Methods of intellectual data analysis in COVID -19 research

O. V. Sen'ko ; A. V. Kuznetsova ; E. M. Voronin ; O. A. Kravtsova ; L. R. Borisova ; I. L. Kirilyuk ; V. G. Akimkin

Journal of the Belarusian State University. Mathematics and Informatics, Tome 1 (2022), pp. 83-96.

Résumé

The paper presents an original method for solving the problem of finding a connection between the course of the epidemic and socio-economic, demographic and climatic factors. The method was applied to solve this problem for 110 countries of the world using a set of corresponding curves of the COVID-19 growth rate for the period from January 2020 to August 2021. Hierarchical agglomerative clustering was applied. Four large clusters with uniform curves were identified – 11, 39, 17 and 13 countries, respectively. Another 30 countries were not included in any cluster. Using machine learning methods, we identified the differences in socio-economic, demographic and geographical and climatic indicators in the selected clusters of countries of the world. The most important indicators by which the clusters differ from each other are amplitude of temperatures throughout the year, high-tech exports, Gini coefficient, size of the urban population and the general population, index of net barter terms of trade, population growth, average January temperature, territory (land area), number of deaths due to natural disasters, birth rate, coastline length, oil reserves, population in urban agglomerations with a population of more than 1 million etc. This approach (the use of clustering in combination with classification by methods of logical-statistical analysis) has not been used by anyone before. The found patterns will make it possible to more accurately predict the epidemiological process in countries belonging to different clusters. Supplementing this approach with autoregressive models will automate the forecast and improve its accuracy.

Détail

Keywords: cluster analysis; machine learning methods; statistics; epidemiological process; COVID-19.

Bibliographie

[1] A. A. Romanyukha, T. E. Sannikova, I. D. Drynov, “Emergence of epidemics of acute respiratory diseases”, Vestnik Rossiiskoi akademii nauk, 81:2 (2011), 122–126

[2] L. R. Borisova, M. N. Fridman, “Some aspects of the impact of the coronavirus pandemic on the economy”, Samoupravlenie, 5 (2021), 147–152

[3] P. Sengupta, B. Ganguli, S. SenRoy, A. Chatterjee, “An analysis of COVID-19 clusters in India”, BMC Public Health, 21 (2021), 631 | DOI

[4] V. Zarikas, S. G. Poulopoulos, Z. Gareiou, E. Zervas, “Clustering analysis of countries using the COVID-19 cases dataset”, Data in Brief, 31 (2020), 105787 | DOI

[5] Liu. Mengyang, Liu. Mengmeng, L. i. Zhiwei, Zhu. Yingxuan, Liu. Yue, Wang. Xiaonan, “The spatial clustering analysis of COVID-19 and its associated factors in mainland China at the prefecture level”, Science of the Total Environment, 777 (2021), 145–992 | DOI

[6] R. A. Rios, T. Nogueira, D. B. Coimbra, TJS. Lopes, A. Abraham, Mello. de, “Country transition index based on hierarchical clustering to predict next COVID-19 waves”, Scientific Reports, 11:1 (2021), 15271 | DOI

[7] S. A. Rizvi, M. Umair, M. A. Cheema, “Clustering of countries for COVID-19 cases based on disease prevalence, health systems and environmental indicators”, Chaos, Solitons and Fractals, 151 (2021), 111240 | DOI

[8] J. Brzyska, I. Szamrej-Baran, “Classification of the EU countries according to the vulnerability of their economies to the impact of COVID-19 pandemic”, European Research Studies Journal, XXIV:2B (2021), 967–978 | DOI

[9] A. V. Kuznetsova, I. V. Kostomarova, O. V. Senko, “Modification of the method of optimal valid partitioning for comparison of patterns related to the occurrence of ischemic stroke in two groups of patients”, Pattern Recognition and Image Analysis. Advances in Mathematical Theory and Applications, 24:1 (2014), 114–123 | DOI

[10] O. V. Senko, D. S. Dzyba, E. A. Pigarova, LYa. Rozhinskaya, A. V. Kuznetsova, “Amethod for evaluating validity of piecewise-linear models”, Proceedings of the 6th International Conference on Knowledge Discovery and Information Retrieval (Rome, Italy), Science and Technology Publications, 2014, 37–442 | DOI

[11] O. V. Senko, A. V. Kuznetsova, “A recognition method based on collective decision making using systems of regularities of various types”, Pattern Recognition and Image Analysis. Advances in Mathematical Theory and Applications, 20:2 (2010), 152–162 | DOI

[12] I. L. Kirilyuk, A. I. Volynsky, M. S. Kruglova, A. V. Kuznetsova, A. A. Rubinstein, O. V. Senko, “Empirical testing of institutional matrices theory by data mining”, Computer Research and Modeling, 7:4 (2015), 923–939 | DOI

[13] L. R. Borisova, “Study of the dynamics of the incidence of coronavirus infection in Moscow”, Sovremennye problemy fizikomatematicheskikh nauk, Materialy VII Vserossiiskoi nauchno-prakticheskoi konferentsii s mezhdunarodnym uchastiem (Orel, Rossiya), Orel State University named after Turgenev IS, Orel, 2021, 217–220

[14] VYu. Smirnov, A. V. Kuznetsova, “Approximation of experimental data by solving linear difference equations with constant coefficients (in particular, by exponentials and exponential cosines)”, Pattern Recognition and Image Analysis. Advances in Mathematical Theory and Applications, 27:2 (2017), 175–183 | DOI