{"id":"https://openalex.org/W2020858209","doi":"https://doi.org/10.1142/s0218213013500085","title":"SYNTHETIC OVERSAMPLING OF INSTANCES USING CLUSTERING","display_name":"SYNTHETIC OVERSAMPLING OF INSTANCES USING CLUSTERING","publication_year":2013,"publication_date":"2013-01-18","ids":{"openalex":"https://openalex.org/W2020858209","doi":"https://doi.org/10.1142/s0218213013500085","mag":"2020858209"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213013500085","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213013500085","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","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/A5016083962","display_name":"ATL\u00c1NTIDA I. S\u00c1NCHEZ","orcid":null},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"ATL\u00c1NTIDA I. S\u00c1NCHEZ","raw_affiliation_strings":["Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Computer Science Department, Luis Enrique Erro 1, 72840 Tonantzintla, M\u00e9xico"],"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Computer Science Department, Luis Enrique Erro 1, 72840 Tonantzintla, M\u00e9xico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035687300","display_name":"Eduardo F. Morales","orcid":"https://orcid.org/0000-0002-7618-8762"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"EDUARDO F. MORALES","raw_affiliation_strings":["Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Computer Science Department, Luis Enrique Erro 1, 72840 Tonantzintla, M\u00e9xico"],"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Computer Science Department, Luis Enrique Erro 1, 72840 Tonantzintla, M\u00e9xico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081730909","display_name":"Jes\u00fas A. Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-5232-4109"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"JESUS A. GONZALEZ","raw_affiliation_strings":["Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Computer Science Department, Luis Enrique Erro 1, 72840 Tonantzintla, M\u00e9xico"],"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Computer Science Department, Luis Enrique Erro 1, 72840 Tonantzintla, M\u00e9xico","institution_ids":["https://openalex.org/I39824353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016083962"],"corresponding_institution_ids":["https://openalex.org/I39824353"],"apc_list":null,"apc_paid":null,"fwci":0.4809,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.75269206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"22","issue":"02","first_page":"1350008","last_page":"1350008"},"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":0.9908000230789185,"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":0.9767000079154968,"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/oversampling","display_name":"Oversampling","score":0.980532705783844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8257009387016296},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6556168794631958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5813727378845215},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5714468955993652},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5205205678939819},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5161145925521851},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5067222714424133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44453415274620056},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.42279693484306335}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.980532705783844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8257009387016296},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6556168794631958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5813727378845215},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5714468955993652},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5205205678939819},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5161145925521851},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5067222714424133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44453415274620056},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.42279693484306335},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218213013500085","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213013500085","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321739","display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/059ex5q34"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W169052826","https://openalex.org/W171473080","https://openalex.org/W1498975220","https://openalex.org/W1551909886","https://openalex.org/W1696243063","https://openalex.org/W1819386543","https://openalex.org/W1941659294","https://openalex.org/W1966347128","https://openalex.org/W1993220166","https://openalex.org/W2022639046","https://openalex.org/W2040010062","https://openalex.org/W2053724458","https://openalex.org/W2058732827","https://openalex.org/W2084812512","https://openalex.org/W2119168155","https://openalex.org/W2126996952","https://openalex.org/W2132791018","https://openalex.org/W2148143831","https://openalex.org/W2155653793","https://openalex.org/W2163667253","https://openalex.org/W2163952039","https://openalex.org/W2966207845","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W4206637278","https://openalex.org/W2781247653","https://openalex.org/W4386005305","https://openalex.org/W3082051559","https://openalex.org/W1682621979","https://openalex.org/W4386214543","https://openalex.org/W1969988626","https://openalex.org/W3173198409","https://openalex.org/W2300921526"],"abstract_inverted_index":{"Imbalanced":[0],"data":[1],"sets":[2],"in":[3,79,187],"the":[4,23,55,72,101,141,181,193,196,201],"class":[5,57,81,169],"distribution":[6],"is":[7,98],"common":[8],"to":[9,18,31,87,100,178],"many":[10,15,188],"real":[11],"world":[12],"applications.":[13],"As":[14],"classifiers":[16,152],"tend":[17],"degrade":[19],"their":[20],"performance":[21],"over":[22],"minority":[24,56],"class,":[25],"several":[26],"approaches":[27,74],"have":[28],"been":[29],"proposed":[30,50,73,182],"deal":[32,120],"with":[33,68,122,132,157],"this":[34,37],"problem.":[35],"In":[36,66],"paper,":[38],"we":[39,149],"propose":[40],"two":[41,128],"new":[42,77,93,110],"cluster-based":[43],"oversampling":[44,70,197],"methods,":[45,71],"SOI-C":[46],"and":[47,59,117,124,136,153,161,175,186],"SOI-CJ.":[48],"The":[49,104,127],"methods":[51,111,129,183,198],"create":[52],"clusters":[53,105],"from":[54,140],"instances":[58,62,78,94],"generate":[60],"synthetic":[61],"inside":[63],"those":[64],"clusters.":[65],"contrast":[67],"other":[69],"avoid":[75],"creating":[76],"majority":[80],"regions.":[82],"They":[83],"are":[84,106,165,184],"more":[85,166],"robust":[86],"noisy":[88],"examples":[89],"(the":[90],"number":[91],"of":[92,195],"generated":[95],"per":[96],"cluster":[97],"proportional":[99],"cluster's":[102],"size).":[103],"automatically":[107],"generated.":[108],"Our":[109],"do":[112],"not":[113],"need":[114],"tuning":[115],"parameters,":[116],"they":[118],"can":[119],"both":[121],"numerical":[123],"nominal":[125],"attributes.":[126],"were":[130,155],"tested":[131],"twenty":[133,137],"artificial":[134],"datasets":[135,139],"three":[138],"UCI":[142],"Machine":[143],"Learning":[144],"repository.":[145],"For":[146],"our":[147],"experiments,":[148],"used":[150,199],"six":[151],"results":[154],"evaluated":[156],"recall,":[158],"precision,":[159],"F-measure,":[160],"AUC":[162],"measures,":[163],"which":[164],"suitable":[167],"for":[168],"imbalanced":[170],"datasets.":[171],"We":[172],"performed":[173],"ANOVA":[174],"paired":[176],"t-tests":[177],"show":[179],"that":[180],"competitive":[185],"cases":[189],"significantly":[190],"better":[191],"than":[192],"rest":[194],"during":[200],"comparison.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}