{"id":"https://openalex.org/W4285212650","doi":"https://doi.org/10.1109/tkde.2022.3179381","title":"An Investigation of SMOTE based Methods for Imbalanced Datasets with Data Complexity Analysis","display_name":"An Investigation of SMOTE based Methods for Imbalanced Datasets with Data Complexity Analysis","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285212650","doi":"https://doi.org/10.1109/tkde.2022.3179381"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2022.3179381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3179381","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5060563456","display_name":"Nur Athirah Azhar","orcid":null},"institutions":[{"id":"https://openalex.org/I72600253","display_name":"Malaysian Agricultural Research and Development Institute","ror":"https://ror.org/04sky4s35","country_code":"MY","type":"government","lineage":["https://openalex.org/I72600253"]},{"id":"https://openalex.org/I94625822","display_name":"Northern University of Malaysia","ror":"https://ror.org/01ss10648","country_code":"MY","type":"education","lineage":["https://openalex.org/I94625822"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Nur Athirah Azhar","raw_affiliation_strings":["Malaysian Investment Development Authority, Malaysia","School of Computing, Universiti Utara Malaysia, 65293 Pokok sena, Kedah, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Malaysian Investment Development Authority, Malaysia","institution_ids":["https://openalex.org/I72600253"]},{"raw_affiliation_string":"School of Computing, Universiti Utara Malaysia, 65293 Pokok sena, Kedah, Malaysia","institution_ids":["https://openalex.org/I94625822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023268855","display_name":"Muhammad Syafiq Mohd Pozi","orcid":"https://orcid.org/0000-0001-9379-7351"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]},{"id":"https://openalex.org/I94625822","display_name":"Northern University of Malaysia","ror":"https://ror.org/01ss10648","country_code":"MY","type":"education","lineage":["https://openalex.org/I94625822"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Muhammad Syafiq Mohd Pozi","raw_affiliation_strings":["Institute for Advanced and Smart Digital Opportunities, School of Computing, Universiti Utara Malaysia, and the Institute of IR 4.0, Universiti Kebangsaan Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Advanced and Smart Digital Opportunities, School of Computing, Universiti Utara Malaysia, and the Institute of IR 4.0, Universiti Kebangsaan Malaysia","institution_ids":["https://openalex.org/I885383172","https://openalex.org/I94625822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118148856","display_name":"Aniza Mohamed Din","orcid":"https://orcid.org/0000-0002-5859-023X"},"institutions":[{"id":"https://openalex.org/I94625822","display_name":"Northern University of Malaysia","ror":"https://ror.org/01ss10648","country_code":"MY","type":"education","lineage":["https://openalex.org/I94625822"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Aniza Mohamed Din","raw_affiliation_strings":["Data Science Research Lab, School of Computing, Universiti Utara Malaysia","School of Computing, Universiti Utara Malaysia, 65293 Sintok, Kedah, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Research Lab, School of Computing, Universiti Utara Malaysia","institution_ids":["https://openalex.org/I94625822"]},{"raw_affiliation_string":"School of Computing, Universiti Utara Malaysia, 65293 Sintok, Kedah, Malaysia","institution_ids":["https://openalex.org/I94625822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079733597","display_name":"Adam Jatowt","orcid":"https://orcid.org/0000-0001-7235-0665"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Adam Jatowt","raw_affiliation_strings":["Department of Computer Science and Digital Science Center at the University of Innsbruck, Innsbruck, Tirol, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Digital Science Center at the University of