{"id":"https://openalex.org/W4394879596","doi":"https://doi.org/10.3390/info15040223","title":"An Extensive Performance Comparison between Feature Reduction and Feature Selection Preprocessing Algorithms on Imbalanced Wide Data","display_name":"An Extensive Performance Comparison between Feature Reduction and Feature Selection Preprocessing Algorithms on Imbalanced Wide Data","publication_year":2024,"publication_date":"2024-04-16","ids":{"openalex":"https://openalex.org/W4394879596","doi":"https://doi.org/10.3390/info15040223"},"language":"en","primary_location":{"id":"doi:10.3390/info15040223","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15040223","pdf_url":"https://www.mdpi.com/2078-2489/15/4/223/pdf?version=1713276477","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/15/4/223/pdf?version=1713276477","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031727759","display_name":"Ismael Ramos\u2010P\u00e9rez","orcid":"https://orcid.org/0000-0002-0330-1605"},"institutions":[{"id":"https://openalex.org/I46176106","display_name":"Universidad de Burgos","ror":"https://ror.org/049da5t36","country_code":"ES","type":"education","lineage":["https://openalex.org/I46176106"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ismael Ramos-P\u00e9rez","raw_affiliation_strings":["Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain","institution_ids":["https://openalex.org/I46176106"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039605195","display_name":"Jos\u00e9 A. Barbero\u2010Aparicio","orcid":"https://orcid.org/0000-0002-3269-0806"},"institutions":[{"id":"https://openalex.org/I46176106","display_name":"Universidad de Burgos","ror":"https://ror.org/049da5t36","country_code":"ES","type":"education","lineage":["https://openalex.org/I46176106"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Antonio Barbero-Aparicio","raw_affiliation_strings":["Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain","institution_ids":["https://openalex.org/I46176106"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016056338","display_name":"Antonio Canepa","orcid":"https://orcid.org/0000-0002-0608-2743"},"institutions":[{"id":"https://openalex.org/I46176106","display_name":"Universidad de Burgos","ror":"https://ror.org/049da5t36","country_code":"ES","type":"education","lineage":["https://openalex.org/I46176106"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Canepa-Oneto","raw_affiliation_strings":["Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain","institution_ids":["https://openalex.org/I46176106"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020290167","display_name":"\u00c1lvar Arnaiz\u2010Gonz\u00e1lez","orcid":"https://orcid.org/0000-0001-6965-0237"},"institutions":[{"id":"https://openalex.org/I46176106","display_name":"Universidad de Burgos","ror":"https://ror.org/049da5t36","country_code":"ES","type":"education","lineage":["https://openalex.org/I46176106"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00c1lvar Arnaiz-Gonz\u00e1lez","raw_affiliation_strings":["Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain","institution_ids":["https://openalex.org/I46176106"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030526894","display_name":"Jes\u00fas Maudes","orcid":null},"institutions":[{"id":"https://openalex.org/I46176106","display_name":"Universidad de Burgos","ror":"https://ror.org/049da5t36","country_code":"ES","type":"education","lineage":["https://openalex.org/I46176106"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Maudes-Raedo","raw_affiliation_strings":["Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain","institution_ids":["https://openalex.org/I46176106"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031727759"],"corresponding_institution_ids":["https://openalex.org/I46176106"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.3901,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83262045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"15","issue":"4","first_page":"223","last_page":"223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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/T10057","display_name":"Face and Expression Recognition","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.7420507669448853},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6959924101829529},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6890209913253784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6433085203170776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5955008268356323},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5760797262191772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.529303789138794},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5190173387527466},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5052440762519836},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4979887008666992},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.49462172389030457},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4728917181491852},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.42125117778778076},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4132618308067322},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39575183391571045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36753159761428833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22036424279212952}],"concepts":[{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.7420507669448853},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6959924101829529},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6890209913253784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6433085203170776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5955008268356323},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5760797262191772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.529303789138794},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5190173387527466},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5052440762519836},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4979887008666992},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.49462172389030457},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4728917181491852},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.42125117778778076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4132618308067322},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39575183391571045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36753159761428833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22036424279212952},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info15040223","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15040223","pdf_url":"https://www.mdpi.com/2078-2489/15/4/223/pdf?version=1713276477","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:62abeb852d844c059817ca5685feb344","is_oa":true,"landing_page_url":"https://doaj.org/article/62abeb852d844c059817ca5685feb344","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 