{"id":"https://openalex.org/W3157558756","doi":"https://doi.org/10.1007/s10115-021-01572-6","title":"A study on using data clustering for feature extraction to improve the quality of classification","display_name":"A study on using data clustering for feature extraction to improve the quality of classification","publication_year":2021,"publication_date":"2021-05-04","ids":{"openalex":"https://openalex.org/W3157558756","doi":"https://doi.org/10.1007/s10115-021-01572-6","mag":"3157558756"},"language":"en","primary_location":{"id":"doi:10.1007/s10115-021-01572-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-021-01572-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-021-01572-6.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"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":"Knowledge and Information Systems","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/s10115-021-01572-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041401789","display_name":"Maciej Piernik","orcid":"https://orcid.org/0000-0001-7281-284X"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Maciej Piernik","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, Poznan, ul. Piotrowo 2, 60-965, Poland"],"raw_orcid":"https://orcid.org/0000-0001-7281-284X","affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, Poznan, ul. Piotrowo 2, 60-965, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111998472","display_name":"Tadeusz Morzy","orcid":null},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tadeusz Morzy","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, Poznan, ul. Piotrowo 2, 60-965, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, Poznan, ul. Piotrowo 2, 60-965, Poland","institution_ids":["https://openalex.org/I46597724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041401789"],"corresponding_institution_ids":["https://openalex.org/I46597724"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":10.2426,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.98141686,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"63","issue":"7","first_page":"1771","last_page":"1805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994000196456909,"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":0.9951000213623047,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8706691265106201},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6904834508895874},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.5909244418144226},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5469496846199036},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.49592098593711853},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46759292483329773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4580714702606201},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44669318199157715},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43939143419265747},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4139890670776367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3730664849281311},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.36965256929397583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35404735803604126},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.20187142491340637}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8706691265106201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6904834508895874},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.5909244418144226},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5469496846199036},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.49592098593711853},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46759292483329773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580714702606201},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44669318199157715},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43939143419265747},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4139890670776367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3730664849281311},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.36965256929397583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35404735803604126},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.20187142491340637},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10115-021-01572-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-021-01572-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-021-01572-6.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"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":"Knowledge and Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10115-021-01572-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-021-01572-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-021-01572-6.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"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":"Knowledge and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7303223394","display_name":null,"funder_award_id":"DEC-2015/19/B/ST6/02637","funder_id":"https://openalex.org/F4320322511","funder_display_name":"Narodowe Centrum Nauki"}],"funders":[{"id":"https://openalex.org/F4320322511","display_name":"Narodowe Centrum Nauki","ror":"https://ror.org/03ha2q922"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3157558756.pdf","grobid_xml":"https://content.openalex.org/works/W3157558756.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W130725823","https://openalex.org/W404240460","https://openalex.org/W418482196","https://openalex.org/W1480376833","https://openalex.org/W1499677495","https://openalex.org/W1576726980","https://openalex.org/W1974758710","https://openalex.org/W1991848143","https://openalex.org/W2011376672","https://openalex.org/W2014098003","https://openalex.org/W2071274075","https://openalex.org/W2071949631","https://openalex.org/W2074466695","https://openalex.org/W2101234009","https://openalex.org/W2116396873","https://openalex.org/W2117169652","https://openalex.org/W2119785531","https://openalex.org/W2133462743","https://openalex.org/W2150593711","https://openalex.org/W2165232124","https://openalex.org/W2168745915","https://openalex.org/W2242397416","https://openalex.org/W2353534269","https://openalex.org/W2800788706","https://openalex.org/W2808465901","https://openalex.org/W2911681169","https://openalex.org/W2940988870","https://openalex.org/W2963316301","https://openalex.org/W3090103671","https://openalex.org/W3120740533","https://openalex.org/W4229977739","https://openalex.org/W4241727697","https://openalex.org/W4249247926","https://openalex.org/W4252684946","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1457719682","https://openalex.org/W2165695836","https://openalex.org/W4220795558","https://openalex.org/W2398543122","https://openalex.org/W2546942002","https://openalex.org/W2525029050","https://openalex.org/W2375192125","https://openalex.org/W2280013922","https://openalex.org/W2184440854","https://openalex.org/W2992612242"],"abstract_inverted_index":{"Abstract":[0],"There":[1,44],"is":[2,26,30,125,151],"a":[3,37,64,80,110,116,138,155,182],"certain":[4],"belief":[5,25],"among":[6],"data":[7],"science":[8],"researchers":[9],"and":[10,34,53,133,135,173,185],"enthusiasts":[11],"alike":[12],"that":[13],"clustering":[14,50,100,114,130,191],"can":[15],"be":[16],"used":[17],"to":[18,78,91,140],"improve":[19,58],"classification":[20,52],"quality.":[21],"Insofar":[22],"as":[23,115,137,192],"this":[24,84,87],"fairly":[27],"uncontroversial,":[28],"it":[29,54,72],"also":[31],"very":[32],"general":[33,187],"therefore":[35],"produces":[36],"lot":[38],"of":[39,48,61,98,118],"confusion":[40],"around":[41],"the":[42,59,96,146,171,175],"subject.":[43,148],"are":[45],"many":[46],"ways":[47],"using":[49,99,190],"in":[51,67,86],"obviously":[55],"cannot":[56],"always":[57],"quality":[60],"predictions,":[62],"so":[63],"question":[65],"arises,":[66],"which":[68],"scenarios":[69],"exactly":[70],"does":[71],"help?":[73],"Since":[74],"we":[75,89,106,178],"were":[76],"unable":[77],"find":[79],"rigorous":[81],"study":[82],"addressing":[83],"question,":[85],"paper,":[88],"try":[90],"shed":[92],"some":[93],"light":[94],"on":[95,154,158],"concept":[97],"for":[101,112,121,195],"classification.":[102,122,196],"To":[103],"do":[104],"so,":[105],"first":[107],"put":[108],"forward":[109],"framework":[111,124],"incorporating":[113],"method":[117],"feature":[119,193],"extraction":[120,194],"The":[123],"generic":[126],"w.r.t.":[127],"similarity":[128],"measures,":[129],"algorithms,":[131],"classifiers,":[132],"datasets":[134],"serves":[136],"platform":[139],"answer":[141,150],"ten":[142],"essential":[143],"questions":[144],"regarding":[145,189],"studied":[147],"Each":[149],"formulated":[152],"based":[153],"separate":[156],"experiment":[157],"16":[159],"publicly":[160],"available":[161],"datasets,":[162],"followed":[163],"by":[164],"an":[165],"appropriate":[166],"statistical":[167],"analysis.":[168],"After":[169],"performing":[170],"experiments":[172],"analyzing":[174],"results":[176],"separately,":[177],"discuss":[179],"them":[180],"from":[181],"global":[183],"perspective":[184],"form":[186],"conclusions":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}