{"id":"https://openalex.org/W2185089194","doi":null,"title":"Overfitting in feature selection: Pitfalls and solutions","display_name":"Overfitting in feature selection: Pitfalls and solutions","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2185089194","mag":"2185089194"},"language":"en","primary_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/4830","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/4830","pdf_url":"https://aaltodoc.aalto.fi/handle/123456789/4830","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"G5 Artikkeliv\u00e4it\u00f6skirja"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://aaltodoc.aalto.fi/handle/123456789/4830","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025484879","display_name":"Juha Reunanen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Juha Reunanen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5025484879"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.4372999966144562,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.4372999966144562,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.2969000041484833,"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/T13141","display_name":"Statistical Methods and Applications","score":0.03280000016093254,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.9959999918937683},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.996999979019165},{"id":"https://openalex.org/keywords/accuracy-estimation","display_name":"accuracy estimation","score":0.5009999871253967},{"id":"https://openalex.org/keywords/small-sample-size","display_name":"small sample size","score":0.753000020980835},{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.8479999899864197},{"id":"https://openalex.org/keywords/sensor-selection","display_name":"sensor selection","score":0.9800000190734863},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"regression analysis","score":0.6819999814033508},{"id":"https://openalex.org/keywords/microarray-data","display_name":"microarray data","score":0.8429999947547913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"pattern recognition","score":0.6470000147819519}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.857638955116272},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6217375993728638},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5758365392684937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5616137385368347},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5511526465415955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5227347016334534},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3281121850013733},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12955158948898315},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1048768162727356},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07481268048286438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/4830","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/4830","pdf_url":"https://aaltodoc.aalto.fi/handle/123456789/4830","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"G5 Artikkeliv\u00e4it\u00f6skirja"},{"id":"mag:2185089194","doi":null,"is_oa":false,"landing_page_url":"http://lib.tkk.fi/Diss/2012/isbn9789526045160/isbn9789526045160.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/4830","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/4830","pdf_url":"https://aaltodoc.aalto.fi/handle/123456789/4830","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"G5 Artikkeliv\u00e4it\u00f6skirja"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2185089194.pdf","grobid_xml":"https://content.openalex.org/works/W2185089194.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W32535764","https://openalex.org/W53188351","https://openalex.org/W109927865","https://openalex.org/W122504902","https://openalex.org/W158831016","https://openalex.org/W313721732","https://openalex.org/W1483524195","https://openalex.org/W1486658274","https://openalex.org/W1498800329","https://openalex.org/W1523989055","https://openalex.org/W1538973122","https://openalex.org/W1554663460","https://openalex.org/W1554944419","https://openalex.org/W1559923427","https://openalex.org/W1574919022","https://openalex.org/W1587362683","https://openalex.org/W1592785605","https://openalex.org/W1619226191","https://openalex.org/W1643412971","https://openalex.org/W1680392829","https://openalex.org/W1824262692","https://openalex.org/W1840091437","https://openalex.org/W1983223005","https://openalex.org/W1992616163","https://openalex.org/W2014915963","https://openalex.org/W2017337590","https://openalex.org/W2032057535","https://openalex.org/W2040870580","https://openalex.org/W2065004162","https://openalex.org/W2072026441","https://openalex.org/W2076118331","https://openalex.org/W2087853099","https://openalex.org/W2091321577","https://openalex.org/W2097884614","https://openalex.org/W2104862701","https://openalex.org/W2107835995","https://openalex.org/W2107956883","https://openalex.org/W2113957934","