{"id":"https://openalex.org/W1660881198","doi":"https://doi.org/10.1109/nafips-wconsc.2015.7284158","title":"Distributed fuzzy rough prototype selection for Big Data regression","display_name":"Distributed fuzzy rough prototype selection for Big Data regression","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W1660881198","doi":"https://doi.org/10.1109/nafips-wconsc.2015.7284158","mag":"1660881198"},"language":"en","primary_location":{"id":"doi:10.1109/nafips-wconsc.2015.7284158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nafips-wconsc.2015.7284158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Annual Conference of the North American Fuzzy Information Processing Society (NAFIPS) held jointly with 2015 5th World Conference on Soft Computing (WConSC)","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/A5081322718","display_name":"Sarah Vluymans","orcid":"https://orcid.org/0000-0003-1782-8114"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210139803","display_name":"VIB-UGent Center for Inflammation Research","ror":"https://ror.org/04q4ydz28","country_code":"BE","type":"facility","lineage":["https://openalex.org/I2802017950","https://openalex.org/I32597200","https://openalex.org/I4210139803"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Sarah Vluymans","raw_affiliation_strings":["Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Gent, Belgium","VIB Inflammation Research Center, Zwijnaarde, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"VIB Inflammation Research Center, Zwijnaarde, Belgium","institution_ids":["https://openalex.org/I4210139803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079287389","display_name":"Hasan Asfoor","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasan Asfoor","raw_affiliation_strings":["Center for Data Science, University of Washington Tacoma, Tacoma, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, University of Washington Tacoma, Tacoma, USA","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001585713","display_name":"Yvan Saeys","orcid":"https://orcid.org/0000-0002-0415-1506"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210139803","display_name":"VIB-UGent Center for Inflammation Research","ror":"https://ror.org/04q4ydz28","country_code":"BE","type":"facility","lineage":["https://openalex.org/I2802017950","https://openalex.org/I32597200","https://openalex.org/I4210139803"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yvan Saeys","raw_affiliation_strings":["Department of Respiratory Medicine, Ghent University, Gent, Belgium","VIB Inflammation Research Center, Zwijnaarde, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Respiratory Medicine, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"VIB Inflammation Research Center, Zwijnaarde, Belgium","institution_ids":["https://openalex.org/I4210139803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091486233","display_name":"Chris Cornelis","orcid":"https://orcid.org/0000-0002-6852-4041"},"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"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE","ES"],"is_corresponding":false,"raw_author_name":"Chris Cornelis","raw_affiliation_strings":["Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Gent, Belgium","Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050252817","display_name":"Matthew E. Tolentino","orcid":"https://orcid.org/0000-0002-7407-2387"},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Tolentino","raw_affiliation_strings":["Center for Data Science, University of Washington Tacoma, Tacoma, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, University of Washington Tacoma, Tacoma, USA","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061359226","display_name":"Ankur Teredesai","orcid":"https://orcid.org/0000-0002-2112-5895"},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Teredesai","raw_affiliation_strings":["Center for Data Science, University of Washington Tacoma, Tacoma, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, University of Washington Tacoma, Tacoma, USA","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056749857","display_name":"Martine De Cock","orcid":"https://orcid.org/0000-0001-7917-0771"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["BE","US"],"is_corresponding":false,"raw_author_name":"Martine De Cock","raw_affiliation_strings":["Center for Data Science, University of Washington Tacoma, Tacoma, USA","Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Gent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, University of Washington Tacoma, Tacoma, USA","institution_ids":["https://openalex.org/I4210150356"]},{"raw_affiliation_string":"Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6661,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.61416913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/spark","display_name":"SPARK (programming language)","score":0.8207472562789917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8163087368011475},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7281008362770081},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5511908531188965},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5488810539245605},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5167369246482849},{"id":"https://openalex.org/keywords/symbolic-regression","display_name":"Symbolic