{"id":"https://openalex.org/W3165118285","doi":"https://doi.org/10.1186/s40537-021-00502-1","title":"Missing values compensation in duplicates detection using hot deck method","display_name":"Missing values compensation in duplicates detection using hot deck method","publication_year":2021,"publication_date":"2021-08-21","ids":{"openalex":"https://openalex.org/W3165118285","doi":"https://doi.org/10.1186/s40537-021-00502-1","mag":"3165118285"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-021-00502-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-021-00502-1","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-021-00502-1","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-021-00502-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064660283","display_name":"Abdulrazzak Ali","orcid":null},"institutions":[{"id":"https://openalex.org/I70374766","display_name":"University of Aden","ror":"https://ror.org/02w043707","country_code":"YE","type":"education","lineage":["https://openalex.org/I70374766"]}],"countries":["YE"],"is_corresponding":true,"raw_author_name":"Abdulrazzak Ali","raw_affiliation_strings":["Faculty of Computer and Information Technology, Aden University, Aden, Yemen"],"raw_orcid":"https://orcid.org/0000-0002-8004-6791","affiliations":[{"raw_affiliation_string":"Faculty of Computer and Information Technology, Aden University, Aden, Yemen","institution_ids":["https://openalex.org/I70374766"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072551128","display_name":"Nurul A. Emran","orcid":"https://orcid.org/0000-0003-2051-8336"},"institutions":[{"id":"https://openalex.org/I32589535","display_name":"Technical University of Malaysia Malacca","ror":"https://ror.org/01xb6rs26","country_code":"MY","type":"education","lineage":["https://openalex.org/I32589535"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Nurul A. Emran","raw_affiliation_strings":["Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, Ayer Keroh, Melaka, 76100, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, Ayer Keroh, Melaka, 76100, Malaysia","institution_ids":["https://openalex.org/I32589535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057475156","display_name":"Siti Azirah Asmai","orcid":"https://orcid.org/0000-0003-0413-3225"},"institutions":[{"id":"https://openalex.org/I32589535","display_name":"Technical University of Malaysia Malacca","ror":"https://ror.org/01xb6rs26","country_code":"MY","type":"education","lineage":["https://openalex.org/I32589535"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Siti A. Asmai","raw_affiliation_strings":["Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, Ayer Keroh, Melaka, 76100, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, Ayer Keroh, Melaka, 76100, Malaysia","institution_ids":["https://openalex.org/I32589535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064660283"],"corresponding_institution_ids":["https://openalex.org/I70374766"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":1.7909,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85038417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"8","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.98580002784729,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7966177463531494},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.7782756090164185},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7190409898757935},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5694334506988525},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5352550148963928},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5016641616821289},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49316948652267456},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4637959599494934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3416560888290405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3052625060081482},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1507171094417572},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14387938380241394},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12894654273986816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966177463531494},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.7782756090164185},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7190409898757935},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5694334506988525},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5352550148963928},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5016641616821289},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49316948652267456},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4637959599494934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3416560888290405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3052625060081482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1507171094417572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14387938380241394},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12894654273986816},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-021-00502-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-021-00502-1","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-021-00502-1","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8a650d873ea444b7b6d289cdeb7a8888","is_oa":true,"landing_page_url":"https://doaj.org/article/8a650d873ea444b7b6d289cdeb7a8888","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 8, Iss 1, Pp 1-19 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-021-00502-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-021-00502-1","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-021-00502-1","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3165118285.pdf","grobid_xml":"https://content.openalex.org/works/W3165118285.