Time Series Models using in Prediction of COVID-19 Infection Cases in Mexico
https://doi.org/10.15514/ISPRAS-2024-36(6)-13
Abstract
The COVID-19 pandemic was the first health crisis to affect the entire world in this century. The data captured revealed a lack of organization and control in health measures, containment, and mitigation policies, as well as a lack of planning and coordination in the use of medical supplies, which motivated the development of prediction models that provided predictive information on the evolution of the pandemic. In this work, a time series of accumulated cases of infection was generated through official data provided by the Ministry of Health of the Government of Mexico. Six deterministic and stochastic predictive models were applied to this information to compare their efficiency in predicting cases of COVID-19 infection. These models were applied to data from two cities in Mexico, Colima and the State of Mexico. The study concludes that the ARIMA and ANN MLP models adapt better to the data that is generated daily, therefore, they have an improved prediction capacity.
About the Authors
Keila Vasthi CORTÉS-MARTÍNEZ
TECNM/Centro Nacional de Investigación y Desarrollo Tecnológico
Mexico
Mexico
Received a master’s degree in computer science from the National Center for Research and Technology Development of Cuernavaca, México, in 2019. Her research interests are machine learning, image recognition and data mining.
Hugo ESTRADA-ESQUIVEL
TECNM/Centro Nacional de Investigación y Desarrollo Tecnológico
Mexico
Mexico
Received a master’s degree in Computer Science from the National Center for Research and Technology Development of Cuernavaca, México, and a PhD degree in Informatics from the Technical University of Valencia, Spain, and a Ph.D. degree in Informatics and Telecommunications from the Trento University Italy, in 2008. PhD Estrada has been researcher in INFOTEC research center, the National Council of Science and Technology and currently in the National Center for Research and Technological Development, CENIDET. His research interests include big data, Internet of things and smart cities.
Alicia MARTINEZ-REBOLLAR
TECNM/Centro Nacional de Investigación y Desarrollo Tecnológico
Mexico
Mexico
Received her master degree in Computer Science from the National Center for Research and Technology Development of Cuernavaca, México, and a PhD degree in Informatics from the Technical University of Valencia, Spain, and a PhD degree in Informatics and Telecommunications from the Trento University Italy, in 2008. Since 2009, she has been Research professor with the National Center for Research and Technological Development, CENIDET. She is the author of 4 books, and more than 130 papers. Her research interests include big data, Internet of things, smart cities, and affective computing.
References
1. Organización Mundial de la Salud (OMS), “Enfermedad por el Coronavirus,” Novel Coronavirus 2019, 42–49 (2021). [Last access: February 28th, 2021]. https://www.paho.org/es/enfermedad-por-coronavirus-covid-19.
2. Instituto Nacional de Transparencia, Acceso a la Información y Protección de Datos Personales (INAI), “Línea de tiempo COVID-19 en México”, [Last access: December 27th,2023]. https://micrositios.inai.org.mx/conferenciascovid-19tp/?page_id=8432.
3. Instituto Nacional de Transparencia, Acceso a la Información y Protección de Datos Personales (INAI), “Sugerencias de Actividades para realizar durante la contingencia sanitaria #Quédate en Casa”, pp. 1-45 (2021). https://inicio.inai.org.mx/nuevo/RecomendacionesINAICOVID-19.pdf.
4. J. C. Clement, V. K. Ponnusamy, K. Sriharipriya, et al., “A Survey on Mathematical, Machine Learning and Deep Learning Models for COVID-19 Transmission and Diagnosis”, IEEE reviews in biomedical engineering, 15, 325–340(2022). https://doi.org/10.1109/RBME.2021.3069213.
5. A. Mehrotraa y R. Agarwal, “A Review of Use of Data Mining duringCOVID-19 Pandemic”, Turkish Journal of Computer and Mathematics Education, 12(6), 4547-4552(2021). https://doi.org/10.17762/turcomat.v12i6.8441.
6. Vasilev, I.A., Petrovskiy, M.I., Mashechkin, I.V, et al. “Predicting COVID-19-Induced Lung Damage Based on Machine Learning Methods”. Programming and Computer Software, 48, 243–255 (2022).doi: https://doi.org/10.1134/S0361768822040065.
