Research Article
BibTex RIS Cite

Prediction of COVID-19 Cases in the United States of America with Machine Learning Algorithms

Year 2021, Issue: 22, 134 - 139, 31.01.2021
https://doi.org/10.31590/ejosat.855113

Abstract

The coronavirus first appeared in Wuhan, China in December 2019 and was declared as a pandemic by the World Health Organization on March 11, 2020. In order to control the number of cases, many countries have taken various measures such as quarantine, curfew and closing social areas for a while. Prediction data can be used in logistics, procurement, hospital personnel and supplies planning and vaccination scenarios. In the confirmed case estimate; in the literature, there are studies that use many methods such as machine learning, compartmental model, and time series analysis in confirmed case prediction. In this study, various machine learning models have been generated to estimate future cases using the number of confirmed cases in the United States. The predictions made using Python and R programming language were made with Prophet, Polynomial Regression, ARIMA, Linear Regression and Random Forest models. The performances of the data estimated by the test data are evaluated using the mean absolute percent error (MAPE), root mean square deviation (RMSE) and mean absolute error (MAE). As a result, the algorithm that gives the best estimates based on the MAPE error metric was found as Polynomial Regression.

References

  • Awan, T. M., & Aslam, F. (2020). Prediction of daily COVID-19 cases in European countries using automatic ARIMA model. Journal of Public Health Research, 9(3), 227-233. https://doi.org/10.4081/jphr.2020.1765.
  • Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)?. Geosci. Model Dev., 7, 1247-1250. https://doi.org/10.5194/gmd-7-1247-2014.
  • Date, S., & Deshmukh, S. (2020). Forecasting novel COVID-19 confirmed cases in India using Machine Learning Methods, International Journal of Computer Sciences and Engineering, 8(6), 57-62. https://doi.org/10.26438/ijcse/v8i6.5762.
  • Juo, J., Shi, T., & Chang, J., (2016). Comparison of Random Forest and SVM for Electrical Short-term Load Forecast with Different Data Sources. 7th IEEE International Conference on Software Engineering and Service Science (ICSESS), Beijing, 1077-1080, https://doi.org/10.1109/ICSESS.2016.7883252.
  • Keleş, M. B., Keleş, A., & Keleş, A. (2020). Yapay Zekâ Teknolojisi ile Uçuş Fiyatı Tahmin Modeli Geliştirme. Turkish Studies - Applied Sciences, 15(4). 511-520. https://dx.doi.org/10.29228/TurkishStudies.45993.
  • McCoy, T. H., Pellegrini, A. M., & Perlis, R. H. (2018). Assessment of Time-Series Machine Learning Methods for Forecasting Hospital Discharge Volume. JAMA Netw Open, 1(7). https://doi.org/10.1001/jamanetworkopen.2018.4087.
  • Nunno, L. (2014). Stock Market Price Prediction Using Linear and Polynomial Regression Models.
  • Ostertagová, E. (2012). Modelling using polynomial regression. Procedia Engineering, 48, 500-506. https://doi.org/10.1016/j.proeng.2012.09.545.
  • Papacharalampous, G. A., & Tyralis, H., (2018). Evaluation of random forests and Prophet for daily streamflow forecasting. Advances in Geosciences, 45, 201-208. https://doi.org/10.5194/adgeo-45-201-2018.
  • Rustam, F., Reshi, A. A., Mehmood, A., Ullah, S., On, B., Aslam, W., & Choi, G. S. (2020). COVID-19 Future Forecasting Using Supervised Machine Learning Models, IEEE Access, 8, 101489-101499. https://doi.org/10.1109/ACCESS.2020.2997311.
  • Sahai, A. K., Rath, N., Sood, V., & Singh, M. P. (2020). ARIMA modelling&forecasting of COVID-19 in top five affected countries. Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 14(5), 1419-1427. https://doi.org/10.1016/j.dsx.2020.07.042.
  • Sevli, O., & Başer, V. G. (2020). COVID-19 Salgınına Yönelik Zaman Serisi Verileri ile Prophet Model Kullanarak Makine Öğrenmesi Temelli Vaka Tahminlemesi. European Journal of Science and Technology, 19, 827-835. https://doi.org/10.31590/ejosat.766623.
  • Taylor, S. J., & Letham, B. (2018). Forecasting at Scale. The American Statician, 72 (1), 37-45. https://doi.org/10.1080/00031305.2017.1380080.

