{"id":"https://openalex.org/W2559375882","doi":"https://doi.org/10.1587/transinf.2016edp7130","title":"Cluster-Based Minority Over-Sampling for Imbalanced Datasets","display_name":"Cluster-Based Minority Over-Sampling for Imbalanced Datasets","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2559375882","doi":"https://doi.org/10.1587/transinf.2016edp7130","mag":"2559375882"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016edp7130","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7130","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/12/E99.D_2016EDP7130/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/12/E99.D_2016EDP7130/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110459915","display_name":"Kamthorn Puntumapon","orcid":null},"institutions":[{"id":"https://openalex.org/I198105771","display_name":"Kasetsart University","ror":"https://ror.org/05gzceg21","country_code":"TH","type":"education","lineage":["https://openalex.org/I198105771"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Kamthorn PUNTUMAPON","raw_affiliation_strings":["Department of Computer Engineering, Faculty of Engineering, Kasetsart University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Faculty of Engineering, Kasetsart University","institution_ids":["https://openalex.org/I198105771"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024782351","display_name":"Thanawin RAKTHAMAMON","orcid":null},"institutions":[{"id":"https://openalex.org/I198105771","display_name":"Kasetsart University","ror":"https://ror.org/05gzceg21","country_code":"TH","type":"education","lineage":["https://openalex.org/I198105771"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Thanawin RAKTHAMAMON","raw_affiliation_strings":["Department of Computer Engineering, Faculty of Engineering, Kasetsart University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Faculty of Engineering, Kasetsart University","institution_ids":["https://openalex.org/I198105771"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012602048","display_name":"Kitsana Waiyamai","orcid":null},"institutions":[{"id":"https://openalex.org/I198105771","display_name":"Kasetsart University","ror":"https://ror.org/05gzceg21","country_code":"TH","type":"education","lineage":["https://openalex.org/I198105771"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Kitsana WAIYAMAI","raw_affiliation_strings":["Department of Computer Engineering, Faculty of Engineering, Kasetsart University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Faculty of Engineering, Kasetsart University","institution_ids":["https://openalex.org/I198105771"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I198105771"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.08679724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"E99.D","issue":"12","first_page":"3101","last_page":"3109"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9584000110626221,"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":0.9390000104904175,"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/overfitting","display_name":"Overfitting","score":0.7629486322402954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7564935684204102},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.750749945640564},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6873050332069397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6186501383781433},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5707416534423828},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5264047980308533},{"id":"https://openalex.org/keywords/trim","display_name":"Trim","score":0.4747988283634186},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.44560399651527405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3882446885108948},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36504366993904114},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3232574462890625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2088506817817688},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10764467716217041},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.06985858082771301}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7629486322402954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564935684204102},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.750749945640564},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6873050332069397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6186501383781433},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5707416534423828},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5264047980308533},{"id":"https://openalex.org/C88611116","wikidata":"https://www.wikidata.org/wiki/Q957004","display_name":"Trim","level":2,"score":0.4747988283634186},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.44560399651527405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3882446885108948},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36504366993904114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3232574462890625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2088506817817688},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10764467716217041},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.06985858082771301},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2016edp7130","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7130","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/12/E99.D_2016EDP7130/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2016edp7130","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7130","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/12/E99.D_2016EDP7130/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2559375882.pdf","grobid_xml":"https://content.openalex.org/works/W2559375882.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W48554555","https://openalex.org/W85350352","https://openalex.org/W125763370","https://openalex.org/W191726569","https://openalex.org/W1496056137","https://openalex.org/W1591261915","https://openalex.org/W1994445591","https://openalex.org/W1998467055","https://openalex.org/W2070808135","https://openalex.org/W2087240369","https://openalex.org/W2104933073","https://openalex.org/W2128965734","https://openalex.org/W2132791018","https://openalex.org/W2133990480","https://openalex.org/W2148143831","https://openalex.org/W2155653793","https://openalex.org/W3120740533","https://openalex.org/W3155649056"],"related_works":["https://openalex.org/W4389965896","https://openalex.org/W4387747402","https://openalex.org/W3119578451","https://openalex.org/W3196098778","https://openalex.org/W3211250490","https://openalex.org/W4360584310","https://openalex.org/W2981515171","https://openalex.org/W2924282518","https://openalex.org/W80466363","https://openalex.org/W3080872054"],"abstract_inverted_index":{"Synthetic":[0],"over-sampling":[1,23,200],"is":[2,75,84,132,153],"a":[3,54,58,65,71,111,128,149,195],"well-known":[4],"method":[5,72],"to":[6,64,77,85,134,155],"solve":[7],"class":[8,12,40,47,60,88,101,117,140,160],"imbalance":[9],"by":[10],"modifying":[11],"distribution":[13],"and":[14,94,169,188,205],"generating":[15],"synthetic":[16,22,38,199],"samples.":[17],"A":[18],"large":[19,112],"number":[20,113],"of":[21,30,106,114,144,186],"techniques":[24],"have":[25],"been":[26],"proposed;":[27],"however,":[28],"most":[29],"them":[31],"suffer":[32],"from":[33,50],"the":[34,45,79,99,104,125,138,145,151],"over-generalization":[35,80,136],"problem":[36],"whereby":[37],"minority":[39,66,87,100,116,146,159],"samples":[41,161],"are":[42],"generated":[43],"into":[44,119],"majority":[46,59,139],"region.":[48],"Learning":[49],"an":[51],"over-generalized":[52],"dataset,":[53],"classifier":[55,152],"could":[56],"misclassify":[57],"member":[61],"as":[62,173,194,203],"belonging":[63],"class.":[67,147],"In":[68],"this":[69],"paper":[70],"called":[73],"TRIM":[74,96,179,190],"proposed":[76,133],"overcome":[78],"problem.":[81],"The":[82],"idea":[83],"identify":[86],"regions":[89,102],"that":[90,178],"compromise":[91],"between":[92],"generalization":[93,126,143],"overfitting.":[95],"identifies":[97],"all":[98],"in":[103,184],"form":[105],"clusters.":[107,122],"Then,":[108],"it":[109],"merges":[110],"small":[115],"clusters":[118],"more":[120,158],"generalized":[121],"To":[123],"enhance":[124],"ability,":[127],"cluster":[129],"connection":[130],"step":[131,197],"avoid":[135],"toward":[137],"while":[141,162],"increasing":[142],"As":[148],"result,":[150],"able":[154],"correctly":[156],"classify":[157],"maintaining":[163],"its":[164,206],"precision.":[165],"Compared":[166],"with":[167],"SMOTE":[168,204],"extended":[170,207],"versions":[171],"such":[172,202],"Borderline-SMOTE,":[174],"experimental":[175],"results":[176],"show":[177],"exhibits":[180],"significant":[181],"performance":[182],"improvement":[183],"terms":[185],"F-measure":[187],"AUC.":[189],"can":[191],"be":[192],"used":[193],"pre-processing":[196],"for":[198],"methods":[201],"versions.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}