ZAMANSAL EVRİŞİMLİ AĞLAR KULLANILARAK AVRUPA ÜLKELERİNDEKİ COVID-19 VAKALARININ ÇOK ADIMLI TAHMİNİ

Yeni tip Koronavirüs (COVID-19), ilk bildirimden bu günlere kadar dünya çapında milyonlarca insanı önemli ölçüde etkilemiştir. Virüsün hızla yayılması, birçok ülkede sağlık hizmetlerinin iş yükünü önemli ölçüde artırmıştır. Bu nedenle, sağlık sisteminin verimli kullanımına duyulan ihtiyaç, araştırmacıları virüsün yayılma eğilimini tahmin etmeye yönlendirmiştir. Bu amaçla, makine öğrenimi (ML) ve yapay zeka (AI) uygulamaları, koronavirüs salgınına karşı mücadele etmek için yoğun bir şekilde kullanılmıştır. Bu çalışmada, kümülatif doğrulanmış COVID-19 vakalarını modellemek ve zaman serisi verilerini kullanarak çeşitli Avrupa ülkelerinde yayılmasını tahmin etmek için Zamansal Evrişimli Ağları kullanılmıştır. Ayrıca Zamansal Evrişimli Ağların (TCN) performanslarını, hesaplama süresi, kök ortalama kare hatası (RMSE), normalleştirilmiş kök ortalama kare hatası (NRMSE), kök ortalama kare günlük hatası (RMSLE), ortalama mutlak yüzde hatası (MAPE) ve simetrik ortalama mutlak yüzde hatası (SMAPE) cinsinden literatürdeki diğer modeller olan Uzun-Kısa Süreli Bellek (LSTM) ve Kapılı Yinelemeli Birim (GRU) ile karşılaştırdık. Bu çalışmada kullandığımız Benzetim sonuçlarında, bu makalede kullandığımız Zamansal Evrişimli Ağların performansının COVID-19 vakalarının tahmininde diğer modellere göre daha iyi olduğu gösterilmiştir

MULTI-STEP FORECASTING OF COVID-19 CASES IN EUROPEAN COUNTRIES USING TEMPORAL CONVOLUTIONAL NETWORKS

The novel Coronavirus (COVID-19) has significantly affected millions of people around the world since the first notification until nowadays. The rapid spread of the virus has dramatically increased the workload of healthcare systems in many countries. Therefore, the need for efficient use of the healthcare system leads researchers to forecast the trend of virus spread. For this purpose, Machine Learning (ML) and Artificial Intelligence (AI) applications have intensively used to struggle against the coronavirus outbreak. In this study, Temporal Convolutional Network (TCN) is applied for modeling the cumulative confirmed COVID-19 cases and forecasting the spread of it in various European countries using time series data. It is also presented that numerical examples for comparing performances of TCN against Long-Short Term Memory (LSTM) and Gates Recurrent Units(GRU) in terms of computation time, root-mean-square error (RMSE), normalized root-mean-square error (NRMSE), root mean squared log error (RMSLE), mean absolute percentage error (MAPE), and symmetric mean absolute percentage error (SMAPE). Simulation results indicate that the Temporal Convolutional Networks used in this manuscript performs better than other models for forecasting the cumulative confirmed COVID-19 cases.