COVID-19 Vakalarının Makine Öğrenmesi Algoritmaları ile Tahmini: Amerika Birleşik Devletleri Örneği

Year 2021, Issue: 22, 134 - 139, 31.01.2021
https://doi.org/10.31590/ejosat.855113

Abstract

Koronavirüs, 2019 yılının Aralık ayında ilk olarak Çin’in Wuhan kentinde ortaya çıkmış ve 11 Mart 2020’de Dünya Sağlık Örgütü tarafından pandemi olarak ilan edilmiştir. Vaka sayılarını kontrol altına almak için pek çok ülke karantina, sokağa çıkma yasağı ve sosyal alanların bir süreliğine kapatılması gibi çeşitli önlemler almıştır. Doğrulanmış vaka tahminlemesi pandemide olası planlamalar için büyük önem taşımaktadır. Gelecek verilerinin gerçeğe en yakın bir şekilde tahminlenmesi; pandemi döneminde lojistik, tedarik, hastane personel ve malzeme planlaması için kullanılabileceği gibi aşılama senaryolarında da girdi olarak kullanılabilir. Literatürde doğrulanmış vaka tahmininde makine öğrenmesi, bölmeli model, zaman serisi analizi gibi pek çok yöntem kullanarak tahminleme yapılan çalışmalar vardır. Bu çalışmada, Amerika Birleşik Devletleri’ndeki doğrulanmış vaka sayılarını kullanarak gelecek günlerdeki vaka tahminlerini çeşitli makine öğrenmesi modelleri yapılmıştır. Python ve R programlama dili kullanılarak yapılan tahminlemeler Prophet, Polinom Regresyon, ARIMA, Doğrusal Regresyon ve Random Forest modelleri ile yapılmıştır. Test verisiyle tahmin edilen verilerin performansları ortalama mutlak yüzde hatası (MAPE), ortalama karekök sapması (RMSE) ve ortalama mutlak hata (MAE) kullanılarak değerlendirilmiştir. Sonuç olarak, MAPE hata metriği baz alınarak en iyi tahminleri veren algoritma Polinom Regresyon olarak bulunmuştur.

References

  • Awan, T. M., & Aslam, F. (2020). Prediction of daily COVID-19 cases in European countries using automatic ARIMA model. Journal of Public Health Research, 9(3), 227-233. https://doi.org/10.4081/jphr.2020.1765.
  • Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)?. Geosci. Model Dev., 7, 1247-1250. https://doi.org/10.5194/gmd-7-1247-2014.
  • Date, S., & Deshmukh, S. (2020). Forecasting novel COVID-19 confirmed cases in India using Machine Learning Methods, International Journal of Computer Sciences and Engineering, 8(6), 57-62. https://doi.org/10.26438/ijcse/v8i6.5762.
  • Juo, J., Shi, T., & Chang, J., (2016). Comparison of Random Forest and SVM for Electrical Short-term Load Forecast with Different Data Sources. 7th IEEE International Conference on Software Engineering and Service Science (ICSESS), Beijing, 1077-1080, https://doi.org/10.1109/ICSESS.2016.7883252.
  • Keleş, M. B., Keleş, A., & Keleş, A. (2020). Yapay Zekâ Teknolojisi ile Uçuş Fiyatı Tahmin Modeli Geliştirme. Turkish Studies - Applied Sciences, 15(4). 511-520. https://dx.doi.org/10.29228/TurkishStudies.45993.
  • McCoy, T. H., Pellegrini, A. M., & Perlis, R. H. (2018). Assessment of Time-Series Machine Learning Methods for Forecasting Hospital Discharge Volume. JAMA Netw Open, 1(7). https://doi.org/10.1001/jamanetworkopen.2018.4087.
  • Nunno, L. (2014). Stock Market Price Prediction Using Linear and Polynomial Regression Models.
  • Ostertagová, E. (2012). Modelling using polynomial regression. Procedia Engineering, 48, 500-506. https://doi.org/10.1016/j.proeng.2012.09.545.
  • Papacharalampous, G. A., & Tyralis, H., (2018). Evaluation of random forests and Prophet for daily streamflow forecasting. Advances in Geosciences, 45, 201-208. https://doi.org/10.5194/adgeo-45-201-2018.
  • Rustam, F., Reshi, A. A., Mehmood, A., Ullah, S., On, B., Aslam, W., & Choi, G. S. (2020). COVID-19 Future Forecasting Using Supervised Machine Learning Models, IEEE Access, 8, 101489-101499. https://doi.org/10.1109/ACCESS.2020.2997311.
  • Sahai, A. K., Rath, N., Sood, V., & Singh, M. P. (2020). ARIMA modelling&forecasting of COVID-19 in top five affected countries. Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 14(5), 1419-1427. https://doi.org/10.1016/j.dsx.2020.07.042.
  • Sevli, O., & Başer, V. G. (2020). COVID-19 Salgınına Yönelik Zaman Serisi Verileri ile Prophet Model Kullanarak Makine Öğrenmesi Temelli Vaka Tahminlemesi. European Journal of Science and Technology, 19, 827-835. https://doi.org/10.31590/ejosat.766623.
  • Taylor, S. J., & Letham, B. (2018). Forecasting at Scale. The American Statician, 72 (1), 37-45. https://doi.org/10.1080/00031305.2017.1380080.
There are 13 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Nur Selin Özen 0000-0001-8545-8771

Selin Saraç 0000-0002-4729-0637

Melik Koyuncu 0000-0003-0513-6276

Publication Date January 31, 2021
Published in Issue Year 2021 Issue: 22

Cite

APA Özen, N. S., Saraç, S., & Koyuncu, M. (2021). COVID-19 Vakalarının Makine Öğrenmesi Algoritmaları ile Tahmini: Amerika Birleşik Devletleri Örneği. Avrupa Bilim Ve Teknoloji Dergisi(22), 134-139. https://doi.org/10.31590/ejosat.855113