{"id":"https://openalex.org/W4378471254","doi":"https://doi.org/10.1515/comp-2022-0273","title":"Machine learning-based processing of unbalanced data sets for computer algorithms","display_name":"Machine learning-based processing of unbalanced data sets for computer algorithms","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4378471254","doi":"https://doi.org/10.1515/comp-2022-0273"},"language":"en","primary_location":{"id":"doi:10.1515/comp-2022-0273","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2022-0273","pdf_url":"https://www.degruyter.com/document/doi/10.1515/comp-2022-0273/pdf","source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.degruyter.com/document/doi/10.1515/comp-2022-0273/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084396322","display_name":"Qingwei Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110849","display_name":"Sichuan Tourism University","ror":"https://ror.org/018rwb805","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110849"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingwei Zhou","raw_affiliation_strings":["School of Information and Engineering, Sichuan Tourism University , Chengdu 610000, Sichuan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, Sichuan Tourism University , Chengdu 610000, Sichuan , China","institution_ids":["https://openalex.org/I4210110849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029658447","display_name":"Yongjun Qi","orcid":"https://orcid.org/0000-0001-8903-4474"},"institutions":[{"id":"https://openalex.org/I144917393","display_name":"Mongolian University of Science and Technology","ror":"https://ror.org/02shmve39","country_code":"MN","type":"education","lineage":["https://openalex.org/I144917393"]},{"id":"https://openalex.org/I4210164009","display_name":"Guangdong Baiyun University","ror":"https://ror.org/04wmrj902","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164009"]}],"countries":["CN","MN"],"is_corresponding":true,"raw_author_name":"Yongjun Qi","raw_affiliation_strings":["Faculty of Megadata and Computing, Guangdong Baiyun University , Guangzhou 510450 Guangdong , China","School of Information and Communication Technology, Mongolian University of Science and Technology, Bayanzurkh District , 13341 , Ulaanbaatar , Mongolia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Megadata and Computing, Guangdong Baiyun University , Guangzhou 510450 Guangdong , China","institution_ids":["https://openalex.org/I4210164009"]},{"raw_affiliation_string":"School of Information and Communication Technology, Mongolian University of Science and Technology, Bayanzurkh District , 13341 , Ulaanbaatar , Mongolia","institution_ids":["https://openalex.org/I144917393"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070055825","display_name":"Hailin Tang","orcid":"https://orcid.org/0000-0002-2123-4450"},"institutions":[{"id":"https://openalex.org/I144917393","display_name":"Mongolian University of Science and Technology","ror":"https://ror.org/02shmve39","country_code":"MN","type":"education","lineage":["https://openalex.org/I144917393"]},{"id":"https://openalex.org/I4210164009","display_name":"Guangdong Baiyun University","ror":"https://ror.org/04wmrj902","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164009"]}],"countries":["CN","MN"],"is_corresponding":false,"raw_author_name":"Hailin Tang","raw_affiliation_strings":["Faculty of Megadata and Computing, Guangdong Baiyun University , Guangzhou 510450 Guangdong , China","School of Information and Communication Technology, Mongolian University of Science and Technology, Bayanzurkh District , 13341 , Ulaanbaatar , Mongolia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Megadata and Computing, Guangdong Baiyun University , Guangzhou 510450 Guangdong , China","institution_ids":["https://openalex.org/I4210164009"]},{"raw_affiliation_string":"School of Information and Communication Technology, Mongolian University of Science and Technology, Bayanzurkh District , 13341 , Ulaanbaatar , Mongolia","institution_ids":["https://openalex.org/I144917393"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109088889","display_name":"Peng Wu","orcid":"https://orcid.org/0000-0001-7455-926X"},"institutions":[{"id":"https://openalex.org/I4210110849","display_name":"Sichuan Tourism University","ror":"https://ror.org/018rwb805","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110849"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wu","raw_affiliation_strings":["School of Information and Engineering, Sichuan Tourism University , Chengdu 610000, Sichuan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, Sichuan Tourism University , Chengdu 610000, Sichuan , China","institution_ids":["https://openalex.org/I4210110849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029658447"],"corresponding_institution_ids":["https://openalex.org/I144917393","https://openalex.org/I4210164009"],"apc_list":{"value":1000,"currency":"EUR","value_usd":1078},"apc_paid":{"value":1000,"currency":"EUR","value_usd":1078},"fwci":3.9129,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93715726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"13","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14139","display_name":"E-commerce and Technology Innovations","score":0.9416000247001648,"subfield":{"id":"https://openalex.org/subfields/1403","display_name":"Business and International Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14139","display_name":"E-commerce and Technology Innovations","score":0.9416000247001648,"subfield":{"id":"https://openalex.org/subfields/1403","display_name":"Business and International Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14413","display_name":"Advanced Technologies in Various Fields","score":0.9207000136375427,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13693","display_name":"Smart Systems and Machine Learning","score":0.9054999947547913,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7585113048553467},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.7337010502815247},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.6449803709983826},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.6444705128669739},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.615447461605072},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5992817878723145},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5975480079650879},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5921401977539062},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5509825348854065},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5439193248748779},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5205870270729065},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.507923424243927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4702759385108948},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.45359960198402405},{"id":"https://openalex.org/keywords/data-classification","display_name":"Data