YAPAY SİNİR AĞLARI VE DERİN ÖĞRENME KULLANARAK TÜRKİYE''DEKİ COVID-19 VAKALARI İÇİN TAHMİN MODELLERİ

Hükumetler, bir pandemi salgını sırasında stratejik kararlar alırken, halk sağlığı ve ekonomi arasında bir ikilemle karşı karşıyadır. Özellikle salgın dönemlerinde hükumetler tarafından alınacak stratejik kararlar açısından vaka sayısını tahmin etmek ve belirtilen ikilemi yönetmek büyük önem taşımaktadır. Bugün neredeyse tüm ülkeler için önemli konulardan birisi de Covid-19 salgınıdır. Ne yazık ki, henüz Covid-19 için etkili bir aşı veya tedavi bulunamamıştır. Ayrıca, bu çalışmanın hazırlığı sırasında, Dünya Sağlık Örgütü tarafından dünya çapında toplam vaka sayısının on üç milyondan fazla olduğu bildirilmiştir. Böyle büyük bir salgınla başa çıkmak için çeşitli karantina önlemlerinin alınması gerekli olmuştur. Hükumetler tarafından alınan karantina önlemleri, ülkeleri ekonomik krizle karşı karşıya getirmiştir. Bu durum ekonomik belirsizlikler yaratmaktadır ve hükumetleri doğru ve en az zararlı stratejik kararlar almak için muazzam bir baskı altına sokmaktadır. Bu nedenlerle hükumetler, ani bir karar vermek yerine durumu adım adım gözlemleyerek Covid-19 için stratejik kararlar almayı tercih etmektedirler. Eğer pandemi vakalarının sayısı belirlenmiş bir zamandan önce tahmin edilebilirse, hükümetlerin halk sağlığı ve ekonomi ikilemini daha doğru bir şekilde yönetmeleri için önemli bir rehber olarak kullanılabilir. Bu nedenle, bu çalışmada 7 gün önceden Covid-19 vakalarını tahmin etmek için yapay sinir ağı (YSA) ve derin öğrenme (uzun-kısa süreli bellek, LSTM ağları) modelleri sunulmuştur. Önerilen modeller Türkiye'nin gerçek verileri üzerinde test edilmiştir. Sonuçlar LSTM modellerinin eğitim seti için hem kümülatif hem de yeni vaka tahminlerinde YSA modellerinden daha iyi performans gösterdiğini göstermiştir. Önerilen modellerin tüm veri seti üzerindeki performansları kıyaslandığında YSA ve LSTM algoritmalarının birbirleri ile rekabet edebilir sonuçlar verdiği gözlemlenmiştir. Ayrıca hem YSA hem de LSTM modellerinin kümülatif vaka tahmini performanslarının yeni vaka tahminlerinden daha iyi olduğu gözlenmiştir.

Anahtar Kelimeler:

Covid-19, Pandemiler, Tahminleme, Yapay Sinir Ağları, Derin Öğrenme, LSTM, Türkiye

FORECASTING MODELS FOR COVID-19 CASES OF TURKEY USING ARTIFICIAL NEURAL NETWORKS AND DEEP LEARNING

Governments face a dilemma between public health and the economy while making strategic decisions on health during a pandemic outbreak. It is of great importance to forecast the number of cases in terms of strategic decisions to be taken by governments especially in outbreak periods and to manage the dilemma mentioned. One of the important issues today is the Covid-19 outbreak for almost all countries. Unfortunately, no effective vaccine or treatment has been found for Covid-19 yet. At the time of this study, however, it was reported that the total number of reported cases by the World Health Organization worldwide was more than thirteen million. Various quarantine measures have been necessary to deal with such a large epidemic. Quarantine measures taken by governments bring countries to face to face with the economic crisis. This creates economic uncertainties and puts governments under tremendous pressure to make accurate and least harmful strategic decisions. For these reasons, governments prefer to make strategic decisions for Covid-19 step by step observing the situation rather than making a sudden decision. If the number of pandemic cases could be predicted before a predetermined time, it would be used as an important guide for governments to manage public health and economic dilemma more accurately. Therefore, this study provides artificial neural network (ANN) and deep learning models (long-short term memory, LSTM networks) to forecast Covid-19 cases before 7-day. The proposed models were tested on real data for Turkey. The results showed that LSTM models performed better than ANN models in both cumulative cases and new cases on the training data set. Comparing the performance of the proposed models over the whole data set, it was observed that the ANN and LSTM algorithms gave competitive results. In addition, the cumulative case forecast performances of both ANN and LSTM models were observed to be better than the new case forecast.

Keywords:

Covid-19, Pandemics, Forecasting, Artificial Neural Networks, Deep Learning, LSTM, Turkey,

