{"id":"https://openalex.org/W4321373744","doi":"https://doi.org/10.3390/s23042333","title":"A Comparative Study of the Use of Stratified Cross-Validation and Distribution-Balanced Stratified Cross-Validation in Imbalanced Learning","display_name":"A Comparative Study of the Use of Stratified Cross-Validation and Distribution-Balanced Stratified Cross-Validation in Imbalanced Learning","publication_year":2023,"publication_date":"2023-02-20","ids":{"openalex":"https://openalex.org/W4321373744","doi":"https://doi.org/10.3390/s23042333","pmid":"https://pubmed.ncbi.nlm.nih.gov/36850931"},"language":"en","primary_location":{"id":"doi:10.3390/s23042333","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23042333","pdf_url":"https://www.mdpi.com/1424-8220/23/4/2333/pdf?version=1676885969","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/4/2333/pdf?version=1676885969","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019833655","display_name":"Szilvia Szeghalmy","orcid":"https://orcid.org/0000-0003-4121-4745"},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Szilvia Szeghalmy","raw_affiliation_strings":["Faculty of Informatics, University of Debrecen, H-4028 Debrecen, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-4121-4745","affiliations":[{"raw_affiliation_string":"Faculty of Informatics, University of Debrecen, H-4028 Debrecen, Hungary","institution_ids":["https://openalex.org/I132735039"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025477191","display_name":"Attila Fazekas","orcid":"https://orcid.org/0000-0001-6893-3067"},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Attila Fazekas","raw_affiliation_strings":["Faculty of Informatics, University of Debrecen, H-4028 Debrecen, Hungary"],"raw_orcid":"https://orcid.org/0000-0001-6893-3067","affiliations":[{"raw_affiliation_string":"Faculty of Informatics, University of Debrecen, H-4028 Debrecen, Hungary","institution_ids":["https://openalex.org/I132735039"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5025477191"],"corresponding_institution_ids":["https://openalex.org/I132735039"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":23.7387,"has_fulltext":false,"cited_by_count":144,"citation_normalized_percentile":{"value":0.99654393,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"23","issue":"4","first_page":"2333","last_page":"2333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9013000130653381,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7157829999923706},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.707829475402832},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.7004203200340271},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6592960953712463},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.643256664276123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6073256731033325},{"id":"https://openalex.org/keywords/stratified-sampling","display_name":"Stratified sampling","score":0.4568125009536743},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.44279390573501587},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41455116868019104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39104729890823364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22593224048614502},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17879733443260193},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07818332314491272}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7157829999923706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.707829475402832},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.7004203200340271},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6592960953712463},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.643256664276123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6073256731033325},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.4568125009536743},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.44279390573501587},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41455116868019104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39104729890823364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22593224048614502},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17879733443260193},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07818332314491272},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/s23042333","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23042333","pdf_url":"https://www.mdpi.com/1424-8220/23/4/2333/pdf?version=1676885969","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:36850931","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36850931","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9967638","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9967638","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:5a8f932350b84a5d8ebf98af0b8884b2","is_oa":true,"landing_page_url":"https://doaj.org/article/5a8f932350b84a5d8ebf98af0b8884b2","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":"Sensors, Vol 23, Iss 4, p 2333 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/4/2333/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23042333","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23042333","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23042333","pdf_url":"https://www.mdpi.com/1424-8220/23/4/2333/pdf?version=1676885969","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4321373744.