PDF

___

[1] Lu, H., Stratton, C. W. and Tang, Y.-W., "Outbreak of pneumonia of un-known etiology in wuhan china: the mystery and the miracle", Jour.Med. Virol. 92 (4), 401–402, 2020.
[2] Sohrabi, C., Alsafi, Z., O’Neill, N., Khan, M., Kerwan, A., Al-Jabir, A, Iosifidis C. and Agha, R., "World Health Organization Declares Global Emergency: A Review of The 2019 Novel Coronavirus (Covid-19)", Int. Jour. Surgery, 76, 71–76, 2020.
[3] World Health Organization, Archived: Who timeline -covid-19, Retrieved from: https://www.who.int/news/item/27-04-2020- who-timeline---covid-19(21/11/2020).
[4] Ribeiro, M. H. D. M., Silva, R. G., Mariani, V. C., Coelho, L. S., "Short-Term Forecasting Covid-19 Cumulative Confirmed Cases: Perspectives for Brazil", Chaos, Solit. and Frac., 135, 109853, 2020.
[5] Zeroual, A., Harrou, F., Dairi, A. and Sun, Y., "Deep Learning Methods Forforecasting Covid-19 TimeSeries Data: A Comparative Study", Chaos,Solit. and Frac., 140, 110121, 2020.
[6] Chimmula, V. K. R. and Zhang, L., "Time Series Forecasting of Covid-19 Transmission in Canada Using LSTM Networks", Chaos, Solit. and Frac., 135, 109864, 2020.
[7] F. Shahid, F., Zameer, A. and Muneeb, M., "Predictions For Covid-19 With Deep Learning Models of LSTM, GRU and Bi-LSTM", Chaos, Solit. and Frac., 140, 110212, 2020.
[8] Kırbaş, İ., Sözen, A, Tuncer, A. D. and Kazancıoğlu, F. S. "Comparative Analysis and Forecasting Of Covid19 Cases in Various European Countries with ARIMA, NARNN and LSTM Approaches", Chaos, Solit. and Frac., 138, 110015, 2020.
[9] Arora, P., Kumar, H. and Panigrahi, B., "Prediction and Analysis of Covid-19 Positive Cases Using Deep Learning Models: A Descriptive Case Study of India", Chaos, Solit. and Frac., 139, 110017, 2020.
[10] Sarkar, K., Khajanchi, S. and Nieto, J., "Modeling and Forecasting the Covid-19 Pandemic in India", Chaos, Solit. and Frac., 139, 110049, 2020.
[11] Yang, Q., Yi, C., Vajdi, A., Cohnstaedt, L. W., Wu, H., Guo, X. and Scoglio, C. M., "Short-Term Forecasts and Long-Term Mitigation Evaluations for the Covid-19 Epidemic in Hubei Province, China", Infectious Disease Modelling, 5, 563–574, 2020.
[12] Wang, P., Zheng, X., Li, J. and Zhu, B.,"Prediction of Epidemic Trends in Covid-19 with Logistic Model and Machine Learning Technics", Chaos,Solit. and Frac., 139, 110058, 2020.
[13] Salgotra, R., Gandomi, M. and Gandomi, A., "Time Series Analysis and Forecast of the Covid-19 Pandemic in India Using Genetic Programming", Chaos, Solit. and Frac. 138, 109945, 2020.
[14] Rustam, F., Reshi, A. A., Mehmood, A., Ullah, S., On, B.-W., Aslam, W. and Choi, A. G. S.,"Covid-19 Future Forecasting Using Supervised Machine Learning Models", IEEE Access, 8, 101489 – 101499, 2020.
[15] Cao, L., Liu, H., Li, J., Yin, X., Duan, Y. and Wang, J., "Relationship of Meteorological Factors and Human Brucellosis in Hebei Province, China", Sci. Total Envir., 703, 135491, (2020).
[16] He, Z. and Tao, H., "Epidemiology and Arima Model Of Positive-Rate of Influenza Viruses Among Children in Wuhan, China: A Nine-Year Retrospective Study", Int. Jour. Infect. Dis., 74, 61– 70, 2018.
[17] Ceylan, Z., "Estimation of Covid-19 Prevalence in Italy, Spain, and France", Sci. Total Environ. 729(4), 1–7, 2020.
[18] Tomar, A. and Gupta, A., "Prediction for the Spread of Covid-19 in India and Effectiveness of Preventive Measures", Sci. Total Envir., 728, 138762, (2020).