7. F. Rustam, A., et al. “COVID-19 Future Forecasting Using Supervised Machine Learning Models”, IEEE Access Xplore, 8, 101489-101499(2020). doi:10.1109/ACCESS.2020.2997311.
8. Madini O. Alassafi, Mutasem Jarrah, Reem Alotaibi, “Time series predicting of COVID-19 based on deep learning”, Neurocomputing 468, 335-344 (2022). ISSN 0925-2312, https://doi.org/10.1016/j.neucom.2021.10.035.
9. R. Chandra, A. Jain y D. Singh Chauhan, “Deep learning via LSTM models for COVID-19 infection forecasting in India”, PLOS ONE, 17(1), 1-28 (2022), https://doi.org/10.1371/journal.pone.0262708.
10. S. Kumar, R. Sharma, T. Tsunoda, et al., “Forecasting the spread of COVID-19 using LSTM network”. BMC Bioinformatics, 22 (6), 316 (2021). https://doi.org/10.1186/s12859-021-04224-2.
11. Z. Car, S. Baressi Šegota, N. Anđelić, et al., “Modeling the Spread of COVID-19 Infection Using a Multilayer Perceptron”, Hindawi. Computational and Mathematical Methods in Medicine, 2020 (5714714), 1-10 (2020). https://doi.org/10.1155/2020/5714714.
12. R. Somyanonthanakul, K. Warin, W. Amasiri, et al., “Forecasting COVID-19 cases using time series modeling and association rule mining”, BMC Medical Research Methodology, 22(281), 1-18 (2022), doi: 10.1186/s12874-022-01755-x.
13. M. Abdelaziz, A. Ahmed, A. Riad, et al., “Forecasting daily confirmed COVID-19 cases in Algeria using ARIMA models”, Short research communication- EMHJ, 29 (7), 515-519 (2023), https://doi.org/10.26719/emhj.23.054.
14. S. Sah, B. Surendiran, R. Dhanalakshmi, et al., “Forecasting COVID-19 Pandemic Using Prophet, ARIMA, and Hybrid Stacked LSTM-GRU Models in India”, Hindawi. Computational and Mathematical Methods in Medicine, 2022 (1556025), 1-19 (2022), https://doi.org/10.1155/2022/1556025.
15. Y. Jin, R. Wang, X. Zhuang, et al., “Prediction of COVID-19 Data Using an ARIMA-LSTM Hybrid Forecast Model”, MDPI Mathematics, 10 (21), 1-13 (2022), https://doi.org/10.3390/math10214001.
16. Dirección General de Epidemiología, “Datos Abiertos Bases Históricas”. Available at.: https://www.gob.mx/salud/documentos/datos-abiertos-bases-historicas-direccion-general-de-epidemiologia, [Last access: January 25th, 2024].
17. Instituto Nacional de Estadística y Geografía (INEGI), “Consulta de indicadores sociodemográficos y económicos por área geográfica”. Available at.: https://www.inegi.org.mx/, [Last access: Decembre 27th,2023].
18. Instituto Nacional de Estadística y Geografía (INEGI) para niños. “Densidad de Población”, Available at.: https://cuentame.inegi.org.mx/poblacion/densidad.aspx?tema=P, [Last access: Decembre 27th,2023].
19. G. Ramírez-Valverde y B. Ramírez-Valverde, “Modelo estadístico para defunciones y casos positivos de COVID-19 en México”, EconoQuantum, 18(1), 1-20 (2021). https://doi.org/10.18381/eq.v18i1.7223.
20. Rojas-García, M., Vázquez, B., Torres-Poveda, K.et al. “Lethality risk markers by sex and age-group for COVID-19 in Mexico: a cross-sectional study based on machine learning approach”. BMC Infectious Diseases, 23(18), 1-14 (2023). https://doi.org/10.1186/s12879-022-07951-w.
21. Cueva Moncayo, M., Jami Carrera, J., & Betancourt Rubio, E., “Previsión de COVID-19 mediante modelo de series temporales en pacientes de una clínica de salud rural”, Revista Cubana de Investigaciones Biomédicas, 42(3127), 1-21 (2023), Editorial de Ciencias Médicas (ECIMED). https://revibiomedica.sld.cu/index.php/ibi/article/view/3127.
