Modified SEIQHRDP and machine learning prediction for the epidemics

Li Yike ; Elena Gubar

Contributions to game theory and management, Tome 16 (2023), pp. 110-131.

Résumé

This paper is dedicated to investigating the transmission and prediction of viruses within human society. In the first phase, we augment the classical Susceptible-Exposed-Infectious-Recovered (SEIR) model by incorporating four novel states: protected status ($P$), quarantine status ($Q$), self-home status ($H$), and death status ($D$). The numerical solution of this extended model is obtained using the well-established fourth-order Runge-Kutta algorithm. Subsequently, we employ the next matrix method to calculate the basic reproduction number ($R_0$) of the infectious disease model. We substantiate the stability of the basic reproductive number through an analysis grounded in Routh-Hurwitz theory. Lastly, we turn to the application and comparison of statistical models, specifically the Autoregressive Integrated Moving Average (ARIMA) and Bidirectional Long Short-Term Memory (Bi-LSTM) models, for time series prediction.

Détail

Keywords: dynamics model, Runge-Kutta, ARIMA, Bi-LSTM model.

Bibliographie

[1] Bozdogan, H., “Model selection and Akaike's information criterion (AIC): The general theory and its analytical extensions”, Psychometrika, 52:3 (1987), 345–370 | DOI | MR | Zbl

[2] Chicco, D., Warrens, M. J. and Jurman, G., “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation”, PeerJ Computer Science, 7 (2021), e623 | DOI

[3] Dong, E., Du, H. and Gardner, L., “An interactive web-based dashboard to track COVID-19 in real time”, The Lancet infectious diseases, 20:5 (2020), 533–534 | DOI

[4] Gavin, H. P., The Levenberg-Marquardt algorithm for nonlinear least squares curve-fitting problems, Department of Civil and Environmental Engineering, Duke University, 2019, 19 pp.

[5] Gubar, E., Taynitskiy, V., Fedyanin, D. and Petrov, I., “Quarantine and Vaccination in Hierarchical Epidemic Model”, Mathematics, 11:6 (2023), 1450 | DOI

[6] Gubar, E., Taynitskiy, V. and Zhu, Q., “Optimal control of heterogeneous mutating viruses”, Games, 9:4 (2018), 103 | DOI | MR | Zbl

[7] Ho, S. L. and Xie, M., “The use of ARIMA models for reliability forecasting and analysis”, Computers and industrial engineering, 35:1–2 (1998), 213–216

[8] Jia, W. P., Han, K., Song, Y., Cao, W. Z., Wang, S. S., Yang, S. S., Wang, J. W., Kou, F. Y., Tai, P. G. and Li, J., “Extended SIR prediction of the epidemics trend of COVID-19 in Italy and compared with Hunan, China”, Frontiers in medicine, 7 (2020), 169 | DOI | MR

[9] Kermack, W. O. and Mckendrick, A. G., “A contribution to the mathematical theory of epidemics”, Proceedings of the royal society of london. Series A, Containing papers of a mathematical and physical character, 115:772 (1927), 700–721

[10] Porta, M., A dictionary of epidemiology, Oxford university press, 2014 | MR

[11] Pastor, S. R., Castellano, C., Van, M. P. and Vespignani, A., “Epidemic processes in complex networks”, Reviews of modern physics, 87:3 (2015), 925 | DOI | MR

[12] Shahid, F., Zameer, A. and Muneeb, M., “Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM”, Chaos, Solitons and Fractals, 140 (2020), 110212 | DOI | MR

[13] Sun, H. C., Liu, X. F., Du, Z. W., Xu, X. K. and Wu, Y., “Optimal control of heterogeneous mutating viruses”, IEEE Transactions on Computational Social Systems, 8:6 (2021), 1302–1310 | DOI

[14] Van den, D. P., and Watmough, J., “Reproduction numbers and sub-threshold endemic equilibria for compartmental models of disease transmission”, Mathematical biosciences, 180:1–2 (2002), 29–48 | MR | Zbl

[15] Wonham, M. J. and Lewis, M. A., “A comparative analysis of models for West Nile virus”, Mathematical epidemiology, 2008, 365–390 | DOI | MR | Zbl