{"id":"https://openalex.org/W2068524108","doi":"https://doi.org/10.1109/indin.2014.6945559","title":"A framework for detecting unnecessary industrial data in ETL processes","display_name":"A framework for detecting unnecessary industrial data in ETL processes","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2068524108","doi":"https://doi.org/10.1109/indin.2014.6945559","mag":"2068524108"},"language":"en","primary_location":{"id":"doi:10.1109/indin.2014.6945559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin.2014.6945559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 12th IEEE International Conference on Industrial Informatics (INDIN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.repository.cam.ac.uk/bitstreams/40e1486b-3c22-4748-a10f-0c863238a2b1/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086764393","display_name":"Philip Woodall","orcid":"https://orcid.org/0000-0003-0412-1347"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Philip Woodall","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK","Department of Engineering, University of Cambridge,,UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge,,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004750112","display_name":"Torben Jess","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Torben Jess","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK","Department of Engineering, University of Cambridge,,UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge,,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009773655","display_name":"Mark Harrison","orcid":"https://orcid.org/0000-0002-7584-0130"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Harrison","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK","Department of Engineering, University of Cambridge,,UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge,,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029346937","display_name":"Duncan McFarlane","orcid":"https://orcid.org/0000-0002-1558-7823"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Duncan McFarlane","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK","Department of Engineering, University of Cambridge,,UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge,,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109371822","display_name":"Amar Shah","orcid":"https://orcid.org/0009-0002-0930-6949"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amar Shah","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK","Department of Engineering, University of Cambridge,,UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge,,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002970717","display_name":"William E. Krechel","orcid":null},"institutions":[{"id":"https://openalex.org/I1295339012","display_name":"Boeing (United States)","ror":"https://ror.org/04sm5zn07","country_code":"US","type":"company","lineage":["https://openalex.org/I1295339012"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Krechel","raw_affiliation_strings":["Boeing, USA"],"affiliations":[{"raw_affiliation_string":"Boeing, USA","institution_ids":["https://openalex.org/I1295339012"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085806886","display_name":"Eric Nicks","orcid":null},"institutions":[{"id":"https://openalex.org/I1295339012","display_name":"Boeing (United States)","ror":"https://ror.org/04sm5zn07","country_code":"US","type":"company","lineage":["https://openalex.org/I1295339012"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Nicks","raw_affiliation_strings":["Boeing, USA"],"affiliations":[{"raw_affiliation_string":"Boeing, USA","institution_ids":["https://openalex.org/I1295339012"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5086764393"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.8408,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78732054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"8","issue":null,"first_page":"472","last_page":"476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T12607","display_name":"Personal Information Management and User Behavior","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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":0.9929999709129333,"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-warehouse","display_name":"Data warehouse","score":0.803593635559082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7768442034721375},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6465367078781128},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5861606001853943},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.5602977871894836},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4826793968677521},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4689701795578003},{"id":"https://openalex.org/keywords/online-analytical-processing","display_name":"Online analytical processing","score":0.4122750163078308},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.2199060022830963},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1339036524295807},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0925191342830658}],"concepts":[{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.803593635559082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768442034721375},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6465367078781128},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5861606001853943},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.5602977871894836},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4826793968677521},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4689701795578003},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.4122750163078308},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2199060022830963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1339036524295807},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0925191342830658},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/indin.2014.6945559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin.2014.6945559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 12th IEEE International Conference on Industrial Informatics (INDIN)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/251059","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/251059","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/40e1486b-3c22-4748-a10f-0c863238a2b1/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},{"id":"pmh:oai:generic.eprints.org:662128","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/662128/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:www.repository.cam.ac.uk:1810/251059","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/251059","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/40e1486b-3c22-4748-a10f-0c863238a2b1/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2068524108.pdf"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1893018","https://openalex.org/W1579068499","https://openalex.org/W1982428762","https://openalex.org/W2100153179","https://openalex.org/W2143180374","https://openalex.org/W2157010027","https://openalex.org/W3146259567","https://openalex.org/W4238104076","https://openalex.org/W6634545978"],"related_works":["https://openalex.org/W2378213774","https://openalex.org/W2357522326","https://openalex.org/W2363019959","https://openalex.org/W1535822977","https://openalex.org/W23190051","https://openalex.org/W2367419170","https://openalex.org/W6138692","https://openalex.org/W2377387014","https://openalex.org/W2382180329","https://openalex.org/W2375394542"],"abstract_inverted_index":{"Extract":[0],"transform":[1],"and":[2,80,107,111,141,149,170],"load":[3],"(ETL)":[4],"is":[5],"a":[6,28,102],"critical":[7],"process":[8,90],"used":[9,95,163],"by":[10,38,121],"industrial":[11,39],"organisations":[12],"to":[13,19,27,51,66,136,181,188],"shift":[14],"data":[15,29,36,64,76,84,110,138,144],"from":[16,23,114],"one":[17],"database":[18],"another,":[20],"such":[21],"as":[22,176],"an":[24],"operational":[25],"system":[26],"warehouse.":[30],"With":[31],"the":[32,63,72,83,88,131,168,184],"increasing":[33],"amount":[34],"of":[35,48,82,130,167,178],"stored":[37],"organisations,":[40],"some":[41,172],"ETL":[42,73,89,117,190],"processes":[43,118],"can":[44,54,78,161,186],"take":[45],"in":[46],"excess":[47],"12":[49],"hours":[50],"complete;":[52],"this":[53],"leave":[55],"decision":[56],"makers":[57],"stranded":[58],"while":[59],"they":[60],"wait":[61],"for":[62,104,164],"needed":[65],"support":[67],"their":[68],"decisions.":[69],"After":[70],"designing":[71],"processes,":[74],"inevitably":[75],"requirements":[77],"change,":[79],"much":[81],"that":[85,160],"goes":[86],"through":[87],"may":[91],"not":[92],"ever":[93],"be":[94,146,162],"or":[96,125],"needed.":[97],"This":[98],"paper":[99],"therefore":[100],"proposes":[101],"framework":[103,132,185],"dynamically":[105],"detecting":[106],"predicting":[108],"unnecessary":[109],"preventing":[112],"it":[113,123],"slowing":[115],"down":[116],"-":[119],"either":[120],"removing":[122],"entirely":[124],"deprioritizing":[126],"it.":[127],"Other":[128],"advantages":[129],"include":[133],"being":[134],"able":[135],"prioritise":[137],"cleansing":[139],"tasks":[140],"determining":[142],"what":[143],"should":[145],"processed":[147],"first":[148],"placed":[150],"into":[151],"fast":[152],"access":[153],"memory.":[154],"We":[155],"show":[156],"existing":[157],"example":[158],"algorithms":[159],"each":[165],"component":[166],"framework,":[169],"present":[171],"initial":[173],"testing":[174],"results":[175],"part":[177],"our":[179],"research":[180],"determine":[182],"whether":[183],"help":[187],"reduce":[189],"time.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
