{"id":"https://openalex.org/W2073251771","doi":"https://doi.org/10.1109/icde.2010.5447789","title":"Data cleansing as a transient service","display_name":"Data cleansing as a transient service","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2073251771","doi":"https://doi.org/10.1109/icde.2010.5447789","mag":"2073251771"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447789","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 (ICDE 2010)","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/A5004954473","display_name":"Tanveer A. Faruquie","orcid":"https://orcid.org/0009-0008-9474-7928"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Tanveer A Faruquie","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058758292","display_name":"Kalika Prasad","orcid":"https://orcid.org/0000-0001-8666-856X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"K Hima Prasad","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110629023","display_name":"L. Venkata Subramaniam","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"L Venkata Subramaniam","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047987914","display_name":"Mukesh Mohania","orcid":"https://orcid.org/0000-0003-4429-1412"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Mukesh Mohania","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023599295","display_name":"Girish Venkatachaliah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Girish Venkatachaliah","raw_affiliation_strings":["IBM India Software Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM India Software Lab, Bangalore, India","institution_ids":["https://openalex.org/I4210129961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056485618","display_name":"S. R. Kulkarni","orcid":"https://orcid.org/0000-0001-5390-8563"},"institutions":[{"id":"https://openalex.org/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shrinivas Kulkarni","raw_affiliation_strings":["IBM India Software Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM India Software Lab, Bangalore, India","institution_ids":["https://openalex.org/I4210129961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063058770","display_name":"Pramit Basu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pramit Basu","raw_affiliation_strings":["IBM India Software Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM India Software Lab, Bangalore, India","institution_ids":["https://openalex.org/I4210129961"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004954473"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":6.6478,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.96637878,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1025","last_page":"1036"},"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9918000102043152,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9807999730110168,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.7760332226753235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7683594226837158},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5977246165275574},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5672269463539124},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5488763451576233},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5411322712898254},{"id":"https://openalex.org/keywords/software-as-a-service","display_name":"Software as a service","score":0.5274460911750793},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.5030393004417419},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4864482581615448},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34255778789520264},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2513224184513092},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.18145433068275452},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10482719540596008},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09820836782455444},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.07951274514198303}],"concepts":[{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.7760332226753235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683594226837158},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5977246165275574},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5672269463539124},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5488763451576233},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5411322712898254},{"id":"https://openalex.org/C175133352","wikidata":"https://www.wikidata.org/wiki/Q1254596","display_name":"Software as a service","level":4,"score":0.5274460911750793},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.5030393004417419},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4864482581615448},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34255778789520264},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2513224184513092},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.18145433068275452},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10482719540596008},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09820836782455444},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.07951274514198303},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2010.5447789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447789","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 (ICDE 2010)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1610496399","https://openalex.org/W1964464249","https://openalex.org/W1967167578","https://openalex.org/W1975637389","https://openalex.org/W2068376489","https://openalex.org/W2072764742","https://openalex.org/W2120876973","https://openalex.org/W2137775416","https://openalex.org/W2164625277","https://openalex.org/W2337969425","https://openalex.org/W6636177537","https://openalex.org/W6680599078"],"related_works":["https://openalex.org/W1864280877","https://openalex.org/W3173750053","https://openalex.org/W2997590552","https://openalex.org/W4206347313","https://openalex.org/W2935682778","https://openalex.org/W2186039352","https://openalex.org/W4386159400","https://openalex.org/W2170955077","https://openalex.org/W2098734934","https://openalex.org/W2127148983"],"abstract_inverted_index":{"There":[0],"is":[1,99,135],"often":[2],"a":[3,20,25,56,75,78,92,96,132],"transient":[4,21],"need":[5,28],"within":[6],"enterprises":[7],"for":[8,40,64],"data":[9,17,26,65,84,141],"cleansing":[10,18,27,85,120,142],"which":[11,109],"can":[12,88],"be":[13,32,89],"satisfied":[14],"by":[15],"offering":[16],"as":[19,91],"service.":[22,93],"Every":[23],"time":[24],"arises":[29],"it":[30,111],"should":[31],"possible":[33],"to":[34,81,113,122,138],"provision":[35],"hardware,":[36],"software":[37,63],"and":[38,44,62,102,118],"staff":[39],"accomplishing":[41],"the":[42,47,116,119,140],"task":[43],"then":[45],"dismantling":[46],"set":[48],"up.":[49],"In":[50,126],"this":[51,127],"paper":[52,128],"we":[53,129],"present":[54,131],"such":[55,74],"system":[57,97,133],"that":[58,87,98,134],"uses":[59],"virtualized":[60,83],"hardware":[61],"cleansing.":[66],"We":[67,94],"share":[68],"actual":[69],"experiences":[70],"gained":[71],"from":[72],"building":[73],"system.We":[76],"use":[77],"cloud":[79],"infrastructure":[80,117],"offer":[82],"instances":[86],"accessed":[90],"build":[95],"scalable,":[100],"elastic":[101],"configurable.":[103],"Each":[104],"enterprise":[105],"has":[106],"unique":[107],"needs":[108,143],"makes":[110],"necessary":[112],"customize":[114],"both":[115],"algorithms":[121],"address":[123],"these":[124],"needs.":[125],"will":[130],"easily":[136],"configurable":[137],"suit":[139],"of":[144],"an":[145],"enterprise.":[146]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}