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1536099054","https://openalex.org/W1557752234","https://openalex.org/W1569123402","https://openalex.org/W1582201029","https://openalex.org/W1647671624","https://openalex.org/W1826929910","https://openalex.org/W1912295864","https://openalex.org/W1914869953","https://openalex.org/W1936150905","https://openalex.org/W1995099886","https://openalex.org/W2024770506","https://openalex.org/W2042913039","https://openalex.org/W2095644746","https://openalex.org/W2104511295","https://openalex.org/W2108991785","https://openalex.org/W2116781287","https://openalex.org/W2121424666","https://openalex.org/W2122131850","https://openalex.org/W2135942647","https://openalex.org/W2153977007","https://openalex.org/W2157468491","https://openalex.org/W2161370387","https://openalex.org/W2166988329","https://openalex.org/W2167011595","https://openalex.org/W2168650487","https://openalex.org/W2170674956","https://openalex.org/W2171710987","https://openalex.org/W2183278147","https://openalex.org/W2261631147","https://openalex.org/W2271690868","https://openalex.org/W2283645261","https://openalex.org/W2297918680","https://openalex.org/W2320366123","https://openalex.org/W2331986251","https://openalex.org/W2475932436","https://openalex.org/W2493860774","https://openalex.org/W2567094038","https://openalex.org/W2569876941","https://openalex.org/W2584402701","https://openalex.org/W2605690107","https://openalex.org/W2612457169","https://openalex.org/W2754627401","https://openalex.org/W2781143270","https://openalex.org/W2782976553","https://openalex.org/W2796406438","https://openalex.org/W2889578482","https://openalex.org/W2894986625","https://openalex.org/W2941197459","https://openalex.org/W2958248471","https://openalex.org/W3104667342","https://openalex.org/W3110475619","https://openalex.org/W3128248565","https://openalex.org/W3146259567","https://openalex.org/W4254788633","https://openalex.org/W6633267158","https://openalex.org/W6717023391"],"related_works":["https://openalex.org/W4380150146","https://openalex.org/W3024870410","https://openalex.org/W2410652950","https://openalex.org/W4283773154","https://openalex.org/W3139174110","https://openalex.org/W4289597203","https://openalex.org/W2085630472","https://openalex.org/W3216372614","https://openalex.org/W2187819724","https://openalex.org/W2594414941"],"abstract_inverted_index":{"Abstract":[0],"Duplicate":[1,89],"record":[2],"is":[3],"a":[4,85,205],"common":[5],"problem":[6],"within":[7,41,84,91,228],"data":[8,86,110,124,196,230],"sets":[9,111,197],"especially":[10],"in":[11,150,182],"huge":[12],"volume":[13],"databases.":[14],"The":[15,98,126,189,216],"accuracy":[16,186,207],"of":[17,23,38,81,108,133,184,218,225],"duplicate":[18,24,28,73,134,162,177,210,226],"detection":[19,29,74,135,163,178,211,227],"determines":[20],"the":[21,36,42,46,62,79,92,105,131,140,147,151,169,195],"efficiency":[22],"removal":[25],"process.":[26],"However,":[27],"has":[30],"become":[31],"more":[32],"challenging":[33],"due":[34],"to":[35,58,67,104,118,144,174,203,214],"presence":[37,80],"missing":[39,51,82,99,148],"values":[40,52,83,100,149],"records":[43,55],"where":[44],"during":[45],"clustering":[47],"and":[48,122,187,208],"matching":[49],"process,":[50],"can":[53],"cause":[54],"deemed":[56],"similar":[57],"be":[59,166],"inserted":[60],"into":[61,223],"wrong":[63],"group,":[64],"hence,":[65],"leading":[66],"undetected":[68],"duplicates.":[69],"In":[70],"this":[71,219],"paper,":[72],"improvement":[75],"was":[76,136,155,172,201],"proposed":[77],"despite":[78],"set":[87,95],"through":[88],"Detection":[90],"Incomplete":[93],"Data":[94],"(DDID)":[96],"method.":[97],"were":[101,128,198],"hypothetically":[102],"added":[103],"key":[106,152],"attributes":[107],"three":[109],"under":[112],"study,":[113],"using":[114,139,159],"an":[115,175],"arbitrary":[116],"pattern":[117],"simulate":[119],"both":[120],"complete":[121],"incomplete":[123,229],"sets.":[125,231],"results":[127,217],"analyzed,":[129],"then,":[130],"performance":[132,164,171],"evaluated":[137],"by":[138,158],"Hot":[141,160],"Deck":[142],"method":[143,179],"compensate":[145],"for":[146],"attributes.":[153],"It":[154],"hypothesized":[156],"that":[157,192],"Deck,":[161],"would":[165],"improved.":[167],"Furthermore,":[168],"DDID":[170,200],"compared":[173,213],"early":[176],"namely":[180],"DuDe,":[181],"terms":[183],"its":[185],"speed.":[188],"findings":[190],"yielded":[191],"even":[193],"though":[194],"incomplete,":[199],"able":[202],"offer":[204,221],"better":[206],"faster":[209],"as":[212],"DuDe.":[215],"study":[220],"insights":[222],"constraints":[224]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}