The mortality modeling of covid-19 patients using a combined time series model and evolutionary algorithm

(1) * Imam Tahyudin Mail (Universitas Amikom Purwokerto, Indonesia)
(2) Rizki Wahyudi Mail (Universitas Amikom Purwokerto, Indonesia)
(3) Wiga Maulana Mail (Universitas Amikom Purwokerto, Indonesia)
(4) Hidetaka Nambo Mail (Artificial Intelligence Laboratory, Kanazawa University, Japan)
*corresponding author

Abstract


COVID-19 pandemics for as long as two years ago since 2019 gives many insights into various aspects, including scientific development. One of them is the fundamental research of computer science. This research aimed to construct the best model of COVID-19 patients’ mortality and obtain less prediction errors. We performed the combination methods of time series, SARIMA, and Evolutionary algorithm, PARCD, to predict male patients who died because of COVID-19 in the USA, containing 1.008 data. So, this research proposed that SARIMA-PARCD has a powerful combination for addressing the complex problem in a dataset. The prediction error of SARIMA-PARCD was compared with other methods, i.e., SARIMA, LSTM, and the combination of SARIMA-LSTM. The result showed that the SARIMA-PARCD has the smallest MSE value of 0.0049. Therefore, the proposed method is competitive to implement in other cases with similar characteristics. This combination is robust for solving linear and non-linear problems.

Keywords


Time Series Analysis; Evolutionary Algorithm; SARIMA-PARCD; COVID-19 Patients; LSTM

   

DOI

https://doi.org/10.26555/ijain.v8i1.669
      

Article metrics

Abstract views : 433 | PDF views : 143

   

Cite

   

Full Text

Download

References


[1] R. A. Davis, “Introduction to Statistical Analysis of Time Series.” Department of Statistics Columbia University, pp. 1–24, 2014. Available at: Google Scholar.

[2] C. B. Borkowf, “Time-Series Forecasting,” Technometrics, vol. 44, no. 2, pp. 194–195, 2002, doi: 10.1198/tech.2002.s718.

[3] T. Schluter, “Knowledge discovery from time series,” Universit ̈at D ̈usseldorf, 2012. Available at: Google Scholar.

[4] I. Tahyudin, Berlilana, and H. Nambo, “Sarima model of bioelectic potential dataset,” Commun. Comput. Inf. Sci., vol. 872, pp. 367–378, 2018, doi: 10.1007/978-3-319-96292-4_29.

[5] X. Li, Y. Liu, L. Fan, S. Shi, T. Zhang, and M. Qi, “Research on the prediction of dangerous goods accidents during highway transportation based on the ARMA model,” J. Loss Prev. Process Ind., vol. 72, p. 104583, 2021, doi: 10.1016/j.jlp.2021.104583.

[6] D. Chakraborty and S. K. Sanyal, “Time-series data optimized AR/ARMA model for frugal spectrum estimation in Cognitive Radio,” Phys. Commun., vol. 44, p. 101252, 2021, doi: 10.1016/j.phycom.2020.101252.

[7] I. Tahyudin and H. Nambo, “Comparison study of deep learning and time series for bioelectric potential analysis,” Proc. - 2018 3rd Int. Conf. Inf. Technol. Inf. Syst. Electr. Eng. ICITISEE 2018, pp. 79–83, 2019, doi: 10.1109/ICITISEE.2018.8720998.

[8] D. Benvenuto, M. Giovanetti, L. Vassallo, S. Angeletti, and M. Ciccozzi, “Application of the ARIMA model on the COVID-2019 epidemic dataset,” Data Br., vol. 29, p. 105340, 2020, doi: 10.1016/j.dib.2020.105340.

[9] Z. Malki et al., “ARIMA models for predicting the end of COVID-19 pandemic and the risk of second rebound,” Neural Comput. Appl., vol. 0, 2020, doi: 10.1007/s00521-020-05434-0.

[10] Z. Ceylan, “Estimation of COVID-19 prevalence in Italy , Spain, and France,” Sci. Total Environ., no. January, 2020. doi: 10.1016/j.scitotenv.2020.138817

[11] Haviluddin and A. Jawahir, “Comparing of ARIMA and RBFNN for short-term forecasting,” Int. J. Adv. Intell. Informatics, vol. 1, no. 1, pp. 15–22, 2015, doi: 10.26555/ijain.v1i1.10.

[12] Suhartono, S. Isnawati, N. A. Salehah, D. D. Prastyo, H. Kuswanto, and M. H. Lee, “Hybrid SSA-TSR-ARIMA for water demand forecasting,” Int. J. Adv. Intell. Informatics, vol. 4, no. 3, pp. 238–250, 2018, doi: 10.26555/ijain.v4i3.275.

[13] K. Y. Chen and C. H. Wang, “A hybrid SARIMA and support vector machines in forecasting the production values of the machinery industry in Taiwan,” Expert Syst. Appl., vol. 32, no. 1, pp. 254–264, 2007, doi: 10.1016/j.eswa.2005.11.027.

