Uyarlamalı Ağ Tabanlı Bulanık Mantık Çıkarım Sistemi ve Yapay Sinir Ağları ile Türkiye’deki COVID-19 Vefat Sayısının Tahmin Edilmesi

COVID-19, küresel pandemi olarak ilan edilmiş, kritik ve ölümcül bir hastalıktır. Küresel salgın tehlikesinin sürmekte olduğu bu süreçte, pandemi ile yüzleşmek için özel politikalar ve planlar yapmak oldukça önemlidir. COVID-19 doğrulanmış verilerini kullanarak, yapay zeka teknikleri ile tahminlerde bulunmak ise gelecek planlarının geliştirilmesine yardımcı olduğu için önemli bir konudur. Bu çalışmada, Türkiye Sağlık Bakanlığı COVID-19 bilgilendirme sayfasında yayınlanan veriler kullanılarak, uyarlamalı ağ tabanlı bulanık mantık çıkarım sistemi (ANFIS) ve yapay sinir ağları (YSA) ile tahmin modelleri geliştirilmiştir. Bu modeller farklı istatistiksel değerlendirme kriterleri kullanılarak karşılaştırılmıştır. Değerlendirme sonucunda ANFIS modeli 0.0247 ortalama mutlak hata (MAE) değeri, 0.0012 ortalama kare hata (MSE) değeri, 0.0351 kök ortalama kare hata (RMSE) değeri ve 0.9847 regresyon katsayısı R2 sonucu ile en iyi model sonucunu elde etmiştir. Ayrıca ANFIS ile oluşturulan modelin gelecek beş günlük vefat sayılarını %96 doğruluk oranı ile tahmin ettiği görülmüştür.

Anahtar Kelimeler:

COVID-19, pandemi, ANFIS, Yapay Sinir Ağları, tahmin, Türkiye, vefat sayısı

Prediction of the COVID-19 Number of Death in Turkey by Adaptive Neuro-Fuzzy Inference System and Artifical Neural Networks

COVID-19 is a critical and fatal disease, which was declated as the global pandemic. In this process in which the global pandemic state is alive, it is too important to make specific policies and plans to face the pandemic. Using COVID-19 verified data and making predictions with artificial intelligence techniques is an important issue as it allows deriving of future plans. In this study, Turkey's Health Ministry COVID-19 in the informational pages published using data, adaptive neuro-fuzzy inference system (ANFIS), and the artificial neural network (ANN) prediction models have been developed. These models were compared using different statistical evaluation criteria. As a result of the evaluation, the ANFIS model obtained the best model results with 0.0247 mean absolute error (MAE) value, 0.0012 mean square error (MSE) value, 0.0351 root mean square error (RMSE) value and 0.9847 regression coefficient R2. In addition, it was seen that the model created with ANFIS showed a better performance and predicted the number of deaths in the next five days with an accuracy rate of 96%.

Keywords:

COVID-19, pandemic, ANFIS, Artificial Neural Networks, forecast, Turkey, death count,

