COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case

被引：13

作者：

Pavlyutin, Matvey ^{[1
]}

Samoyavcheva, Marina ^{[1
]}

Kochkarov, Rasul ^{[1
]}

Pleshakova, Ekaterina ^{[1
]}

Korchagin, Sergey ^{[1
]}

Gataullin, Timur ^{[2
]}

Nikitin, Petr ^{[1
]}

Hidirova, Mohiniso ^{[3
]}

机构：

[1] Financial Univ Govt Russian Federat, Dept Data Anal & Machine Learning, Moscow 109456, Russia

[2] State Univ Management, Dept Math Methods Econ & Management, Moscow 109542, Russia

[3] Res Inst Dev Digital Technol & Artificial Intelli, Tashkent 100094, Uzbekistan

来源：

MATHEMATICS | 2022年 / 10卷 / 02期

关键词：

COVID-19; epidemic spreading; forecasting; mathematical methods; machine learning; MODEL;

D O I：

10.3390/math10020195

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

To predict the spread of the new coronavirus infection COVID-19, the critical values of spread indicators have been determined for deciding on the introduction of restrictive measures using the city of Moscow as an example. A model was developed using classical methods of mathematical modeling based on exponential regression, the accuracy of the forecast was estimated, and the shortcomings of mathematical methods for predicting the spread of infection for more than two weeks. As a solution to the problem of the accuracy of long-term forecasts for more than two weeks, two models based on machine learning methods are proposed: a recurrent neural network with two layers of long short-term memory (LSTM) blocks and a 1-D convolutional neural network with a description of the choice of an optimization algorithm. The forecast accuracy of ML models was evaluated in comparison with the exponential regression model and one another using the example of data on the number of COVID-19 cases in the city of Moscow.

引用

页数：19

共 35 条

[1]

Abramov S.M., 2020, MODELING FORECAST CO

[2]

Agrawal M., 2021, ARXIV210109158

[3] Empirical Evaluation of Alternative Time-Series Models for COVID-19 Forecasting in Saudi Arabia [J].