{"id":"https://openalex.org/W2055473071","doi":"https://doi.org/10.1145/1141277.1141406","title":"The impact of sample reduction on PCA-based feature extraction for supervised learning","display_name":"The impact of sample reduction on PCA-based feature extraction for supervised learning","publication_year":2006,"publication_date":"2006-04-23","ids":{"openalex":"https://openalex.org/W2055473071","doi":"https://doi.org/10.1145/1141277.1141406","mag":"2055473071"},"language":"en","primary_location":{"id":"doi:10.1145/1141277.1141406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","raw_type":"proceedings-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/A5022601535","display_name":"Mykola Pechenizkiy","orcid":"https://orcid.org/0000-0003-4955-0743"},"institutions":[{"id":"https://openalex.org/I94722563","display_name":"University of Jyv\u00e4skyl\u00e4","ror":"https://ror.org/05n3dz165","country_code":"FI","type":"education","lineage":["https://openalex.org/I94722563"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Mykola Pechenizkiy","raw_affiliation_strings":["Univ. of Jyv\u00e4skyl\u00e4, Finland"],"affiliations":[{"raw_affiliation_string":"Univ. of Jyv\u00e4skyl\u00e4, Finland","institution_ids":["https://openalex.org/I94722563"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058563569","display_name":"Seppo Puuronen","orcid":null},"institutions":[{"id":"https://openalex.org/I94722563","display_name":"University of Jyv\u00e4skyl\u00e4","ror":"https://ror.org/05n3dz165","country_code":"FI","type":"education","lineage":["https://openalex.org/I94722563"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Seppo Puuronen","raw_affiliation_strings":["Univ. of Jyv\u00e4skyl\u00e4, Finland"],"affiliations":[{"raw_affiliation_string":"Univ. of Jyv\u00e4skyl\u00e4, Finland","institution_ids":["https://openalex.org/I94722563"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109047597","display_name":"Alexey Tsymbal","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Alexey Tsymbal","raw_affiliation_strings":["Trinity College Dublin, Ireland","Trinity College, Dublin Ireland"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"Trinity College, Dublin Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022601535"],"corresponding_institution_ids":["https://openalex.org/I94722563"],"apc_list":null,"apc_paid":null,"fwci":1.2644,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.80379155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9979000091552734,"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":0.9979000091552734,"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":0.995199978351593,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9951000213623047,"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/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6636778712272644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6562199592590332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5494527220726013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5359611511230469},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.49729397892951965},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4763638973236084},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4622459411621094},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.45395323634147644},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.42119771242141724},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38514024019241333},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34435388445854187},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2901269197463989},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.09316951036453247},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.07674375176429749}],"concepts":[{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6636778712272644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6562199592590332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5494527220726013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5359611511230469},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.49729397892951965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4763638973236084},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4622459411621094},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.45395323634147644},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.42119771242141724},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38514024019241333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34435388445854187},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2901269197463989},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09316951036453247},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.07674375176429749}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1141277.1141406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/a8b82e31-54a8-4d34-8cd9-335c2bfb3512","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/a8b82e31-54a8-4d34-8cd9-335c2bfb3512","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pechenizkiy, M, Puuronen, S & Tsymbal, A 2006, The impact of sample reduction on PCA-based feature extraction for supervised learning. in H Haddad (ed.), Proceedings 21st ACM Symposium on Applied Computing (SAC'06, Dijon, France, April 23-27, 2006). Association for Computing Machinery, Inc., pp. 553-558.