{"id":"https://openalex.org/W1569885642","doi":"https://doi.org/10.3233/jcm-2012-0444","title":"Fast attribute-based table clustering using Predicate-Trees: A vertical data mining approach","display_name":"Fast attribute-based table clustering using Predicate-Trees: A vertical data mining approach","publication_year":2012,"publication_date":"2012-11-05","ids":{"openalex":"https://openalex.org/W1569885642","doi":"https://doi.org/10.3233/jcm-2012-0444","mag":"1569885642"},"language":"en","primary_location":{"id":"doi:10.3233/jcm-2012-0444","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jcm-2012-0444","pdf_url":null,"source":{"id":"https://openalex.org/S2765058733","display_name":"Journal of Computational Methods in Sciences and Engineering","issn_l":"1472-7978","issn":["1472-7978","1875-8983"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Methods in Sciences and Engineering","raw_type":"journal-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/A5078516991","display_name":"Arjun Roy","orcid":"https://orcid.org/0000-0002-4279-9442"},"institutions":[{"id":"https://openalex.org/I57328836","display_name":"North Dakota State University","ror":"https://ror.org/05h1bnb22","country_code":"US","type":"education","lineage":["https://openalex.org/I57328836"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arjun G. Roy","raw_affiliation_strings":["Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA","[Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA","institution_ids":["https://openalex.org/I57328836"]},{"raw_affiliation_string":"[Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA]","institution_ids":["https://openalex.org/I57328836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101394686","display_name":"Arijit Chatterjee","orcid":null},"institutions":[{"id":"https://openalex.org/I57328836","display_name":"North Dakota State University","ror":"https://ror.org/05h1bnb22","country_code":"US","type":"education","lineage":["https://openalex.org/I57328836"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arijit Chatterjee","raw_affiliation_strings":["Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA","[Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA","institution_ids":["https://openalex.org/I57328836"]},{"raw_affiliation_string":"[Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA]","institution_ids":["https://openalex.org/I57328836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103842065","display_name":"Mohammad Kabir Hossain","orcid":null},"institutions":[{"id":"https://openalex.org/I57328836","display_name":"North Dakota State University","ror":"https://ror.org/05h1bnb22","country_code":"US","type":"education","lineage":["https://openalex.org/I57328836"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad K. Hossain","raw_affiliation_strings":["Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA","[Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA","institution_ids":["https://openalex.org/I57328836"]},{"raw_affiliation_string":"[Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA]","institution_ids":["https://openalex.org/I57328836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007656388","display_name":"William Perrizo","orcid":null},"institutions":[{"id":"https://openalex.org/I57328836","display_name":"North Dakota State University","ror":"https://ror.org/05h1bnb22","country_code":"US","type":"education","lineage":["https://openalex.org/I57328836"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Perrizo","raw_affiliation_strings":["Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA","[Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA","institution_ids":["https://openalex.org/I57328836"]},{"raw_affiliation_string":"[Department of Computer Science and Operations Research, North Dakota State University, Fargo, ND, USA]","institution_ids":["https://openalex.org/I57328836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078516991"],"corresponding_institution_ids":["https://openalex.org/I57328836"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.05024755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":"s1","first_page":"S139","last_page":"S146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"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":0.9991000294685364,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8264886140823364},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7786705493927002},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.6431951522827148},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6120057702064514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29009491205215454},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.22181901335716248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264886140823364},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7786705493927002},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.6431951522827148},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6120057702064514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29009491205215454},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.22181901335716248}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jcm-2012-0444","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jcm-2012-0444","pdf_url":null,"source":{"id":"https://openalex.org/S2765058733","display_name":"Journal of Computational Methods in Sciences and Engineering","issn_l":"1472-7978","issn":["1472-7978","1875-8983"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Methods in Sciences and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W126502183","https://openalex.org/W145304147","https://openalex.org/W769055222","https://openalex.org/W1554682463","https://openalex.org/W1992419399","https://openalex.org/W2005112390","https://openalex.org/W2061681234","https://openalex.org/W2098318741","https://openalex.org/W2157979971","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3106969033","https://openalex.org/W2186939576","https://openalex.org/W2357988910","https://openalex.org/W2377158164","https://openalex.org/W2187600494","https://openalex.org/W2114030128","https://openalex.org/W2948148442","https://openalex.org/W2135707701","https://openalex.org/W2352493357"],"abstract_inverted_index":{"With":[0],"technological":[1],"advancements,":[2],"massive":[3],"amount":[4,65],"of":[5,18,42,55,66,75,80],"data":[6,68,76,82,133,153],"is":[7,77,83],"being":[8],"collected":[9],"in":[10,150],"various":[11],"domains.":[12],"For":[13],"instance,":[14],"since":[15],"the":[16,33,51,139],"advent":[17],"digital":[19],"image":[20,152],"technology":[21],"and":[22,28,96,106,112,131,145,154],"remote":[23],"sensing":[24],"imagery":[25],"(RSI),":[26],"NASA":[27],"U.S.":[29],"Geological":[30],"Survey":[31],"through":[32],"Landsat":[34],"Data":[35],"Continuity":[36],"Mission,":[37],"has":[38],"been":[39],"capturing":[40],"images":[41,111],"Earth":[43],"down":[44],"to":[45],"15":[46],"meters":[47],"resolution.":[48],"Likewise,":[49],"consider":[50],"Internet,":[52],"where,":[53],"growth":[54],"social":[56],"media,":[57],"blog":[58],"Web":[59],"sites":[60],",":[61],"etc.":[62],"generates":[63],"exponential":[64],"textual":[67,118],"on":[69,125,138],"a":[70,113],"daily":[71],"basis.":[72],"Since":[73],"clustering":[74],"time-consuming,":[78],"much":[79,137],"these":[81,121],"archived":[84],"even":[85],"before":[86],"proper":[87],"analysis.":[88,156],"In":[89],"this":[90],"paper,":[91],"we":[92],"propose":[93],"two":[94],"novel":[95],"extremely":[97],"fast":[98,144],"algorithms":[99,122,142],"called":[100,115],"imgFAUST":[101],"or":[102],"Fast":[103],"Attribute-based":[104],"Unsupervised":[105],"Supervised":[107],"Table":[108],"Clustering":[109],"for":[110,117],"variation":[114],"docFAUST":[116],"data.":[119],"Both":[120],"are":[123,128,143],"based":[124],"Predicate-Trees":[126],"which":[127],"compressed,":[129],"lossless":[130],"data-mining-ready":[132],"structures.":[134],"Without":[135],"compromising":[136],"accuracy,":[140],"our":[141],"can":[146],"be":[147],"effectively":[148],"used":[149],"high-speed":[151],"document":[155]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}