{"id":"https://openalex.org/W2537734429","doi":"https://doi.org/10.1109/tsmc.2017.2670926","title":"An Information Theory-Based Feature Selection Framework for Big Data Under Apache Spark","display_name":"An Information Theory-Based Feature Selection Framework for Big Data Under Apache Spark","publication_year":2017,"publication_date":"2017-07-06","ids":{"openalex":"https://openalex.org/W2537734429","doi":"https://doi.org/10.1109/tsmc.2017.2670926","mag":"2537734429"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2017.2670926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2017.2670926","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","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/A5004213897","display_name":"Sergio Ram\u00edrez\u2010Gallego","orcid":"https://orcid.org/0000-0003-4804-5884"},"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":"Sergio Ramirez-Gallego","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, CITIC-UGR, University of Granada, Granada, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, CITIC-UGR, University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074987169","display_name":"H\u00e9ctor Mouri\u00f1o\u2010Tal\u00edn","orcid":null},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Hector Mourino-Talin","raw_affiliation_strings":["Department of Computer Science, University of Corunna, Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Corunna, Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047411888","display_name":"David Mart\u00ednez\u2010Rego","orcid":null},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Martinez-Rego","raw_affiliation_strings":["Department of Computer Science, University of Corunna, Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Corunna, Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042436168","display_name":"Ver\u00f3nica Bol\u00f3n\u2010Canedo","orcid":"https://orcid.org/0000-0002-0524-6427"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Veronica Bolon-Canedo","raw_affiliation_strings":["Department of Computer Science, University of Corunna, Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Corunna, Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"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, University of Granada, Granada, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, CITIC-UGR, University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048207145","display_name":"Amparo Alonso\u2010Betanzos","orcid":"https://orcid.org/0000-0003-0950-0012"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Amparo Alonso-Betanzos","raw_affiliation_strings":["Department of Computer Science, University of Corunna, Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Corunna, Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"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, University of Granada, Granada, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, CITIC-UGR, University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004213897"],"corresponding_institution_ids":["https://openalex.org/I173304897"],"apc_list":null,"apc_paid":null,"fwci":4.7173,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.96954692,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"48","issue":"9","first_page":"1441","last_page":"1453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10057","display_name":"Face and Expression Recognition","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9975000023841858,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8734472990036011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7835674285888672},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7333582639694214},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7170562148094177},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6275171041488647},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5695674419403076},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.542682945728302},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5305433869361877},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5133739709854126},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.46769025921821594},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43555355072021484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38448551297187805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3542212247848511}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8734472990036011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7835674285888672},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7333582639694214},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7170562148094177},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6275171041488647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5695674419403076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.542682945728302},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5305433869361877},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5133739709854126},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.46769025921821594},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43555355072021484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38448551297187805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3542212247848511},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2017.2670926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2017.2670926","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2716201042","display_name":null,"funder_award_id":"POS-A/2013/196","funder_id":"https://openalex.org/F4320326655","funder_display_name":"Xunta de Galicia"},{"id":"https://openalex.org/G8659582199","display_name":null,"funder_award_id":"ED481B 2014/164-0","funder_id":"https://openalex.org/F4320326655","funder_display_name":"Xunta de Galicia"}],"funders":[{"id":"https://openalex.org/F4320326655","display_name":"Xunta de Galicia","ror":"https://ror.org/0181xnw06"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W53188351","https://openalex.org/W323404752","https://openalex.org/W410850256","https://openalex.org/W593443143","https://openalex.org/W1485408073","https://openalex.org/W2008056655","https://openalex.org/W2017337590","https://openalex.org/W2035593643","https://openalex.org/W2040884411","https://openalex.org/W2046864590","https://openalex.org/W2052164429","https://openalex.org/W2054804336","https://openalex.org/W2055233384","https://openalex.org/W2099111195","https://openalex.org/W2119387367","https://openalex.org/W2142594886","https://openalex.org/W2143789272","https://openalex.org/W2149772057","https://openalex.org/W2153635508","https://openalex.org/W2154053567","https://openalex.org/W2156504490","https://openalex.org/W2166445532","https://openalex.org/W2169541495","https://openalex.org/W2171647935","https://openalex.org/W2173213060","https://openalex.org/W2181744257","https://openalex.org/W2198041540","https://openalex.org/W2293600471","https://openalex.org/W2478708596","https://openalex.org/W2963288913","https://openalex.org/W2995564009","https://openalex.org/W2998216295","https://openalex.org/W3120740533","https://openalex.org/W4205699531","https://openalex.org/W4285719527","https://openalex.org/W6614148910","https://openalex.org/W6682686508","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W1484111231","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W20047544","https://openalex.org/W3089231081","https://openalex.org/W2093956241"],"abstract_inverted_index":{"With":[0],"the":[1,15,120,125],"advent":[2],"of":[3,23,72,82,93,103,117],"extremely":[4],"high":[5],"dimensional":[6],"datasets,":[7],"dimensionality":[8],"reduction":[9],"techniques":[10,17],"are":[11],"becoming":[12],"mandatory.":[13],"Of":[14],"many":[16],"available,":[18],"feature":[19],"selection":[20],"(FS)":[21],"is":[22,101],"growing":[24],"interest":[25],"for":[26,89],"its":[27],"ability":[28],"to":[29,43,61],"identify":[30],"both":[31,63],"relevant":[32],"features":[33],"and":[34,65],"frequently":[35],"repeated":[36],"instances":[37],"in":[38,52,123],"huge":[39,115],"datasets.":[40],"We":[41,67],"aim":[42],"demonstrate":[44],"that":[45,77,97],"standard":[46],"FS":[47,75],"methods":[48],"can":[49],"be":[50],"parallelized":[51],"big":[53],"data":[54],"platforms":[55],"like":[56],"Apache":[57],"Spark":[58],"so":[59],"as":[60,109,111],"boost":[62],"performance":[64],"accuracy.":[66],"propose":[68],"a":[69,73,79,90,114],"distributed":[70,99],"implementation":[71],"generic":[74],"framework":[76,100],"includes":[78],"broad":[80,91],"group":[81],"well-known":[83],"information":[84],"theory-based":[85],"methods.":[86],"Experimental":[87],"results":[88],"set":[92],"real-world":[94],"datasets":[95,108],"show":[96],"our":[98],"capable":[102],"rapidly":[104],"dealing":[105],"with":[106,113],"ultrahigh-dimensional":[107],"well":[110],"those":[112],"number":[116],"samples,":[118],"outperforming":[119],"sequential":[121],"version":[122],"all":[124],"cases":[126],"studied.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}