{"id":"https://openalex.org/W2942745845","doi":"https://doi.org/10.1145/3312714.3312717","title":"Application of Attribute Correlation in Unsupervised Data Cleaning","display_name":"Application of Attribute Correlation in Unsupervised Data Cleaning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2942745845","doi":"https://doi.org/10.1145/3312714.3312717","mag":"2942745845"},"language":"en","primary_location":{"id":"doi:10.1145/3312714.3312717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3312714.3312717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 the 5th International Conference on e-Society, e-Learning and e-Technologies  - ICSLT 2019","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/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, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha, 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":false,"raw_author_name":"Chaofan Dai","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088273529","display_name":"Wenqian Wang","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":false,"raw_author_name":"Wenqian Wang","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2058,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57077506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9948999881744385,"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":0.9948999881744385,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9853000044822693,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9782999753952026,"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/redundancy","display_name":"Redundancy (engineering)","score":0.7034545540809631},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.698699951171875},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5499248504638672},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4805760383605957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47523263096809387},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47117048501968384},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.46982645988464355},{"id":"https://openalex.org/keywords/element","display_name":"Element (criminal law)","score":0.46694958209991455},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.4505477845668793},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4315890967845917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3887893557548523},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35850173234939575},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32929062843322754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19573679566383362}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7034545540809631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698699951171875},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5499248504638672},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4805760383605957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47523263096809387},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47117048501968384},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.46982645988464355},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.46694958209991455},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.4505477845668793},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4315890967845917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3887893557548523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35850173234939575},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32929062843322754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19573679566383362},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3312714.3312717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3312714.3312717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 the 5th International Conference on e-Society, e-Learning and e-Technologies  - ICSLT 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2048053751","https://openalex.org/W2067102178","https://openalex.org/W2083643015","https://openalex.org/W2247690851","https://openalex.org/W2259715629","https://openalex.org/W2263060133","https://openalex.org/W2368635037","https://openalex.org/W2379578127","https://openalex.org/W2410531948","https://openalex.org/W2480641892","https://openalex.org/W2524615958","https://openalex.org/W2579124921","https://openalex.org/W2616146705","https://openalex.org/W2782835884","https://openalex.org/W2783367877","https://openalex.org/W3004825711","https://openalex.org/W3008653445"],"related_works":["https://openalex.org/W2122678784","https://openalex.org/W1495042958","https://openalex.org/W2494338568","https://openalex.org/W2380000090","https://openalex.org/W2282510344","https://openalex.org/W139987158","https://openalex.org/W2374797863","https://openalex.org/W2183994405","https://openalex.org/W4234013965","https://openalex.org/W2349023125"],"abstract_inverted_index":{"Referring":[0],"to":[1,45,81,85,101,120,131,138,150,181],"the":[2,13,28,46,52,68,86,92,103,110,117,124,133,140,152,168,173,177],"supervised":[3,18],"learning":[4,7],"and":[5,19,24,40,62,90,122],"unsupervised":[6,20,49],"in":[8,113,136,155],"machine":[9],"learning,":[10],"we":[11,26,56,73,108,145,171],"divide":[12],"data":[14,29,95],"cleaning":[15],"processes":[16],"into":[17,32],"two":[21],"forms":[22],"too,":[23],"then,":[25],"reclassify":[27],"quality":[30],"problems":[31],"canonicalization":[33],"error,":[34,36],"redundancy":[35],"strong":[37],"logic":[38,42,54],"error":[39,43,159],"weak":[41,53],"according":[44,84],"characteristics":[47],"of":[48],"cleaning.":[50],"For":[51],"errors,":[55],"propose":[57],"a":[58,76,98,147],"repair":[59,129,179],"framework":[60],"AC-Framework":[61],"an":[63],"algorithm":[64,141,175,180],"AC-Repair":[65,174],"based":[66],"on":[67],"attribute":[69],"correlation.":[70],"When":[71],"repairing,":[72],"first":[74,111],"establish":[75],"priority":[77],"queue(PQ)":[78],"for":[79],"elements":[80],"be":[82,162],"repaired":[83,153,163],"minimum":[87],"cost":[88],"idea":[89],"take":[91],"corresponding":[93],"conflict-free":[94],"set(Icf)":[96],"as":[97,116],"training":[99],"set":[100,146],"learn":[102],"correlation":[104],"among":[105],"attributes.":[106],"Then,":[107],"select":[109],"element":[112,119,160],"PQ":[114,125],"list":[115,126],"candidate":[118],"repair,":[121],"recompute":[123],"after":[127],"one":[128],"round":[130],"improve":[132],"efficiency.":[134],"Finally,":[135],"order":[137],"prevent":[139],"from":[142],"endless":[143],"loops,":[144],"label":[148],"flag":[149],"mark":[151],"elements,":[154],"this":[156],"way,":[157],"every":[158],"will":[161],"at":[164],"most":[165],"once.":[166],"In":[167],"experimental":[169],"part,":[170],"compare":[172],"with":[176],"interpolation-based":[178],"verify":[182],"its":[183],"validity.":[184]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}