Research output: Contribution to journal › Conference article › peer-review
Deep learning approaches to mid-term forecasting of social-economic and demographic effects of a pandemic. / Devyatkin, Dmitry; Otmakhova, Yulia; Usenko, Natalia et al.
In: Procedia Computer Science, Vol. 190, 07.2021, p. 156-163.Research output: Contribution to journal › Conference article › peer-review
}
TY - JOUR
T1 - Deep learning approaches to mid-term forecasting of social-economic and demographic effects of a pandemic
AU - Devyatkin, Dmitry
AU - Otmakhova, Yulia
AU - Usenko, Natalia
AU - Sochenkov, Ilya
AU - Budzko, Vladimir
N1 - Publisher Copyright: © 2020 Elsevier B.V.. All rights reserved.
PY - 2021/7
Y1 - 2021/7
N2 - The COVID-19 outburst has brought serious demographical, economic, and social impacts. Moreover, in large countries, these consequences can vary from region to region. Therefore, authorities and experts lack the models to predict these various impacts at the regional level. This paper presents deep neural network models to do a mid-term forecast of the COVID-19 effect in the Russian regions. The models are based on the various recurrent and sliding-window architectures and utilize the attention mechanism to consider the indicators of the neighbor regions. These models are trained on various data, including daily cases and deaths, the diseased age structure, transport availability of the regions, and the unemployment rate. The experimental evaluation of the models shows that the demographic and healthcare indicators can significantly improve mid-term economic impact prediction accuracy. We also revealed that the neighboring regions' data helps predict the pandemic's healthcare and demographical impact. Namely, we have detected improvement for both the number of infected and the death rate.
AB - The COVID-19 outburst has brought serious demographical, economic, and social impacts. Moreover, in large countries, these consequences can vary from region to region. Therefore, authorities and experts lack the models to predict these various impacts at the regional level. This paper presents deep neural network models to do a mid-term forecast of the COVID-19 effect in the Russian regions. The models are based on the various recurrent and sliding-window architectures and utilize the attention mechanism to consider the indicators of the neighbor regions. These models are trained on various data, including daily cases and deaths, the diseased age structure, transport availability of the regions, and the unemployment rate. The experimental evaluation of the models shows that the demographic and healthcare indicators can significantly improve mid-term economic impact prediction accuracy. We also revealed that the neighboring regions' data helps predict the pandemic's healthcare and demographical impact. Namely, we have detected improvement for both the number of infected and the death rate.
KW - attention mechanism
KW - COVID-19 pandemic
KW - Long-Short Term Memory
KW - mid-term impact prediction
KW - recurrent neural network
KW - socio-economic impact
UR - http://www.scopus.com/inward/record.url?scp=85112594547&partnerID=8YFLogxK
U2 - 10.1016/j.procs.2021.06.020
DO - 10.1016/j.procs.2021.06.020
M3 - Conference article
AN - SCOPUS:85112594547
VL - 190
SP - 156
EP - 163
JO - Procedia Computer Science
JF - Procedia Computer Science
SN - 1877-0509
T2 - 2020 Annual International Conference on Brain-Inspired Cognitive Architectures for Artificial Intelligence: Eleventh Annual Meeting of the BICA Society, BICA*AI 2020
Y2 - 10 November 2020 through 15 November 2020
ER -
ID: 34163055