{"id":"https://openalex.org/W2009754619","doi":"https://doi.org/10.1145/2701126.2701181","title":"An over-sampling technique with rejection for imbalanced class learning","display_name":"An over-sampling technique with rejection for imbalanced class learning","publication_year":2015,"publication_date":"2015-01-08","ids":{"openalex":"https://openalex.org/W2009754619","doi":"https://doi.org/10.1145/2701126.2701181","mag":"2009754619"},"language":"en","primary_location":{"id":"doi:10.1145/2701126.2701181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2701126.2701181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-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/A5071444571","display_name":"Jae-Dong Lee","orcid":"https://orcid.org/0000-0001-9054-0091"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaedong Lee","raw_affiliation_strings":["Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea","Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea#TAB#"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea#TAB#","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085873189","display_name":"Noo-ri Kim","orcid":"https://orcid.org/0000-0002-7887-8396"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Noo-ri Kim","raw_affiliation_strings":["Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea","Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea#TAB#"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea#TAB#","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067651075","display_name":"Jee-Hyong Lee","orcid":"https://orcid.org/0000-0001-7242-7677"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jee-Hyong Lee","raw_affiliation_strings":["Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea","Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea#TAB#"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Sungkyunkwan University, Jangan-gu, Suwon, Gyeunggi-do, Republic of Korea#TAB#","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071444571"],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.75867715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.974399983882904,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9366000294685364,"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/oversampling","display_name":"Oversampling","score":0.9603382349014282},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9500076770782471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6803673505783081},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6437705159187317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6070736646652222},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5316904783248901},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4810483753681183},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.47034600377082825},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4677339494228363},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45567119121551514},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11733478307723999},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.057248324155807495}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9603382349014282},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9500076770782471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6803673505783081},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6437705159187317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6070736646652222},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5316904783248901},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4810483753681183},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.47034600377082825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4677339494228363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45567119121551514},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11733478307723999},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.057248324155807495},{"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2701126.2701181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2701126.2701181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1513874326","https://openalex.org/W1941659294","https://openalex.org/W1972104254","https://openalex.org/W2001935432","https://openalex.org/W2032922431","https://openalex.org/W2040010062","https://openalex.org/W2040181375","https://openalex.org/W2084812512","https://openalex.org/W2087240369","https://openalex.org/W2107516301","https://openalex.org/W2134927072","https://openalex.org/W2148143831","https://openalex.org/W2156909104"],"related_works":["https://openalex.org/W4389965896","https://openalex.org/W4387747402","https://openalex.org/W3119578451","https://openalex.org/W2152863486","https://openalex.org/W2300921526","https://openalex.org/W127528661","https://openalex.org/W123443654","https://openalex.org/W3055496383","https://openalex.org/W2903718012","https://openalex.org/W4322617773"],"abstract_inverted_index":{"Imbalanced":[0],"data":[1,10,107],"situation":[2],"is":[3,56,155],"that":[4,73],"there":[5,37],"are":[6,38,81,87],"unequal":[7],"distributions":[8],"of":[9,42,50,76,127,145],"samples":[11,35,62,114,167],"between":[12],"different":[13],"classes.":[14],"It":[15],"usually":[16],"poses":[17],"a":[18,99],"challenge":[19],"to":[20,28,46,57,118,158,160],"any":[21],"classification":[22],"methods":[23],"as":[24,168,170],"it":[25,90,122],"becomes":[26],"hard":[27],"learn":[29],"and":[30,78,115],"predict":[31],"the":[32,74,125,128,138,143,171],"minority":[33,43,65],"class":[34,54],"since":[36],"too":[39],"small":[40],"number":[41],"instances":[44,66,80],"compare":[45],"majority":[47],"instances.":[48],"One":[49],"approaches":[51,173],"for":[52,103,164,174],"imbalanced":[53,106,148],"problems":[55],"oversample":[58],"by":[59,123],"generating":[60,165],"synthetic":[61,113,129,166],"around":[63],"given":[64],"based":[67],"on":[68],"their":[69],"nearest":[70,85,162],"neighbors,":[71],"so":[72],"numbers":[75],"major":[77],"minor":[79],"balanced.":[82],"However,":[83],"if":[84],"neighbors":[86,163],"wrongly":[88],"chosen,":[89],"may":[91],"cause":[92],"overfitting":[93],"or":[94,120],"underfitting":[95],"problems.":[96,108],"We":[97],"propose":[98],"novel":[100],"oversampling":[101],"method":[102,111,154],"efficiently":[104],"handling":[105],"Our":[109],"proposed":[110,133,153],"generates":[112],"decides":[116],"whether":[117],"reject":[119],"accept":[121],"considering":[124],"location":[126],"samples.":[130],"With":[131],"our":[132,152],"method,":[134],"we":[135],"have":[136],"observed":[137],"outperformed":[139],"results":[140],"obtained":[141],"within":[142],"framework":[144],"real":[146],"world":[147],"datasets.":[149],"In":[150],"addition,":[151],"not":[156],"sensitive":[157],"how":[159],"choose":[161],"much":[169],"existing":[172],"imbalance":[175],"problem.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}