{"id":"https://openalex.org/W2040439988","doi":"https://doi.org/10.1145/2245276.2245437","title":"Improving the offline clustering stage of data stream algorithms in scenarios with variable number of clusters","display_name":"Improving the offline clustering stage of data stream algorithms in scenarios with variable number of clusters","publication_year":2012,"publication_date":"2012-03-26","ids":{"openalex":"https://openalex.org/W2040439988","doi":"https://doi.org/10.1145/2245276.2245437","mag":"2040439988"},"language":"en","primary_location":{"id":"doi:10.1145/2245276.2245437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2245276.2245437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th Annual ACM Symposium on Applied Computing","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/A5042178956","display_name":"Elaine R. Faria","orcid":"https://orcid.org/0000-0001-5242-9026"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]},{"id":"https://openalex.org/I80850581","display_name":"Universidade Federal de Uberl\u00e2ndia","ror":"https://ror.org/04x3wvr31","country_code":"BR","type":"education","lineage":["https://openalex.org/I80850581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Elaine R. Faria","raw_affiliation_strings":["University of S\u00e3o Paulo and Fed. University of Uberl\u00e2ndia, S\u00e3o Carlos/Uberl\u00e2ndia, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo and Fed. University of Uberl\u00e2ndia, S\u00e3o Carlos/Uberl\u00e2ndia, Brazil","institution_ids":["https://openalex.org/I80850581","https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039629929","display_name":"Rodrigo C. Barros","orcid":"https://orcid.org/0000-0002-0782-9482"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rodrigo C. Barros","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114376321","display_name":"Jo\u00e3o Gama","orcid":"https://orcid.org/0000-0003-3357-1195"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Gama","raw_affiliation_strings":["University of Porto, Porto, Portugal","University of Porto , Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"University of Porto , Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079499583","display_name":"Andr\u00e9 C. P. L. F. de Carvalho","orcid":"https://orcid.org/0000-0002-4765-6459"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 C. P. L. F. Carvalho","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8846,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79554625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","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/T12761","display_name":"Data Stream Mining Techniques","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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9975000023841858,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9771999716758728,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8462401628494263},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.8452614545822144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7208035588264465},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.6000199317932129},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.5991716384887695},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5868421792984009},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5816152095794678},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5664251446723938},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5602928400039673},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5212610363960266},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5171489119529724},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48283156752586365},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.46253421902656555},{"id":"https://openalex.org/keywords/determining-the-number-of-clusters-in-a-data-set","display_name":"Determining the number of clusters in a data set","score":0.4435441792011261},{"id":"https://openalex.org/keywords/k-medians-clustering","display_name":"k-medians clustering","score":0.42954620718955994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25102826952934265},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21065735816955566}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8462401628494263},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8452614545822144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7208035588264465},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.6000199317932129},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.5991716384887695},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5868421792984009},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5816152095794678},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5664251446723938},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5602928400039673},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5212610363960266},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5171489119529724},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48283156752586365},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.46253421902656555},{"id":"https://openalex.org/C149872217","wikidata":"https://www.wikidata.org/wiki/Q5265701","display_name":"Determining the number of clusters in a data set","level":5,"score":0.4435441792011261},{"id":"https://openalex.org/C115328559","wikidata":"https://www.wikidata.org/wiki/Q4041956","display_name":"k-medians clustering","level":5,"score":0.42954620718955994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25102826952934265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21065735816955566},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2245276.2245437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2245276.2245437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th Annual ACM Symposium on Applied Computing","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":5,"referenced_works":["https://openalex.org/W1983492939","https://openalex.org/W2128040964","https://openalex.org/W2145898068","https://openalex.org/W2170936641","https://openalex.org/W2729451965"],"related_works":["https://openalex.org/W2393816671","https://openalex.org/W2156810603","https://openalex.org/W2188840951","https://openalex.org/W2293953271","https://openalex.org/W3080228052","https://openalex.org/W4241252752","https://openalex.org/W4240147959","https://openalex.org/W3176177124","https://openalex.org/W4384026335","https://openalex.org/W4292434959"],"abstract_inverted_index":{"Many":[0],"data":[1,13,89],"stream":[2],"clustering":[3],"algorithms":[4],"operate":[5],"in":[6,63,88],"two":[7,102],"well-defined":[8],"steps:":[9],"(i)":[10],"online":[11],"statistical":[12],"collection":[14],"stage;":[15],"and":[16],"(ii)":[17],"offline":[18,31,111],"macro-clustering":[19,32],"stage.":[20],"The":[21,34],"well-known":[22],"k-means":[23,36],"algorithm":[24,37],"is":[25,45,84],"often":[26],"employed":[27],"for":[28,105,125],"performing":[29],"the":[30,40,50,53,57,107,110,119,122],"step.":[33],"conventional":[35],"assumes":[38],"that":[39,71],"number":[41,80],"of":[42,55,59,81,114],"clusters":[43],"(k)":[44],"defined":[46],"a":[47,61,68,85,91],"priori":[48,62],"by":[49],"user.":[51],"Given":[52],"difficulty":[54],"defining":[56],"value":[58],"k":[60,74],"real-world":[64],"problems,":[65],"we":[66,96],"describe":[67],"new":[69],"approach":[70,100],"allows":[72],"estimating":[73],"dynamically":[75],"from":[76],"streams":[77],"with":[78,90,101],"variable":[79],"clusters,":[82],"which":[83],"common":[86],"scenario":[87],"non-stationary":[92],"distribution.":[93],"In":[94],"addition,":[95],"combine":[97],"our":[98],"dynamic":[99,120],"different":[103],"strategies":[104],"initializing":[106],"centroids":[108,126],"during":[109],"clustering.":[112],"Analysis":[113],"results":[115],"suggest":[116],"that,":[117],"using":[118],"approach,":[121],"method":[123],"k-means++":[124],"initialization":[127],"present":[128],"better":[129],"results.":[130]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}