{"id":"https://openalex.org/W2783084278","doi":"https://doi.org/10.1109/bigdata.2017.8258380","title":"Understanding data quality: Ensuring data quality by design in the rail industry","display_name":"Understanding data quality: Ensuring data quality by design in the rail industry","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783084278","doi":"https://doi.org/10.1109/bigdata.2017.8258380","mag":"2783084278"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.birmingham.ac.uk/en/publications/dbf15b02-2382-4078-8725-a32c39576fcd","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028483132","display_name":"Qian Fu","orcid":"https://orcid.org/0000-0002-6502-9934"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qian Fu","raw_affiliation_strings":["Birmingham Centre for Railway Research and Education School of Engineering, University of Birmingham, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birmingham Centre for Railway Research and Education School of Engineering, University of Birmingham, Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035605136","display_name":"John M. Easton","orcid":"https://orcid.org/0000-0001-8745-6753"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John M. Easton","raw_affiliation_strings":["Birmingham Centre for Railway Research and Education School of Engineering, University of Birmingham, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birmingham Centre for Railway Research and Education School of Engineering, University of Birmingham, Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3436,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84012549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3792","last_page":"3799"},"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9617999792098999,"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/quality","display_name":"Quality (philosophy)","score":0.7297207117080688},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.7226456999778748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5769758820533752},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.27531009912490845},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.10026198625564575}],"concepts":[{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.7297207117080688},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.7226456999778748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5769758820533752},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.27531009912490845},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.10026198625564575},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/bigdata.2017.8258380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:Publications/dbf15b02-2382-4078-8725-a32c39576fcd","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/dbf15b02-2382-4078-8725-a32c39576fcd","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/dbf15b02-2382-4078-8725-a32c39576fcd","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fu, Q & Easton, J 2018, Understanding data quality : ensuring data quality by design in the rail industry. in Proceedings of the 2017 IEEE International Conference on Big Data (BIGDATA). IEEE Xplore, pp. 3792-3799, 2017 IEEE International Conference on Big Data, Boston, Massachusetts, United States, 11/12/17. https://doi.org/10.1109/BigData.2017.8258380","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/dbf15b02-2382-4078-8725-a32c39576fcd","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/xpl/conhome/1802964/all-proceedings","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/dbf15b02-2382-4078-8725-a32c39576fcd","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/dbf15b02-2382-4078-8725-a32c39576fcd","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fu, Q & Easton, J 2018, Understanding data quality : ensuring data quality by design in the rail industry. in Proceedings of the 2017 IEEE International Conference on Big Data (BIGDATA). IEEE Xplore, pp. 3792-3799, 2017 IEEE International Conference on Big Data, Boston, Massachusetts, United States, 11/12/17. https://doi.org/10.1109/BigData.2017.8258380","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320339","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W175461165","https://openalex.org/W578970298","https://openalex.org/W595044628","https://openalex.org/W1535359155","https://openalex.org/W1548526958","https://openalex.org/W1550366119","https://openalex.org/W1558934762","https://openalex.org/W1567491469","https://openalex.org/W1576661435","https://openalex.org/W1939474812","https://openalex.org/W1966188439","https://openalex.org/W1986525510","https://openalex.org/W1998502859","https://openalex.org/W2000237244","https://openalex.org/W2003402737","https://openalex.org/W2004291985","https://openalex.org/W2011788014","https://openalex.org/W2018497961","https://openalex.org/W2034334856","https://openalex.org/W2036616350","https://openalex.org/W2046977065","https://openalex.org/W2053725099","https://openalex.org/W2088022181","https://openalex.org/W2092342745","https://openalex.org/W2100565110","https://openalex.org/W2101915266","https://openalex.org/W2128000597","https://openalex.org/W2136082883","https://openalex.org/W2140037779","https://openalex.org/W2140667122","https://openalex.org/W2144192824","https://openalex.org/W2151580670","https://openalex.org/W2156723220","https://openalex.org/W2166056089","https://openalex.org/W2197646089","https://openalex.org/W2330714974","https://openalex.org/W2478177667","https://openalex.org/W2732522353","https://openalex.org/W4206612144","https://openalex.org/W4242181390","https://openalex.org/W6607143681","https://openalex.org/W6616787365","https://openalex.org/W6632802655","https://openalex.org/W6633031314","https://openalex.org/W6681364530","https://openalex.org/W6683393963","https://openalex.org/W6740906098"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"The":[0],"railways":[1],"worldwide":[2],"are":[3,161],"increasingly":[4,123],"looking":[5],"to":[6,17,21,31,35,41,44,180,234],"the":[7,26,55,58,73,76,105,115,125,137,164,185,193,196,216,236,241],"integration":[8],"of":[9,28,72,75,109,148,184,187,195,199,204,243],"their":[10,47],"data":[11,82,112,138,146,174,208,224,245],"resources":[12,147],"coupled":[13,143],"with":[14,111,144],"advanced":[15],"analytics":[16],"enhance":[18],"traffic":[19],"management,":[20],"provide":[22,32],"new":[23],"insights":[24],"on":[25,233],"health":[27],"infrastructure":[29],"assets,":[30],"soft":[33],"linkages":[34],"other":[36],"transport":[37],"modes,":[38],"and":[39,103,213,239],"ultimately":[40],"enable":[42],"them":[43],"better":[45],"serve":[46],"customers.":[48],"As":[49],"in":[50,65,158,171,215,227],"many":[51,159],"industrial":[52],"sectors,":[53],"over":[54],"past":[56],"decade":[57],"rail":[59,165,217,229],"industry":[60,107,126,166],"has":[61],"been":[62],"investing":[63],"heavily":[64],"sensing":[66],"technologies":[67],"that":[68,117,129,157],"record":[69],"every":[70],"aspect":[71],"operation":[74],"railway":[77],"network.":[78],"However,":[79],"as":[80,104,152],"any":[81],"scientist":[83],"knows,":[84],"it":[85,118,130,134,139],"does":[86],"not":[87],"matter":[88],"how":[89,207],"good":[90],"an":[91],"algorithm":[92],"is,":[93],"if":[94],"you":[95,99],"put":[96],"rubbish":[97,101],"in,":[98],"get":[100],"out;":[102],"traditional":[106],"model":[108],"working":[110],"only":[113],"within":[114],"system":[116],"was":[119],"collected":[120],"by":[121,221],"becomes":[122],"fragile,":[124],"is":[127,140],"discovering":[128],"knows":[131],"less":[132],"than":[133],"thought":[135],"about":[136,206],"gathering.":[141],"When":[142],"legacy":[145],"unknown":[149],"accuracy,":[150],"such":[151],"design":[153],"diagrams":[154],"for":[155],"assets":[156],"cases":[160],"decades":[162],"old,":[163],"now":[167],"faces":[168],"a":[169,181,200,228,244],"crisis":[170],"which":[172],"its":[173,188],"may":[175],"become":[176],"essentially":[177],"worthless":[178],"due":[179],"poor":[182],"understanding":[183],"quality":[186,209,225,246],"data.":[189],"This":[190],"paper":[191],"reports":[192],"findings":[194],"first":[197],"phase":[198],"three-phase":[201],"systematic":[202],"review":[203],"literature":[205],"can":[210],"be":[211],"managed":[212],"evaluated":[214],"domain.":[218],"It":[219],"begins":[220],"discussing":[222],"why":[223],"matters":[226],"context,":[230],"before":[231],"going":[232],"define":[235],"quality,":[237],"introduce":[238],"expand":[240],"concept":[242],"schema.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}