Sistem Prediksi Kasus Covid-19 di Indonesia Menggunakan Algoritma Linear Regression

Yusriyah Isnaini  Mufidah; Andika Bayu  Saputra; Netania Indi Kusumaningtyas

doi:10.30989/teknomatika.v16i1.1099

Yusriyah Isnaini Mufidah Universitas Jenderal Achmad Yani Yogyakarta
Andika Bayu Saputra Universitas Jenderal Achmad Yani Yogyakarta
Netania Indi Kusumaningtyas Universitas Jenderal Achmad Yani Yogyakarta

DOI: https://doi.org/10.30989/teknomatika.v16i1.1099

Abstract

The Coronavirus disease outbreak caused by severe acute respiratory syndrome by coronavirus 2 was first reported in Wuhan, Hubei province, China in December 2019, until March 2, 2020, President Joko Widodo announced the first case of an Indonesian citizen who was confirmed positive for COVID-19. The development of new cases of COVID-19 patients in Indonesia is still being reported even though the pandemic has lasted for almost two years. Then need a way to determine predictions or predict the number of increases in Indonesia’s COVID-19 cases in the future using machine learning technology with the Linear Regression algorithm. Estimating the number of active cases adding positive COVID-19 cases in Indonesia over the next 3 months using the machine learning method using the Linear Regression algorithm. This study predicts COVID-19 cases using machine learning with the Linear Regression algorithm. The model results have a linear coefficient, so the model predicts very well for linear data on days 0 – 300, and on the day after that, the number of positive cases of the national COVID-19 virus does not continue to show a linear relationship, the model becomes inaccurate again. The results of the parameter evaluation show that the level of accuracy is low, but this model can be used as a reference for case predictions for the next month with the results of comparison of predicted data and actual data not much different.

References

[1] Z. Ceylan, “Estimation of COVID-19 prevalence in Italy, Spain, and France,” Science of The Total Environment, vol. 729, p. 138817, 2020.

[2] L. Zhang, J. Zhu, X. Wang, J. Yang, X. F. Liu, and X.-K. Xu, “Characterizing COVID-19 transmission: incubation period, reproduction rate, and multiple-generation spreading,” Front Phys, vol. 8, p. 589963, 2021.

[3] M. A. Golberg and H. A. Cho, Introduction to regression analysis. WIT press, 2004.

[4] G. C. de Melo, R. A. de Araújo Neto, and K. C. G. M. de Araújo, “Forecasting the rate of cumulative cases of COVID-19 infection in Northeast Brazil: a Boltzmann function-based modeling study,” Cad Saude Publica, vol. 36, p. e00105720, 2020.

[5] F. Fadly and E. Sari, “An approach to measure the death impact of Covid-19 in Jakarta using autoregressive integrated moving average (ARIMA),” Unnes Journal of Public Health, vol. 9, no. 2, pp. 108–116, 2020.

[6] A. I. Saba and A. H. Elsheikh, “Forecasting the prevalence of COVID-19 outbreak in Egypt using nonlinear autoregressive artificial neural networks,” Process safety and environmental protection, vol. 141, pp. 1–8, 2020.

[7] F. Rustam et al., “COVID-19 future forecasting using supervised machine learning models,” IEEE access, vol. 8, pp. 101489–101499, 2020.

[8] R. O. Ogundokun, A. F. Lukman, G. B. M. Kibria, J. B. Awotunde, and B. B. Aladeitan, “Predictive modelling of COVID-19 confirmed cases in Nigeria,” Infect Dis Model, vol. 5, pp. 543–548, 2020.

[9] Python 3.10.6 documentation. (n.d.)., “pickle — Python object serialization.” https://docs.python.org/3/library/pickle.html (accessed Jul. 12, 2022).

[10] “Deploying with Git | Heroku Dev Center.” https://devcenter.heroku.com/articles/git (accessed Jul. 07, 2022).