{"id":"https://openalex.org/W2897069984","doi":"https://doi.org/10.3390/sym10100516","title":"Inconsistent Data Cleaning Based on the Maximum Dependency Set and Attribute Correlation","display_name":"Inconsistent Data Cleaning Based on the Maximum Dependency Set and Attribute Correlation","publication_year":2018,"publication_date":"2018-10-16","ids":{"openalex":"https://openalex.org/W2897069984","doi":"https://doi.org/10.3390/sym10100516","mag":"2897069984"},"language":"en","primary_location":{"id":"doi:10.3390/sym10100516","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym10100516","pdf_url":"https://www.mdpi.com/2073-8994/10/10/516/pdf?version=1539696007","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/10/10/516/pdf?version=1539696007","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100439832","display_name":"Pei Li","orcid":"https://orcid.org/0000-0001-8699-8825"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Li","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102326790","display_name":"Chaofan Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chaofan Dai","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100631553","display_name":"Wenqian Wang","orcid":"https://orcid.org/0000-0001-8382-7545"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqian Wang","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102326790"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.6605,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75075666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"10","issue":"10","first_page":"516","last_page":"516"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9884999990463257,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9672999978065491,"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/tuple","display_name":"Tuple","score":0.8433008193969727},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.7183262705802917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6953747868537903},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6902445554733276},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6270967721939087},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.5200604796409607},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.5172579884529114},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.462932288646698},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.437344491481781},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42335745692253113},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3991538882255554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23264658451080322},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22284790873527527},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.18329820036888123}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.8433008193969727},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.7183262705802917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6953747868537903},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6902445554733276},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6270967721939087},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.5200604796409607},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.5172579884529114},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.462932288646698},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.437344491481781},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42335745692253113},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3991538882255554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23264658451080322},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22284790873527527},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.18329820036888123},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym10100516","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym10100516","pdf_url":"https://www.mdpi.com/2073-8994/10/10/516/pdf?version=1539696007","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:af4a52c2774a4f82a65c11a89cfbd6f3","is_oa":true,"landing_page_url":"https://doaj.org/article/af4a52c2774a4f82a65c11a89cfbd6f3","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":"Symmetry, Vol 10, Iss 10, p 516 (2018)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/10/10/516/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/sym10100516","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym10100516","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym10100516","pdf_url":"https://www.mdpi.com/2073-8994/10/10/516/pdf?version=1539696007","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2897069984.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W885169983","https://openalex.org/W1910356505","https://openalex.org/W1924499163","https://openalex.org/W2048053751","https://openalex.org/W2067102178","https://openalex.org/W2167333415","https://openalex.org/W2247690851","https://openalex.org/W2270503162","https://openalex.org/W2287926972","https://openalex.org/W2376503150","https://openalex.org/W2480641892","https://openalex.org/W2507851989","https://openalex.org/W2524615958","https://openalex.org/W2594210058","https://openalex.org/W2594516545","https://openalex.org/W2607507174","https://openalex.org/W2885895599","https://openalex.org/W3008653445"],"related_works":["https://openalex.org/W2116767780","https://openalex.org/W2392606101","https://openalex.org/W3162070149","https://openalex.org/W2072918301","https://openalex.org/W165346131","https://openalex.org/W2133756937","https://openalex.org/W1594511838","https://openalex.org/W4285259755","https://openalex.org/W2385315033","https://openalex.org/W2362842011"],"abstract_inverted_index":{"In":[0,135,171],"banks,":[1],"governments,":[2],"and":[3,19,43,100,120,131,150,166,219,232,252,264,297,309,319,325],"Internet":[4],"companies,":[5],"inconsistent":[6,31,67,93],"data":[7,21,32,42,68,73,94],"problems":[8,48,103],"may":[9,49],"often":[10],"arise":[11],"when":[12],"various":[13],"information":[14,39],"systems":[15],"are":[16],"collecting,":[17],"processing,":[18],"updating":[20],"due":[22],"to":[23,36,65,85,97,146,163,183,192,213,240,260,269,274],"human":[24],"or":[25],"equipment":[26],"reasons.":[27],"The":[28],"emergence":[29],"of":[30,228],"makes":[33],"it":[34,61,83],"impossible":[35],"obtain":[37,147],"correct":[38],"from":[40,141],"the":[41,92,115,128,142,148,152,161,168,188,200,210,215,221,226,229,241,250,254,262,271,276,279,290,293,298,314,317],"reduces":[44],"its":[45],"availability.":[46],"Such":[47],"be":[50,184],"fatal":[51],"in":[52,69,104,235],"data-intensive":[53],"enterprises,":[54],"which":[55,159],"causes":[56],"huge":[57],"economic":[58],"losses.":[59],"Moreover,":[60],"is":[62],"very":[63],"difficult":[64,102],"clean":[66],"databases,":[70,105],"especially":[71],"for":[72,181],"containing":[74,95],"conditional":[75],"functional":[76],"dependencies":[77,140],"with":[78,292,300],"built-in":[79],"predicates":[80],"(CFDPs),":[81],"because":[82],"tends":[84],"contain":[86],"more":[87],"candidate":[88,195,230],"repair":[89,101,326],"values.":[90],"For":[91],"CFDPs":[96,294],"detect":[98],"incomplete":[99],"we":[106,137,173,198,245,288],"propose":[107],"a":[108,121,177,194,266,285,301,306,310,329],"dependency":[109,117,144],"lifting":[110],"algorithm":[111,123,154,304],"(DLA)":[112],"based":[113,125,186,248,295],"on":[114,126,187,249,305],"maximum":[116],"set":[118,145,175,212],"(MDS)":[119],"reparation":[122,247,258],"(C-Repair)":[124],"integrating":[127],"minimum":[129,189],"cost":[130,190],"attribute":[132],"correlation,":[133],"respectively.":[134],"detection,":[136],"find":[138],"recessive":[139],"original":[143,153],"MDS":[149],"improve":[151,261],"by":[155],"dynamic":[156],"domain":[157],"adjustment,":[158],"extends":[160],"applicability":[162],"continuous":[164],"attributes":[165,218],"improves":[167],"detection":[169,324],"accuracy.":[170],"reparation,":[172],"first":[174],"up":[176,284],"priority":[178],"queue":[179],"(PQ)":[180],"elements":[182,273],"repaired":[185,272],"idea":[191],"select":[193],"element;":[196],"then,":[197],"treat":[199],"corresponding":[201],"conflict-free":[202],"instance":[203,308],"(":[204],"I":[205,236],"n":[206,237],"v":[207,238],")":[208],"as":[209],"training":[211],"learn":[214],"correlation":[216],"among":[217],"compute":[220],"weighted":[222],"distance":[223],"(WDis)":[224],"between":[225],"tuple":[227],"element":[231],"other":[233],"tuples":[234],"according":[239],"correlation;":[242],"and,":[243],"lastly,":[244],"perform":[246],"WDis":[251],"re-compute":[253],"PQ":[255],"after":[256],"each":[257],"round":[259],"efficiency,":[263],"use":[265],"label,":[267],"flag,":[268],"mark":[270],"ensure":[275],"convergence":[277],"at":[278,328],"same":[280],"time.":[281],"By":[282],"setting":[283],"contrast":[286],"experiment,":[287],"compare":[289],"DLA":[291,318],"algorithm,":[296],"C-Repair":[299,320],"cost-based,":[302],"interpolation-based":[303],"simulated":[307],"real":[311],"instance.":[312],"From":[313],"experimental":[315],"results,":[316],"algorithms":[321],"have":[322],"better":[323],"ability":[327],"higher":[330],"time":[331],"cost.":[332]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}