{"id":"https://openalex.org/W4387088968","doi":"https://doi.org/10.1109/cita58204.2023.10262802","title":"A Framework of Data Quality Assurance using Machine Learning","display_name":"A Framework of Data Quality Assurance using Machine Learning","publication_year":2023,"publication_date":"2023-08-03","ids":{"openalex":"https://openalex.org/W4387088968","doi":"https://doi.org/10.1109/cita58204.2023.10262802"},"language":"en","primary_location":{"id":"doi:10.1109/cita58204.2023.10262802","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cita58204.2023.10262802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 13th International Conference on Information Technology in Asia (CITA)","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/A5114085741","display_name":"Ng Boon Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106414","display_name":"Forest Department Sarawak","ror":"https://ror.org/01n67jr26","country_code":"MY","type":"government","lineage":["https://openalex.org/I4210106414"]},{"id":"https://openalex.org/I2800797430","display_name":"Sarawak General Hospital","ror":"https://ror.org/01y946378","country_code":"MY","type":"healthcare","lineage":["https://openalex.org/I2800797430"]},{"id":"https://openalex.org/I4210091788","display_name":"Sarawak Biodiversity Centre","ror":"https://ror.org/00g3bkn86","country_code":"MY","type":"other","lineage":["https://openalex.org/I4210091788"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Ng Boon Ding","raw_affiliation_strings":["Politeknik Kuching Sarawak,Kuching,Sarawak","Politeknik Kuching Sarawak, Kuching, Sarawak"],"affiliations":[{"raw_affiliation_string":"Politeknik Kuching Sarawak,Kuching,Sarawak","institution_ids":["https://openalex.org/I4210106414","https://openalex.org/I2800797430","https://openalex.org/I4210091788"]},{"raw_affiliation_string":"Politeknik Kuching Sarawak, Kuching, Sarawak","institution_ids":["https://openalex.org/I4210106414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112033570","display_name":"Edwin Mit","orcid":null},"institutions":[{"id":"https://openalex.org/I41461413","display_name":"Universiti Malaysia Sarawak","ror":"https://ror.org/05b307002","country_code":"MY","type":"education","lineage":["https://openalex.org/I41461413"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Edwin Mit","raw_affiliation_strings":["Universiti Malaysia Sarawak,Kota Samarahan,Sarawak","Universiti Malaysia Sarawak, Kota Samarahan, Sarawak"],"affiliations":[{"raw_affiliation_string":"Universiti Malaysia Sarawak,Kota Samarahan,Sarawak","institution_ids":["https://openalex.org/I41461413"]},{"raw_affiliation_string":"Universiti Malaysia Sarawak, Kota Samarahan, Sarawak","institution_ids":["https://openalex.org/I41461413"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114085741"],"corresponding_institution_ids":["https://openalex.org/I2800797430","https://openalex.org/I4210091788","https://openalex.org/I4210106414"],"apc_list":null,"apc_paid":null,"fwci":0.2545,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59359008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"45","issue":null,"first_page":"88","last_page":"93"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9878000020980835,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9804999828338623,"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/computer-science","display_name":"Computer science","score":0.8031953573226929},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.7771264314651489},{"id":"https://openalex.org/keywords/quality-assurance","display_name":"Quality assurance","score":0.724015474319458},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6925889849662781},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5363577008247375},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5296991467475891},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5117599964141846},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46933451294898987},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.4468909502029419},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40651658177375793},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3334311246871948},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16777855157852173},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1295330822467804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031953573226929},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.7771264314651489},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.724015474319458},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6925889849662781},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5363577008247375},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5296991467475891},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5117599964141846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46933451294898987},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.4468909502029419},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40651658177375793},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3334311246871948},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16777855157852173},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1295330822467804},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C2778618615","wikidata":"https://www.wikidata.org/wiki/Q4008393","display_name":"External quality assessment","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cita58204.2023.10262802","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cita58204.2023.10262802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 13th International Conference on Information Technology in Asia (CITA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324896","display_name":"Universiti Malaysia Sarawak","ror":"https://ror.org/05b307002"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1472067","https://openalex.org/W1567491469","https://openalex.org/W1932472321","https://openalex.org/W1978874995","https://openalex.org/W2117366235","https://openalex.org/W2216946510","https://openalex.org/W2798218576","https://openalex.org/W2897611820","https://openalex.org/W3139588915","https://openalex.org/W3158459113","https://openalex.org/W3158569595","https://openalex.org/W4309367404","https://openalex.org/W4313433600","https://openalex.org/W4384039661","https://openalex.org/W4384345694","https://openalex.org/W4393977493","https://openalex.org/W6750872235","https://openalex.org/W6841065016"],"related_works":["https://openalex.org/W962911587","https://openalex.org/W4200551113","https://openalex.org/W2270762093","https://openalex.org/W4255072332","https://openalex.org/W2028861106","https://openalex.org/W3126834064","https://openalex.org/W1754154538","https://openalex.org/W3169246587","https://openalex.org/W4253714063","https://openalex.org/W2984010599"],"abstract_inverted_index":{"This":[0,79],"paper":[1],"presented":[2],"a":[3,17,56],"framework":[4,90,93,136],"of":[5,28,36,44,48,52,65,71,115,128,150],"data":[6,30,49,67,73,76,102,117,129,142],"quality":[7,14,27],"assurance":[8,15],"by":[9],"applying":[10],"machine":[11,58],"learning.":[12],"Data":[13],"often":[16],"major":[18],"concern":[19],"in":[20,111],"the":[21,29,34,37,41,72,84,89,101,112,116,126,141,148,151],"decision-making":[22],"derivation":[23],"since":[24],"decades.":[25],"Poor":[26],"will":[31,146],"eventually":[32],"affect":[33],"result":[35],"decision":[38],"making.":[39],"Despite":[40],"frequent":[42],"occurrence":[43],"missing":[45],"data,":[46,53],"reliability":[47],"and":[50,75],"inconsistency":[51],"there":[54],"are":[55],"few":[57],"learning":[59],"algorithms":[60,99],"that":[61,134],"can":[62],"perform":[63],"prevention":[64],"poor-quality":[66],"at":[68],"early":[69],"stage":[70,114],"acquisition":[74],"cleansing":[77],"effectively.":[78],"research":[80],"aims":[81],"to":[82,96,108,139],"solve":[83],"challenges":[85],"mentioned":[86],"above":[87],"through":[88],"designed.":[91],"The":[92],"is":[94,123,132,137],"designed":[95],"integrate":[97],"two":[98],"into":[100],"management":[103,118],"lifecycle.":[104],"Preventive":[105],"algorithm":[106,122],"meant":[107],"be":[109,147],"applied":[110,124],"earlier":[113],"lifecycle":[119],"while":[120],"predictive":[121],"for":[125],"purpose":[127],"cleansing.":[130],"It":[131],"foresee":[133],"this":[135],"able":[138],"improve":[140],"quality.":[143],"Future":[144],"work":[145],"implementation":[149],"framework.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
