{"id":"https://openalex.org/W2027678871","doi":"https://doi.org/10.1109/tsmcb.2012.2206381","title":"OligoIS: Scalable Instance Selection for Class-Imbalanced Data Sets","display_name":"OligoIS: Scalable Instance Selection for Class-Imbalanced Data Sets","publication_year":2012,"publication_date":"2012-07-30","ids":{"openalex":"https://openalex.org/W2027678871","doi":"https://doi.org/10.1109/tsmcb.2012.2206381","mag":"2027678871","pmid":"https://pubmed.ncbi.nlm.nih.gov/22868583"},"language":"en","primary_location":{"id":"doi:10.1109/tsmcb.2012.2206381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2012.2206381","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5011401194","display_name":"Nicol\u00e1s Garc\u00eda\u2010Pedrajas","orcid":"https://orcid.org/0000-0002-4488-6849"},"institutions":[{"id":"https://openalex.org/I53110688","display_name":"University of C\u00f3rdoba","ror":"https://ror.org/05yc77b46","country_code":"ES","type":"education","lineage":["https://openalex.org/I53110688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nicolas Garcia-Pedrajas","raw_affiliation_strings":["Department of Computing and Numerical Analysis, University of C\u00f3rdoba, C\u00f3rdoba, Spain","Dept. of Comput. & Numerical Anal, Univ. of Cordoba, Cordoba, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Numerical Analysis, University of C\u00f3rdoba, C\u00f3rdoba, Spain","institution_ids":["https://openalex.org/I53110688"]},{"raw_affiliation_string":"Dept. of Comput. & Numerical Anal, Univ. of Cordoba, Cordoba, Spain","institution_ids":["https://openalex.org/I53110688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043133854","display_name":"Javier P\u00e9rez-Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-0437-3264"},"institutions":[{"id":"https://openalex.org/I53110688","display_name":"University of C\u00f3rdoba","ror":"https://ror.org/05yc77b46","country_code":"ES","type":"education","lineage":["https://openalex.org/I53110688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier P\u00e9rez-Rodr\u00edguez","raw_affiliation_strings":["Department of Computing and Numerical Analysis, University of C\u00f3rdoba, C\u00f3rdoba, Spain","Dept. of Comput. & Numerical Anal, Univ. of Cordoba, Cordoba, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Numerical Analysis, University of C\u00f3rdoba, C\u00f3rdoba, Spain","institution_ids":["https://openalex.org/I53110688"]},{"raw_affiliation_string":"Dept. of Comput. & Numerical Anal, Univ. of Cordoba, Cordoba, Spain","institution_ids":["https://openalex.org/I53110688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009177503","display_name":"Aida de Haro-Garc\u00eda","orcid":"https://orcid.org/0000-0003-0194-8082"},"institutions":[{"id":"https://openalex.org/I53110688","display_name":"University of C\u00f3rdoba","ror":"https://ror.org/05yc77b46","country_code":"ES","type":"education","lineage":["https://openalex.org/I53110688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Aida de Haro-Garc\u00eda","raw_affiliation_strings":["Department of Computing and Numerical Analysis, University of C\u00f3rdoba, C\u00f3rdoba, Spain","Dept. of Comput. & Numerical Anal, Univ. of Cordoba, Cordoba, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Numerical Analysis, University of C\u00f3rdoba, C\u00f3rdoba, Spain","institution_ids":["https://openalex.org/I53110688"]},{"raw_affiliation_string":"Dept. of Comput. & Numerical Anal, Univ. of Cordoba, Cordoba, Spain","institution_ids":["https://openalex.org/I53110688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I53110688"],"apc_list":null,"apc_paid":null,"fwci":6.6461,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96540959,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"43","issue":"1","first_page":"332","last_page":"346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9950000047683716,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8238722085952759},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7527291774749756},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6807953119277954},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6798490881919861},{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.6701265573501587},{"id":"https://openalex.org/keywords/intrusion-detection-system","display_name":"Intrusion detection