COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case
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...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/2/195 |
| _version_ | 1797492292906385408 |
|---|---|
| author | Matvey Pavlyutin Marina Samoyavcheva Rasul Kochkarov Ekaterina Pleshakova Sergey Korchagin Timur Gataullin Petr Nikitin Mohiniso Hidirova |
| author_facet | Matvey Pavlyutin Marina Samoyavcheva Rasul Kochkarov Ekaterina Pleshakova Sergey Korchagin Timur Gataullin Petr Nikitin Mohiniso Hidirova |
| author_sort | Matvey Pavlyutin |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T01:01:32Z |
| format | Article |
| id | doaj.art-67fb130764624ffc9990c1acfb6b0e02 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T01:01:32Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-67fb130764624ffc9990c1acfb6b0e022023-11-23T14:33:47ZengMDPI AGMathematics2227-73902022-01-0110219510.3390/math10020195COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow CaseMatvey Pavlyutin0Marina Samoyavcheva1Rasul Kochkarov2Ekaterina Pleshakova3Sergey Korchagin4Timur Gataullin5Petr Nikitin6Mohiniso Hidirova7Department of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 109456 Moscow, RussiaDepartment of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 109456 Moscow, RussiaDepartment of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 109456 Moscow, RussiaDepartment of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 109456 Moscow, RussiaDepartment of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 109456 Moscow, RussiaDepartment of Mathematical Methods in Economics and Management, State University of Management, 109542 Moscow, RussiaDepartment of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 109456 Moscow, RussiaResearch Institute for Development of Digital Technologies and Artificial Intelligence, Tashkent 100094, UzbekistanTo 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.https://www.mdpi.com/2227-7390/10/2/195COVID-19epidemic spreadingforecastingmathematical methodsmachine learning |
| spellingShingle | Matvey Pavlyutin Marina Samoyavcheva Rasul Kochkarov Ekaterina Pleshakova Sergey Korchagin Timur Gataullin Petr Nikitin Mohiniso Hidirova COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case Mathematics COVID-19 epidemic spreading forecasting mathematical methods machine learning |
| title | COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case |
| title_full | COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case |
| title_fullStr | COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case |
| title_full_unstemmed | COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case |
| title_short | COVID-19 Spread Forecasting, Mathematical Methods vs. Machine Learning, Moscow Case |
| title_sort | covid 19 spread forecasting mathematical methods vs machine learning moscow case |
| topic | COVID-19 epidemic spreading forecasting mathematical methods machine learning |
| url | https://www.mdpi.com/2227-7390/10/2/195 |
| work_keys_str_mv | AT matveypavlyutin covid19spreadforecastingmathematicalmethodsvsmachinelearningmoscowcase AT marinasamoyavcheva covid19spreadforecastingmathematicalmethodsvsmachinelearningmoscowcase AT rasulkochkarov covid19spreadforecastingmathematicalmethodsvsmachinelearningmoscowcase AT ekaterinapleshakova covid19spreadforecastingmathematicalmethodsvsmachinelearningmoscowcase AT sergeykorchagin covid19spreadforecastingmathematicalmethodsvsmachinelearningmoscowcase AT timurgataullin covid19spreadforecastingmathematicalmethodsvsmachinelearningmoscowcase AT petrnikitin covid19spreadforecastingmathematicalmethodsvsmachinelearningmoscowcase AT mohinisohidirova covid19spreadforecastingmathematicalmethodsvsmachinelearningmoscowcase |