{"id":"https://openalex.org/W4401852395","doi":"https://doi.org/10.1145/3676288.3676302","title":"Similarity Measures Recommendation for Mixed Data Clustering","display_name":"Similarity Measures Recommendation for Mixed Data Clustering","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4401852395","doi":"https://doi.org/10.1145/3676288.3676302"},"language":"en","primary_location":{"id":"doi:10.1145/3676288.3676302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676288.3676302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04635057/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046961425","display_name":"Abdoulaye Diop","orcid":"https://orcid.org/0000-0001-6428-0038"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Abdoulaye Diop","raw_affiliation_strings":["SIG, IRIT, France and SolutionData Group, France"],"affiliations":[{"raw_affiliation_string":"SIG, IRIT, France and SolutionData Group, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058607906","display_name":"Nabil El Malki","orcid":"https://orcid.org/0000-0002-5823-8412"},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nabil El Malki","raw_affiliation_strings":["IRIT, France"],"affiliations":[{"raw_affiliation_string":"IRIT, France","institution_ids":["https://openalex.org/I4210119061"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085908375","display_name":"Max Chevalier","orcid":"https://orcid.org/0000-0001-5402-6255"},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Max Chevalier","raw_affiliation_strings":["IRIT, France"],"affiliations":[{"raw_affiliation_string":"IRIT, France","institution_ids":["https://openalex.org/I4210119061"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062690195","display_name":"Andr\u00e9 P\u00e9ninou","orcid":"https://orcid.org/0000-0001-6387-0079"},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210108194","display_name":"Chambre de Commerce et d'Industrie Occitanie Pyr\u00e9n\u00e9es-M\u00e9diterran\u00e9e","ror":"https://ror.org/01kmkkm51","country_code":"FR","type":"government","lineage":["https://openalex.org/I4210108194"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 P\u00e9ninou","raw_affiliation_strings":["IRIT, France","IUT Toulouse 2 Blagnac (France)"],"affiliations":[{"raw_affiliation_string":"IRIT, France","institution_ids":["https://openalex.org/I4210119061"]},{"raw_affiliation_string":"IUT Toulouse 2 Blagnac (France)","institution_ids":["https://openalex.org/I4210108194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077152747","display_name":"Geoffrey Roman\u2010Jimenez","orcid":"https://orcid.org/0000-0002-2355-5901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roman Jimenez Geoffrey","raw_affiliation_strings":["SolutionData Group, France"],"affiliations":[{"raw_affiliation_string":"SolutionData Group, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036483175","display_name":"Olivier Teste","orcid":"https://orcid.org/0000-0003-0338-9886"},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Teste","raw_affiliation_strings":["IRIT, France"],"affiliations":[{"raw_affiliation_string":"IRIT, France","institution_ids":["https://openalex.org/I4210119061"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046961425"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3592,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66057755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9988999962806702,"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":0.9988999962806702,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9970999956130981,"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":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.7173464894294739},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7147501707077026},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5805197358131409},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43207719922065735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42214030027389526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.368304967880249},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.321493923664093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173464894294739},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7147501707077026},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5805197358131409},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43207719922065735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42214030027389526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.368304967880249},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.321493923664093},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3676288.3676302