{"id":"https://openalex.org/W4283741549","doi":"https://doi.org/10.3390/e24070917","title":"How the Outliers Influence the Quality of Clustering?","display_name":"How the Outliers Influence the Quality of Clustering?","publication_year":2022,"publication_date":"2022-06-30","ids":{"openalex":"https://openalex.org/W4283741549","doi":"https://doi.org/10.3390/e24070917","pmid":"https://pubmed.ncbi.nlm.nih.gov/35885141"},"language":"en","primary_location":{"id":"doi:10.3390/e24070917","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e24070917","pdf_url":"https://www.mdpi.com/1099-4300/24/7/917/pdf?version=1657200433","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"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":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/24/7/917/pdf?version=1657200433","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088457184","display_name":"Agnieszka Nowak-Brzezi\u0144ska","orcid":"https://orcid.org/0000-0001-7238-1170"},"institutions":[{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I864159182","display_name":"University of Silesia in Katowice","ror":"https://ror.org/0104rcc94","country_code":"PL","type":"education","lineage":["https://openalex.org/I864159182"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Agnieszka Nowak-Brzezi\u0144ska","raw_affiliation_strings":["Institute of Computer Science, Faculty of Science and Technology, University of Silesia, Bankowa 12, 40-007 Katowice, Poland"],"raw_orcid":"https://orcid.org/0000-0001-7238-1170","affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Faculty of Science and Technology, University of Silesia, Bankowa 12, 40-007 Katowice, Poland","institution_ids":["https://openalex.org/I864159182","https://openalex.org/I4210087266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035670915","display_name":"Igor Gaibei","orcid":"https://orcid.org/0000-0002-4708-9036"},"institutions":[{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I864159182","display_name":"University of Silesia in Katowice","ror":"https://ror.org/0104rcc94","country_code":"PL","type":"education","lineage":["https://openalex.org/I864159182"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Igor Gaibei","raw_affiliation_strings":["Institute of Computer Science, Faculty of Science and Technology, University of Silesia, Bankowa 12, 40-007 Katowice, Poland"],"raw_orcid":"https://orcid.org/0000-0002-4708-9036","affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Faculty of Science and Technology, University of Silesia, Bankowa 12, 40-007 Katowice, Poland","institution_ids":["https://openalex.org/I864159182","https://openalex.org/I4210087266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088457184"],"corresponding_institution_ids":["https://openalex.org/I4210087266","https://openalex.org/I864159182"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":4.5794,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95241544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"24","issue":"7","first_page":"917","last_page":"917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9779000282287598,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8593729138374329},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.8068366050720215},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.7017062902450562},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6884600520133972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6703716516494751},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.6555281281471252},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6208587288856506},{"id":"https://openalex.org/keywords/local-outlier-factor","display_name":"Local outlier factor","score":0.6137889623641968},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5696810483932495},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.539989709854126},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43715745210647583},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.43282222747802734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43122535943984985}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8593729138374329},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.8068366050720215},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.7017062902450562},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6884600520133972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6703716516494751},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.6555281281471252},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6208587288856506},{"id":"https://openalex.org/C169029474","wikidata":"https://www.wikidata.org/wiki/Q387942","display_name":"Local outlier factor","level":3,"score":0.6137889623641968},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5696810483932495},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.539989709854126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43715745210647583},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.43282222747802734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43122535943984985}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/e24070917","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e24070917","pdf_url":"https://www.mdpi.com/1099-4300/24/7/917/pdf?version=1657200433","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"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":"Entropy","raw_type":"journal-article"},{"id":"pmid:35885141","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35885141","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:6e1f629c178645e3840814c45ed73536","is_oa":true,"landing_page_url":"https://doaj.org/article/6e1f629c178645e3840814c45ed73536","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 24, Iss 7, p 917 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/24/7/917/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/e24070917","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Entropy; Volume 24; Issue 7; Pages: 917","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9324173","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9324173","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Entropy (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e24070917","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e24070917","pdf_url":"https://www.mdpi.com/1099-4300/24/7/917/pdf?version=1657200433","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"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":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283741549.pdf","grobid_xml":"https://content.openalex.org/works/W4283741549.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2029064186","https://openalex.org/W2066965880","https://openalex.org/W2811274885","https://openalex.org/W3034094373","https://openalex.org/W3090756274","https://openalex.org/W3141150700","https://openalex.org/W4230545555","https://openalex.org/W4234808003","https://openalex.org/W4254182148","https://openalex.org/W6678414873","https://openalex.org/W6792108928"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W2160785859","https://openalex.org/W3120229345","https://openalex.org/W2103650652","https://openalex.org/W2188840951","https://openalex.org/W2171610853","https://openalex.org/W2360225591","https://openalex.org/W2101637161","https://openalex.org/W2342518500","https://openalex.org/W2374506950"],"abstract_inverted_index":{"In":[0,91,132],"this":[1,54],"article,":[2],"we":[3,78,94,123],"evaluate":[4],"the":[5,33,38,43,60,73,87,98,126,133],"efficiency":[6],"and":[7,17,28,45,80,96,103,113,118],"performance":[8],"of":[9,40,53,62,120,128,145],"two":[10],"clustering":[11,34,41,89,129],"algorithms:":[12],"AHC":[13],"(Agglomerative":[14],"Hierarchical":[15],"Clustering)":[16],"K-Means.":[18],"We":[19,36],"are":[20,24],"aware":[21],"that":[22,31],"there":[23],"various":[25],"linkage":[26],"options":[27],"distance":[29],"measures":[30],"influence":[32],"results.":[35],"assess":[37],"quality":[39,61,127],"using":[42],"Davies-Bouldin":[44],"Dunn":[46],"cluster":[47],"validity":[48],"indexes.":[49],"The":[50],"main":[51],"contribution":[52],"research":[55],"is":[56,66],"to":[57],"verify":[58],"whether":[59],"clusters":[63],"without":[64],"outliers":[65,71,111],"higher":[67],"than":[68],"those":[69],"with":[70,141],"in":[72],"data.":[74],"To":[75],"do":[76],"this,":[77],"compare":[79,97],"analyze":[81,124],"outlier":[82],"detection":[83],"algorithms":[84,108],"depending":[85],"on":[86],"applied":[88],"algorithm.":[90],"our":[92],"research,":[93],"use":[95],"LOF":[99],"(Local":[100],"Outlier":[101,106],"Factor)":[102,107],"COF":[104],"(Connectivity-based":[105],"for":[109],"detecting":[110],"before":[112],"after":[114],"removing":[115],"1%,":[116],"5%,":[117],"10%":[119],"outliers.":[121],"Next,":[122],"how":[125],"has":[130],"improved.":[131],"experiments,":[134],"three":[135],"real":[136],"data":[137],"sets":[138],"were":[139],"used":[140],"a":[142],"different":[143],"number":[144],"instances.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-31T08:46:17.908082","created_date":"2025-10-10T00:00:00"}