system","score":0.5607231855392456},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5309922695159912},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49945616722106934},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4520712196826935},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4038398265838623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34817230701446533},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15563473105430603},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12214076519012451}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238722085952759},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7527291774749756},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6807953119277954},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6798490881919861},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.6701265573501587},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.5607231855392456},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5309922695159912},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49945616722106934},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4520712196826935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4038398265838623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34817230701446533},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15563473105430603},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12214076519012451},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsmcb.2012.2206381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2012.2206381","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:22868583","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22868583","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W85350352","https://openalex.org/W110352429","https://openalex.org/W142793689","https://openalex.org/W149995340","https://openalex.org/W1499706286","https://openalex.org/W1515481915","https://openalex.org/W1565746575","https://openalex.org/W1574715085","https://openalex.org/W1591261915","https://openalex.org/W1974079881","https://openalex.org/W1986515506","https://openalex.org/W1993220166","https://openalex.org/W1994410331","https://openalex.org/W2023639956","https://openalex.org/W2076817280","https://openalex.org/W2107686700","https://openalex.org/W2115629999","https://openalex.org/W2118978333","https://openalex.org/W2119051895","https://openalex.org/W2119479037","https://openalex.org/W2122496402","https://openalex.org/W2125055259","https://openalex.org/W2128140306","https://openalex.org/W2135547590","https://openalex.org/W2138770315","https://openalex.org/W2145279172","https://openalex.org/W2148143831","https://openalex.org/W2158724449","https://openalex.org/W2162583212","https://openalex.org/W2166106466","https://openalex.org/W2979832949","https://openalex.org/W3120740533","https://openalex.org/W3141481736","https://openalex.org/W4230674625","https://openalex.org/W4285719527","https://openalex.org/W6603460400","https://openalex.org/W6605806949","https://openalex.org/W6635474240"],"related_works":["https://openalex.org/W1486246673","https://openalex.org/W2364921833","https://openalex.org/W1525643724","https://openalex.org/W2961085424","https://openalex.org/W2067938758","https://openalex.org/W2382623646","https://openalex.org/W2383698455","https://openalex.org/W2366221835","https://openalex.org/W1543345676","https://openalex.org/W1971595496"],"abstract_inverted_index":{"In":[0,82],"current":[1],"research,":[2],"an":[3],"enormous":[4],"amount":[5],"of":[6,21,50,65,105,109,122,129,140,185,205,210,214],"information":[7],"is":[8,97,113,150],"constantly":[9],"being":[10],"produced,":[11],"which":[12],"poses":[13],"a":[14,87,155],"challenge":[15],"for":[16,58,190],"data":[17,45,62,75,100,132,165,173,192,198],"mining":[18],"algorithms.":[19],"Many":[20],"the":[22,40,72,93,116,123,130,138,141,147,163,183,203],"problems":[23],"in":[24,143],"extremely":[25],"active":[26],"research":[27,80],"areas,":[28],"such":[29],"as":[30],"bioinformatics,":[31],"security":[32],"and":[33,47,107,158,212],"intrusion":[34],"detection,":[35],"or":[36],"text":[37],"mining,":[38],"share":[39],"following":[41],"two":[42],"features:":[43],"large":[44,74,197],"sets":[46,76,101],"class-imbalanced":[48,61,171,191],"distribution":[49],"samples.":[51],"Although":[52],"many":[53,103],"methods":[54,67,189],"have":[55],"been":[56],"proposed":[57,148],"dealing":[59,91],"with":[60,92,102,120],"sets,":[63,174,199],"most":[64],"these":[66],"are":[68],"not":[69],"scalable":[70,98],"to":[71,78,90,99,126,152,181,208],"very":[73,196],"common":[77],"those":[79],"fields.":[81],"this":[83],"paper,":[84],"we":[85,175,200],"propose":[86],"new":[88],"approach":[89],"class-imbalance":[94],"problem":[95],"that":[96],"millions":[104,209],"instances":[106,211],"hundreds":[108,213],"features.":[110,215],"This":[111,134],"proposal":[112,207],"based":[114],"on":[115],"divide-and-conquer":[117,135],"principle":[118,136],"combined":[119],"application":[121],"selection":[124,188],"process":[125],"balanced":[127],"subsets":[128],"whole":[131,164],"set.":[133],"allows":[137],"execution":[139],"algorithm":[142],"linear":[144],"time.":[145],"Furthermore,":[146],"method":[149],"easy":[151],"implement":[153],"using":[154],"parallel":[156],"environment":[157],"can":[159],"work":[160],"without":[161],"loading":[162],"set":[166],"into":[167],"memory.":[168],"Using":[169,194],"40":[170],"medium-sized":[172],"will":[176,201],"demonstrate":[177],"our":[178,206],"method's":[179],"ability":[180],"improve":[182],"results":[184],"state-of-the-art":[186],"instance":[187],"sets.":[193],"three":[195],"show":[202],"scalability":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}