{"id":"https://openalex.org/W2184648260","doi":"https://doi.org/10.1109/trustcom.2015.579","title":"Analysis of Data Preprocessing Increasing the Oversampling Ratio for Extremely Imbalanced Big Data Classification","display_name":"Analysis of Data Preprocessing Increasing the Oversampling Ratio for Extremely Imbalanced Big Data Classification","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2184648260","doi":"https://doi.org/10.1109/trustcom.2015.579","mag":"2184648260"},"language":"en","primary_location":{"id":"doi:10.1109/trustcom.2015.579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/trustcom.2015.579","pdf_url":null,"source":{"id":"https://openalex.org/S4363605531","display_name":"2015 IEEE Trustcom/BigDataSE/ISPA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Trustcom/BigDataSE/ISPA","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/A5054196705","display_name":"Sara del R\u00edo","orcid":"https://orcid.org/0000-0002-2382-9765"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Sara del Rio","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, CITIC-UGR (Res. Center on Inf. & Commun. Technol.), University of Granada, Granada, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, CITIC-UGR (Res. Center on Inf. & Commun. Technol.), University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089237494","display_name":"Jos\u00e9 M. Ben\u00edtez","orcid":"https://orcid.org/0000-0002-2346-0793"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose Manuel Benitez","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, CITIC-UGR (Res. Center on Inf. & Commun. Technol.), University of Granada, Granada, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, CITIC-UGR (Res. Center on Inf. & Commun. Technol.), University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045016749","display_name":"Francisco Herrera","orcid":"https://orcid.org/0000-0002-7283-312X"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco Herrera","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, CITIC-UGR (Res. Center on Inf. & Commun. Technol.), University of Granada, Granada, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, CITIC-UGR (Res. Center on Inf. & Commun. Technol.), University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054196705"],"corresponding_institution_ids":["https://openalex.org/I173304897"],"apc_list":null,"apc_paid":null,"fwci":2.5807,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.90844794,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"285","issue":null,"first_page":"180","last_page":"185"},"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":0.9958999752998352,"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":0.9952999949455261,"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/big-data","display_name":"Big data","score":0.8050810098648071},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.784885048866272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7577648162841797},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6377116441726685},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5786535143852234},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5660977363586426},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5115652680397034},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5076562166213989},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4965711236000061},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4962790608406067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47651970386505127},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.471280038356781}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8050810098648071},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.784885048866272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577648162841797},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6377116441726685},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5786535143852234},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5660977363586426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5115652680397034},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5076562166213989},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4965711236000061},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4962790608406067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47651970386505127},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.471280038356781},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/trustcom.2015.579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/trustcom.2015.579","pdf_url":null,"source":{"id":"https://openalex.org/S4363605531","display_name":"2015 IEEE Trustcom/BigDataSE/ISPA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Trustcom/BigDataSE/ISPA","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W619160221","https://openalex.org/W1485408073","https://openalex.org/W1505837402","https://openalex.org/W1530955034","https://openalex.org/W1965895350","https://openalex.org/W2040263621","https://openalex.org/W2045042261","https://openalex.org/W2063364984","https://openalex.org/W2088059023","https://openalex.org/W2107498970","https://openalex.org/W2114968414","https://openalex.org/W2118978333","https://openalex.org/W2164330572","https://openalex.org/W2171647935","https://openalex.org/W2173213060","https://openalex.org/W2995564009","https://openalex.org/W6630303302"],"related_works":["https://openalex.org/W2012117566","https://openalex.org/W2985634157","https://openalex.org/W1981856929","https://openalex.org/W2989490741","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3092506759","https://openalex.org/W138569904","https://openalex.org/W3010890513"],"abstract_inverted_index":{"The":[0,33,135,167],"\"big":[1],"data\"":[2],"term":[3,18],"has":[4,140],"caught":[5],"the":[6,11,23,79,99,117,120,132,152,162,179,185],"attention":[7],"of":[8,13,28,35,74,82,84,91,101,119,137],"experts":[9],"in":[10,113,143,161,181],"context":[12],"learning":[14],"from":[15,45],"data.":[16],"This":[17,94],"is":[19,96,148,172],"used":[20,160],"to":[21,78,115,174,183],"describe":[22],"exponential":[24],"growth":[25],"and":[26,31,41],"availability":[27],"data":[29,47,129,156],"(structured":[30],"unstructured).":[32],"design":[34],"effective":[36],"models":[37],"that":[38,147,158,171],"can":[39],"process":[40],"extract":[42],"useful":[43],"knowledge":[44],"these":[46],"represents":[48],"a":[49,60,71,111,176],"immense":[50],"challenge.":[51],"Focusing":[52],"on":[53],"classification":[54,102],"problems,":[55],"many":[56],"real-world":[57],"applications":[58],"present":[59],"class":[61,122],"distribution":[62],"where":[63],"one":[64],"or":[65],"more":[66],"classes":[67,180],"are":[68,88],"represented":[69],"by":[70],"large":[72],"number":[73,81],"examples":[75,83],"with":[76,103,125],"respect":[77],"negligible":[80],"other":[85],"classes,":[86],"which":[87],"precisely":[89],"those":[90],"primary":[92],"interest.":[93],"circumstance":[95],"known":[97],"as":[98],"problem":[100,157],"imbalanced":[104,127,154],"datasets.":[105],"In":[106],"this":[107],"work,":[108],"we":[109],"analyze":[110],"hypothesis":[112],"order":[114,182],"increment":[116],"accuracy":[118],"underrepresented":[121],"when":[123],"dealing":[124],"extremely":[126,153],"big":[128,155],"problems":[130],"under":[131],"MapReduce":[133],"framework.":[134],"performance":[136],"our":[138],"solution":[139],"been":[141],"analyzed":[142],"an":[144],"experimental":[145],"study":[146],"carried":[149],"out":[150],"over":[151],"was":[159],"ECBDL'14":[163],"Big":[164],"Data":[165],"Competition.":[166],"results":[168],"obtained":[169],"show":[170],"necessary":[173],"find":[175],"balance":[177],"between":[178],"obtain":[184],"highest":[186],"precision.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}