Hiper-Parametre Ayarlı YSA, Bi-LSTM ve Yığılmış-LSTM Kullanarak Türkiye'de COVID-19 Salgını Tahmini

Year 2026, Volume: 14 Issue: 1 , 20 - 37 , 21.01.2026

Serpil Özer , Mustafa Göçken , Ayse Tugba Dosdogru

https://doi.org/10.29130/dubited.1662505

https://izlik.org/JA36YN45KW

Abstract

COVID-19 ilk olarak Aralık 2019'da Çin'de ortaya çıkmıştır. Türkiye'de ise ilk vaka 11 Mart 2020 tarihinde görülmüştür. COVID-19 ortaya çıktığından bu yana dünyayı hızla etkisi altına aldı ve birçok insanın ölümüne neden oldu. Virüsün dünya genelinde hızla yayılması ve küresel bir tehdit oluşturması yetkililerin hızlı önlem ve karar almasını zorunlu hale getirmiştir. Bu nedenle COVID-19 hastalığının teşhisi, tedavisi ve vaka sayısının tahmini hayati bir konudur. Bu çalışmada, Türkiye'nin COVID-19 verileri kullanılarak günlük ölümler, günlük vakalar, kümülatif ölümler ve kümülatif vaka sayıları tahmin edilmiştir. COVID-19 için tahmin analizi, yapay zeka (AI) teknikleri, özellikle Yığılmış Uzun-Kısa Dönem Bellek (Stacked-LSTM), Çift Yönlü Uzun Kısa Dönem Bellek (Bi-LSTM) ve Yapay Sinir Ağı (ANN) yöntemleri kullanılarak gerçekleştirilmiştir. Bu modelleri optimize etmek için Gray Wolf Optimizer Algoritması (GWO) kullanılarak hiperparametre optimizasyonu uygulanmıştır. Tahmin modellerinin doğruluğunu ve etkinliğini değerlendirmek için Ortalama Mutlak Yüzde Hata (MAPE), Belirleme Katsayısı (R^2 Puanı), Ortalama Karesel Hatanın Kökü (RMSE), Ortalama Mutlak Hata (MAE), Ortalama Karesel Hata (MSE) ve Açıklanan Varyans Puanı (EVS) gibi çeşitli performans ölçütleri kullanılmıştır. Pandemi tahmin modellerinin doğruluğunun ve etkinliğinin değerlendirilmesi, tahmin edilen veri değerlerinin gerçek değerlerle karşılaştırılmasını içermiştir. Bu analize dayanarak, gerçek değerlere en yüksek derecede benzerlik gösteren tahmin modelinin en güvenilir ve etkili olduğu belirlenmiştir.

Keywords

Veri analizi , derin öğrenme , yapay sinir ağları , uzun kısa süreli bellek (LSTM) , COVID-19 , GWO

COVID-19 Pandemic Prediction Using Hyper-Parameter-Tuned ANN, Bi-LSTM, and Stacked-LSTM in Türkiye

https://izlik.org/JA36YN45KW

Abstract

COVID-19 first appeared in China in December 2019. In Türkiye, the first case was seen on March 11, 2020. Since the emergence of COVID-19, it has rapidly affected the world and caused the death of many people. The rapid spread of the virus around the world and the fact that it poses a global threat have made it mandatory for the authorities to take quick measures and decisions. For this reason, the diagnosis, treatment, and prediction of the number of cases of COVID-19 disease is a vital issue. In this paper, daily deaths, daily cases, cumulative deaths, and cumulative case numbers were predicted using Türkiye's COVID-19 data. The prediction analysis for COVID-19 was conducted employing artificial intelligence (AI) techniques, specifically Stacked Long-Short Term Memory (Stacked-LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), and Artificial Neural Network (ANN) methods. Hyperparameter optimization using the Gray Wolf Optimizer Algorithm (GWO) was applied to optimize these models. To assess the accuracy and efficacy of prediction models, various performance metrics were employed, including Mean Absolute Percentage Error (MAPE), Coefficient of Determination (R^2 Score), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Squared Error (MSE), and Explained Variance Score (EVS). The assessment of the accuracy and efficacy of the pandemic prediction models involved comparing the predicted data values with the actual values. Based on this analysis, the prediction model that exhibited the highest degree of similarity to the actual values was determined to be the most reliable and effective.