classification","score":0.42588502168655396},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14112737774848938},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12075060606002808}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585113048553467},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.7337010502815247},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6449803709983826},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.6444705128669739},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.615447461605072},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5992817878723145},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5975480079650879},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5921401977539062},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5509825348854065},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5439193248748779},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5205870270729065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.507923424243927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4702759385108948},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.45359960198402405},{"id":"https://openalex.org/C2780724565","wikidata":"https://www.wikidata.org/wiki/Q5227256","display_name":"Data classification","level":2,"score":0.42588502168655396},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14112737774848938},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12075060606002808},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1515/comp-2022-0273","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2022-0273","pdf_url":"https://www.degruyter.com/document/doi/10.1515/comp-2022-0273/pdf","source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6fd042e84f564ddd933ba35b0a07d53e","is_oa":true,"landing_page_url":"https://doaj.org/article/6fd042e84f564ddd933ba35b0a07d53e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Open Computer Science, Vol 13, Iss 1, Pp pp. 1-25 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1515/comp-2022-0273","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2022-0273","pdf_url":"https://www.degruyter.com/document/doi/10.1515/comp-2022-0273/pdf","source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4378471254.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W220382040","https://openalex.org/W2154001600","https://openalex.org/W2173122598","https://openalex.org/W2214628823","https://openalex.org/W2230353612","https://openalex.org/W2270234620","https://openalex.org/W2308230922","https://openalex.org/W2313507061","https://openalex.org/W2321108298","https://openalex.org/W2337323496","https://openalex.org/W2345588986","https://openalex.org/W2410883106","https://openalex.org/W2464658274","https://openalex.org/W2468676150","https://openalex.org/W2478248559","https://openalex.org/W2549551440","https://openalex.org/W2552106163","https://openalex.org/W2553101787","https://openalex.org/W2560205181","https://openalex.org/W2580885910","https://openalex.org/W2594039330","https://openalex.org/W2619961728","https://openalex.org/W2624142016","https://openalex.org/W2742271598","https://openalex.org/W2770785043","https://openalex.org/W2771508779","https://openalex.org/W2801491268","https://openalex.org/W2883206278","https://openalex.org/W3006030645"],"related_works":["https://openalex.org/W3010890513","https://openalex.org/W3086422166","https://openalex.org/W2053247611","https://openalex.org/W3165117444","https://openalex.org/W2084395052","https://openalex.org/W3016972457","https://openalex.org/W2792375448","https://openalex.org/W2605106030","https://openalex.org/W3138271675","https://openalex.org/W3117229956"],"abstract_inverted_index":{"Abstract":[0],"The":[1,41,79,241],"rapid":[2],"development":[3],"of":[4,13,37,43,54,81,102,119,134,163,171,188,252],"technology":[5],"allows":[6],"people":[7],"to":[8,23,98,113,149,179,227],"obtain":[9,24],"a":[10,71,116,131,202],"large":[11,117],"amount":[12,118],"data,":[14],"which":[15,138,224,263],"contains":[16],"important":[17,32,49],"information":[18,124],"and":[19,57,66,69,77,109,125,145,183,221],"various":[20],"noises.":[21],"How":[22],"useful":[25,123],"knowledge":[26],"from":[27],"data":[28,55,86,91,104,121,128,151,173,194,208,214,218,236,271],"is":[29,46,70,89,130,143,147,261],"the":[30,52,99,139,157,160,168,186,249,253],"most":[31],"thing":[33],"at":[34],"this":[35,61,245],"stage":[36],"machine":[38],"learning":[39],"(ML).":[40],"problem":[42,62,80],"unbalanced":[44,82,103,172,193,207,235,270],"classification":[45,83,135,219],"currently":[47],"an":[48],"topic":[50],"in":[51,137,244],"field":[53],"mining":[56],"ML.":[58,198,240,275],"At":[59],"present,":[60],"has":[63],"attracted":[64],"more":[65,67,106],"attention":[68],"relatively":[72],"new":[73,107],"challenge":[74],"for":[75,185,205,234,268],"academia":[76],"industry.":[78],"involves":[84],"classifying":[85],"when":[87],"there":[88],"insufficient":[90],"or":[92],"severe":[93],"category":[94],"distribution":[95,140],"deviations.":[96],"Due":[97],"inherent":[100],"complexity":[101],"sets,":[105],"algorithms":[108,165,190],"tools":[110],"are":[111,225],"needed":[112],"effectively":[114],"convert":[115],"raw":[120],"into":[122],"knowledge.":[126],"Unbalanced":[127],"set":[129],"special":[132],"case":[133],"problem,":[136],"between":[141],"classes":[142],"uneven,":[144],"it":[146],"difficult":[148],"classify":[150],"accurately.":[152],"This":[153,199],"article":[154,200,246],"mainly":[155],"introduces":[156],"research":[158,203,229],"on":[159,167,176,192,197,211,231,239,259,274],"processing":[161,169,187,206,232,269],"method":[162,170],"computer":[164,189],"based":[166,175,191,196,210,238,258,273],"sets":[174,195,209,237,272],"ML,":[177,212],"aiming":[178],"provide":[180],"some":[181],"ideas":[182],"directions":[184],"proposes":[201],"strategy":[204],"including":[213],"preprocessing,":[215],"decision":[216,254],"tree":[217,255],"algorithm,":[220,223],"C4.5":[222,256],"used":[226,267],"conduct":[228],"experiments":[230],"methods":[233],"experimental":[242],"results":[243],"show":[247],"that":[248],"accuracy":[250],"rate":[251],"algorithm":[257],"ML":[260],"94.80%,":[262],"can":[264],"be":[265],"better":[266]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}