Protecting South Sulawesi: Combination of Random Forest Regressor and SEIRS Mathematical Model in the Analysis and Prediction of the Spread of Covid-19

Nur Qadri Bahar, Syafruddin Side, Muhammad Abdy

Abstract


This applied research seeks to examine the dynamics of Covid-19 transmission in South Sulawesi Province. Additionally, this study will also forecast the future spread of Covid-19. This research comprises two phases: the investigation of Covid-19 transmission utilizing the SEIRS mathematical model, incorporating Vaccination and PPKM (Enforcement of Community Activity Restrictions), and the prediction of Covid-19 spread through machine learning techniques. The utilized data is secondary data sourced from the South Sulawesi Provincial Health Office. This study developed a machine learning model utilizing a random forest regressor algorithm due to its proficiency in identifying nonlinear data patterns. This model effectively accounts for the variability of the dataset (target variable) with a R2 score of 95%. The evaluation findings of the random forest regressor model indicated satisfactory performance, with a mean absolute error (MAE) of 29.57 and a root mean square error (RMSE) of 54.42 during training, and an MAE of 58.55 and an RMSE of 98.67 during testing. Given the significant variability in Covid-19 data and the prevalence of zeros in the dataset, the MAE and RMSE values for both training and testing are deemed acceptable. This model is designed to forecast daily Covid-19 instances in the future. This work not only employs machine learning but also analyzes the dissemination of Covid-19 through the SEIRS mathematical model, incorporating vaccination and PPKM factors. The SEIRS model analysis indicates that the disease-free equilibrium point is stable when R0<1 and unstable when R0>1. The fundamental reproduction rate derived from the vaccine's efficacy is v=65.3%, and the compliance rate with PPKM is ?=1%. Consequently, R0=1.2407288, indicating that Covid-19 will propagate in South Sulawesi Province. For ?=11%, R0=1.0167230. This indicates that Covid-19 will stabilize, and with ?=69%, R0=0.2338689, suggesting that Covid-19 will vanish from South Sulawesi Province.

?


Keywords


Machine Learning, Random Forest Regressor, SEIRS Model, Covid-19

Full Text:

PDF

References


D. F. N. Anisa, I. Mukhlash, and M. Iqbal, “Deteksi Berita Online Hoax Covid-19 Di Indonesia Menggunakan Metode Hybrid Long Short Term Memory dan Support Vector Machine,” J. Sains dan Seni ITS, vol. 11, no. 3, 2023, doi: 10.12962/j23373520.v11i3.83227.

M. I. Mubarok, Hasil Survei Sosial Demografi Dampak Covid-19 Provinsi Sulawesi Selatan 2020. Badan Pusat Statistik Provinsi Sulawesi Selatan, 2020.

N. Q. Bahar and N. M. Rauf, “Analisis Penyebaran COVID-19 di Sulawesi Selatan Menggunakan Machine Learning ( Regression Models ),” EQUIVA J. Math. Inf. Technol., vol. 2, no. 2, 2024, [Online]. Available: https://journal.itk.ac.id/index.php/equiva/article/view/1258

S. Annas, M. Isbar Pratama, M. Rifandi, W. Sanusi, and S. Side, “Stability analysis and numerical simulation of SEIR model for pandemic COVID-19 spread in Indonesia,” Chaos, Solitons and Fractals, vol. 139, p. 110072, 2020, doi: 10.1016/j.chaos.2020.110072.

M. Abdy, S. Side, S. Annas, W. Nur, and W. Sanusi, “An SIR epidemic model for COVID-19 spread with fuzzy parameter: the case of Indonesia,” Adv. Differ. Equations, vol. 2021, no. 1, 2021, doi: 10.1186/s13662-021-03263-6.

M. A. Karim and Y. Yulida, “Analisis Kestabilan dan Sensitivitas pada Model Matematika SEIRD dari Penyebaran COVID-19: Studi Kasus di Kalimantan Selatan,” J. Binawakya, vol. 16, no. 5, p. 7003, 2021, [Online]. Available: http://ejurnal.binawakya.or.id/index.php/MBI

H. Lamouadene et al., “Detection of COVID-19, lung opacity, and viral pneumonia via X-ray using machine learning and deep learning,” Comput. Biol. Med., vol. 191, p. 110131, 2025, doi: 10.1016/j.compbiomed.2025.110131.