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W123443654","https://openalex.org/W1565746575","https://openalex.org/W1647645866","https://openalex.org/W1673310716","https://openalex.org/W1680392829","https://openalex.org/W1680797894","https://openalex.org/W1989249186","https://openalex.org/W1993220166","https://openalex.org/W2008973833","https://openalex.org/W2009754619","https://openalex.org/W2061481434","https://openalex.org/W2085770564","https://openalex.org/W2091085232","https://openalex.org/W2092126505","https://openalex.org/W2101234009","https://openalex.org/W2105340608","https://openalex.org/W2107138773","https://openalex.org/W2109509105","https://openalex.org/W2122111042","https://openalex.org/W2124685890","https://openalex.org/W2146619110","https://openalex.org/W2148143831","https://openalex.org/W2153635508","https://openalex.org/W2158143121","https://openalex.org/W2192249782","https://openalex.org/W2783151797","https://openalex.org/W2886990716","https://openalex.org/W2895495973","https://openalex.org/W2966679659","https://openalex.org/W2969674096","https://openalex.org/W2980424548","https://openalex.org/W2983547987","https://openalex.org/W2999096842","https://openalex.org/W3022607879","https://openalex.org/W3138595103","https://openalex.org/W3142722547","https://openalex.org/W3159066252","https://openalex.org/W3180223285","https://openalex.org/W3201969843","https://openalex.org/W4220897422","https://openalex.org/W4229017706","https://openalex.org/W4232533539","https://openalex.org/W4242257264","https://openalex.org/W4243367342","https://openalex.org/W4282006100","https://openalex.org/W4286433211","https://openalex.org/W4287448787","https://openalex.org/W4296512953","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W4362501033","https://openalex.org/W2905582729","https://openalex.org/W3195168932","https://openalex.org/W1996541855","https://openalex.org/W3093300636","https://openalex.org/W4206962509","https://openalex.org/W2556319748","https://openalex.org/W4295713393","https://openalex.org/W4296286130","https://openalex.org/W4321373744"],"abstract_inverted_index":{"Nowadays,":[0],"the":[1,14,27,48,58,62,76,79,98,142,145,163,190,195,198,205,209,212,215],"solution":[2],"to":[3,74,92,97],"many":[4,55],"practical":[5],"problems":[6,22],"relies":[7],"on":[8,131,147,154],"machine":[9],"learning":[10,64,81],"tools.":[11],"However,":[12,189],"compiling":[13],"appropriate":[15],"training":[16],"data":[17,31,93,105,133,156],"set":[18],"for":[19,32,60,103,184,204],"real-world":[20],"classification":[21,124,185,206],"is":[23,35,201],"challenging":[24],"because":[25],"collecting":[26],"right":[28],"amount":[29],"of":[30,50,78,100,138,144,197],"each":[33],"class":[34],"often":[36,175],"difficult":[37],"or":[38],"even":[39],"impossible.":[40],"In":[41],"such":[42,107],"cases,":[43],"we":[44],"can":[45,86,128],"easily":[46],"face":[47],"problem":[49],"imbalanced":[51,63,80,104,132],"learning.":[52],"There":[53],"are":[54],"methods":[56,101,161],"in":[57],"literature":[59],"solving":[61],"problem,":[65],"so":[66],"it":[67],"has":[68],"become":[69],"a":[70,177],"serious":[71],"question":[72],"how":[73],"compare":[75],"performance":[77,125,207],"methods.":[82],"Inadequate":[83],"validation":[84],"techniques":[85],"provide":[87],"misleading":[88],"results":[89,191],"(e.g.,":[90],"due":[91],"shift),":[94],"which":[95],"leads":[96],"development":[99],"designed":[102],"sets,":[106,157],"as":[108],"stratified":[109],"cross-validation":[110],"(SCV)":[111],"and":[112,162,167,181,214],"distribution":[113],"optimally":[114],"balanced":[115],"SCV":[116,216],"(DOB-SCV).":[117],"Previous":[118],"studies":[119],"have":[120],"shown":[121],"that":[122,173,194],"higher":[123,179],"scores":[126],"(AUC)":[127],"be":[129],"achieved":[130],"sets":[134],"using":[135],"DOB-SCV":[136,174,213],"instead":[137],"SCV.":[139],"We":[140,170],"investigated":[141],"effect":[143],"oversamplers":[146],"this":[148],"difference.":[149],"The":[150],"study":[151],"was":[152],"conducted":[153],"420":[155],"involving":[158],"several":[159],"sampling":[160],"DTree,":[164],"kNN,":[165],"SVM,":[166],"MLP":[168],"classifiers.":[169],"point":[171],"out":[172],"provides":[176],"little":[178],"F1":[180],"AUC":[182],"values":[183],"combined":[186],"with":[187],"sampling.":[188],"also":[192],"prove":[193],"selection":[196],"sampler\u2013classifier":[199],"pair":[200],"more":[202],"important":[203],"than":[208],"choice":[210],"between":[211],"techniques.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":60},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":16}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}