RESNET MODEL FOR THE FORECASTING THE EXPANSION OF COVID-19 IN UKRAINE
DOI:
https://doi.org/10.31649/1999-9941-2022-53-1-64-68Keywords:
predicting, time series, residual neural network, Covid-19, comparative analysisAbstract
The article considers the ResNet residual neural network model and its application to the problem of predicting the spread of COVID-19 in Ukraine. The study was implemented programmatically in Python. To train the model, time series of morbidity and vaccination rates were used. The result of the model was investigated for accuracy and speed. A comparative analysis of the results showed the performance of the ResNet model relative to another model of convolutional neural networks InceptionTime, but the accuracy of ResNet is lower.
References
Y. Andrusenko «Analiz osnovnykh modelei prohnozuvannia chasovykh riadiv», Zbirnyk naukovykh prats Kharkivskoho natsionalnoho universytetu Povitrianykh Syl, № 3(65), s. 91–96, 2020 [in Ukrainian].
Thomas Fischer and Christopher Krauss, «Deep learn- ing with long short-term memory networks for financial market predictions», European Journal of Operational Research, vol. 270, no. 2, pp. 654–669, 2018.
M. Shabani and A. Iosifidis, «Low-rank temporal attention-augmented bilinear network for financial time- series forecasting», in 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 2156–2161, 2020.
Z. Pala and R. Atici, «Forecasting sunspot time series using deep learning methods», Solar Physics, 294(5), 2019. doi: 10.1007/s11207-019-1434-6.
S, Ravuri, K, Lenc, M, Willson, «Skilful precipitation nowcasting using deep generative models of radar», Nature, 597, pp. 672–677, 2021. doi: 10.1038/s41586-021-03854-z.
X. Yi, J. Zhang, Z. Wang, T. Li, and Y. Zheng, «Deep distributed fusion network for air quality predic-tion», in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, pp. 965–973, 2018.
ZifengWang, RuiWen, XiChen, ShileiCao, Shao-LunHuang, Buyue Qian, and Yefeng Zheng, «Online Disease Diagnosis with Inductive Heterogeneous Graph Convolutional Networks», in Proceedings of the Web Conference 2021, pp.3349– 3358, 2021.
George Panagopoulos, Giannis Nikolentzos, and Michalis Vazirgiannis, «Transfer Graph Neural Net-works for Pandemic Forecasting», in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp.4838–4845, 2021.
Ardabili SF, Mosavi A, Ghamisi P, Ferdinand F, Varkonyi-Koczy AR, Reuter U, et al. «Covid-19 out-break prediction with machine learning», Algorithms, 13(10), pp. 249-256, 2020.
D. E. Sytnikov, Y. O. Andrusenko, «Zastosuvannia modeli na osnovi zghortkovykh neironnykh merezh dlia zadachi prohnozuvannia poshyrennia COVID-19 v Ukraini», Vseukrainskyi mizhvidomchyi nau-kovo-tekhnichnyi zbirnyk «Avtomatyzovani systemy upravlinnia ta prylady avtomatyky», № 177 s. 43–47, 2021 [in Ukrainian].
He Kaiming, Zhang Xiangyu, Ren Shaoqing, Sun Jian, «Deep Residual Learning for Image Recogni-tion», 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE. pp. 770–778, 2016. doi:10.1109/CVPR.2016.90.
Hyndman, Rob J., and Anne B. Koehler, «Another look at measures of forecast accuracy», Interna-tional Journal of Forecasting, 22(4), pp. 679−688, 2006. doi:10.1016/j.ijforecast.2006.03.001.
Downloads
-
PDF (Українська)
Downloads: 130