[14] N. H. A. Rahman, M. H. Lee, Suhartono, and M. T. Latif, “Hybrid seasonal ARIMA and artificial neural network in forecasting southeast Asia City Air Pollutant Index,” ASM Sci. J., vol. 12, no. Special Issue 1, pp. 215–226, 2019. Available at: Google Scholar.

[15] M. Yollanda and D. Devianto, “Hybrid Model of Seasonal ARIMA-ANN to Forecast Tourist Arrivals through Minangkabau International Airport,” 2020, doi: 10.4108/eai.2-8-2019.2290473.

[16] M. Braun, T. Bernard, O. Piller, and F. Sedehizade, “24-hours demand forecasting based on SARIMA and support vector machines,” Procedia Eng., vol. 89, pp. 926–933, 2014, doi: 10.1016/j.proeng.2014.11.526.

[17] A. Ozozen, G. Kayakutlu, M. Ketterer, and O. Kayalica, “A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting: Case study in Turkey,” PICMET 2016 - Portl. Int. Conf. Manag. Eng. Technol. Technol. Manag. Soc. Innov. Proc., pp. 2681–2690, 2017, doi: 10.1109/PICMET.2016.7806831.

[18] L. Parviz, “Comparative evaluation of hybrid sarima and machine learning techniques based on time varying and decomposition of precipitation time series,” J. Agric. Sci. Technol., vol. 22, no. 2, pp. 563–578, 2020. doi: 10.3390/e22050578

[19] D. P. M. Abellana, D. M. C. Rivero, M. E. Aparente, and A. Rivero, “Hybrid SVR-SARIMA model for tourism forecasting using PROMETHEE II as a selection methodology: a Philippine scenario,” J. Tour. Futur., 2020, doi: 10.1108/JTF-07-2019-0070.

[20] H. Liu et al., “Forecast of the trend in incidence of acute hemorrhagic conjunctivitis in China from 2011–2019 using the Seasonal Autoregressive Integrated Moving Average (SARIMA) and Exponential Smoothing (ETS) models,” J. Infect. Public Health, vol. 13, no. 2, pp. 287–294, 2020, doi: 10.1016/j.jiph.2019.12.008.

[21] M. Z. Md Maarof, Z. Ismail, and M. Fadzli, “Optimization of SARIMA model using genetic algorithm method in forecasting Singapore tourist arrivals to Malaysia,” Appl. Math. Sci., vol. 8, no. 169–172, pp. 8481–8491, 2014, doi: 10.12988/ams.2014.410847.

[22] P. Arora, H. Kumar, and B. K. Panigrahi, “Prediction and analysis of COVID-19 positive cases using deep learning models: A descriptive case study of India,” Chaos, Solitons and Fractals, vol. 139, p. 110017, 2020, doi: 10.1016/j.chaos.2020.110017.

[23] J. Kumar, R. Goomer, and A. K. Singh, “Long Short Term Memory Recurrent Neural Network (LSTM-RNN) Based Workload Forecasting Model for Cloud Datacenters,” Procedia Comput. Sci., vol. 125, pp. 676–682, 2018, doi: 10.1016/j.procs.2017.12.087.

[24] T. A. Rashid, P. Fattah, and D. K. Awla, “Using accuracy measure for improving the training of LSTM with metaheuristic algorithms,” Procedia Comput. Sci., vol. 140, pp. 324–333, 2018, doi: 10.1016/j.procs.2018.10.307.

[25] T. Kim and H. Y. Kim, “Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data,” PLoS One, vol. 14, no. 2, pp. 1–23, 2019, doi: 10.1371/journal.pone.0212320.

[26] I. Kirbas, A. Sozen, A. D. Tuncer, and F. S. Kazancioglu, “Comparative analysis and forecasting of COVID-19 cases in various European countries with ARIMA , NARNN and LSTM approaches,” no. January, 2020. doi: 10.1016/j.chaos.2020.110015

[27] M. A. Jishan, K. R. Mahmud, A. K. Al Azad, M. S. Alam, and A. M. Khan, “Hybrid deep neural network for bangla automated image descriptor,” Int. J. Adv. Intell. Informatics, vol. 6, no. 2, 2020, doi: 10.26555/ijain.v6i2.499.

[28] I. Tahyudin, Berlilana, and H. Nambo, “Predicting human position using improved numerical association analysis for bioelectric potential data,” Lect. Notes Networks Syst., vol. 69, pp. 655–666, 2020, doi: 10.1007/978-3-030-12388-8_46.

[29] J.-Y. Yeh, T.-H. Wu, and C.-W. Tsao, “Using data mining techniques to predict hospitalization of hemodialysis patients,” Decis. Support Syst., vol. 50, no. 2, pp. 439–448, Jan. 2011, doi: 10.1016/j.dss.2010.11.001.

[30] Q. Wu and R. Law, “Cauchy mutation based on objective variable of Gaussian particle swarm optimization for parameters selection of SVM,” Expert Syst. Appl., vol. 38, no. 6, pp. 6405–6411, 2011, doi: 10.1016/j.eswa.2010.08.069.




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

___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571  (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
   andri.pranolo.id@ieee.org (publication issues)

View IJAIN Stats

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0