{"id":"https://openalex.org/W2992049863","doi":"https://doi.org/10.1109/bracis.2019.00113","title":"K-Fact: Using the Frequency Factor for Clustering Categorical Data","display_name":"K-Fact: Using the Frequency Factor for Clustering Categorical Data","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2992049863","doi":"https://doi.org/10.1109/bracis.2019.00113","mag":"2992049863"},"language":"en","primary_location":{"id":"doi:10.1109/bracis.2019.00113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bracis.2019.00113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th Brazilian Conference on Intelligent Systems (BRACIS)","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/A5000150014","display_name":"Robespierre Pita","orcid":"https://orcid.org/0000-0002-0616-620X"},"institutions":[{"id":"https://openalex.org/I126158947","display_name":"Universidade Federal da Bahia","ror":"https://ror.org/03k3p7647","country_code":"BR","type":"education","lineage":["https://openalex.org/I126158947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Robespierre Pita","raw_affiliation_strings":["Computer Science Department, Federal University of Bahia - UFBA, Salvador, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Federal University of Bahia - UFBA, Salvador, Brazil","institution_ids":["https://openalex.org/I126158947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068624980","display_name":"Gabriela L Borges","orcid":null},"institutions":[{"id":"https://openalex.org/I52325","display_name":"Funda\u00e7\u00e3o Oswaldo Cruz","ror":"https://ror.org/04jhswv08","country_code":"BR","type":"facility","lineage":["https://openalex.org/I52325"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gabriela Borges","raw_affiliation_strings":["CIDACS Oswaldo Cruz Foundation - Fiocruz, Salvador, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIDACS Oswaldo Cruz Foundation - Fiocruz, Salvador, Brazil","institution_ids":["https://openalex.org/I52325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006367790","display_name":"N\u00edvea Bispo","orcid":null},"institutions":[{"id":"https://openalex.org/I52325","display_name":"Funda\u00e7\u00e3o Oswaldo Cruz","ror":"https://ror.org/04jhswv08","country_code":"BR","type":"facility","lineage":["https://openalex.org/I52325"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Nivea Bispo","raw_affiliation_strings":["CIDACS Oswaldo Cruz Foundation - Fiocruz, Salvador, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIDACS Oswaldo Cruz Foundation - Fiocruz, Salvador, Brazil","institution_ids":["https://openalex.org/I52325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101823479","display_name":"Daniela Almeida","orcid":"https://orcid.org/0000-0002-9054-5797"},"institutions":[{"id":"https://openalex.org/I52325","display_name":"Funda\u00e7\u00e3o Oswaldo Cruz","ror":"https://ror.org/04jhswv08","country_code":"BR","type":"facility","lineage":["https://openalex.org/I52325"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Daniela Almeida","raw_affiliation_strings":["CIDACS Oswaldo Cruz Foundation - Fiocruz, Salvador, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIDACS Oswaldo Cruz Foundation - Fiocruz, Salvador, Brazil","institution_ids":["https://openalex.org/I52325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009811249","display_name":"Rosemeire Leovigildo Fiaccone","orcid":"https://orcid.org/0000-0001-5439-1551"},"institutions":[{"id":"https://openalex.org/I126158947","display_name":"Universidade Federal da Bahia","ror":"https://ror.org/03k3p7647","country_code":"BR","type":"education","lineage":["https://openalex.org/I126158947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rosemeire Fiaccone","raw_affiliation_strings":["Statistics Department, Federal University of Bahia - UFBA, Salvador, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Statistics Department, Federal University of Bahia - UFBA, Salvador, Brazil","institution_ids":["https://openalex.org/I126158947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000123273","display_name":"Marcos Barreto","orcid":"https://orcid.org/0000-0002-7818-1855"},"institutions":[{"id":"https://openalex.org/I126158947","display_name":"Universidade Federal da Bahia","ror":"https://ror.org/03k3p7647","country_code":"BR","type":"education","lineage":["https://openalex.org/I126158947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos E. Barreto","raw_affiliation_strings":["Computer Science Department, Federal University of Bahia - UFBA, Salvador, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Federal University of Bahia - UFBA, Salvador, Brazil","institution_ids":["https://openalex.org/I126158947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15591715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"616","last_page":"621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9997000098228455,"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":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.9054003357887268},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.8237581849098206},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6805647611618042},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.6472366452217102},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5688925385475159},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5612486004829407},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.536088764667511},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5208181142807007},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5169076919555664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5023741722106934},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4849860668182373},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4472784996032715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.42720675468444824},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.41067665815353394},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.39889708161354065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36867114901542664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3106459975242615}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.9054003357887268},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.8237581849098206},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6805647611618042},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6472366452217102},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5688925385475159},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5612486004829407},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.536088764667511},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5208181142807007},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5169076919555664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5023741722106934},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4849860668182373},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4472784996032715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42720675468444824},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.41067665815353394},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.39889708161354065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36867114901542664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3106459975242615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bracis.2019.00113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bracis.2019.00113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th Brazilian Conference on Intelligent Systems (BRACIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W87092222","https://openalex.org/W103013408","https://openalex.org/W220087089","https://openalex.org/W1150705219","https://openalex.org/W1562135275","https://openalex.org/W1574954263","https://openalex.org/W1967987265","https://openalex.org/W1971784203","https://openalex.org/W1999929642","https://openalex.org/W2020344074","https://openalex.org/W2073849744","https://openalex.org/W2127218421","https://openalex.org/W2140405352","https://openalex.org/W2149230623","https://openalex.org/W2165142526","https://openalex.org/W2270192120","https://openalex.org/W2319660501","https://openalex.org/W2338355756","https://openalex.org/W2487770199","https://openalex.org/W2772904413","https://openalex.org/W2797764714","https://openalex.org/W3141012822","https://openalex.org/W6604212994","https://openalex.org/W6678914141","https://openalex.org/W6746641665","https://openalex.org/W7028815626"],"related_works":["https://openalex.org/W2381926679","https://openalex.org/W2007009951","https://openalex.org/W2082644203","https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2350539780","https://openalex.org/W3165040664","https://openalex.org/W97068511","https://openalex.org/W2092161674","https://openalex.org/W1549395822"],"abstract_inverted_index":{"K-modes,":[0,38],"an":[1,20,35,84],"extension":[2,36],"of":[3,37,55],"K-means,":[4],"aims":[5],"to":[6,14,23,48,60,80],"cluster":[7],"categorical":[8,61],"data":[9],"by":[10,95],"using":[11],"the":[12,25,41,50,53,87],"mode":[13],"update":[15,49],"clusters'":[16],"centroids,":[17,51],"as":[18],"well":[19],"overlap":[21],"measure":[22,47],"define":[24],"distance":[26],"between":[27],"objects":[28],"and":[29,52,71,75],"centers.":[30],"This":[31],"work":[32],"presents":[33],"K-fact,":[34,101],"which":[39],"proposes":[40],"frequency":[42],"factor,":[43],"a":[44],"new":[45],"probability-based":[46],"use":[54],"several":[56],"similarity":[57],"measures":[58],"suitable":[59],"values.":[62],"In":[63],"our":[64],"validity":[65,89],"scheme,":[66],"we":[67],"ran":[68],"both":[69],"K-modes":[70,91],"K-fact":[72],"over":[73],"real-world":[74],"synthetic":[76],"datasets":[77,104],"in":[78,100],"order":[79],"compare":[81],"them":[82],"with":[83,105],"index":[85],"from":[86],"external":[88],"criteria.":[90],"is":[92],"always":[93],"outperformed":[94],"some":[96],"parameter":[97],"set":[98],"used":[99],"especially":[102],"on":[103],"higher":[106],"or":[107],"moderate":[108],"variance.":[109]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}