{"id":"https://openalex.org/W1992529939","doi":"https://doi.org/10.1145/1031171.1031218","title":"Compression schemes for differential categorical stream clustering","display_name":"Compression schemes for differential categorical stream clustering","publication_year":2004,"publication_date":"2004-11-13","ids":{"openalex":"https://openalex.org/W1992529939","doi":"https://doi.org/10.1145/1031171.1031218","mag":"1992529939"},"language":"en","primary_location":{"id":"doi:10.1145/1031171.1031218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","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/A5103927332","display_name":"Weiyun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weiyun Huang","raw_affiliation_strings":["Georgia Institute of Technology","[Georgia Institute of Technology.]"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology.]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089324850","display_name":"Edward Omiecinski","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Omiecinski","raw_affiliation_strings":["Georgia Institute of Technology","[Georgia Institute of Technology.]"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology.]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089765356","display_name":"Leo Mark","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leo Mark","raw_affiliation_strings":["Georgia Institute of Technology","[Georgia Institute of Technology.]"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology.]","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103927332"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.08997699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"232","last_page":"233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9983999729156494,"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":0.9983999729156494,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9944000244140625,"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":0.9934999942779541,"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":0.7229436039924622},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6112954020500183},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6051534414291382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5962079167366028},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.49279096722602844},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.4316234886646271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3543999195098877},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34252795577049255},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10778316855430603},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05976766347885132},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05826127529144287},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.053314536809921265}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7229436039924622},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6112954020500183},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6051534414291382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5962079167366028},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.49279096722602844},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.4316234886646271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3543999195098877},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34252795577049255},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10778316855430603},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05976766347885132},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05826127529144287},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.053314536809921265},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1031171.1031218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W147860157","https://openalex.org/W2122943553","https://openalex.org/W2131687179","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668","https://openalex.org/W2133382151","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"Stream":[0],"data":[1,7,12,24,39,63,69],"analysis":[2],"differs":[3],"significantly":[4],"from":[5],"traditional":[6],"processing.":[8],"To":[9],"process":[10,98],"the":[11,14,41,95,105],"online":[13],"algorithm":[15,96,112],"has":[16],"to":[17,93,97],"work":[18],"in":[19,29,40,52,66,107,121],"one":[20],"pass,":[21],"incorporating":[22],"new":[23],"into":[25],"a":[26,33],"model":[27,34],"maintained":[28],"main":[30],"memory.":[31],"Storing":[32],"or":[35],"synopsis":[36],"of":[37,88],"processed":[38],"memory,":[42],"which":[43],"we":[44],"call":[45],"\"data":[46],"compression\",":[47],"is":[48],"an":[49],"important":[50],"technique":[51],"both":[53],"incremental":[54],"and":[55,71,77,103],"differential":[56],"stream":[57],"mining.":[58],"This":[59],"paper":[60],"proposes":[61],"several":[62],"compression":[64,81,116],"schemes":[65,82,117],"one-pass":[67],"categorical":[68],"clustering,":[70],"demonstrates":[72],"their":[73],"performance":[74],"on":[75,114],"synthetic":[76],"real":[78],"data.":[79,109],"Our":[80],"can":[83],"efficiently":[84],"generate":[85],"compact":[86],"representations":[87],"original":[89],"data,":[90],"so":[91],"as":[92],"enable":[94],"streams":[99],"at":[100],"high":[101],"speed":[102],"detect":[104],"changes":[106],"underlying":[108],"The":[110],"example":[111],"based":[113],"these":[115],"achieves":[118],"good":[119],"accuracy":[120],"short":[122],"execution":[123],"time.":[124]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}