15, Iss 4, p 223 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info15040223","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15040223","pdf_url":"https://www.mdpi.com/2078-2489/15/4/223/pdf?version=1713276477","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6003651768","display_name":null,"funder_award_id":"Predoctoral grant","funder_id":"https://openalex.org/F4320319138","funder_display_name":"Universidad de Burgos"},{"id":"https://openalex.org/G7914059972","display_name":null,"funder_award_id":"BU055P20","funder_id":"https://openalex.org/F4320325114","funder_display_name":"Consejer\u00eda de Educaci\u00f3n, Junta de Castilla y Le\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320319138","display_name":"Universidad de Burgos","ror":"https://ror.org/049da5t36"},{"id":"https://openalex.org/F4320325114","display_name":"Consejer\u00eda de Educaci\u00f3n, Junta de Castilla y Le\u00f3n","ror":"https://ror.org/02s8dab97"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394879596.pdf"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W747850121","https://openalex.org/W1521224934","https://openalex.org/W1565746575","https://openalex.org/W1977007469","https://openalex.org/W2001619934","https://openalex.org/W2016787531","https://openalex.org/W2017337590","https://openalex.org/W2019683663","https://openalex.org/W2037757210","https://openalex.org/W2053154970","https://openalex.org/W2053186076","https://openalex.org/W2087717467","https://openalex.org/W2090135786","https://openalex.org/W2095392975","https://openalex.org/W2097308346","https://openalex.org/W2099454382","https://openalex.org/W2100495367","https://openalex.org/W2105055468","https://openalex.org/W2106136950","https://openalex.org/W2107432340","https://openalex.org/W2108470891","https://openalex.org/W2109553965","https://openalex.org/W2114217318","https://openalex.org/W2118978333","https://openalex.org/W2119387367","https://openalex.org/W2143426320","https://openalex.org/W2148143831","https://openalex.org/W2150165381","https://openalex.org/W2152825437","https://openalex.org/W2167277498","https://openalex.org/W2169284845","https://openalex.org/W2294798173","https://openalex.org/W2295586785","https://openalex.org/W2766736793","https://openalex.org/W2802709838","https://openalex.org/W2802978762","https://openalex.org/W2886574666","https://openalex.org/W2918408501","https://openalex.org/W2970259886","https://openalex.org/W2973941913","https://openalex.org/W2984353870","https://openalex.org/W2999309192","https://openalex.org/W3000409346","https://openalex.org/W3011145085","https://openalex.org/W3021503072","https://openalex.org/W3081074122","https://openalex.org/W3125144398","https://openalex.org/W3183852519","https://openalex.org/W3207361716","https://openalex.org/W4285815691","https://openalex.org/W4289236186","https://openalex.org/W4297880038","https://openalex.org/W4319242178","https://openalex.org/W4321214126","https://openalex.org/W4361026369","https://openalex.org/W6629718364","https://openalex.org/W6675955514","https://openalex.org/W6677191058","https://openalex.org/W6681822384","https://openalex.org/W6682644385","https://openalex.org/W6683161245","https://openalex.org/W6684862044","https://openalex.org/W6697495010","https://openalex.org/W6751646746"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"The":[0,115,135],"most":[1],"common":[2],"preprocessing":[3],"techniques":[4],"used":[5],"to":[6,111,143,169],"deal":[7],"with":[8,83,98,165],"datasets":[9],"having":[10],"high":[11],"dimensionality":[12],"and":[13,27,36,45,101,125,132,146],"a":[14,66,105],"low":[15],"number":[16],"of":[17,34,57,70,86,108],"instances\u2014or":[18],"wide":[19,58,99],"data\u2014are":[20],"feature":[21,24,163],"reduction":[22,106],"(FR),":[23],"selection":[25],"(FS),":[26],"resampling.":[28],"This":[29],"study":[30,69,117],"explores":[31],"the":[32,40,50,55,62,84,102,150,158],"use":[33,85],"FR":[35,44,77,87,93],"resampling":[37,130],"techniques,":[38,120],"expanding":[39],"limited":[41],"comparisons":[42],"between":[43],"filter":[46],"FS":[47,71],"methods":[48,94],"in":[49,54,90],"existing":[51],"literature,":[52],"especially":[53],"context":[56],"data.":[59,114],"We":[60],"compare":[61],"optimal":[63],"outcomes":[64],"from":[65],"previous":[67],"comprehensive":[68],"against":[72],"new":[73],"experiments":[74],"conducted":[75],"using":[76,128],"methods.":[78],"Two":[79],"specific":[80],"challenges":[81],"associated":[82],"are":[88,96,140],"outlined":[89],"detail:":[91],"finding":[92],"that":[95],"compatible":[97],"data":[100],"need":[103],"for":[104],"estimator":[107],"nonlinear":[109,126],"approaches":[110],"process":[112],"out-of-sample":[113],"experimental":[116],"compares":[118],"17":[119],"including":[121],"supervised,":[122],"unsupervised,":[123],"linear,":[124],"approaches,":[127],"7":[129],"strategies":[131],"5":[133],"classifiers.":[134],"results":[136],"demonstrate":[137],"which":[138],"configurations":[139],"optimal,":[141],"according":[142],"their":[144],"performance":[145],"computation":[147],"time.":[148],"Moreover,":[149],"best":[151],"configuration\u2014namely,":[152],"k":[153],"Nearest":[154],"Neighbor":[155],"(KNN)":[156],"+":[157],"Maximal":[159],"Margin":[160],"Criterion":[161],"(MMC)":[162],"reducer":[164],"no":[166],"resampling\u2014is":[167],"shown":[168],"outperform":[170],"state-of-the-art":[171],"algorithms.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}