{"id":"https://openalex.org/W4399245887","doi":"https://doi.org/10.1007/s12559-024-10295-z","title":"Smart Data Driven Decision Trees Ensemble Methodology for Imbalanced Big Data","display_name":"Smart Data Driven Decision Trees Ensemble Methodology for Imbalanced Big Data","publication_year":2024,"publication_date":"2024-05-31","ids":{"openalex":"https://openalex.org/W4399245887","doi":"https://doi.org/10.1007/s12559-024-10295-z"},"language":"en","primary_location":{"id":"doi:10.1007/s12559-024-10295-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-024-10295-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-024-10295-z.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s12559-024-10295-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052686664","display_name":"Diego Garc\u00eda\u2010Gil","orcid":"https://orcid.org/0000-0002-1927-8673"},"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/I4210095677","display_name":"Instituto Andaluz de Ciencias de la Tierra","ror":"https://ror.org/00v0g9w49","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210095677"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Diego Garc\u00eda-Gil","raw_affiliation_strings":["Department of Software Engineering, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, 18071, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1927-8673","affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, 18071, Spain","institution_ids":["https://openalex.org/I173304897","https://openalex.org/I4210095677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078909305","display_name":"Salvador Garc\u00eda","orcid":"https://orcid.org/0000-0003-4494-7565"},"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/I4210095677","display_name":"Instituto Andaluz de Ciencias de la Tierra","ror":"https://ror.org/00v0g9w49","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210095677"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Salvador Garc\u00eda","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, 18071, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, 18071, Spain","institution_ids":["https://openalex.org/I173304897","https://openalex.org/I4210095677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102290471","display_name":"Ning Xiong","orcid":"https://orcid.org/0000-0001-9857-4317"},"institutions":[{"id":"https://openalex.org/I82509713","display_name":"M\u00e4lardalen University","ror":"https://ror.org/033vfbz75","country_code":"SE","type":"education","lineage":["https://openalex.org/I82509713"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ning Xiong","raw_affiliation_strings":["School of Innovation, Design and Engineering, M\u00e4lardalen University V\u00e4ster\u00e5s, V\u00e4ster\u00e5s, SE, 72123, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Innovation, Design and Engineering, M\u00e4lardalen University V\u00e4ster\u00e5s, V\u00e4ster\u00e5s, SE, 72123, Sweden","institution_ids":["https://openalex.org/I82509713"]}]},{"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/I4210095677","display_name":"Instituto Andaluz de Ciencias de la Tierra","ror":"https://ror.org/00v0g9w49","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210095677"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco Herrera","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, 18071, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, 18071, Spain","institution_ids":["https://openalex.org/I173304897","https://openalex.org/I4210095677"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052686664"],"corresponding_institution_ids":["https://openalex.org/I173304897","https://openalex.org/I4210095677"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.7011,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8572102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"16","issue":"4","first_page":"1572","last_page":"1588"},"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.797722578048706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.792775571346283},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7800809144973755},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6938970685005188},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.6020069718360901},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5945981740951538},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5752933025360107},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5671222805976868},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5486364364624023},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5369164347648621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5021998882293701},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4859522581100464},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.47264283895492554},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.44021496176719666}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.797722578048706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792775571346283},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7800809144973755},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6938970685005188},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6020069718360901},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5945981740951538},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5752933025360107},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5671222805976868},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5486364364624023},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5369164347648621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5021998882293701},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4859522581100464},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.47264283895492554},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44021496176719666},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s12559-024-10295-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-024-10295-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-024-10295-z.