M. Rostami and M. Oussalah, “A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest,” Informatics Med. Unlocked, vol. 30, p. 100941, 2022, doi: 10.1016/j.imu.2022.100941.

A. M. Fayyaz, S. Jadid Abdulkadir, S. U. Hassan, S. Al-Selwi, E. Sumiea, and L. Talib, “The Role of Advanced Machine Learning in COVID-19 Medical Imaging: A Technical Review,” Results Eng., vol. 26, p. 105154, 2025, doi: 10.1016/j.rineng.2025.105154.

K. Sumwiza, C. Twizere, G. Rushingabigwi, P. Bakunzibake, and P. Bamurigire, “Enhanced cardiovascular disease prediction model using random forest algorithm,” Informatics Med. Unlocked, vol. 41, p. 101316, 2023, doi: 10.1016/j.imu.2023.101316.

Z. Sun et al., “Applications of resting-state fMRI and machine learning in cognitive impairment in type 2 diabetes mellitus: A scoping review,” Meta-Radiology, vol. 3, no. 2, p. 100136, 2025, doi: 10.1016/j.metrad.2025.100136.

K. Pang, “A comparative study of explainable machine learning models with Shapley values for diabetes prediction,” Healthc. Anal., vol. 7, p. 100390, 2025, doi: 10.1016/j.health.2025.100390.

C. H. Feng, M. L. Disis, C. Cheng, and L. Zhang, “Multimetric feature selection for analyzing multicategory outcomes of colorectal cancer: random forest and multinomial logistic regression models,” Lab. Investig., vol. 102, no. 3, pp. 236–244, 2022, doi: 10.1038/s41374-021-00662-x.

K. Puttegowda et al., “Enhanced machine learning models for accurate breast cancer mammogram classification,” Glob. Transitions, vol. 7, pp. 276–295, 2025, doi: 10.1016/j.glt.2025.04.007.

A. Intissar, “A Mathematical Study of a Generalized SEIR Model of COVID-19,” SciMedicine J., vol. 2, pp. 30–67, 2020, doi: 10.28991/scimedj-2020-02-si-4.

S. He, Y. Peng, and K. Sun, “SEIR modeling of the COVID-19 and its dynamics,” Nonlinear Dyn., vol. 101, no. 3, pp. 1667–1680, 2020, doi: 10.1007/s11071-020-05743-y.

P. Brouqui et al., “COVID-19 re-infection,” Eur. J. Clin. Invest., vol. 51, no. 5, pp. 4–8, 2021, doi: 10.1111/eci.13537.

J. Beladiya et al., “Safety and efficacy of COVID-19 vaccines: A systematic review and meta-analysis of controlled and randomized clinical trials,” Rev. Med. Virol., vol. 34, no. 1, Jan. 2024, doi: 10.1002/RMV.2507.

M. Yamani, “Tingkat Kepatuhan Protokol Kesehatan Masa PPKM - jatengdaily,” jatengdaily, 2021. [Online]. Available: https://jatengdaily.com/2021/tingkat-kepatuhan-protokol-kesehatan-masa-ppkm/

P. Wintachai and K. Prathom, “Stability analysis of SEIR model related to efficiency of vaccines for COVID-19 situation,” Heliyon, vol. 7, no. 4, Apr. 2021, doi: 10.1016/J.HELIYON.2021.E06812.




DOI: https://doi.org/10.31763/simple.v7i1.126

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Nur Qadri Bahar, Syafruddin Side, Muhammad Abdy

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

 

Signal and Image Processing Letters
ISSN Online: 2714-6677 | Print: 2714-6669
Published by Association for Scientific Computing Electrical and Engineering (ASCEE)
Website: https://simple.ascee.org/index.php/simple/
Email: simple@ascee.org

 

Creative Commons License
 


View My Stats