PDF

___

[1] Y. N. Mi, T. T. Huang, J. X. Zhang, Q. Qin, Y. X. Gong, S. Y. Liu, Y. X. Cao, “Estimating The İnstant Case Fatality Rate of COVID19 İn China”, International Journal of Infectious Diseases, 97, 1- 6, 2020.
[2] K. Senel, M. Özdinç, S. Ozturkcan, A, Akgul, “Instantaneous R for COVID-19 in Turkey: estimation by Bayesian statistical inference”, Turkiye Klinikleri Journal of Medical Sciences, 40(2), 127-131, 2020.
[3] B. Ergül, A. Altın Yavuz, E. Gündoğan Aşık, B. Kalay, “Dünya'da ve Türkiye’de nisan ayı itibariyle COVID-19 salgın verilerinin istatistiksel değerlendirilmesi”, Anadolu Kliniği Tıp Bilimleri Dergisi, 25(1), 130-141, 2020.
[4] Internet: T.C. Sağlık Bakanlığı, https://COVID19.saglik.gov.tr/, 3.01.2021.
[5] T. B. Alakus, I. Turkoglu, “Comparison of deep learning approaches to predict COVID-19 infection”. Chaos Solitons & Fractals, 140, 110120, 2020.
[6] Internet: Dünya Sağlık Örgütü, https://www.who.int/emergencies/diseases/novel-coronavirus2019/question-and-answers-hub/q-a-detail/coronavirus-diseaseCOVID-19,03.01.2021.
[7] N. S. Punn, S. K., Sonbhadra, S. Agarwal, “COVID-19 Epidemic Analysis Using Machine Learning And Deep Learning Algorithms”, MedRxiv, 2020.
[8] A. Zeroual, F. Harrou, A. Dairi, Y. Sun, “Deep learning methods for forecasting COVID-19 time-Series data: A Comparative study”. Chaos Solitons & Fractals, 140, 110121,2020.
[9] R. Zhang, X. Tie, Z. Qi, N. B. Bevins, C. Zhang, D. Griner, G. H. Chen, “Diagnosis of Coronavirus Disease 2019 Pneumonia by Using Chest Radiography Value of Artificial Intelligence”, Radiology, 298(2), E88–E97,2020.
[10] J. S. Suri, S. Agarwal, S. K. Gupta, A. Puvvula, M. Biswas, L. Saba, &, S. Naidu, “A Narrative Review on Characterization of Acute Respiratory Distress Syndrome in COVID-19-infected Lungs using Artificial Intelligence”, Computers in Biology and Medicine, 130, 2021.
[11] N. Lessmann, C. I. Sánchez, L. Beenen, L. H. Boulogne, M. Brink, E. Calli, ... &, B. Ginneken, “Automated Assessment of COVID19 Reporting and Data System and Chest CT Severity Scores in Patients Suspected of Having COVID-19 Using Artificial Intelligence”, Radiology, 298(1), E18-E28, 2021.
[12] K. Rangarajan, S. Muku, A. K. Garg, P. Gabra, S. H. Shankar, N. Nischal, ... & C. Arora, “Artificial Intelligence–assisted chest Xray assessment scheme for COVID-19”, European Radiology, 31(1), 1-10, 2021.
[13] S. Schalekamp, M. Huisman, R. A. van Dijk, M. F. Boomsma, P. J. Freire Jorge, W. S. de Boer, ... & C. M. Schaefer-Prokop, “Model-based prediction of critical illness in hospitalized patients with COVID-19”, Radiology, 298(1), E46-E54, 2021.
[14] A. Caillon, K. Zhao, K. O. Klein, C. Greenwood, Z. Lu, P. Paradis, & E. L. Schiffrin, “High systolic blood pressure at hospital admission is an important risk factor in models predicting outcome of COVID-19 patients”, American Journal of Hypertension,34(1), 1-29, 2021.
[15] X. Guan, B. Zhang, M. Fu, M. Li, X. Yuan, Y. Zhu, ... & Y. Lu, “Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study”, Annals of Medicine, 53(1), 257- 266, 2021.
[16] Z. He, Y. Chin, S. Yu, J. Huang, C. J. Zhang, K. Zhu, ... & W. K. Ming, “The Influence of Average Temperature and Relative Humidity on New Cases of COVID-19: Time-Series Analysis”, JMIR Public Health and Surveillance, 7(1), 1-14, 2021.
[17] H. T. Rauf, M. I. U. Lali, M. A. Khan, S. Kadry, H. Alolaiyan, A. Razaq, ... & R. Irfan, “Time series forecasting of COVID-19 transmission in Asia Pacific countries using deep neural networks”, Personal and Ubiquitous Computing, 25(1), 1-18, 2021.
[18] S. Ballı, “Data analysis of COVID-19 pandemic and short-term cumulative case forecasting using machine learning time series methods”, Chaos, Solitons & Fractals, 142(1), 1-7,2021.