTM

Marina Wahyuni Paedah, Fergyanto E. Gunawan

Abstract


COVID-19 has severely impacted the global economy, including ASEAN countries. Various plans and strategies are still needed during the pandemic-to-epidemic transition period to minimize the risk of COVID-19 transmission. The research focuses on the total number of confirmed cases of COVID-19 in Indonesia, Malaysia, the Philippines, and Vietnam, which are among the ASEAN countries with the highest number of cases in Southeast Asia. Those countries have cultural similarities, where gathering with friends and family is an important part of social life. This research evaluates the ability of ARIMA and LSTM to predict COVID-19 cases in each country, using daily data from January 23, 2020 to October 22, 2022. Datasets published by Johns Hopkins University (JHU) and Our World in Data (OWID) are used, which are accessible through Github. Compared to ARIMA with  R2 of 0,8883 for Indonesia, 0,8353 for Malaysia, 0.97291 for the Philippines, and -3.105 for Vietnam, LSTM model can predict better in the four sampled ASEAN countries, with an R2 of 0.9996 for Indonesia, 0.9707 for Malaysia, 0.97291 for the Philippines, and 0.9200 for Vietnam.


Keywords


COVID-19; ASEAN; Prediction; Forecasting; Time Series; LSTM

Full Text:

PDF

References


N. A. Yaacob, M. I. Yusof, S. M. Nuruddin, Z. M. Zain och N. A. Mustapa, ”Non-Traditional Security Issues in Southeast Asia during COVID-19: Implications and Mitigation Strategies by ASEAN,” Proceedings, vol. 82, nr 1, p. 90, 2022.

M. R. Ridzuan och N. A. S. A. Rahman, ”The deployment of fiscal policy in several ASEAN countries in dampening the impact of COVID-19,” Journal of Emerging Economies & Islamic Research, vol. 9, nr 1, pp. 16-28, 2021.

R. J. Hyndman och G. Athanasopoulos, Forecasting: principles and practice, 3rd edition, Melbourne: OTexts, 2021.

H. Chung och K.-s. Shin, ”Genetic algorithm-optimized long short-term memory network for stock market prediction,” Sustainability, vol. 10, nr 10, p. 3765, 2018.

R. Vega, L. Flores och R. Greiner, ”SIMLR: Machine Learning inside the SIR model for COVID-19 Forecasting,” Forecasting, vol. 4, nr 1, pp. 72-94, 2022.

P. Kumari och D. Toshniwal, ”Real-time estimation of COVID-19 cases using machine learning and mathematical models-The case of India,” 2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS), pp. 369-374, 2020.

H. R. Niazkar och M. Niazkar, ”Application of artificial neural networks to predict the COVID-19 outbreak,” Global health research and policy, vol. 5, nr 1, pp. 1-11, 2020.

M. Shawaqfah och F. Almomani, ”Forecast of the outbreak of COVID-19 using artificial neural network: Case study Qatar, Spain, and Italy,” Results in Physics, vol. 27, p. 104484, 2021.

M. d. B. Braga, R. d. S. Fernandes, G. N. d. S. Jr, J. E. C. d. Rocha, C. J. F. Dolácio, I. d. S. T. Jr, R. R. Pinheiro, F. N. Noronha, L. L. S. Rodrigues och R. Thia, ”Artificial neural networks for short-term forecasting of cases, deaths, and hospital beds occupancy in the COVID-19 pandemic at the Brazilian Amazon,” PLoS ONE 16(3): e0248161, p. https://doi.org/10.1371/journal.pone.0248161, 2021.

G. Toga, B. Atalay och M. D. Toksari, ”COVID-19 prevalence forecasting using autoregressive integrated moving average (ARIMA) and artificial neural networks (ANN): Case of Turkey,” Journal of infection and public health, vol. 14, nr 7, pp. 811-816, 2021.

N. Abidin, A. Ahmarofi och N. Zaibidi, ”Prediction of Intensive Care Cases for COVID-19 Pandemic in Malaysia: An Artificial Neural Networks Approach,” ASM Science Journal 16, p. https://doi.org/10.32802/asmscj.2021.747, 2021.

M. Kumar, S. Gupta, K. P. Kumar och M. Sachdeva, ”Spreading of COVID-19 in India, Italy, Japan, Spain, UK, US: a prediction using ARIMA and LSTM modelDigital Government: Research and Practice,” Digital Government: Research and Practice, vol. 1, nr 4, pp. 1-9., 2020.

K. ArunKumar, D. V.Kalaga, C. S. Kumar, M. Kawaji och T. M.Brenza, ”Comparative analysis of Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM) cells, Autoregressive Integrated Moving Average (ARIMA), Seasonal Autoregressive Integrated Moving Average (SARIMA) for forecasting COVID-19 trends,” Alexandria Engineering Journal, vol. 61, nr 10, pp. 7585-7603, 2022.

İ. e. a. Kırbaş, ”Comparative analysis and forecasting of COVID-19 cases in various European countries with ARIMA, NARNN and LSTM approaches,” Chaos, Solitons & Fractals, vol. 138, p. 110015, 2020.




DOI: https://doi.org/10.24114/cess.v8i1.41209

Article Metrics

Abstract view : 149 times
PDF - 104 times

Refbacks



Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

CESS (Journal of Computer Engineering, System and Science)

Creative Commons License
CESS (Journal of Computer Engineering, System and Science) is licensed under a Creative Commons Attribution 4.0 International License