Innsbruck, Innsbruck, Tirol, Austria","institution_ids":["https://openalex.org/I190249584"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":11.8122,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.98822713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9591000080108643,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8302065134048462},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.7768032550811768},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5748229622840881},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.518809974193573},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4577369689941406},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4565524458885193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4442059099674225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302065134048462},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.7768032550811768},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5748229622840881},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.518809974193573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4577369689941406},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4565524458885193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442059099674225},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2022.3179381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3179381","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","score":0.46000000834465027,"display_name":"Responsible consumption and production"}],"awards":[{"id":"https://openalex.org/G6712145461","display_name":null,"funder_award_id":"FRGS/1/2019/ICT02/UUM/02/2","funder_id":"https://openalex.org/F4320321709","funder_display_name":"Ministry of Higher Education, Malaysia"}],"funders":[{"id":"https://openalex.org/F4320321709","display_name":"Ministry of Higher Education, Malaysia","ror":"https://ror.org/05mcs2t73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":132,"referenced_works":["https://openalex.org/W125763370","https://openalex.org/W578835786","https://openalex.org/W752888290","https://openalex.org/W1496056137","https://openalex.org/W1548505798","https://openalex.org/W1593532658","https://openalex.org/W1596717185","https://openalex.org/W1754612754","https://openalex.org/W1955875725","https://openalex.org/W1964675540","https://openalex.org/W1964940342","https://openalex.org/W1990165991","https://openalex.org/W1993220166","https://openalex.org/W1996523702","https://openalex.org/W1999318832","https://openalex.org/W2016023958","https://openalex.org/W2040181375","https://openalex.org/W2040895929","https://openalex.org/W2070762699","https://openalex.org/W2070902649","https://openalex.org/W2087240369","https://openalex.org/W2104144433","https://openalex.org/W2107138773","https://openalex.org/W2107327607","https://openalex.org/W2115969689","https://openalex.org/W2125877832","https://openalex.org/W2126996952","https://openalex.org/W2131571251","https://openalex.org/W2132791018","https://openalex.org/W2148143831","https://openalex.org/W2152089394","https://openalex.org/W2167464971","https://openalex.org/W2172165257","https://openalex.org/W2333362108","https://openalex.org/W2338318698","https://openalex.org/W2404441930","https://openalex.org/W2509109313","https://openalex.org/W2515146973","https://openalex.org/W2548109252","https://openalex.org/W2552663603","https://openalex.org/W2554501045","https://openalex.org/W2559375882","https://openalex.org/W2562319768","https://openalex.org/W2589453516","https://openalex.org/W2598548966","https://openalex.org/W2601726217","https://openalex.org/W2604243156","https://openalex.org/W2611252858","https://openalex.org/W2612634114","https://openalex.org/W2736435690","https://openalex.org/W2739133112","https://openalex.org/W2740924709","https://openalex.org/W2757120799","https://openalex.org/W2759756773","https://openalex.org/W2766296277","https://openalex.org/W2768552067","https://openalex.org/W2772832743","https://openalex.org/W2772947247","https://openalex.org/W2777619483","https://openalex.org/W2784249848","https://openalex.org/W2789511664","https://openalex.org/W2793375005","https://openalex.org/W2800788706","https://openalex.org/W2810785030","https://openalex.org/W2896309543","https://openalex.org/W2896457183","https://openalex.org/W2899434936","https://openalex.org/W2903362744","https://openalex.org/W2907063321","https://openalex.org/W2908285635","https://openalex.org/W2910137068","https://openalex.org/W2911512579","https://openalex.org/W2911964244","https://openalex.org/W2914361121","https://openalex.org/W2916025621","https://openalex.org/W2919868916","https://openalex.org/W2927933146","https://openalex.org/W2942097997","https://openalex