Brown'ın doğrusal üstel düzleştirme yöntemiyle COVİD-19 vaka sayılarının tahmin edilmesi: 15, 30 ve 60 günlük tahminlerle büyüme eğilimlerinin karşılaştırılması

Year 2022, , 232 - 241, 30.06.2022

Dilek Yapar

https://doi.org/10.18663/tjcl.1108320

Cited By: 1

Abstract

Amaç: Bu çalışmanın amacı, Türkiye, Almanya, Brezilya, Birleşik Arap Emirlikleri (BAE) ve Birleşik Krallık'ın günlük verilerini kullanarak ideal tahmin yöntemleri ile 15, 30 ve 60 günlük COVİD-19 vaka sayılarını tahmin etmektir.
Gereç ve Yöntemler: Verilere Our World in Data COVİD-19 veri setinden ulaşılmıştır. 19 Şubat 2022 tarihine kadar 15, 30 ve 60 günlük dönemler için kümülatif vaka sayıları tahmin edilmiştir. Tahmin için en yaygın kullanılan yöntemler açıklayıcı teknikler ve zaman serisi algoritmalarıdır. Beş ülke için üstel düzleştirme yöntemi (Brown'ın doğrusal trendi) kullanılmıştır.
Bulgular: Analizler, beş ülkenin benzer bir salgın eğrisi izlediğini gösterdi. Türkiye, Brezilya, Almanya, Birleşik Krallık ve BAE için 60 günlük tahminlerde 19 Şubat'a kadar sırasıyla 10322701, 22434809, 9552781, 16937127 ve 767819 toplam vakanın olacağı tahmin edildi. Türkiye, Brezilya, Almanya, İngiltere ve BAE için 30 günlük tahminlerde sırasıyla 12809393, 28752324, 12655999, 18857395 ve 905537, 15 günlük tahminlerde ise sırasıyla 13635838, 29678270, 14241248, 20006207 ve 885958 toplam vaka sayısına ulaşılacağı tahmin edilmiştir.
Sonuç: Uygun yöntemler ile yapılan kısa süreli tahminler, pandemiyi kontrol altına almak gerekli müdahaleleri planlamaya, ayrılan sağlık personeli ve yoğun bakım üniteleri gibi sağlık kaynaklarının yeterli olup olmadığını görmeye yardımcı olacaktır.

Keywords

COVİD-19, Pandemi, Tahmin yöntemleri, Üstel düzleştirme yöntemeleri, Brown

Forecasting for the number of the COVID-19 cases with Brown's linear exponential smoothing method: Comparison of the growth trends with 15 days, 30 and 60 days forecasts

Abstract

Aim: The aim of this study was to estimate the number of the COVID-19 cases for the 15, 30 and 60-days with the ideal forecasting analysis methods by using the daily data of the Turkey, Germany, Brazil, United Arab Emirates and United Kingdom.
Material and Methods: The data were reached from the Our World in Data COVID-19 dataset. The forecasts for the cumulative cases for 15, 30, and 60 days periods to 19 February 2022 were made. The most commonly used methods for forecasting are explanatory techniques and time series algorithms. The exponential smoothing method (Brown’s linear trend) was used for the five countries.
Results: The analyses showed that five countries have followed a similar epidemic curve. For 60-day forecasts, it was estimated respectively that 10322701, 22434809, 9552781, 16937127, and 767819 total cases would be in Turkey, Brazil, Germany, the UK, and The UAE until February 19. For 30-day forecasts, it was estimated respectively that 12809393, 28752324, 12655999, 18857395, and 905537 total cases would be in Turkey, Brazil, Germany, the UK, and The UAE until February 19. For 15-day forecasts, it was estimated respectively that 13635838, 29678270, 14241248, 20006207, and 885958 total cases would be in Turkey, Brazil, Germany, the UK, and The UAE until February 19.
Conclusion: The short-time forecasting methods will help to plan the necessary interventions to control the pandemic, and to see whether health resources such as allocated health personnel and intensive care units are sufficient.