https://openalex.org/W2114256688","https://openalex.org/W2117669534","https://openalex.org/W2119479037","https://openalex.org/W2119869458","https://openalex.org/W2120216197","https://openalex.org/W2123060977","https://openalex.org/W2130759652","https://openalex.org/W2131022537","https://openalex.org/W2133418613","https://openalex.org/W2135547590","https://openalex.org/W2143426320","https://openalex.org/W2143908786","https://openalex.org/W2154776925","https://openalex.org/W2155482699","https://openalex.org/W2163321856","https://openalex.org/W2165217207","https://openalex.org/W2189398955","https://openalex.org/W2493581502","https://openalex.org/W2596228892","https://openalex.org/W2766736793","https://openalex.org/W3017143921","https://openalex.org/W3022887551","https://openalex.org/W3154964538"],"related_works":["https://openalex.org/W2181933894","https://openalex.org/W7096821381","https://openalex.org/W7095809457","https://openalex.org/W3125396204","https://openalex.org/W6941411499","https://openalex.org/W2293190597","https://openalex.org/W7128484629","https://openalex.org/W940014737","https://openalex.org/W7099391239","https://openalex.org/W2163915562"],"abstract_inverted_index":{"When":[0],"facing":[1],"a":[2,12,52,64,247,296],"typical":[3],"pattern":[4],"recognition":[5,46],"task,":[6],"one":[7,55],"usually":[8],"comes":[9],"up":[10],"with":[11],"number":[13],"of":[14,31,47,68,111,118,127,164,224,249,306,324,329],"so-called":[15],"features:":[16],"properties":[17],"that":[18,41,141,151,188,200,208,221,273,288,328],"describe":[19],"the":[20,29,32,45,59,85,108,116,137,144,149,162,167,178,190,201,225,242,274,293,304,322,332,347],"objects":[21],"to":[22,37,57,103,135,173,262,264,281,317,327,337],"be":[23,90,125,258,278],"recognised.":[24],"Based":[25,160],"on":[26,161],"these":[27],"features,":[28,333],"task":[30,71],"classifier":[33],"building":[34],"algorithm":[35],"is":[36,51,72,142,156,183,192,227,237,308,343],"find":[38],"useful":[39,60,230],"rules":[40],"are":[42,154,209,290,312],"suitable":[43],"for":[44,82,299],"new":[48],"objects.\\nFeature":[49],"selection":[50,139,243,316,323],"process":[53,244],"where":[54,346],"tries":[56],"identify":[58,136],"features":[61,226,326],"from":[62,314,321,335],"among":[63],"potentially":[65],"large":[66],"set":[67],"candidates.":[69],"The":[70],"notoriously":[73],"hard,":[74],"and":[75,203,251,334],"researchers":[76],"have":[77,131,263],"been":[78,284],"tackling":[79],"it":[80,182,195,232,256,266],"already":[81],"decades.":[83],"Solving":[84],"problem":[86],"properly":[87],"might":[88],"today":[89],"more":[91,229],"important":[92],"than":[93,106,177,231],"ever":[94],"before,":[95],"because":[96,241],"in":[97,115,185,239,302],"many":[98,218],"applications,":[99],"dataset":[100],"sizes":[101],"seem":[102,172],"grow":[104],"faster":[105],"does":[107],"processing":[109],"power":[110],"computers.":[112],"For":[113],"example,":[114],"domain":[117],"genetic":[119],"microarray":[120],"data,":[121],"there":[122],"can":[123],"easily":[124],"thousands":[126],"features.\\nSeveral":[128],"research":[129],"groups":[130],"published":[132],"comparisons":[133,153],"aiming":[134],"feature":[138,315],"method":[140],"universally":[143],"best.":[145],"Unfortunately,":[146],"too":[147],"often":[148,197],"way":[150],"such":[152,165],"done":[155,193],"just":[157,210],"plain":[158],"wrong.":[159],"results":[163,207],"studies,":[166],"computationally":[168],"intensive":[169],"search":[170],"algorithms":[171,205],"perform":[174],"much":[175,228],"better":[176],"simple":[179,202],"approaches.":[180],"However,":[181],"shown":[184],"this":[186],"thesis":[187,271,294],"when":[189],"comparison":[191],"properly,":[194],"very":[196,259],"turns":[198],"out":[199,267,345],"fast":[204],"give":[206],"as":[211],"good,":[212],"if":[213],"not":[214,261],"even":[215],"better.\\nIn":[216],"addition,":[217],"studies":[219],"suggest":[220],"excluding":[222],"some":[223],"actually":[233],"is.":[234],"This":[235,270],"observation":[236],"relevant":[238],"practice,":[240],"typically":[245],"takes":[246],"lot":[248],"time":[250],"computing":[252],"resources":[253],"-":[254],"therefore,":[255],"would":[257],"convenient":[260],"carry":[265],"at":[268],"all.":[269],"shows":[272],"benefits":[275],"obtained":[276],"may":[277],"negligible":[279],"compared":[280],"what":[282],"has":[283],"presented":[285],"previously,":[286],"provided":[287],"they":[289],"measured":[291],"correctly.\\nMoreover,":[292],"presents":[295],"better-performing":[297],"approach":[298],"accuracy":[300],"estimation":[301],"case":[303],"amount":[305],"data":[307],"small.":[309],"Further,":[310],"extensions":[311],"discussed":[313,349],"generic":[318],"model":[319],"selection,":[320],"individual":[325],"sensors":[330],"measuring":[331],"classification":[336],"regression.":[338],"Finally,":[339],"an":[340],"industrial":[341],"application":[342],"pointed":[344],"methods":[348],"prove":[350],"useful.":[351]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}