.org/W2953675148","https://openalex.org/W2963108767","https://openalex.org/W2966679659","https://openalex.org/W2966800547","https://openalex.org/W2969674096","https://openalex.org/W2980282514","https://openalex.org/W2981515171","https://openalex.org/W2981803355","https://openalex.org/W2987788345","https://openalex.org/W2992616003","https://openalex.org/W2996821517","https://openalex.org/W2999438024","https://openalex.org/W2999592897","https://openalex.org/W3008527144","https://openalex.org/W3013316335","https://openalex.org/W3014524176","https://openalex.org/W3022206528","https://openalex.org/W3034578890","https://openalex.org/W3036099941","https://openalex.org/W3038155884","https://openalex.org/W3041568739","https://openalex.org/W3041664846","https://openalex.org/W3042297952","https://openalex.org/W3046141163","https://openalex.org/W3047976641","https://openalex.org/W3082051559","https://openalex.org/W3083631411","https://openalex.org/W3087981749","https://openalex.org/W3088242795","https://openalex.org/W3088624649","https://openalex.org/W3089420282","https://openalex.org/W3090514951","https://openalex.org/W3093212523","https://openalex.org/W3104604581","https://openalex.org/W3109072952","https://openalex.org/W3127988644","https://openalex.org/W3135252693","https://openalex.org/W3193635602","https://openalex.org/W4245807786","https://openalex.org/W4249572517","https://openalex.org/W4254182148","https://openalex.org/W6640946799","https://openalex.org/W6675776767","https://openalex.org/W6679713772","https://openalex.org/W6682273016","https://openalex.org/W6725794477","https://openalex.org/W6744737871","https://openalex.org/W6746913514","https://openalex.org/W6755207826","https://openalex.org/W6768817161","https://openalex.org/W6770152941","https://openalex.org/W6775238938","https://openalex.org/W6782541988","https://openalex.org/W6791617104"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W2781247653","https://openalex.org/W4206637278","https://openalex.org/W4386005305","https://openalex.org/W4386214543","https://openalex.org/W3082051559","https://openalex.org/W1969988626","https://openalex.org/W1682621979","https://openalex.org/W2953675148","https://openalex.org/W2300921526"],"abstract_inverted_index":{"Many":[0],"binary":[1,151],"class":[2,10,18,44,152],"datasets":[3,154],"in":[4,31,41,62,130,141,159,169,186],"real-life":[5],"applications":[6],"are":[7,24,138,147,179],"affected":[8],"by":[9,109],"imbalance":[11,45],"problem.":[12,46],"Data":[13],"complexities":[14,37,72,137],"like":[15,175],"noise":[16],"examples,":[17],"overlap":[19],"and":[20,73,133,177],"small":[21],"disjuncts":[22],"problems":[23],"observed":[25],"to":[26,39,56,102,124,155,182],"play":[27],"a":[28,53],"key":[29],"role":[30],"producing":[32],"poor":[33],"classification":[34,187],"performance.":[35],"These":[36],"tend":[38],"exist":[40],"tandem":[42],"with":[43,112],"Synthetic":[47],"Minority":[48],"Oversampling":[49],"Technique":[50],"(SMOTE)":[51],"is":[52,91],"well-known":[54],"method":[55],"re-balance":[57],"the":[58,77,81,86,89,104,117,127,157,160,184],"number":[59],"of":[60,79,83,88,106,145],"examples":[61],"imbalanced":[63,153],"datasets.":[64,171],"However,":[65],"this":[66],"technique":[67],"cannot":[68],"effectively":[69],"tackle":[70],"data":[71,136,161],"it":[74],"also":[75,180],"has":[76],"capability":[78],"magnifying":[80],"degree":[82],"complexities.":[84],"Also,":[85],"performance":[87,188],"SMOTE":[90,97,107,111,119,131,165,190],"still":[92],"not":[93],"satisfactory.":[94],"Therefore,":[95],"various":[96],"variants":[98,132,166],"have":[99],"been":[100],"proposed":[101],"overcome":[103],"downsides":[105],"either":[108],"combining":[110],"other":[113],"algorithms":[114,128],"or":[115],"modifying":[116],"existing":[118],"algorithm.":[120],"This":[121],"paper":[122],"aims":[123],"comparatively":[125],"review":[126],"applied":[129,168],"investigate":[134,183],"which":[135],"being":[139],"addressed":[140],"what":[142],"variants.":[143,191],"Series":[144],"experiments":[146],"conducted":[148],"on":[149],"24":[150],"observe":[156],"changes":[158],"complexity":[162],"measures":[163],"after":[164],"were":[167],"these":[170],"The":[172],"evaluation":[173],"metrics":[174],"G-Mean":[176],"F1-Score":[178],"analyzed":[181],"difference":[185],"between":[189]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}