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},{"id":"pmh:oai:digibug.ugr.es:10481/93430","is_oa":true,"landing_page_url":"https://hdl.handle.net/10481/93430","pdf_url":"https://digibug.ugr.es/bitstream/10481/93430/1/s12559-024-10295-z.pdf","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"}],"best_oa_location":{"id":"doi:10.1007/s12559-024-10295-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-024-10295-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-024-10295-z.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4589309582","display_name":null,"funder_award_id":"2016-05431","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320323834","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399245887.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W619160221","https://openalex.org/W1986515506","https://openalex.org/W1993220166","https://openalex.org/W2061090972","https://openalex.org/W2096451472","https://openalex.org/W2099454382","https://openalex.org/W2125621954","https://openalex.org/W2155289277","https://openalex.org/W2169541495","https://openalex.org/W2171647935","https://openalex.org/W2305347498","https://openalex.org/W2593875029","https://openalex.org/W2612634114","https://openalex.org/W2615542577","https://openalex.org/W2617587433","https://openalex.org/W2756079035","https://openalex.org/W2764005395","https://openalex.org/W2790862734","https://openalex.org/W2800788706","https://openalex.org/W2802878531","https://openalex.org/W2806416578","https://openalex.org/W2895421615","https://openalex.org/W2899434936","https://openalex.org/W2938734733","https://openalex.org/W2955500452","https://openalex.org/W2963730760","https://openalex.org/W2979526564","https://openalex.org/W2989219518","https://openalex.org/W3094843711","https://openalex.org/W3104396725","https://openalex.org/W3112637742","https://openalex.org/W3113001100","https://openalex.org/W3113314792","https://openalex.org/W3160385040","https://openalex.org/W3166197191","https://openalex.org/W3194694505","https://openalex.org/W4226211505","https://openalex.org/W4243367342","https://openalex.org/W4243830291","https://openalex.org/W4246484440","https://openalex.org/W4381469969","https://openalex.org/W4386000021","https://openalex.org/W4386420847","https://openalex.org/W6614148910","https://openalex.org/W6637231022"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W3136871737","https://openalex.org/W3202554610","https://openalex.org/W4390860632","https://openalex.org/W2186437798","https://openalex.org/W138569904","https://openalex.org/W3021414116","https://openalex.org/W2756012949","https://openalex.org/W176219849","https://openalex.org/W2380699730"],"abstract_inverted_index":{"Abstract":[0],"Differences":[1],"in":[2,52,73,139,194],"data":[3,11,19,46,51,88,94,160,167],"size":[4],"per":[5],"class,":[6],"also":[7],"known":[8],"as":[9],"imbalanced":[10,30,87,136],"distribution,":[12],"have":[13,63,78,199],"become":[14],"a":[15,25,116,124],"common":[16],"problem":[17,138],"affecting":[18],"quality.":[20],"Big":[21,74,111,140],"Data":[22,75,91,112,127,141,185],"scenarios":[23],"pose":[24],"new":[26,65],"challenge":[27],"to":[28,38,57,81,84,93,98],"traditional":[29],"classification":[31,137],"algorithms,":[32],"since":[33],"they":[34],"are":[35],"not":[36],"prepared":[37],"work":[39],"with":[40],"such":[41],"amount":[42],"of":[43,50,60,95,104,153,187],"data.":[44,190],"Split":[45],"strategies":[47],"and":[48,106,177],"lack":[49],"the":[53,58,69,135,151,162,188],"minority":[54],"class":[55],"due":[56],"use":[59],"MapReduce":[61],"paradigm":[62],"posed":[64],"challenges":[66],"for":[67,133,161,181],"tackling":[68],"imbalance":[70],"between":[71],"classes":[72],"scenarios.":[76],"Ensembles":[77],"been":[79],"shown":[80,200],"be":[82,115],"able":[83],"successfully":[85],"address":[86],"problems.":[89],"Smart":[90,107,126,184],"refers":[92],"enough":[96],"quality":[97,159,166],"achieve":[99],"high-performance":[100],"models.":[101],"The":[102],"combination":[103],"ensembles":[105],"Data,":[108],"achieved":[109,169],"through":[110],"preprocessing,":[113],"should":[114],"great":[117],"synergy.":[118],"In":[119],"this":[120],"paper,":[121],"we":[122],"propose":[123],"novel":[125],"driven":[128],"Decision":[129],"Trees":[130],"Ensemble":[131],"methodology":[132,147,203],"addressing":[134],"domains,":[142],"namely":[143],"SD_DeTE":[144],"methodology.":[145],"This":[146,165],"is":[148,168],"based":[149],"on":[150],"learning":[152],"different":[154,183],"decision":[155],"trees":[156],"using":[157],"distributed":[158],"ensemble":[163],"process.":[164],"by":[170],"fusing":[171],"random":[172,179,205],"discretization,":[173],"principal":[174],"components":[175],"analysis,":[176],"clustering-based":[178],"oversampling":[180],"obtaining":[182],"versions":[186],"original":[189],"Experiments":[191],"carried":[192],"out":[193],"21":[195],"binary":[196],"adapted":[197],"datasets":[198],"that":[201],"our":[202],"outperforms":[204],"forest.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}