[19] Wan, R., Mei, S., Wang, J., Liu, M. and Yang, F., "Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting", electronics, 8(8):876, 1– 18, 2019.
[20] Gan, Z., Li, C., Zhou, J. and Tang, G., "Temporal Convolutional Networks Interval Prediction Model for Wind Speed Forecasting", Electric Power Sys. Res., 191, 106865, 2021.
[21] Lara-Benítez, P., Carranza-García, M., Luna-Romera, J. M. and Riquelme, J. C., "Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting", applied sciences, 10, 1–17, 2020.
[22] Pelletier, C., Webb, G. I. and Petitjean, F., "Temporal Convolutional Neuralnetwork for the Classification of Satellite Image Time Series", remotesensing, 11(5):523, 1–22, 2019.
[23] Guo, G. and Yuan, W., "Short-Term Traffic Speed Forecasting Based on Graph Attention Temporal Convolutional Networks", Neurocomputing, 410, 387–393, 2020.
[24] Li, S., Farha, Y. A., Liu, Y., Cheng, M.-M. and Gall, J.,"MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation", IEEE Trans. Patt. Anal. Mach. Intel., Early Access, 1–13, 2020.
[25] Kok, C., Jahmunah, V., Oh, S. L., Zhou, X., Gururajan, R., Tao, X., Cheong, K. H., Gururajan, R., Molinari, F. and Acharya, U. R., "Automated Prediction of Sepsis Using Temporal Convolutional Network", Comp. Bio. Med., 1–10, 2020.
[26] Yan, J., Mu, L., Wang, L., Ranjan, R. and Zomaya, A. Y., "Temporal Convolutional Networks For The Advance Prediction Of ENSO", Scientific Reports (Nature Publisher Group), 10, 1–15, 2020.
[27] Hochreiter, S. and Schmidhuber, J., "Long ShortTerm Memory", Neural Computation, 9(8), 1735– 1780, 1997.
[28] Gers, F. A., Schmidhuber, J., Cummins, F., "Learning to Forget: Continual Prediction with LSTM", Neural Computation, 12(10), 2451–2471, 2000.
[29] Chung, J., Gulcehre, C., Cho, K., Bengio, Y., "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling", arXiv preprint, arXiv:1412.3555, 1–9, 2014.
[30] Cho, K., Van Merriënboer, B., Bahdanau, D. and Bengio, Y., "On the Properties of Neural Machine Translation: Encoder-Decoder Approaches", arXiv preprint, arXiv:1409.1259, 2014.
[31] Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A. and Kavukcuoglu, K., "Wavenet: A Generative Model for Raw Audio", arXiv preprint, arXiv:1609.03499, 1–15, 2016.
[32] Hewage, P., Behera, A., Trovati, M., Pereira, E., Ghahremani, M., Palmieri, F. and Liu, Y., "Temporal Convolutional Neural (TCN) Network for an Effective Weather Forecasting Using Time-Series Data from the Local Weather Station", Methodologies and Application, 24, 16453–16482, 2020.
[33] Zhen, X., Chakraborty, R., Vogt, N., Bendlin, B. B. and Singh, V., "Dilated Convolutional Neural Networks For Sequential Manifold-valued Data", Proceedings of the IEEE/CVF International Conference on Computer Vision, 10621–10631, 2019.
[34] European Centre for Disease Prevention and Control, Geographic Distribution of Covid-19 Cases, Retrieved from: https://www.ecdc.europa.eu/en/publicationsdata/download-todays-data-geographicdistribution-covid-19-cases-worldwide 08/12/2020.
[35] Kingma, D. P. and Ba, J. L., "Adam: A Method For Stochastic Optimization", arXiv preprint, arXiv:1412.6980, 2014.

Mugla Journal of Science and Technology-Cover

ISSN: 2149-3596
Yayın Aralığı: Yılda 2 Sayı
Başlangıç: 2015
Yayıncı: Muğla Sıtkı Koçman Üniversitesi Fen Bilimleri Enstitüsü

Arşiv