{"id":"https://openalex.org/W2018639042","doi":"https://doi.org/10.1145/1989323.1989458","title":"One-pass data mining algorithms in a DBMS with UDFs","display_name":"One-pass data mining algorithms in a DBMS with UDFs","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2018639042","doi":"https://doi.org/10.1145/1989323.1989458","mag":"2018639042"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","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/A5031610238","display_name":"Carlos Ordo\u0144\u1ebdz","orcid":"https://orcid.org/0009-0005-1135-9726"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carlos Ordonez","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001575666","display_name":"Sasi K. Pitchaimalai","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sasi K. Pitchaimalai","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031610238"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":3.8425,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93845547,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1217","last_page":"1220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9990000128746033,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.8621575832366943},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6598154306411743},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6396259069442749},{"id":"https://openalex.org/keywords/user-defined-function","display_name":"User-defined function","score":0.6216555237770081},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6031954288482666},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5575237274169922},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5345543622970581},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5169774293899536},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47294995188713074},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.4253599941730499},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35990291833877563},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.3191402554512024},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.21371528506278992},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14754974842071533},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.08571845293045044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8621575832366943},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6598154306411743},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6396259069442749},{"id":"https://openalex.org/C206384180","wikidata":"https://www.wikidata.org/wiki/Q599380","display_name":"User-defined function","level":5,"score":0.6216555237770081},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6031954288482666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5575237274169922},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5345543622970581},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5169774293899536},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47294995188713074},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.4253599941730499},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35990291833877563},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.3191402554512024},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.21371528506278992},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14754974842071533},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.08571845293045044},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1989323.1989458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1966901553","https://openalex.org/W1983306134","https://openalex.org/W2058494157","https://openalex.org/W2129212037"],"related_works":["https://openalex.org/W2382973082","https://openalex.org/W4312632526","https://openalex.org/W2086783690","https://openalex.org/W2056177422","https://openalex.org/W2573939812","https://openalex.org/W151494989","https://openalex.org/W4320473518","https://openalex.org/W2155838697","https://openalex.org/W2108932068","https://openalex.org/W2614112517"],"abstract_inverted_index":{"Data":[0],"mining":[1,31,80],"research":[2],"is":[3,59],"extensive,":[4],"but":[5],"most":[6],"work":[7,17,35],"has":[8],"proposed":[9],"efficient":[10],"algorithms,":[11],"data":[12,30,64,73,79,89],"structures":[13],"and":[14,49,94],"optimizations":[15],"that":[16,33,57],"outside":[18],"a":[19,29,39,44,88],"DBMS,":[20],"mostly":[21],"on":[22,36,43],"flat":[23],"files.":[24],"In":[25],"contrast,":[26],"we":[27],"present":[28],"system":[32,69],"can":[34,70,86],"top":[37],"of":[38,46],"relational":[40],"DBMS":[41],"based":[42],"combination":[45],"SQL":[47,58],"queries":[48],"User-Defined":[50],"Functions":[51],"(UDFs),":[52],"debuking":[53],"the":[54],"common":[55],"perception":[56],"inefficient":[60],"or":[61],"inadequate":[62],"for":[63],"mining.":[65],"We":[66],"show":[67],"our":[68,83],"analyze":[71],"large":[72],"sets":[74],"significantly":[75],"faster":[76],"than":[77],"external":[78],"tools.":[81],"Moreover,":[82],"UDF-based":[84],"algorithms":[85],"process":[87],"set":[90],"in":[91],"one":[92],"pass":[93],"have":[95],"linear":[96],"scalability.":[97]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}