PDF

___

Al-Qaness, M. A., Ewees, A. A., Fan, H., & Abd El Aziz, M. (2020). Optimization method for forecasting confirmed cases of COVID-19 in China. Journal of Clinical Medicine, 9(3), 674.
Chen, Y., Liu, Q., & Guo, D. (2020). Emerging coronaviruses: genome structure, replication, and pathogenesis. Journal of medical virology, 92(4), 418-423.
DeFelice, N. B., Little, E., Campbell, S. R., & Shaman, J. (2017). Ensemble forecast of human West Nile virus cases and mosquito infection rates. Nature Communications, 8(1), 1-6.
Elmousalami, H. H., & Hassanien, A. E. (2020). Day level forecasting for Coronavirus Disease (COVID-19) spread: analysis, modeling and recommendations. arXiv preprint arXiv:2003.07778.
Fanelli, D., & Piazza, F. (2020). Analysis and forecast of COVID-19 spreading in China, Italy and France. Chaos, Solitons & Fractals, 134, 109761.
Fong, S. J., Li, G., Dey, N., Crespo, R. G., & Herrera-Viedma, E. (2020). Finding an accurate early forecasting model from small dataset: A case of 2019-ncov novel coronavirus outbreak. arXiv preprint arXiv:2003.10776.
Gamero, J., Tamayo, J. A., & Martinez-Roman, J. A. (2020). Forecast of the evolution of the contagious disease caused by novel coronavirus (2019-nCoV) in China. arXiv preprint arXiv:2002.04739.
Ghazaly, N. M., Abdel-Fattah, M. A., & Abd El-Aziz, A. A. (2020). Novel Coronavirus Forecasting Model using Nonlinear Autoregressive Artificial Neural Network. Journal of advanced science.
Hardwick, N. V. (2006). Disease forecasting. In The epidemiology of plant diseases (pp. 239-267). Springer, Dordrecht.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
Hufnagel, L., Brockmann, D., & Geisel, T. (2004). Forecast and control of epidemics in a globalized world. Proceedings of the National Academy of Sciences, 101(42), 15124-15129.
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112, p. 18). New York: Springer.
Kaundal, R., Kapoor, A. S., & Raghava, G. P. (2006). Machine learning techniques in disease forecasting: a case study on rice blast prediction. BMC bioinformatics, 7(1), 485.
McDonald, M. R., & Boland, G. J. (2004). Forecasting diseases caused by Sclerotinia spp. in eastern Canada: fact or fiction?. Canadian Journal of Plant Pathology, 26(4), 480-488.
Moran, K. R., Fairchild, G., Generous, N., Hickmann, K., Osthus, D., Priedhorsky, R., ... & Del Valle, S. Y. (2016). Epidemic forecasting is messier than weather forecasting: The role of human behavior and internet data streams in epidemic forecast. The Journal of infectious diseases, 214(suppl_4), S404-S408.
Nsoesie, E., Mararthe, M., & Brownstein, J. (2013). Forecasting peaks of seasonal influenza epidemics. PLoS currents, 5.
Perc, M., Gorišek Miksić, N., Slavinec, M., & Stožer, A. (2020). Forecasting Covid-19. Frontiers in Physics, 8, 127.
Petropoulos, F., & Makridakis, S. (2020). Forecasting the novel coronavirus COVID-19. PloS one, 15(3), e0231236.
Prechelt, L. (1998). Early stopping-but when?. In Neural Networks: Tricks of the trade (pp. 55-69). Springer, Berlin, Heidelberg.
Roosa, K., Lee, Y., Luo, R., Kirpich, A., Rothenberg, R., Hyman, J. M., ... & Chowell, G. (2020). Real-time forecasts of the COVID-19 epidemic in China from February 5th to February 24th, 2020. Infectious Disease Modelling, 5, 256-263.
Ruan, S. (2020). Likelihood of survival of coronavirus disease 2019. The Lancet Infectious Diseases, 20(6), 630-631.
Sannakki, S., Rajpurohit, V. S., Sumira, F., & Venkatesh, H. (2013, July). A neural network approach for disease forecasting in grapes using weather parameters. In 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT) (pp. 1-5). IEEE.
Santosh, K. C. (2020). AI-driven tools for coronavirus outbreak: need of active learning and cross-population train/test models on multitudinal/multimodal data. Journal of medical systems, 44(5), 1-5.
Shaman, J., Karspeck, A., Yang, W., Tamerius, J., & Lipsitch, M. (2013). Real-time influenza forecasts during the 2012–2013 season. Nature communications, 4(1), 1-10.
Shaman, J., Yang, W., & Kandula, S. (2014). Inference and forecast of the current West African Ebola outbreak in Guinea, Sierra Leone and Liberia. PLoS currents, 6.
Stübinger, J., & Schneider, L. (2020, June). Epidemiology of coronavirus COVID-19: Forecasting the future incidence in different countries. In Healthcare (Vol. 8, No. 2, p. 99). Multidisciplinary Digital Publishing Institute.
Ture, M., & Kurt, I. (2006). Comparison of four different time series methods to forecast hepatitis A virus infection. Expert Systems with Applications, 31(1), 41-46.
Van Maanen, A., & Xu, X. M. (2003). Modelling plant disease epidemics. European Journal of Plant Pathology, 109(7), 669-682.
Wang, L. F., Shi, Z., Zhang, S., Field, H., Daszak, P., & Eaton, B. T. (2006). Review of bats and SARS. Emerging infectious diseases, 12(12), 1834.
WHO, Novel Coronavirus (2019-nCoV) 2020, 2020. Retrieved from: https://www.who.int/ (accessed on 8 May 2020)
World Health Organization, (2020). WHO Coronavirus Disease (COVID-19) Dashboard. Retrieved from https://covid19.who.int/ (accessed on 16 July 2020)
Wu, J. T., Leung, K., & Leung, G. M. (2020). Nowcasting and forecasting the potential domestic and international spread of the 2019-nCoV outbreak originating in Wuhan, China: a modelling study. The Lancet, 395(10225), 689-697.
Zhao, S., Musa, S. S., Lin, Q., Ran, J., Yang, G., Wang, W., ... & Wang, M. H. (2020). Estimating the unreported number of novel coronavirus (2019-nCoV) cases in China in the first half of January 2020: a data-driven modelling analysis of the early outbreak. Journal of clinical medicine, 9(2), 388.