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676288.3676302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04635057v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04635057","pdf_url":"https://hal.science/hal-04635057/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ssdbm.org/2024/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04635057v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04635057","pdf_url":"https://hal.science/hal-04635057/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ssdbm.org/2024/","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6053939218","display_name":null,"funder_award_id":"CIFRE","funder_id":"https://openalex.org/F4320321663","funder_display_name":"Association Nationale de la Recherche et de la Technologie"},{"id":"https://openalex.org/G8973379794","display_name":null,"funder_award_id":"2020/0868","funder_id":"https://openalex.org/F4320321663","funder_display_name":"Association Nationale de la Recherche et de la Technologie"}],"funders":[{"id":"https://openalex.org/F4320321663","display_name":"Association Nationale de la Recherche et de la Technologie","ror":"https://ror.org/00ht2ab73"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401852395.pdf","grobid_xml":"https://content.openalex.org/works/W4401852395.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1894116512","https://openalex.org/W1974209792","https://openalex.org/W1990643970","https://openalex.org/W1990694217","https://openalex.org/W2005699237","https://openalex.org/W2028155376","https://openalex.org/W2102705755","https://openalex.org/W2120887445","https://openalex.org/W2132862423","https://openalex.org/W2149230623","https://openalex.org/W2150398422","https://openalex.org/W2163212577","https://openalex.org/W2216706082","https://openalex.org/W2294912085","https://openalex.org/W2478708596","https://openalex.org/W2729531028","https://openalex.org/W2737994327","https://openalex.org/W2898576334","https://openalex.org/W2900404321","https://openalex.org/W2965408537","https://openalex.org/W2969220032","https://openalex.org/W3007204986","https://openalex.org/W3048498970","https://openalex.org/W3107721972","https://openalex.org/W3112291449","https://openalex.org/W3167687764","https://openalex.org/W4200614606","https://openalex.org/W4252684946","https://openalex.org/W4283768429","https://openalex.org/W4295308409","https://openalex.org/W4313591778","https://openalex.org/W4391262438","https://openalex.org/W4394633966"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254","https://openalex.org/W1926736923","https://openalex.org/W2942177010"],"abstract_inverted_index":{"Clustering":[0],"is":[1,8,81,152,174],"an":[2,42,69],"important":[3,70,176],"data":[4,92,104,119],"mining":[5],"task":[6,44],"which":[7],"widely":[9],"spread":[10],"in":[11,109,177],"various":[12],"domains":[13],"such":[14],"as":[15,41,105,107,125,127,180],"biology,":[16],"finance,":[17],"marketing,":[18],"healthcare,":[19],"and":[20,159],"social":[21],"sciences.":[22],"It":[23],"allows":[24],"the":[25,82,97,103,113,134,142,184],"end":[26],"user":[27],"to":[28,64,77,94,111,156,162],"discover,":[29],"through":[30],"built":[31],"clusters,":[32,96],"relationships":[33],"within":[34],"data.":[35],"Many":[36],"non-expert":[37],"users":[38],"perceive":[39],"clustering":[40,54,75,86,131,185],"\"easy\"":[43],"because":[45],"it":[46,181],"always":[47],"produces":[48],"a":[49,53,74,78,147],"result.":[50],"However,":[51],"choosing":[52],"algorithm":[55,76],"at":[56],"random,":[57],"without":[58],"proper":[59],"parameter":[60],"tuning,":[61],"often":[62],"leads":[63],"poor":[65],"results.":[66],"In":[67],"particular,":[68],"choice":[71,166],"when":[72],"applying":[73],"specific":[79],"dataset":[80],"similarity":[83,99,136,150,172],"measure.":[84],"Since":[85],"algorithms":[87],"rely":[88],"on":[89],"similarities":[90],"between":[91],"points":[93],"build":[95],"chosen":[98],"measure":[100,137],"should":[101],"fit":[102],"accurately":[106],"possible":[108],"order":[110],"form":[112],"best":[114],"clusters.":[115],"Mixed":[116],"Data":[117],"are":[118,121],"that":[120],"characterized":[122],"by":[123],"numerical":[124,157],"well":[126],"categorical":[128,163],"attributes.":[129,164],"When":[130],"mixed":[132,178],"data,":[133,179],"same":[135],"cannot":[138],"be":[139],"used":[140],"for":[141],"two":[143,169],"attribute":[144],"types.":[145],"Commonly":[146],"pair":[148],"of":[149,167],"measures":[151,173],"used,":[153],"one":[154,160],"dedicated":[155,161],"attributes":[158],"The":[165],"these":[168],"most":[170],"appropriate":[171],"very":[175],"significantly":[182],"affects":[183],"performance.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}
