{"id":"https://openalex.org/W3021330142","doi":"https://doi.org/10.1109/access.2020.2991800","title":"Redundancy and Complexity Metrics for Big Data Classification: Towards Smart Data","display_name":"Redundancy and Complexity Metrics for Big Data Classification: Towards Smart Data","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3021330142","doi":"https://doi.org/10.1109/access.2020.2991800","mag":"3021330142"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2991800","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2991800","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09083972.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09083972.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012082459","display_name":"Jes\u00fas Maillo","orcid":"https://orcid.org/0000-0002-7520-9496"},"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":"Jesus Maillo","raw_affiliation_strings":["The Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0002-7520-9496","affiliations":[{"raw_affiliation_string":"The 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/A5075541426","display_name":"Isaac Triguero","orcid":"https://orcid.org/0000-0002-0150-0651"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Isaac Triguero","raw_affiliation_strings":["Computational Optimisation and Learning Lab (COL), School of Computer Science, University of Nottingham, Nottingham, U.K"],"raw_orcid":"https://orcid.org/0000-0002-0150-0651","affiliations":[{"raw_affiliation_string":"Computational Optimisation and Learning Lab (COL), School of Computer Science, University of Nottingham, Nottingham, U.K","institution_ids":["https://openalex.org/I142263535"]}]},{"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"]},{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["ES","SA"],"is_corresponding":false,"raw_author_name":"Francisco Herrera","raw_affiliation_strings":["Faculty of Computing and Information Technology, King Abdulaziz University (KAU), Jeddah, Saudi Arabia","The Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0002-7283-312X","affiliations":[{"raw_affiliation_string":"Faculty of Computing and Information Technology, King Abdulaziz University (KAU), Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]},{"raw_affiliation_string":"The Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.9495,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.92585042,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"8","issue":null,"first_page":"87918","last_page":"87928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9991000294685364,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9991000294685364,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9932000041007996,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8381408452987671},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8164266347885132},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6047614216804504},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6020645499229431},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.56548011302948},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5104231238365173},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.5056712627410889},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4636462926864624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4472200572490692},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4378068447113037},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.43696317076683044},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4265413284301758},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11255910992622375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381408452987671},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8164266347885132},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6047614216804504},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6020645499229431},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.56548011302948},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5104231238365173},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.5056712627410889},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4636462926864624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4472200572490692},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4378068447113037},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.43696317076683044},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4265413284301758},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11255910992622375},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2020.2991800","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2991800","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09083972.