{"id":"https://openalex.org/W1963798100","doi":"https://doi.org/10.1109/infrkm.2012.6205022","title":"HADCLEAN: A hybrid approach to data cleaning in data warehouses","display_name":"HADCLEAN: A hybrid approach to data cleaning in data warehouses","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W1963798100","doi":"https://doi.org/10.1109/infrkm.2012.6205022","mag":"1963798100"},"language":"en","primary_location":{"id":"doi:10.1109/infrkm.2012.6205022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infrkm.2012.6205022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on Information Retrieval &amp; Knowledge Management","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/A5103570376","display_name":"Arindam Paul","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arindam Paul","raw_affiliation_strings":["Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Pilani, Rajasthan, India","[Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Rajasthan, India - 333031]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Pilani, Rajasthan, India","institution_ids":["https://openalex.org/I74796645"]},{"raw_affiliation_string":"[Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Rajasthan, India - 333031]","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038104679","display_name":"Varuni Ganesan","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Varuni Ganesan","raw_affiliation_strings":["Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Pilani, Rajasthan, India","[Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Rajasthan, India - 333031]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Pilani, Rajasthan, India","institution_ids":["https://openalex.org/I74796645"]},{"raw_affiliation_string":"[Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Rajasthan, India - 333031]","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044760764","display_name":"Jagat Sesh Challa","orcid":"https://orcid.org/0000-0002-9794-0087"},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jagat Sesh Challa","raw_affiliation_strings":["Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Pilani, Rajasthan, India","[Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Rajasthan, India - 333031]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Pilani, Rajasthan, India","institution_ids":["https://openalex.org/I74796645"]},{"raw_affiliation_string":"[Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Rajasthan, India - 333031]","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046414549","display_name":"Yashvardhan Sharma","orcid":"https://orcid.org/0000-0002-6024-1872"},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yashvardhan Sharma","raw_affiliation_strings":["Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Pilani, Rajasthan, India","[Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Rajasthan, India - 333031]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Pilani, Rajasthan, India","institution_ids":["https://openalex.org/I74796645"]},{"raw_affiliation_string":"[Department of Computer Science & Information Systems, Birla Institute of Technology & Science, Pilani, Rajasthan, India - 333031]","institution_ids":["https://openalex.org/I74796645"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.07,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86886658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9814000129699707,"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":0.9800000190734863,"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/data-warehouse","display_name":"Data warehouse","score":0.790082573890686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.729476273059845},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.6730221509933472},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5921226739883423},{"id":"https://openalex.org/keywords/transitive-closure","display_name":"Transitive closure","score":0.5078845620155334},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4704253673553467},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.46867427229881287},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45031335949897766},{"id":"https://openalex.org/keywords/closure","display_name":"Closure (psychology)","score":0.4398876428604126},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15351137518882751}],"concepts":[{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.790082573890686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729476273059845},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6730221509933472},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5921226739883423},{"id":"https://openalex.org/C128896722","wikidata":"https://www.wikidata.org/wiki/Q1501387","display_name":"Transitive closure","level":2,"score":0.5078845620155334},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4704253673553467},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.46867427229881287},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45031335949897766},{"id":"https://openalex.org/C146834321","wikidata":"https://www.wikidata.org/wiki/Q2979672","display_name":"Closure (psychology)","level":2,"score":0.4398876428604126},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15351137518882751},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infrkm.2012.6205022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infrkm.2012.6205022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on Information Retrieval &amp; Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W8844452","https://openalex.org/W95916044","https://openalex.org/W1606352430","https://openalex.org/W1612155886","https://openalex.org/W1677570742","https://openalex.org/W2010595692","https://openalex.org/W2012739991","https://openalex.org/W2068376489","https://openalex.org/W2077841391","https://openalex.org/W2100716182","https://openalex.org/W2154034026","https://openalex.org/W4285719527","https://openalex.org/W6600374956","https://openalex.org/W6603910945"],"related_works":["https://openalex.org/W2359423766","https://openalex.org/W1600485007","https://openalex.org/W2364216866","https://openalex.org/W2362009423","https://openalex.org/W2614633957","https://openalex.org/W4285114917","https://openalex.org/W2286015710","https://openalex.org/W1964533962","https://openalex.org/W3206523334","https://openalex.org/W2387224730"],"abstract_inverted_index":{"Data":[0],"Cleaning":[1],"is":[2,14,40,44],"a":[3,16,38,81],"very":[4,17],"important":[5],"part":[6],"of":[7,24,52,92],"the":[8,48,53,63],"data":[9,26,39,64,87],"warehouse":[10],"management":[11],"process.":[12],"It":[13],"not":[15],"easy":[18],"process":[19],"as":[20],"many":[21],"different":[22],"types":[23],"unclean":[25],"(bad":[27],"data,":[28,30],"incomplete":[29],"typos,":[31],"etc)":[32],"can":[33],"be":[34],"present.":[35],"Also,":[36],"whether":[37],"clean":[41,62],"or":[42],"dirty":[43],"highly":[45],"dependent":[46],"on":[47],"nature":[49],"and":[50,94],"source":[51],"raw":[54],"data.":[55],"Many":[56],"attempts":[57],"have":[58],"been":[59,77],"made":[60,78],"to":[61,79],"using":[65],"blocking":[66],"algorithms,":[67,69],"phonetic":[68],"etc.":[70],"In":[71],"this":[72],"paper":[73],"an":[74],"attempt":[75],"has":[76],"provide":[80],"hybrid":[82],"approach":[83],"HADCLEAN":[84],"for":[85],"cleaning":[86],"which":[88],"combines":[89],"modified":[90],"versions":[91],"PNRS":[93],"Transitive":[95],"closure":[96],"algorithms.":[97]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
