{"id":"https://openalex.org/W2003638356","doi":"https://doi.org/10.1109/iecon.2013.6699499","title":"A novel evolutionary preprocessing method based on over-sampling and under-sampling for imbalanced datasets","display_name":"A novel evolutionary preprocessing method based on over-sampling and under-sampling for imbalanced datasets","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2003638356","doi":"https://doi.org/10.1109/iecon.2013.6699499","mag":"2003638356"},"language":"en","primary_location":{"id":"doi:10.1109/iecon.2013.6699499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon.2013.6699499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051502105","display_name":"Ginny Y. Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ginny Y. Wong","raw_affiliation_strings":["Department of Electronic and Information Engineering, Hong Kong Polytechnic University","Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056524805","display_name":"F.H.F. Leung","orcid":"https://orcid.org/0000-0003-3921-7074"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Frank H.F. Leung","raw_affiliation_strings":["Department of Electronic and Information Engineering, Hong Kong Polytechnic University","Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079852457","display_name":"Sai Ho Ling","orcid":"https://orcid.org/0000-0003-0849-5098"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["AU","PK"],"is_corresponding":false,"raw_author_name":"Sai-Ho Ling","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology, Sydney","[Fac. of Eng. & Inf. Technol., Univ. of Technol., Sydney, NSW, Australia]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology, Sydney","institution_ids":["https://openalex.org/I114017466","https://openalex.org/I1323252656"]},{"raw_affiliation_string":"[Fac. of Eng. & Inf. Technol., Univ. of Technol., Sydney, NSW, Australia]","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2288,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.45674363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2354","last_page":"2359"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9904999732971191,"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":0.9854000210762024,"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/preprocessor","display_name":"Preprocessor","score":0.7953898906707764},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7943505048751831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7602790594100952},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.6876606941223145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5719956755638123},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.55810546875},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5414046049118042},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4960039556026459},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4905957281589508},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4696837067604065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4426816701889038},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4384475350379944},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2042645514011383},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16821786761283875},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.05347302556037903}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7953898906707764},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7943505048751831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602790594100952},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.6876606941223145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5719956755638123},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.55810546875},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5414046049118042},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4960039556026459},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4905957281589508},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4696837067604065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4426816701889038},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4384475350379944},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2042645514011383},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16821786761283875},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.05347302556037903},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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":3,"locations":[{"id":"doi:10.1109/iecon.2013.6699499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon.2013.6699499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/14451","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/14451","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/119873","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/119873","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W85350352","https://openalex.org/W1514048016","https://openalex.org/W1533970595","https://openalex.org/W1588282782","https://openalex.org/W1591261915","https://openalex.org/W1607624180","https://openalex.org/W1696243063","https://openalex.org/W1993220166","https://openalex.org/W1994410331","https://openalex.org/W2023299139","https://openalex.org/W2040010062","https://openalex.org/W2076817280","https://openalex.org/W2096942889","https://openalex.org/W2114968414","https://openalex.org/W2118978333","https://openalex.org/W2124685890","https://openalex.org/W2125055259","https://openalex.org/W2135547590","https://openalex.org/W2140102659","https://openalex.org/W2148143831","https://openalex.org/W2156530876","https://openalex.org/W2182722412","https://openalex.org/W2979832949","https://openalex.org/W6603460400","https://openalex.org/W6631885290","https://openalex.org/W6637510311"],"related_works":["https://openalex.org/W2012117566","https://openalex.org/W1981856929","https://openalex.org/W2152863486","https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642"],"abstract_inverted_index":{"Imbalanced":[0],"datasets":[1,35,99],"are":[2,14,55,86],"commonly":[3],"encountered":[4],"in":[5,77],"real-world":[6],"classification":[7,151],"problems.":[8],"However,":[9],"many":[10],"machine":[11],"learning":[12,145],"algorithms":[13],"originally":[15],"designed":[16],"for":[17],"well-balanced":[18],"datasets.":[19,137,156],"Re-sampling":[20],"has":[21],"become":[22],"an":[23],"important":[24],"step":[25],"to":[26,135,148],"preprocess":[27],"imbalanced":[28],"dataset.":[29],"It":[30],"aims":[31],"at":[32],"balancing":[33],"the":[34,38,42,47,51,79,83,89,98,103,113,144,154,161,166,177],"by":[36,88,102,142],"increasing":[37],"sample":[39,48],"size":[40,49],"of":[41,50,82,97,107],"smaller":[43,84],"class":[44,85,115,118],"or":[45],"decreasing":[46],"larger":[52],"class,":[53],"which":[54,78],"known":[56],"as":[57],"over-sampling":[58,72,131,167],"and":[59,73,116,132],"under-sampling":[60,74,133],"respectively.":[61],"In":[62],"this":[63],"paper,":[64],"a":[65,123,150],"novel":[66],"sampling":[67],"strategy":[68],"based":[69],"on":[70,111,176],"both":[71,112,130],"is":[75,100,122,140],"proposed,":[76],"new":[80],"samples":[81],"created":[87],"Synthetic":[90],"Minority":[91],"Over-sampling":[92],"Technique":[93],"(SMOTE).":[94],"The":[95,120,138],"improvement":[96],"done":[101,141],"evolutionary":[104],"computational":[105],"method":[106,127],"CHC":[108],"that":[109,128,160],"works":[110],"minority":[114],"majority":[117],"samples.":[119],"result":[121],"hybrid":[124],"data":[125],"preprocessing":[126],"combines":[129],"techniques":[134],"re-sample":[136],"evaluation":[139],"applying":[143],"algorithm":[146],"C4.5":[147],"obtain":[149],"model":[152],"from":[153],"re-sampled":[155],"Experimental":[157],"results":[158],"reported":[159],"proposed":[162],"approach":[163],"can":[164],"decrease":[165],"rate":[168],"about":[169],"50%":[170],"with":[171],"only":[172],"around":[173],"3%":[174],"discrepancy":[175],"accuracy.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}