{"id":"https://openalex.org/W4312971344","doi":"https://doi.org/10.1109/access.2022.3222786","title":"Cleaning Data With Selection Rules","display_name":"Cleaning Data With Selection Rules","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312971344","doi":"https://doi.org/10.1109/access.2022.3222786"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3222786","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3222786","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09954011.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09954011.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067359675","display_name":"Toon Boeckling","orcid":"https://orcid.org/0000-0002-4972-5294"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Toon Boeckling","raw_affiliation_strings":["Department of Telecommunications and Information Processing, Ghent University, Ghent, Belgium","Department of Telecommunications and Information Processing, Ghent University, St.-Pietersnieuwstraat 41, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-4972-5294","affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Information Processing, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Telecommunications and Information Processing, Ghent University, St.-Pietersnieuwstraat 41, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036892531","display_name":"Guy De Tr\u00e9","orcid":"https://orcid.org/0000-0002-1283-1915"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Guy De Tre","raw_affiliation_strings":["Department of Telecommunications and Information Processing, Ghent University, Ghent, Belgium","Department of Telecommunications and Information Processing, Ghent University, St.-Pietersnieuwstraat 41, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-1283-1915","affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Information Processing, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Telecommunications and Information Processing, Ghent University, St.-Pietersnieuwstraat 41, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063611538","display_name":"Antoon Bronselaer","orcid":"https://orcid.org/0000-0001-6663-192X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Antoon Bronselaer","raw_affiliation_strings":["Department of Telecommunications and Information Processing, Ghent University, Ghent, Belgium","Department of Telecommunications and Information Processing, Ghent University, St.-Pietersnieuwstraat 41, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-6663-192X","affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Information Processing, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Telecommunications and Information Processing, Ghent University, St.-Pietersnieuwstraat 41, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1996,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80197184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"125212","last_page":"125229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987999796867371,"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/T11106","display_name":"Data Management and Algorithms","score":0.9958999752998352,"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":0.7429431080818176},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7231309413909912},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7176017165184021},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5576874613761902},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5322734117507935},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.52427738904953},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.456956148147583},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4164542853832245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3899521231651306},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3749125003814697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34879136085510254},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15597176551818848},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11285895109176636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429431080818176},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7231309413909912},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7176017165184021},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5576874613761902},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5322734117507935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.52427738904953},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.456956148147583},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4164542853832245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3899521231651306},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3749125003814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34879136085510254},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15597176551818848},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11285895109176636},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2022.3222786","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3222786","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09954011.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:archive.ugent.be:01GMT47SKYEJEEDHX448BAEBR5","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01GMT47SKYEJEEDHX448BAEBR5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISSN: 2169-3536","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:24e6da7e6c3b43d38743edf1b38ae7e6","is_oa":true,"landing_page_url":"https://doaj.org/article/24e6da7e6c3b43d38743edf1b38ae7e6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 125212-125229 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3222786","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3222786","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09954011.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312971344.pdf","grobid_xml":"https://content.openalex.org/works/W4312971344.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W150927061","https://openalex.org/W1484727516","https://openalex.org/W1585002373","https://openalex.org/W1595443289","https://openalex.org/W1700279323","https://openalex.org/W1787815906","https://openalex.org/W1891697557","https://openalex.org/W1971672826","https://openalex.org/W1985239372","https://openalex.org/W1992377735","https://openalex.org/W2004291985","https://openalex.org/W2041273463","https://openalex.org/W2044022210","https://openalex.org/W2044469685","https://openalex.org/W2081438120","https://openalex.org/W2099637074","https://openalex.org/W2099780809","https://openalex.org/W2114575260","https://openalex.org/W2116008126","https://openalex.org/W2122295577","https://openalex.org/W2153531471","https://openalex.org/W2167333415","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2185907055","https://openalex.org/W2475754495","https://openalex.org/W2548122763","https://openalex.org/W2591700809","https://openalex.org/W2600485169","https://openalex.org/W2921009679","https://openalex.org/W2948145720","https://openalex.org/W2983641625","https://openalex.org/W3004034804","https://openalex.org/W3082197983","https://openalex.org/W3191403450","https://openalex.org/W4205593042","https://openalex.org/W4223932145","https://openalex.org/W4226094170","https://openalex.org/W4234857865","https://openalex.org/W4240301789","https://openalex.org/W6634963241","https://openalex.org/W6637979377","https://openalex.org/W6639437908","https://openalex.org/W7005314720","https://openalex.org/W7027009766"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W1979740464","https://openalex.org/W2143345456","https://openalex.org/W2138823233","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W4315705795","https://openalex.org/W2101053337","https://openalex.org/W2766944175"],"abstract_inverted_index":{"In":[0],"this":[1,34,55],"paper,":[2],"we":[3],"propose":[4],"and":[5,22,42,146,170,175],"study":[6,39,59],"a":[7],"type":[8,35],"of":[9,19,28,36,47,54,60,76,95,113,121,125,155,168,172],"tuple-level":[10,29],"constraints":[11],"that":[12,23,84,110,157],"arises":[13],"from":[14],"the":[15,26,45,58,70,77,93,111,119,153],"selection":[16,64,96,114,141,180],"operator":[17],"\u03c3":[18],"relational":[20],"algebra":[21],"closely":[24],"resembles":[25],"concepts":[27,41],"denial":[30],"constraints.":[31],"We":[32,108],"call":[33],"constraintsselection":[37],"rulesand":[38],"their":[40],"properties":[43,112],"in":[44,66,100,166],"setting":[46],"data":[48],"consistency":[49],"management.":[50],"The":[51],"main":[52],"contribution":[53],"paper":[56],"is":[57,98,143,163],"rule":[61,85,122,158],"implication":[62,86,159],"with":[63,140,179],"rules":[65,97,115,142,181],"order":[67,101],"to":[68,102,117,129,161],"solve":[69],"error":[71,173],"localization":[72],"problem":[73],"by":[74],"means":[75],"set":[78],"cover":[79],"method.":[80],"It":[81],"turns":[82],"out":[83],"can":[87],"be":[88],"applied":[89],"more":[90],"easily":[91],"if":[92],"representation":[94],"extended":[99],"allow":[103,116],"gaps":[104],"between":[105],"attribute":[106],"values.":[107],"show":[109],"improve":[118],"performance":[120],"implication.":[123],"Evaluation":[124],"our":[126],"approach":[127],"compared":[128],"HoloClean":[130],"on":[131],"four":[132],"real-world":[133],"datasets":[134],"shows":[135],"promising":[136],"results.":[137],"First,":[138],"repair":[139,177],"often":[144],"faster":[145],"less":[147],"memory-consumable":[148],"than":[149],"HoloClean,":[150],"especially":[151],"when":[152],"amount":[154],"work":[156],"has":[160],"do":[162],"limited.":[164],"Second,":[165],"terms":[167],"precision":[169],"recall":[171],"detection":[174],"correction,":[176],"strategies":[178],"almost":[182],"always":[183],"outperform":[184],"HoloClean.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2023-01-05T00:00:00"}