Keywords

Data analysis , Deep learning , Artificial neural networks , Long short-term memory (LSTM) , COVID-19 , GWO

Ethical Statement

This study does not involve human or animal participants. All procedures followed scientific and ethical principles, and all referenced studies are appropriately cited.

Supporting Institution

This research received no external funding.

Thanks

The author/authors do not wish to acknowledge any individual or institution.

References

• Alkhatib, K., Khazaleh, H., Alkhazaleh, H. A., Alsoud, A. R., & Abualigah, L. (2022). A new stock price forecasting method using active deep learning approach. Journal of Open Innovation: Technology, Market, and Complexity, 8(2), Article 96. https://doi.org/10.3390/joitmc8020096
• Anderson, D., & McNeill, G. (1992). Artificial neural networks technology (Technical Report). Kaman Sciences Corporation.
• Arora, P., Kumar, H., & Panigrahi, B. K. (2020). Prediction and analysis of COVID-19 positive cases using deep learning models: A descriptive case study of India. Chaos, Solitons & Fractals, 139, Article 110017. https://doi.org/10.1016/j.chaos.2020.110017
• Ataseven, B. (2013). Yapay sinir ağlari ile öngörü modellemesi. Öneri Dergisi, 10(39), 101-115.
• Ayoobi, N., Sharifrazi, D., Alizadehsani, R., Shoeibi, A., Gorriz, J. M., Moosaei, H., Khosravi, A., Nahavandi, S., Gholamzadeh Chofreh, A., Goni, F. A., Klemeš, J. J., & Mosavi, A. (2021). Time series forecasting of new cases and new deaths rate for COVID-19 using deep learning methods. Results in physics, 27, Article 104495. https://doi.org/10.1016/j.rinp.2021.104495
• Bahri, S., Kdayem, M., & Zoghlami, N. (2020, December). Deep learning for COVID-19 prediction. In 2020 4th International Conference on Advanced Systems and Emergent Technologies (IC_ASET) (pp. 406-411). IEEE.
• Bao, B., Xu, Z., Li, C., Sun, Z., Liu, S., & Li, Y. (2021). TDTS: Three-dimensional traffic scheduling in optical fronthaul networks with Conv-LSTM. Photonics, 8(10), Article 451. https://doi.org/10.3390/photonics8100451
• Crokidakis, N. (2020). Modeling the early evolution of the COVID-19 in Brazil: Results from a Susceptible–Infectious–Quarantined–Recovered (SIQR) model. International Journal of Modern Physics C, 31(10), Article 2050135. https://doi.org/10.1142/S0129183120501351
• Devaraj, J., Elavarasan, R. M., Pugazhendhi, R., Shafiullah, G. M., Ganesan, S., Jeysree, A. K., Khan, I. A., & Hossain, E. (2021). Forecasting of COVID-19 cases using deep learning models: Is it reliable and practically significant? Results in Physics, 21, Article 103817. https://doi.org/10.1016/j.rinp.2021.103817
• Er, F., & Bal, C. (2020). COVID-19 ve Grafiksel Veri Analizi. Osmangazi Tıp Dergisi, 42(4), 450-461.
• Er, M. B., & Işık, İ. (2021). LSTM tabanlı derin ağlar kullanılarak diyabet hastalığı tahmini. Türk Doğa ve Fen Dergisi, 10(1), 68-74.
• Irmak, S., Köksal, C. D., & Asilkan, Ö. (2012). Hastanelerin gelecekteki hasta yoğunluklarının veri madenciliği yöntemleri ile tahmin edilmesi. Uluslararası Alanya İşletme Fakültesi Dergisi, 4(1), 101-114.
• Istaiteh, O., Owais, T., Al-Madi, N., & Abu-Soud, S. (2020, October). Machine learning approaches for covid-19 forecasting. In 2020 International Conference on Intelligent Data Science Technologies and Applications (IDSTA) (pp. 50-57). IEEE.
• Khare, N., Jha, M., Mathur, R., & Jha, A. K. (2020). Data analysis for COVID-19. The International Journal of Analytical and Experimental Modal Analysis, 12(5), 960-974.
• Lalmuanawma, S., Hussain, J., & Chhakchhuak, L. (2020). Applications of machine learning and artificial intelligence for Covid-19 (SARS-CoV-2) pandemic: A review. Chaos, Solitons & Fractals, 139, Article 110059. https://doi.org/10.1016/j.chaos.2020.110059