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.2479","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.2479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.win.tue.nl/~mpechen/publications/Pechenizkiy_etal_SAC06DM.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.642.4215","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.642.4215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.win.tue.nl/~mpechen/publications/pubs/PechenizkiySAC06.pdf","raw_type":"text"},{"id":"pmh:tue:oai:pure.tue.nl:publications/a8b82e31-54a8-4d34-8cd9-335c2bfb3512","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/a8b82e31-54a8-4d34-8cd9-335c2bfb3512","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings 21st ACM Symposium on Applied Computing (SAC'06, Dijon, France, April 23-27, 2006), 553 - 558","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W872314213","https://openalex.org/W1770825568","https://openalex.org/W1837656155","https://openalex.org/W1864355914","https://openalex.org/W1872965898","https://openalex.org/W1991622368","https://openalex.org/W2053694888","https://openalex.org/W2084812512","https://openalex.org/W2106642566","https://openalex.org/W2123504579","https://openalex.org/W2135346934","https://openalex.org/W2138745909","https://openalex.org/W2140785063","https://openalex.org/W2148694408","https://openalex.org/W2162452049","https://openalex.org/W3015571647","https://openalex.org/W4237171445","https://openalex.org/W4292023222"],"related_works":["https://openalex.org/W3124876457","https://openalex.org/W1995622179","https://openalex.org/W2012244993","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/W3122670876"],"abstract_inverted_index":{"\"The":[0],"curse":[1],"of":[2,16,37,48,60,72,80,88,94,127,134,145,154],"dimensionality\"":[3],"is":[4,65,83,121,141,207,211],"pertinent":[5],"to":[6,45,67,84,130,172,213,235],"many":[7],"learning":[8,226],"algorithms,":[9],"and":[10,19,40,74,107,123,187,220],"it":[11,210],"denotes":[12],"the":[13,46,69,86,92,104,125,131,135,146,151,155,200,227,244,251],"drastic":[14],"raise":[15],"computational":[17,70],"complexity":[18,71],"classification":[20,75,248],"error":[21],"in":[22,243],"high":[23],"dimensions.":[24],"In":[25,99],"this":[26,81],"paper,":[27],"different":[28,170],"feature":[29],"extraction":[30],"(FE)":[31],"techniques":[32],"are":[33,161],"analyzed":[34,103],"as":[35],"means":[36],"dimensionality":[38],"reduction,":[39],"constructive":[41],"induction":[42],"with":[43,191],"respect":[44],"performance":[47],"Na\u00efve":[49],"Bayes":[50],"classifier.":[51],"When":[52],"a":[53,57,142,237],"data":[54,166,221],"set":[55],"contains":[56],"large":[58],"number":[59],"instances,":[61],"some":[62],"sampling":[63,190],"approach":[64,120,140,230],"applied":[66],"address":[68],"FE":[73,95,204,229,253],"processes.":[76],"The":[77,117,138,159],"main":[78],"goal":[79],"paper":[82],"show":[85,197],"impact":[87],"sample":[89,201],"reduction":[90],"on":[91,150,163],"process":[93],"for":[96,203,224],"supervised":[97,225],"learning.":[98],"our":[100],"study":[101],"we":[102],"conventional":[105],"PCA":[106],"two":[108],"eigenvector-based":[109],"approaches":[110],"that":[111,198,241],"take":[112,214],"into":[113,215],"account":[114,216],"class":[115,218],"information.":[116],"first":[118,147],"class-conditional":[119],"parametric":[122],"optimizes":[124],"ratio":[126],"between-class":[128,156],"variance":[129,133],"within-class":[132],"transformed":[136],"data.":[137],"second":[139],"nonparametric":[143,228],"modification":[144],"one":[148],"based":[149,184,193],"local":[152],"calculation":[153],"covariance":[157],"matrix.":[158],"experiments":[160,196],"conducted":[162],"ten":[164],"UCI":[165],"sets,":[167],"using":[168],"four":[169],"strategies":[171],"select":[173],"samples:":[174],"(1)":[175],"random":[176,180],"sampling,":[177,181,186],"(2)":[178],"stratified":[179,189],"(3)":[182],"kd-tree":[183,192],"selective":[185],"(4)":[188],"selection.":[194],"Our":[195],"if":[199],"size":[202],"model":[205],"construction":[206],"small":[208],"then":[209],"important":[212],"both":[217],"information":[219],"distribution.":[222],"Further,":[223],"needs":[231],"much":[232],"less":[233],"instances":[234],"produce":[236],"new":[238],"representation":[239],"space":[240],"result":[242],"same":[245],"or":[246],"higher":[247],"accuracy":[249],"than":[250],"other":[252],"approaches.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}