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:digibug.ugr.es:10481/62787","is_oa":true,"landing_page_url":"http://hdl.handle.net/10481/62787","pdf_url":null,"source":{"id":"https://openalex.org/S4306400567","display_name":"Institutional Repository of the University of Granada (University of Granada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173304897","host_organization_name":"Universidad de Granada","host_organization_lineage":["https://openalex.org/I173304897"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:158d65c5dc964a02aee51404507a4809","is_oa":true,"landing_page_url":"https://doaj.org/article/158d65c5dc964a02aee51404507a4809","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 87918-87928 (2020)","raw_type":"article"},{"id":"pmh:oai:nottingham-repository.worktribe.com:4429552","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/4429552","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2991800","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2991800","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09083972.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3021330142.pdf","grobid_xml":"https://content.openalex.org/works/W3021330142.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W91088564","https://openalex.org/W410850256","https://openalex.org/W575847903","https://openalex.org/W1569704244","https://openalex.org/W1575103269","https://openalex.org/W1593345689","https://openalex.org/W1766594731","https://openalex.org/W1964402642","https://openalex.org/W1990165991","https://openalex.org/W2003984511","https://openalex.org/W2082302018","https://openalex.org/W2102861780","https://openalex.org/W2112693458","https://openalex.org/W2122111042","https://openalex.org/W2131975293","https://openalex.org/W2157355837","https://openalex.org/W2162210260","https://openalex.org/W2344842694","https://openalex.org/W2398841771","https://openalex.org/W2432436793","https://openalex.org/W2510026128","https://openalex.org/W2527889223","https://openalex.org/W2555986604","https://openalex.org/W2560528144","https://openalex.org/W2620975687","https://openalex.org/W2884090605","https://openalex.org/W2897069058","https://openalex.org/W2902777483","https://openalex.org/W2902834302","https://openalex.org/W2945790622","https://openalex.org/W2963288913","https://openalex.org/W2964219830","https://openalex.org/W2969219550","https://openalex.org/W2973136425","https://openalex.org/W2979526564","https://openalex.org/W3120740533","https://openalex.org/W4213308398","https://openalex.org/W4243367342","https://openalex.org/W6614148910","https://openalex.org/W6634075551","https://openalex.org/W6635749033","https://openalex.org/W6675382462","https://openalex.org/W6679815717","https://openalex.org/W6704576650"],"related_works":["https://openalex.org/W4205206396","https://openalex.org/W2053247611","https://openalex.org/W2965693718","https://openalex.org/W1618196697","https://openalex.org/W2155850863","https://openalex.org/W4210628983","https://openalex.org/W2368866852","https://openalex.org/W2623725391","https://openalex.org/W4391079262","https://openalex.org/W2756012949"],"abstract_inverted_index":{"It":[0],"is":[1],"recognized":[2],"the":[3,7,22,56,59,131,182,188,191,195,211],"importance":[4],"of":[5,10,27,58,99,130,139,171,181,190,210,213],"knowing":[6],"descriptive":[8],"properties":[9],"a":[11,15,28,97,137,168,204,207,214],"dataset":[12,216],"when":[13,77],"tackling":[14],"data":[16,38,103,113,154,198,221],"science":[17],"problem.":[18],"Having":[19],"information":[20,172],"about":[21],"redundancy,":[23],"complexity":[24],"and":[25,40,117,124],"density":[26,123],"problem":[29],"allows":[30],"us":[31],"to":[32,36,54,142,218],"make":[33],"decisions":[34],"as":[35,203],"which":[37,121,200],"preprocessing":[39],"machine":[41],"learning":[42],"techniques":[43],"are":[44,51,201],"most":[45,174],"suitable.":[46],"In":[47,92,106,133],"classification":[48,104,155,215],"problems,":[49],"there":[50],"multiple":[52],"metrics":[53,71,100,141,160],"describe":[55],"overlapping":[57],"features":[60],"between":[61],"classes,":[62],"class":[63],"imbalances":[64],"or":[65,82],"separability,":[66],"among":[67],"others.":[68],"However,":[69],"these":[70],"may":[72,83],"not":[73,84,185],"scale":[74],"up":[75],"well":[76],"dealing":[78],"with":[79],"big":[80,102,112,144,153,164,197,220],"datasets,":[81,175],"simply":[85],"be":[86],"sufficiently":[87],"informative":[88],"in":[89,151,173],"this":[90,93],"context.":[91],"paper,":[94],"we":[95,108,135],"provide":[96,206],"package":[98],"for":[101],"problems.":[105],"particular,":[107],"propose":[109],"two":[110],"new":[111],"metrics:":[114],"Neighborhood":[115],"Density":[116],"Decision":[118],"Tree":[119],"Progression,":[120],"study":[122,148],"accuracy":[125,189],"progression":[126],"by":[127],"discarding":[128,178],"half":[129],"samples.":[132],"addition,":[134],"enable":[136],"number":[138],"basic":[140],"handle":[143],"data.":[145,225],"The":[146],"experimental":[147],"carried":[149],"out":[150],"standard":[152],"problems":[156],"shows":[157],"that":[158],"our":[159],"can":[161],"quickly":[162],"characterize":[163],"datasets.":[165],"We":[166],"identified":[167],"clear":[169],"redundancy":[170],"so":[176],"that,":[177],"randomly":[179],"75%":[180],"samples":[183],"does":[184],"drastically":[186],"affect":[187],"classifiers":[192],"used.":[193],"Thus,":[194],"proposed":[196],"metrics,":[199],"available":[202],"Spark-Package,":[205],"fast":[208],"assessment":[209],"shape":[212],"prior":[217],"applying":[219],"preprocessing,":[222],"toward":[223],"smart":[224]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2020-05-13T00:00:00"}