[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126839-en":3,"doc-seo-126839-105":29,"detail-sidebar-cat-0-en-105":89},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":11},126839,1099523882367,"Hazel","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Multi-country analysis of the COVID-19 pandemic typology using machine learning and neural network algorithms - paper results for 30 European countries (2020-2022)","The paper delivers multi-country results on the intensity typology of the COVID-19 pandemic across 30 European-region countries using regularly updated public panel data covering 2020–2022. Countries are grouped into three classes with cluster analysis in the feature space, reflecting differing epidemic-process intensities. From the derived country ratings, an integral statistical indicator of pandemic intensity is formed. Discriminant machine-learning and neural-network algorithms then estimate the current class and forecast the expected epidemic state when new data arrive.","Multi-country analysis of the COVID-19 pandemic typology using machine learning and neural network algorithms  \nVladimir Malugin Belarusian State University, Minsk, Belarus,  \n[malugin@bsu.by](malugin@bsu.by)  \n, Akim Sergeev Belarusian State University, Minsk, Belarus,  \n[akvise@gmail.com](akvise@gmail.com)  \nAleksandr Solomevich Belarusian State University, Minsk, Belarus,  \nalexandr.solomevich@gmail.c  \nAbstract – The paper presents the results of a multi-country analysis of the intensity typology of the COVID-19 pandemic in 30 countries of the European region based on publicly available and regularly updated panel data for the entire period 2020-2022 of high pandemic activity. In the generated space of classification features, using cluster analysis algorithms, all countries are divided into three classes, which differ in the intensity of the epidemic process. Based on the obtained country ratings, an integral statistical indicator of the COVID-19 pandemic is constructed. A set of discriminant analysis machine learning and neural network algorithms are used to estimate current as well predict the expected class of the epidemic state based on the newly acquiring data.  \nKeywords — COVID-19 typology, multi-country analysis, country ratings, integral pandemic indicator, machine learning, neural network.  \nI. INTRODUCTION  \nThe problem of analyzing the COVID-19 pandemic in various aspects is given considerable attention in the world scientific literature [1] . An important direction in the ongoing research is the development of methods for statistical analysis of the COVID-19 pandemic based on the data available in the mode of regular updating. Both simulation [2] and statistical models [3] are used to analysis and shortterm predict the epidemic process at the level of individual countries. Considerable attention is paid to the tasks of analyzing the COVID-19 pandemic in a multi-country aspect [1, 4] .  \nPreviously, in [5] the following main problems were solved: development of statistical methods for classifying countries by the intensity of the COVID-19 pandemic based on the available unclassified data, starting from the first wave; construction of statistical indicators characterizing the intensity of the pandemic at the country and multi-country levels. The purpose of this study is to assess the current class of the epidemic state on the base of real-time updating data. Various machine learning and neural network algorithms estimated on the training sample are used and compared for classification accuracy.  \nII. MULTI-COUNTRY ANALYSIS OF THE COVID-19  \nTYPOLOGY USING UNCLASSIFIED SAMPLE  \nA. Problem statement  \nIt is assumed that the available panel data include the values of N indicators of epidemic process obtained for some sample of countries of volume n at time moments  \nt (t = 1,..., T):  \nxi t, = (xi1, t , ..., xiN ,t )􀁣 􀂏 RN (i = 1,..., n, t = 1,..., T) .  \nIn the context of the COVID-19 analysis, panel data have a heterogeneous cluster structure. It is supposed that the most important factor of heterogeneity is the difference between countries by a latent feature, which characterizes the intensity of the COVID-19 epidemic process. According to this property, countries can be assigned to one of the L classes. This property is expressed by a discrete random variable dit 􀂏{1,..., L}, indicating the class number for country i at time t. Class numbers {dit } are interpreted as country ratings ofthe intensity of the epidemic process.  \nThe problem of statistical classification: to divide the sample {xi , t }, heterogeneous in terms of latent feature, into L homogeneous subsamples (classes) that differ in the space of classification features by the degree of intensity of the epidemiological process. The solution to this problem is the classification matrix  \nD = {di ,t }(i = 1,..., n, t = 1,..., T).  \nB. Initial data  \nWe use the daily data for 30 countries of the European region (Armenia, Austria, Azerbaijan, Belarus, Bu","cbCaik2Qu3H5ADud","https://ap.wps.com/l/cbCaik2Qu3H5ADud","pdf",208310,1,3,"English","en",105,"# Introduction\n# Multi-country analysis of the COVID-19 typology using unclassified sample\n## Problem statement\n## Initial data\n## Classification features\n## Used approach and algorithms","[{\"question\":\"How are countries classified in the proposed COVID-19 typology analysis?\",\"answer\":\"The method uses panel data features and applies clustering to divide 30 countries into three classes that differ by epidemic intensity, interpreted as country ratings over time.\"},{\"question\":\"Which indicators and features are used as inputs for classification?\",\"answer\":\"Inputs include total infections, active cases, recovered cases, and deaths, from which ratios such as Closed to Total and Closed to Active, daily infection growth, and Death Rate are derived as classification features.\"},{\"question\":\"How do machine learning and neural networks support estimation and prediction?\",\"answer\":\"Discriminant analysis models based on SVM and neural network algorithms are trained on the available sample to estimate the current epidemic class and forecast the expected class when newly acquired data are provided.\"}]","Multi-country analysis of the COVID-19 pandemic typology using machine learning and neural network algorithms - paper results for 30 European countries (2020-2022) | PDF",1785935163,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":28},"multi-country-analysis-of-the-covid-19-pandemic-typology-using-machine-learning-and-neural-network-algorithms-paper-results-for-30-european-countries-2020-2022","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":21},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/multi-country-analysis-of-the-covid-19-pandemic-typology-using-machine-learning-and-neural-network-algorithms-paper-results-for-30-european-countries-2020-2022/126839/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"How are countries classified in the proposed COVID-19 typology analysis?","Question",{"text":73,"@type":74},"The method uses panel data features and applies clustering to divide 30 countries into three classes that differ by epidemic intensity, interpreted as country ratings over time.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"Which indicators and features are used as inputs for classification?",{"text":78,"@type":74},"Inputs include total infections, active cases, recovered cases, and deaths, from which ratios such as Closed to Total and Closed to Active, daily infection growth, and Death Rate are derived as classification features.",{"name":80,"@type":71,"acceptedAnswer":81},"How do machine learning and neural networks support estimation and prediction?",{"text":82,"@type":74},"Discriminant analysis models based on SVM and neural network algorithms are trained on the available sample to estimate the current epidemic class and forecast the expected class when newly acquired data are provided.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]