{"id":"https://openalex.org/W4406039573","doi":"https://doi.org/10.1080/03610918.2024.2447451","title":"Over-sampling methods for mixed data in imbalanced problems","display_name":"Over-sampling methods for mixed data in imbalanced problems","publication_year":2025,"publication_date":"2025-01-02","ids":{"openalex":"https://openalex.org/W4406039573","doi":"https://doi.org/10.1080/03610918.2024.2447451"},"language":"en","primary_location":{"id":"doi:10.1080/03610918.2024.2447451","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2024.2447451","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Statistics - Simulation and Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016057215","display_name":"Hugo Alonso","orcid":"https://orcid.org/0000-0002-1599-5392"},"institutions":[{"id":"https://openalex.org/I4210146999","display_name":"Universidade Lus\u00f3fona do Porto","ror":"https://ror.org/052kcks88","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210146999"]},{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Hugo Alonso","raw_affiliation_strings":["CIDMA and Departamento de Matem\u00e1tica, Universidade de Aveiro","Universidade Lus\u00f3fona, Centro Universit\u00e1rio do Porto","CIDMA and Departamento de Matem\u00e1tica, Universidade de Aveiro, Aveiro, Portugal","Universidade Lus\u00f3fona, Centro Universit\u00e1rio do Porto, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIDMA and Departamento de Matem\u00e1tica, Universidade de Aveiro","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"Universidade Lus\u00f3fona, Centro Universit\u00e1rio do Porto","institution_ids":["https://openalex.org/I4210146999"]},{"raw_affiliation_string":"CIDMA and Departamento de Matem\u00e1tica, Universidade de Aveiro, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"Universidade Lus\u00f3fona, Centro Universit\u00e1rio do Porto, Porto, Portugal","institution_ids":["https://openalex.org/I4210146999"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073053643","display_name":"Joaquim Pinto da Costa","orcid":"https://orcid.org/0000-0002-3991-2715"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joaquim Fernando Pinto da Costa","raw_affiliation_strings":["CMUP and Departamento de Matem\u00e1tica, Faculdade de Ci\u00eancias, Universidade do Porto","CMUP and Departamento de Matem\u00e1tica, Faculdade de Ci\u00eancias, Universidade do Porto, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMUP and Departamento de Matem\u00e1tica, Faculdade de Ci\u00eancias, Universidade do Porto","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"CMUP and Departamento de Matem\u00e1tica, Faculdade de Ci\u00eancias, Universidade do Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016057215"],"corresponding_institution_ids":["https://openalex.org/I4210146999","https://openalex.org/I60858718"],"apc_list":null,"apc_paid":null,"fwci":5.1514,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94307496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"55","issue":"5","first_page":"1521","last_page":"1543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9990000128746033,"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/T11443","display_name":"Advanced Statistical Process Monitoring","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5239077806472778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4443577826023102},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3748112916946411},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3495134115219116},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.286848247051239},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.058401405811309814}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5239077806472778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4443577826023102},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3748112916946411},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3495134115219116},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.286848247051239},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.058401405811309814},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/03610918.2024.2447451","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2024.2447451","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Statistics - Simulation and Computation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5341562090","display_name":null,"funder_award_id":"UIDP/00144/2020","funder_id":"https://openalex.org/F4320335191","funder_display_name":"Centro de Matem\u00e1tica Universidade do Porto"},{"id":"https://openalex.org/G8367123964","display_name":null,"funder_award_id":"UIDB/00144/2020","funder_id":"https://openalex.org/F4320335191","funder_display_name":"Centro de Matem\u00e1tica Universidade do Porto"}],"funders":[{"id":"https://openalex.org/F4320335191","display_name":"Centro de Matem\u00e1tica Universidade do Porto","ror":"https://ror.org/043pwc612"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1479807131","https://openalex.org/W1583837637","https://openalex.org/W1988790447","https://openalex.org/W1993220166","https://openalex.org/W2011376672","https://openalex.org/W2015452969","https://openalex.org/W2023639956","https://openalex.org/W2040010062","https://openalex.org/W2056884786","https://openalex.org/W2061731688","https://openalex.org/W2065353443","https://openalex.org/W2089409375","https://openalex.org/W2128965734","https://openalex.org/W2148143831","https://openalex.org/W2266133738","https://openalex.org/W2295598076","https://openalex.org/W2329970408","https://openalex.org/W2490420619","https://openalex.org/W2504782928","https://openalex.org/W2526529994","https://openalex.org/W2562319768","https://openalex.org/W2612634114","https://openalex.org/W2740195871","https://openalex.org/W2787894218","https://openalex.org/W2798115135","https://openalex.org/W2800788706","https://openalex.org/W2903162933","https://openalex.org/W2911731670","https://openalex.org/W2966679659","https://openalex.org/W4213388479","https://openalex.org/W4235764643","https://openalex.org/W4242221364","https://openalex.org/W4293102791"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3107697994"],"abstract_inverted_index":{"In":[0,95],"practice,":[1],"it":[2,52,165],"is":[3,53],"common":[4,56],"to":[5,26,32,64,84],"find":[6],"imbalanced":[7,61],"classification":[8,35,62],"problems,":[9],"where":[10],"one":[11,43],"or":[12,130],"more":[13],"classes":[14],"have":[15],"many":[16],"fewer":[17],"examples":[18],"than":[19],"the":[20,34,38,77,81,110,124,149,155,171,175,178],"others.":[21],"There":[22],"are":[23,91,121],"several":[24,100],"ways":[25,146,180],"deal":[27],"with":[28],"imbalance":[29],"in":[30,37,47,60,117],"order":[31],"improve":[33],"results":[36],"less":[39,55],"represented":[40],"class(es)":[41],"and":[42,73,177],"of":[44,68,80,113,136,147,154,174,181],"them":[45],"consists":[46],"applying":[48],"re-sampling":[49,101],"methods.":[50],"Furthermore,":[51],"no":[54],"for":[57,103,139],"data":[58,82,90,176],"sets":[59],"problems":[63],"be":[65,85],"a":[66,161],"mix":[67],"nominal,":[69],"ordinal,":[70],"quantitative":[71],"discrete":[72],"continuous":[74],"data.":[75,119,141],"However,":[76],"true":[78,172],"nature":[79,173],"tends":[83],"ignored,":[86],"like":[87],"when":[88],"ordinal":[89],"treated":[92],"as":[93],"nominal.":[94],"this":[96],"paper,":[97],"we":[98],"propose":[99],"methods":[102],"mixed":[104,140],"data,":[105],"which":[106],"take":[107],"into":[108,169],"account":[109,170],"four":[111],"scales":[112],"measurement":[114],"usually":[115],"found":[116],"real":[118],"They":[120],"based":[122],"on":[123],"popular":[125],"synthetic":[126,150,183],"minority":[127],"over-sampling":[128],"technique":[129],"SMOTE.":[131],"We":[132,142,158],"consider":[133],"different":[134],"measures":[135],"distance":[137],"adequate":[138],"also":[143],"introduce":[144],"new":[145,179],"creating":[148,182],"examples,":[151],"using":[152],"all":[153],"nearest":[156],"neighbors.":[157],"show":[159],"through":[160],"comparative":[162],"study":[163],"that":[164],"pays":[166],"off":[167],"taking":[168],"examples.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}