Modeling of the COVID-19 epidemic in the Russian regions based on deep learning Full article
| Conference |
5th International Conference on Problems of Cybernetics and Informatics 28-30 Aug 2023 , Баку |
||||
|---|---|---|---|---|---|
| Source | 2023 5th International Conference on Problems of Cybernetics and Informatics (PCI) Compilation, IEEE. 2023. ISBN 979-8-3503-1907-1. |
||||
| Output data | Year: 2023, Pages: 1-5 Pages count : 5 DOI: 10.1109/PCI60110.2023.10325993 | ||||
| Tags | data processing, deep learning, epidemic, LSTM, machine learning, short-term forecasting | ||||
| Authors |
|
||||
| Affiliations |
|
Funding (1)
| 1 | Министерство науки и высшего образования РФ | 075-00337-20-03 |
Abstract:
The neural network of COVID-19 5 days forecasting in Russian Federation region based on epidemic and social data from 2020 to 2023 is constructed and analyzed. The structure of neural network consists in recurrent and full-connected layers. In addition to training the neural network, its hyperparameters were optimized, such as the optimal number of neurons in each layer, regularization parameters, and optimizer parameters. It is shown that the mean squared error on the test period from 07.2022 to 05.2023 is approximately 5% for new diagnosed of COVID-19 and hospitalized ones in Moscow, Saint Petersburg and Novosibirsk region. The proposed approach makes it possible to refine mathematical models in epidemiology.
Cite:
Krivorotko O.
, Zyatkov N.
Modeling of the COVID-19 epidemic in the Russian regions based on deep learning
In compilation 2023 5th International Conference on Problems of Cybernetics and Informatics (PCI). – IEEE., 2023. – C.1-5. – ISBN 979-8-3503-1907-1. DOI: 10.1109/PCI60110.2023.10325993 Scopus OpenAlex
Modeling of the COVID-19 epidemic in the Russian regions based on deep learning
In compilation 2023 5th International Conference on Problems of Cybernetics and Informatics (PCI). – IEEE., 2023. – C.1-5. – ISBN 979-8-3503-1907-1. DOI: 10.1109/PCI60110.2023.10325993 Scopus OpenAlex
Dates:
| Published online: | Nov 27, 2023 |
Identifiers:
| Scopus: | 2-s2.0-85179893871 |
| OpenAlex: | W4389041248 |