regression","score":0.5120373368263245},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.49947524070739746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49842143058776855},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4574652314186096},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.41048139333724976},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.20003512501716614},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.1397366225719452},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09087568521499634}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8207472562789917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163087368011475},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7281008362770081},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5511908531188965},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5488810539245605},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5167369246482849},{"id":"https://openalex.org/C2776400721","wikidata":"https://www.wikidata.org/wiki/Q18171762","display_name":"Symbolic regression","level":3,"score":0.5120373368263245},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.49947524070739746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49842143058776855},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4574652314186096},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.41048139333724976},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.20003512501716614},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.1397366225719452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09087568521499634},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/nafips-wconsc.2015.7284158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nafips-wconsc.2015.7284158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Annual Conference of the North American Fuzzy Information Processing Society (NAFIPS) held jointly with 2015 5th World Conference on Soft Computing (WConSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:6936292","is_oa":false,"landing_page_url":"http://hdl.handle.net/1854/LU-6936292","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781467372480","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W6105805","https://openalex.org/W6351973","https://openalex.org/W1505837402","https://openalex.org/W1521417790","https://openalex.org/W1736726159","https://openalex.org/W1780013501","https://openalex.org/W1964930764","https://openalex.org/W1993369399","https://openalex.org/W1994155216","https://openalex.org/W2012497503","https://openalex.org/W2027654459","https://openalex.org/W2037178322","https://openalex.org/W2074005500","https://openalex.org/W2080135560","https://openalex.org/W2094188906","https://openalex.org/W2106692105","https://openalex.org/W2111034147","https://openalex.org/W2122111042","https://openalex.org/W2131975293","https://openalex.org/W2151537585","https://openalex.org/W2154879298","https://openalex.org/W2168185444","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2562544223","https://openalex.org/W4255833381","https://openalex.org/W6631500778","https://openalex.org/W6676599449","https://openalex.org/W6679815717","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2394133867","https://openalex.org/W280605544","https://openalex.org/W1567571923","https://openalex.org/W2176963978","https://openalex.org/W4319653604","https://openalex.org/W4389372248","https://openalex.org/W2844620057","https://openalex.org/W1694810529","https://openalex.org/W2615811837","https://openalex.org/W2075533215"],"abstract_inverted_index":{"Size":[0],"and":[1,109],"complexity":[2,110],"of":[3,71,111,121],"Big":[4],"Data":[5],"requires":[6],"advances":[7],"in":[8,98],"machine":[9,39],"learning":[10,40],"algorithms":[11,105],"to":[12,27,36,57],"adequately":[13],"learn":[14,58],"from":[15],"such":[16,29],"data.":[17],"While":[18],"distributed":[19,69,83,104],"shared-nothing":[20],"architectures":[21],"(Hadoop/Spark)":[22],"are":[23],"becoming":[24],"increasingly":[25],"popular":[26],"develop":[28],"new":[30,68],"algorithms,":[31],"it":[32],"is":[33,56,77],"quite":[34],"challenging":[35],"adapt":[37],"existing":[38],"algorithms.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"a":[47,67,81],"solution":[48],"for":[49,101],"big":[50],"data":[51],"regression,":[52],"where":[53],"the":[54,59,72,102,107,127],"aim":[55],"regression":[60,75,128],"model":[61],"over":[62],"large":[63],"high-dimensional":[64],"datasets.":[65],"First,":[66],"implementation":[70],"weighted":[73],"kNN":[74],"method":[76,86,125],"presented":[78],"followed":[79],"by":[80],"novel":[82],"prototype":[84,123],"selection":[85,124],"based":[87],"on":[88],"fuzzy":[89],"rough":[90],"set":[91],"theory.":[92],"Experiments":[93],"demonstrate":[94],"that":[95,119],"our":[96,122],"implementations":[97],"Apache":[99],"Spark":[100],"proposed":[103],"handle":[106],"size":[108],"modern":[112],"real-world":[113],"datasets":[114],"well.":[115],"We":[116],"furthermore":[117],"show":[118],"application":[120],"improves":[126],"accuracy.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}