{"id":"https://openalex.org/W2119423285","doi":"https://doi.org/10.1109/icdew.2010.5452733","title":"Cleansing uncertain databases leveraging aggregate constraints","display_name":"Cleansing uncertain databases leveraging aggregate constraints","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2119423285","doi":"https://doi.org/10.1109/icdew.2010.5452733","mag":"2119423285"},"language":"en","primary_location":{"id":"doi:10.1109/icdew.2010.5452733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew.2010.5452733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW 2010)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5117634641","display_name":"Haiquan Chen","orcid":"https://orcid.org/0000-0003-1689-0549"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiquan Chen","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, USA","Department of Computer Science and Software Engineering, Auburn University, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, USA#TAB#","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001457193","display_name":"Wei\u2010Shinn Ku","orcid":"https://orcid.org/0000-0001-8636-4689"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Shinn Ku","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, USA","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, USA","institution_ids":[]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063351917","display_name":"Haixun Wang","orcid":"https://orcid.org/0009-0007-0773-7004"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixun Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":null,"first_page":"128","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9890000224113464,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9818000197410583,"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/exploit","display_name":"Exploit","score":0.7466301918029785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7103314995765686},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6921689510345459},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6828247308731079},{"id":"https://openalex.org/keywords/uncertain-data","display_name":"Uncertain data","score":0.6517393589019775},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5401943922042847},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.43508586287498474},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41371679306030273},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4037330746650696},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2479589879512787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1882697343826294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16506356000900269}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7466301918029785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103314995765686},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6921689510345459},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6828247308731079},{"id":"https://openalex.org/C2778865114","wikidata":"https://www.wikidata.org/wiki/Q7882489","display_name":"Uncertain data","level":2,"score":0.6517393589019775},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5401943922042847},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.43508586287498474},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41371679306030273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4037330746650696},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2479589879512787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1882697343826294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16506356000900269},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdew.2010.5452733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew.2010.5452733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.417.4131","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.417.4131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eng.auburn.edu/~weishinn/papers/MOUND2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1512485814","https://openalex.org/W1515568087","https://openalex.org/W1992609556","https://openalex.org/W2026984353","https://openalex.org/W2029138824","https://openalex.org/W2078686663","https://openalex.org/W2088422262","https://openalex.org/W2094500233","https://openalex.org/W2120825705","https://openalex.org/W2127186572","https://openalex.org/W2134152443","https://openalex.org/W2143485006","https://openalex.org/W2150137825","https://openalex.org/W2151322578","https://openalex.org/W2151363206","https://openalex.org/W2154368191","https://openalex.org/W2154709738","https://openalex.org/W2166916904","https://openalex.org/W2166994031","https://openalex.org/W2169600045","https://openalex.org/W2950556518","https://openalex.org/W6630527305","https://openalex.org/W6630652662","https://openalex.org/W6666720238","https://openalex.org/W6672615329","https://openalex.org/W6681474095","https://openalex.org/W6684648153"],"related_works":["https://openalex.org/W2744606804","https://openalex.org/W2125434953","https://openalex.org/W182068010","https://openalex.org/W2103934874","https://openalex.org/W2105402307","https://openalex.org/W2989526642","https://openalex.org/W2774667166","https://openalex.org/W1584872797","https://openalex.org/W1774414873","https://openalex.org/W2109606716"],"abstract_inverted_index":{"Emerging":[0],"uncertain":[1,10,43,111],"database":[2],"applications":[3],"often":[4],"involve":[5],"the":[6,20,50,56,118,125,131,151,171,174,186,193,200,204,210,217],"cleansing":[7],"(conditioning)":[8],"of":[9,52,155,202,221],"databases":[11,112],"using":[12],"additional":[13,40],"information":[14,41],"as":[15,133],"new":[16],"evidence":[17],"for":[18,62],"reducing":[19],"uncertainty.":[21],"However,":[22,84],"past":[23],"researches":[24],"on":[25,32,42,124,192],"conditioning":[26],"probabilistic":[27,212],"databases,":[28],"unfortunately,":[29],"only":[30],"focus":[31,123],"functional":[33],"dependency.":[34],"In":[35,101,158],"real":[36],"world":[37],"applications,":[38],"most":[39],"data":[44,78],"sets":[45,79],"can":[46,71,80],"be":[47,72,81],"acquired":[48],"in":[49,77],"form":[51],"aggregate":[53,57,69,91,115],"constraints":[54,70,92,172],"(e.g.,":[55],"results":[58],"are":[59],"published":[60],"online":[61],"various":[63],"statistical":[64],"purposes).":[65],"Therefore,":[66],"if":[67],"these":[68],"taken":[73],"into":[74],"account,":[75],"uncertainty":[76,95],"largely":[82],"reduced.":[83],"finding":[85],"a":[86,97,134],"practical":[87],"method":[88],"to":[89,93,108,148,160,232],"exploit":[90],"decrease":[94],"is":[96,120],"very":[98],"challenging":[99],"problem.":[100],"this":[102],"paper,":[103],"we":[104,122,177,196],"present":[105],"three":[106],"approaches":[107,229],"cleanse":[109],"(condition)":[110],"by":[113,129],"employing":[114],"constraints.":[116],"Because":[117],"problem":[119,132,137],"NP-hard,":[121],"two":[126],"approximation":[127],"strategies":[128],"modeling":[130],"nonlinear":[135],"optimization":[136],"and":[138,144,168,183,208,219,224],"then":[139,184],"utilizing":[140],"Simulated":[141],"Annealing":[142],"(SA)":[143],"Evolutionary":[145],"Algorithm":[146],"(EA)":[147],"sample":[149,194],"from":[150],"entire":[152],"solution":[153],"space":[154],"possible":[156,163,206],"worlds.":[157],"order":[159],"favor":[161],"those":[162],"worlds":[164],"holding":[165],"higher":[166],"probabilities":[167,201],"satisfying":[169],"all":[170,203],"at":[173],"same":[175],"time,":[176],"define":[178],"Satisfaction":[179],"Degree":[180],"Functions":[181],"(SDF)":[182],"construct":[185],"objective":[187],"function":[188],"accordingly.":[189],"Subsequently,":[190],"based":[191],"result,":[195],"remove":[197],"duplicates,":[198],"re-normalize":[199],"qualified":[205],"worlds,":[207],"derive":[209],"posterior":[211],"database.":[213],"Our":[214],"experiments":[215],"verify":[216],"efficiency":[218],"effectiveness":[220],"our":[222,227],"algorithms":[223],"show":[225],"that":[226],"approximate":[228],"scale":[230],"well":[231],"large-sized":[233],"databases.":[234]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}