{"id":"https://openalex.org/W2030831615","doi":"https://doi.org/10.2298/csis0601023h","title":"Improving categorical data clustering algorithm by weighting uncommon attribute value matches","display_name":"Improving categorical data clustering algorithm by weighting uncommon attribute value matches","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2030831615","doi":"https://doi.org/10.2298/csis0601023h","mag":"2030831615"},"language":"en","primary_location":{"id":"doi:10.2298/csis0601023h","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis0601023h","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02140601023H","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02140601023H","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009588567","display_name":"Zengyou He","orcid":"https://orcid.org/0000-0001-9526-8816"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zengyou He","raw_affiliation_strings":["Department of Computer Science and Engineering, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101453595","display_name":"Xiaofei Xu","orcid":"https://orcid.org/0000-0002-6033-7989"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100853489","display_name":"Shenchun Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenchun Deng","raw_affiliation_strings":["Department of Computer Science and Engineering, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009588567"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.4657,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73761209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":"1","first_page":"23","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9545999765396118,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9545999765396118,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9161999821662903,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9089000225067139,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/categorical-variable","display_name":"Categorical variable","score":0.8205663561820984},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7806352376937866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7550898194313049},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6648538112640381},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6222831606864929},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5508838891983032},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5369588732719421},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5109211802482605},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42194628715515137},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.41812556982040405},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40643560886383057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40380311012268066},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.37347495555877686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3662091791629791},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16818571090698242},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0600699782371521}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8205663561820984},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7806352376937866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7550898194313049},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6648538112640381},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6222831606864929},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5508838891983032},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5369588732719421},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5109211802482605},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42194628715515137},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.41812556982040405},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40643560886383057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40380311012268066},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.37347495555877686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3662091791629791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16818571090698242},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0600699782371521},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.2298/csis0601023h","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis0601023h","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02140601023H","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.6804","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.6804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dmresearch.net/zengyouhe/publications/ComSIS06.pdf","raw_type":"text"},{"id":"pmh:oai:doiserbia:1820-02140601023H","is_oa":false,"landing_page_url":"http://doi.org/10.2298/CSIS0601023H","pdf_url":null,"source":{"id":"https://openalex.org/S4306400515","display_name":"Digital Object Identifier (DOI) Repository Serbia (National Library of Serbia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210142455","host_organization_name":"National Library of Serbia","host_organization_lineage":["https://openalex.org/I4210142455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":". 3(1) 23-32"}],"best_oa_location":{"id":"doi:10.2298/csis0601023h","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis0601023h","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02140601023H","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6058138561","display_name":null,"funder_award_id":", No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2030831615.pdf","grobid_xml":"https://content.openalex.org/works/W2030831615.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W26772505","https://openalex.org/W1535281683","https://openalex.org/W1556833935","https://openalex.org/W1967987265","https://openalex.org/W2020738241","https://openalex.org/W2031903754","https://openalex.org/W2057712948","https://openalex.org/W2066794285","https://openalex.org/W2084812512","https://openalex.org/W2096285766","https://openalex.org/W2138745909","https://openalex.org/W2149230623","https://openalex.org/W2162151748","https://openalex.org/W2982720039"],"related_works":["https://openalex.org/W2491448268","https://openalex.org/W2559422900","https://openalex.org/W2892323093","https://openalex.org/W3144143113","https://openalex.org/W2394193399","https://openalex.org/W2181939267","https://openalex.org/W2390610678","https://openalex.org/W3071522575","https://openalex.org/W2363054820","https://openalex.org/W2101174895"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"improved":[4],"Squeezer":[5,39],"algorithm":[6,33,40,44],"for":[7],"categorical":[8],"data":[9],"clustering":[10,43,48],"by":[11],"giving":[12],"greater":[13],"weight":[14],"to":[15,36,47],"uncommon":[16],"attribute":[17],"value":[18],"matches":[19],"in":[20],"similarity":[21],"computations.":[22],"Experimental":[23],"results":[24],"on":[25],"real":[26],"life":[27],"datasets":[28],"show":[29],"that,":[30],"the":[31,37],"modified":[32],"is":[34],"superior":[35],"original":[38],"and":[41],"other":[42],"with":[45],"respect":[46],"accuracy.":[49]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}