22. Secretaría del Gobierno de México (gob.mx), “Boletín estadístico 2021 del exceso de mortalidad por todas las causas durante la emergencia por COVID-19”, Grupo Interinstitucional para la estimación del exceso de mortalidad por todas las causas, 46 (27), 1-42 (2021). https://coronavirus.gob.mx/wp-content/uploads/2021/09/2021.09.08-Boleti%CC%81n_XXI_Exceso_Mortalidad_SE33_MX.pdf.
23. Z. Malki, E.-S. Atlam, A. Ewis, et al., “The COVID-19 pandemic: prediction study based on machine learning models”, Environmental Science and Pollution, 28(30), 40496-40506 (2021). doi: 10.1007/s11356-021-13824-7.
24. L. Tomov, L. Chervenkov, D. G. Miteva, et al. “Applications of time series analysis in epidemiology: Literature review and our experience during COVID-19 pandemic”, WJCC (World Journal of Clinical Cases), 11 (29), 6974-6983 (2023). PMID: 37946767 doi: 10.12998/wjcc.v11.i29.6974.
25. M. S. Bartlett, “Deterministic and Stochastic Models for Recurrent Epidemics”, Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability, IV, 81-109 (1956). https://apps.dtic.mil/sti/pdfs/AD1028592.pdf.
26. A. M. Radwan, “Forecasting of Covid-19 Using Time Series Regression Models”, 2021 Palestinian International Conference on Information and Communication Technology (PICICT), 7-12 (2021). doi: 10.1109/PICICT53635.2021.00014.
27. S. Bhutia, B. Patra y M. Ray, “COVID-19 epidemic: analysis and prediction”, IAES International Journal of Artificial Intelligence (IJ-AI), 11(2), 736-745 (2022). ISSN: 2252-8938, doi: 10.11591/ijai.v11.i2.
28. V. Chaurasia y S. Pal, “Application of machine learning time series analysis for prediction COVID-19 pandemic”, Research on Biomedical Engineering. Sociedade Brasileira de Engenharia Biomedica, 38(1), 35-47 (2020) . PMCID: PMC7585491. doi: 10.1007/s42600-020-00105-4.
29. Fadhil A. Abidi; Zainb Hasan Radiy, “Using exponential smoothing methods to analysis COVID-19 time series”, 2nd International Conference on Engineering and Science to Achieve the Sustainable Development Goals. AIP Conference Proceedings, 3092 (1), id.070014, 1-10 (2024), https://doi.org/10.1063/5.0200417.
30. G. Sanglier Contreras, M. Robas Mora, P. Jimenez Gomez, "Use of quantitative forecasting methods and error calculation for better adaptability to the application of a mathematical model to determine the speed of spread of a coronavirus infection (COVID-19) in Spain", Contemporary Engineering Sciences, 13(1), 157-175 (2020), doi: 10.12988/ces.2020.91570.
31. R. Somyanonthanakul, K. Warin, W. Amasiri, et al. “Forecasting COVID-19 cases using time series modeling and association rule mining”, BMC Medical Research Methodoly, 22 (281), 1-18 (2022), https://doi.org/10.1186/s12874-022-01755-x.
32. Yu, C. S., Chang, S. S., Chang, et al., “A COVID-19 Pandemic Artificial Intelligence-Based System with Deep Learning Forecasting and Automatic Statistical Data Acquisition: Development and Implementation Study”, Journal of medical Internet research, 23(5), (2021). e27806. https://doi.org/10.2196/27806.
33. Kadirliev T.M., Telpukhov D.V., Solovyev R.A. Application of Neural Networks for Image Segmentation in the Problem of Fast Global Routing. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2023;35(5):145-156. (In Russ.) https://doi.org/10.15514/ISPRAS-2022-35(5)- 10.
Review
For citations:
CORTÉS-MARTÍNEZ K., ESTRADA-ESQUIVEL H., MARTINEZ-REBOLLAR A. Time Series Models using in Prediction of COVID-19 Infection Cases in Mexico. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2024;36(6):231-246. https://doi.org/10.15514/ISPRAS-2024-36(6)-13
Email this article 