Keywords

COVID-19, Pandemic, Forecasting methods, Exponential smoothing method, Brown’s linear trend

References

• 1. Our World in Data. Coronavirus Pandemic (COVID-19). https:// ourworldindata.org/coronavirus#coronavirus-country-profiles. 2022. Access date: 15.03.2022.
• 2. COVID-19 Coronovirus Pandemic. https://www.worldometers. info/coronavirus/. 2022. Access date: 20.03.2022.
• 3. JHU-CSSE. Johns Hopkins. Coronavirus Resource Center. https:// coronavirus.jhu.edu/map.html. 2022. Access date: 20.03.2022.
• 4. Guan W-j, Ni Z-y, Hu Y, et al. Clinical Characteristics of Coronavirus Disease 2019 in China N Engl J Med. 2020 Apr 30;382(18):1708- 1720. (doi: 10.1056/NEJMoa2002032)
• 5. WHO. Draft landscape and tracker of COVID-19 candidate vaccines. 2022. https://www.who.int/publications/m/item/ draft-landscape-of-covid-19-candidate-vaccines. Access date: 20.03.2022.
• 6. Our World in Data. Coronavirus (COVID-19) Vaccinations. https:// ourworldindata.org/covid-vaccinations. 2022. Access date: 20.03.2022.
• 7. Montgomery DC, Johnson LA, Gardiner JS. Forecasting and time series analysis. 2 ed. New York: McGraw-Hill Companies; 1990.
• 8. Xiao H, Jiang X, Chen C, et al. Using time series analysis to forecast the health-related quality of life of post-menopausal women with non-metastatic ER+ breast cancer: A tutorial and case study. Res Social Adm Pharm 2019.
• 9. Yu G, Schwartz Z. Forecasting Short Time-Series Tourism Demand with Artificial Intelligence Models. Journal of Travel Research. 2006; 45: 194-203.
• 10. Viboud C, Simonsen L, Chowell G. A generalized-growth model to characterize the early ascending phase of infectious disease outbreaks. Epidemics 2016; 15: 27-37
• 11. Chowell G, Sattenspiel L, Bansal S, Viboud C. Mathematical models to characterize early epidemic growth: A review. Physics of life reviews 2016; 18: 66-97.
• 12. Chowell G, Viboud C, Hyman JM, Simonsen L. The Western Africa ebola virus disease epidemic exhibits both global exponential and local polynomial growth rates. PLoS currents. 2015; 7: 916803261.
• 13. Ayres R. Turning point: The end of exponential growth? Technological Forecasting and Social Change 2006; 73: 1188-203.
• 14. Brown, R.G. Statistical Forecasting for Inventory Control, McGraw-Hill: New York, NY. 1959.
• 15. Brown, R.G. Smoothing, Forecasting and Prediction of Discrete Time Series, Prentice-Hall: New Jersey. 1962.
• 16. Holt CC, Modigliani F, Muth JF, Simon HA, Bonini CP, Winters PR. Planning Production, Inventories, and Work Force, PrenticeHall: Englewood Cliffs, Chapter 14. 1960.
• 17. Yonar H, Yonar A, Tekindal MA, Tekindal M. Modeling and Forecasting for the number of cases of the COVID-19 pandemic with the Curve Estimation Models, the Box-Jenkins and Exponential Smoothing Methods. EJMO 2020; 4: 160-5.
• 18. .Johns Hopkins University Coronavirus Resource Center. Coronavirus COVID-19 Global Cases by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University (JHU). https://coronavirus.jhu.edu/map.html. 2022. Access date: 20.03.2022.
• 19. Abotaleb M, Makarovskikh T, Yonar H et al. Modeling Covid-19 Infection Cases and Vaccine in 5 Countries Highly Vaccinations. Turkish Journal of Mathematics and Computer Science 2020; 13: 403-17.
• 20. Li Q, Feng W, Quan Y-H. Trend and forecasting of the COVID-19 outbreak in China. Journal of Infection 2020; 80 :469-96.
• 21. Rajgor DD, Lee MH, Archuleta S, Bagdasarian N, Quek SC. The many estimates of the COVID-19 case fatality rate. Lancet Infect Dis. 202
• 22. Tekindal M, Yonar H, Yonar A et al. Analyzing COVID-19 outbreak for Turkey and Eight Country with Curve Estimation Models, BoxJenkins (ARIMA), Brown Linear Exponential Smoothing Method, Autoregressive Distributed Lag (ARDL) and SEIR Models. Eurasian Journal of Veterinary Sciences. 2020; Covid-19 Special Issue: 142-55.
• 23. Remuzzi A, Remuzzi G. COVID-19 and Italy: what next? Lancet. 2020. (doi:10.1016/s0140-6736(20)30627-9).
• 24. Yapar D, Baran Aksakal N. COVID-19 döneminde aşılama. Çöl M, editör. Halk Sağlığı Bakışıyla COVID-19. 1. Baskı. Ankara: Türkiye Klinikleri; 2021. p.47-57