• Marzouk, M., Elshaboury, N., Abdel-Latif, A., & Azab, S. (2021). Deep learning model for forecasting COVID-19 outbreak in Egypt. Process Safety and Environmental Protection, 153, 363-375. https://doi.org/10.1016/j.psep.2021.07.034
• Mirjalili, S., Mirjalili, S. M., & Lewis, A. (2014). Grey wolf optimizer. Advances in engineering software, 69, 46-61. https://doi.org/10.1016/j.advengsoft.2013.12.007
• Picariello, M., & Aliani, P. (2020). Covid-19: Data analysis of the Lombardy region and the provinces of Bergamo and Brescia. arXiv. https://arxiv.org/abs/2003.10518
• Sazlı, M. H. (2006). A brief review of feed-forward neural networks. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 50(01), 11-17. https://doi.org/10.1501/commua1-2_0000000026
• Scientific Committee Study COVID-19 (SARS-CoV-2) Infection Guide. (2020). T.C. Ministry of Health General Directorate of Public Health.
• Sengupta, S. (2020). Forecasting the peak of covid-19 daily cases in India using time series analysis and multivariate LSTM [Preprint]. EasyChair.
• Shahid, F., Zameer, A., & Muneeb, M. (2020). Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM. Chaos, Solitons & Fractals, 140, Article 110212. https://doi.org/10.1016/j.chaos.2020.110212
• Sharma, S., Sharma, S., & Athaiya, A. (2017). Activation functions in neural networks. Towards Data Science, 6(12), 310-316.
• T.C. Sağlık Bakanlığı. (2021, December 7). COVID-19 bilgilendirme platformu. https://covid19.saglik.gov.tr/
• Tandon, H., Ranjan, P., Chakraborty, T., & Suhag, V. (2022). Coronavirus (COVID-19): ARIMA-based time-series analysis to forecast near future and the effect of school reopening in India. Journal of Health Management, 24(3), 373-388. https://doi.org/10.1177/09720634221109087
• Tapiwa, G., Cécile, K., Dongxuan, C., Andrea, T., Christel, F., Jacco, W., & Niel, H. (2020). Estimating the generation interval for COVID-19 based on symptom onset data [Preprint]. medRxiv. https://www.medrxiv.org/content/10.1101/2020.03.05.20031815v1
• Tüzüntürk, S. (2010). Veri madenciliği ve istatistik. Uludağ Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 29(1), 65-90.
• Uğur, A., & Kınacı, A. C. (2006). Yapay zeka teknikleri ve yapay sinir ağları kullanılarak web sayfalarının sınıflandırılması. In XI. Türkiye'de İnternet Konferansı (inet-tr'06), Ankara, Türkiye.
• Vaishya, R., Javaid, M., Khan, I. H., & Haleem, A. (2020). Artificial intelligence (AI) applications for COVID-19 pandemic. Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 14(4), 337-339. https://doi.org/10.1016/j.dsx.2020.04.012
• Wang, P., Zheng, X., Ai, G., Liu, D., & Zhu, B. (2020). Time series prediction for the epidemic trends of COVID-19 using the improved LSTM deep learning method: Case studies in Russia, Peru and Iran. Chaos, Solitons & Fractals, 140, Article 110214. https://doi.org/10.1016/j.chaos.2020.110214
• Waqas, M., Farooq, M., Ahmad, R., & Ahmad, A. (2020). Analysis and prediction of COVID-19 pandemic in Pakistan using time-dependent SIR model [Preprint]. arXiv. https://arxiv.org/abs/2005.02353
• World Health Organization Regional Office for Europe. (n.d.). Coronavirus disease (COVID-19) outbreak: About the virus. Retrieved December 7, 2021, from https://www.euro.who.int/en/health-topics/health-emergencies/coronavirus-covid-19/novel-coronavirus-2019-ncov
• Yönem, E., & Akay, R. (2020). Yapay arı koloni algoritması ile eğitilmiş tekrarlayıcı sinir ağlarının robot navigasyonu için kullanılması. Avrupa Bilim ve Teknoloji Dergisi, 318-324. https://doi.org/10.31590/ejosat.araconf41
• Zeroual, A., Harrou, F., Dairi, A., & Sun, Y. (2020). Deep learning methods for forecasting COVID-19 time-series data: A comparative study. Chaos, Solitons & Fractals, 140, Article 110121. https://doi.org/10.1016/j.chaos.2020.110121