Randomized Machine Learning and Forecasting of Nonlinear Dynamic Models Applied to SIR Epidemiological Model
Keywords:
randomized machine learning, entropy, entropy estimation, forecasting, randomized forecastingAbstract
We propose an approach to estimation of the parameters of non-linear dynamic models using the concept of Randomized Machine Learning (RML), based on the transition from deterministic models to random ones (with random parameters), followed by estimation of the probability distributions of parameters and noises on real data. The main feature of this method is its efficiency in conditions of a small amount of real data. The paper considers models formulated in terms of ordinary differential equations, which are converted to a discrete form for setting and solving the problem of entropy optimization. The application of the proposed approach is demonstrated on the problem of predicting the total number of infected COVID-19 using a
dynamic SIR epidemiological model. To do this, we construct a randomized SIR model (R-SIR) with one parameter, the entropy-optimal estimate of which is realized by its probability density function, as well as the probability density functions of the measurement noise at the points where training is performed. Next, the technique of randomized prediction with noise filtering is applied, based on the generation of the corresponding distributions and the construction of an ensemble of predictive trajectories with the calculation of the trajectory averaged over the ensemble. The paper implements a computational experiment using real operational data on the infection cases in the form of a comparative study with a well-known method for estimating model parameters based on the least squares method. The results obtained in the experiment demonstrate a significant decrease in the mean absolute percentage error (MAPE) with respect to real observations in the forecast interval, which shows the efficiency of the proposed method and its effectiveness in problems of the type considered in the work.
References
2. van den Driessche P. Mathematical Epidemiology / ed. by Brauer F., van den Driessche P., Wu J. Berlin, Heidelberg: Springer Berlin Heidelberg, 2008. Vol. 1945 of Lecture Notes in Mathematics. P. 147–157. https://doi.org/10.1007/978-3-540-78911-6.
3. Aivazyan S.A., Mhitaryan V.S. Prikladnaya statistika i osnovy ekonometriki. — Moscow, Unity, 1998.
4. Lagutin M.B. Naglyadnaya matematicheskaya statistika. — Binom, 2013.
5. Borovkov A.A. Matematicheskaya statistika. — Moscow, Nauka, 1984.
6. Bishop C. Pattern Recognition and Machine Learning (Information Science and Statistics), 2006. Springer, New York, 2006.
7. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data mining, Inference, and Prediction. Springer New York, 2009.
8. Merkov A.B. Raspoznavanie obrazov. Vvedenie v metody statisticheskogo obuchenia. Moscow, URSS, 2010.
9. Popkov Y.S., Popkov A.Y., Dubnov Y.A. Randomizirovannoe mashinnoe obuchenie pri ogranichennych naborach dannykh: ot emp[iricheskoy veroyatnosti k entropyinoy randomizacii. Moscow: LENAND, 2019. ISBN: 978-5-9710-5908-0.
10. Popkov, Y.S., Dubnov, Y.A. Entropy-robust randomized forecasting under small sets of retrospective data. Automation and Remote Control. 2016. Vol. 77, pp. 839–854. https://doi.org/10.1134/S0005117916050076.
11. Popkov A.Y. Randomized Machine Learning of Nonlinear Models with Application to Forecasting the Development of an Epidemic Process // Automation and Remote Control. 2021. Vol. 82, pp. 1049–1064. https://doi.org/10.1134/S0005117921060060.
12. Popkov Y.S., Dubnov Y.A., Popkov A.Y. Introduction to the Theory of Randomized Machine Learning // Learning Systems: From Theory to Practice / ed. by Sgurev V., Piuri V., Jotsov V. Cham: Springer International Publishing, 2018. P. 199–220. ISBN: 978-3-319-75181-8. https://doi.org/10.1007/978-3-319-75181-8_10.
13. Popkov Y., Popkov A., Dubnov Y. Elements ofRandomized Forecasting and Its Application to Daily Electrical Load Prediction in a Regional Power System // Automation and Remote Control. 2020. Vol. 81, pp. 1286–1306. https://doi.org/10.1134/S0005117920070103.
14. Kermack W.O., McKendrick A.G. Contributions to the Mathematical Theory of Epidemics // Proceedings of the Royal Society. 1927. Vol. 115A. P. 700–721.
15. Muller G.R. Zeitschrift fur allgemeine Mikrobiologie / In: The Population Dynamics of Infectious Diseases: Theory and Applications. 368 S., 135 Abb., 104 Tab. London-New York, Chapman and Hall, 1984, Vol. 24, no. 2. pp. 76–76. https://doi.org/10.1002/jobm.19840240203.
16. Hethcote H.W. Three Basic Epidemiological Models // Applied Mathematical Ecology. Springer Berlin Heidelberg, 1989. pp. 119–144. https://doi.org/10.1007/978-3-642-61317-3_5.
17. Peng L., Yang W., Zhang D., Zhuge C., Hong L. Epidemic analysis of COVID-19 in China by dynamical modeling // arXiv, 2020. 10.48550/ARXIV.2002.06563.
18. Yang W., Zhang D., Peng L., Zhuge C., Hong L. Rational evaluation of various epidemic models based on the COVID-19 data of China // Epidemics, 2021. Vol. 37. p. 100501. https://doi.org/10.1016/j.epidem.2021.100501.
19. Cheng C., Zhang D., Dang D., Geng J., Zhu P., Yuan M., Liang R., Yang H., Jin Y., Xie J., Chen S., Duan G. The incubation period of COVID-19: a global meta-analysis of 53 studies and a Chinese observation study of 11 545 patients // Infectious Diseases of Poverty, 2021. Vol. 10, no. 1. https://doi.org/10.1186/s40249-021-00901-9.
20. Huang S., Li J., Dai C., Tie Z., Xu J., Xiong X., Hao X., Wang Z., Lu C. Incubation period of coronavirus disease 2019: New implications for intervention and control // International Journal of Environmental Health Research, 2021. P. 1–9. https://doi.org/10. 1080/09603123.2021.1905781.
21. Li Q. et al. Early Transmission Dynamics in Wuhan, China, of Novel Coronavirus — Infected Pneumonia // New England Journal of Medicine, 2020. Vol. 382, no. 13. P. 1199–1207. https://doi.org/10.1056/nejmoa2001316.
22. Nie X. et al. Epidemiological Characteristics and Incubation Period of 7015 Confirmed Cases With Coronavirus Disease 2019 Outside Hubei Province in China // The Journal of Infectious Diseases, 2020. Vol. 222, no. 1. pp. 26–33. https://doi.org/10.1093/infdis/jiaa211.
23. Guidotti E., Ardia D. COVID-19 Data Hub // Journal of Open Source Software. 2020. Vol. 5, no. 51. P. 2376. https://doi.org/10.21105/joss.02376.
24. COVID-19 Data Hub. https://www.covid19datahub.io. 2021. Accessed: 2022-06-20.
25. Flach P. Nauka и iskusstvo postroenia algoritmov, kotorie izvlekaiut znania iz dannykh. Moscow, DMK Press, 2015.
26. Rubinstein R.Y., Kroese D.P. Simulation and the Monte Carlo method. John Wiley & Sons, 2007. Vol. 707.
Published
How to Cite
Section
Copyright (c) Попков Алексей Юрьевич
![Creative Commons License](http://i.creativecommons.org/l/by/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms: Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).