{"id":"https://openalex.org/W4402381404","doi":"https://doi.org/10.3389/fdata.2024.1446071","title":"SparkDWM: a scalable design of a Data Washing Machine using Apache Spark","display_name":"SparkDWM: a scalable design of a Data Washing Machine using Apache Spark","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4402381404","doi":"https://doi.org/10.3389/fdata.2024.1446071","pmid":"https://pubmed.ncbi.nlm.nih.gov/39314986"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2024.1446071","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1446071","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1446071/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1446071/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015340472","display_name":"Nicholas Kofi Akortia Hagan","orcid":null},"institutions":[{"id":"https://openalex.org/I102401767","display_name":"University of Arkansas at Little Rock","ror":"https://ror.org/04fttyv97","country_code":"US","type":"education","lineage":["https://openalex.org/I102401767"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Kofi Akortia Hagan","raw_affiliation_strings":["Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States","institution_ids":["https://openalex.org/I102401767"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080276323","display_name":"John R. Talburt","orcid":null},"institutions":[{"id":"https://openalex.org/I102401767","display_name":"University of Arkansas at Little Rock","ror":"https://ror.org/04fttyv97","country_code":"US","type":"education","lineage":["https://openalex.org/I102401767"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Talburt","raw_affiliation_strings":["Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States","institution_ids":["https://openalex.org/I102401767"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102401767"],"apc_list":{"value":1285,"currency":"USD","value_usd":1285},"apc_paid":{"value":1285,"currency":"USD","value_usd":1285},"fwci":0.3468,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64218473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"7","issue":null,"first_page":"1446071","last_page":"1446071"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.992900013923645,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.989799976348877,"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":0.814395546913147},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8110167980194092},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.8026351928710938},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7995260953903198},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5962777137756348},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5696366429328918},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5356227159500122},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.53034508228302},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46910104155540466},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.45704442262649536},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4471936523914337},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.44707056879997253},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43685969710350037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3432789444923401},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3430723547935486},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3274805545806885},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26897236704826355},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1183716356754303},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1012650728225708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814395546913147},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8110167980194092},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.8026351928710938},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7995260953903198},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5962777137756348},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5696366429328918},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5356227159500122},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.53034508228302},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46910104155540466},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.45704442262649536},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4471936523914337},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.44707056879997253},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43685969710350037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3432789444923401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3430723547935486},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3274805545806885},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26897236704826355},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1183716356754303},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1012650728225708},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fdata.2024.1446071","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1446071","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1446071/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmid:39314986","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39314986","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in big data","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11416992","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11416992","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11416992/pdf/fdata-07-1446071.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Big Data","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:874615f48276451a947fcbfd60b0967d","is_oa":false,"landing_page_url":"https://doaj.org/article/874615f48276451a947fcbfd60b0967d","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdata.2024.1446071","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1446071","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1446071/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4156043112","display_name":"RII Track-1: Data Analytics that are Robust and Trusted (DART): From Smart Curation to Socially Aware Decision Making","funder_award_id":"1946391","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402381404.pdf","grobid_xml":"https://content.openalex.org/works/W4402381404.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W146810917","https://openalex.org/W1827980970","https://openalex.org/W1921100529","https://openalex.org/W1981590391","https://openalex.org/W1985982729","https://openalex.org/W1986017822","https://openalex.org/W2031250218","https://openalex.org/W2105947650","https://openalex.org/W2119738171","https://openalex.org/W2131975293","https://openalex.org/W2135054486","https://openalex.org/W2173213060","https://openalex.org/W2210065635","https://openalex.org/W2401272958","https://openalex.org/W2408419917","https://openalex.org/W2535168187","https://openalex.org/W2542459869","https://openalex.org/W2748156246","https://openalex.org/W2898885069","https://openalex.org/W2933723051","https://openalex.org/W2934044474","https://openalex.org/W2980226560","https://openalex.org/W2997562227","https://openalex.org/W3014295153","https://openalex.org/W3112013808","https://openalex.org/W3119203516","https://openalex.org/W3176546289","https://openalex.org/W4361286889","https://openalex.org/W4388053097","https://openalex.org/W4392386152","https://openalex.org/W6605873061","https://openalex.org/W6679815717","https://openalex.org/W6712951426","https://openalex.org/W6714190092","https://openalex.org/W6760885858"],"related_works":["https://openalex.org/W4313549863","https://openalex.org/W2395465245","https://openalex.org/W2072205733","https://openalex.org/W2101762871","https://openalex.org/W3176957927","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991"],"abstract_inverted_index":{"Data":[0,90,113,125,148,191],"volume":[1],"has":[2],"been":[3],"one":[4],"of":[5,9,17,23,57,61,110,161,167],"the":[6,15,52,58,73,89,106,111,124,142,146,159],"fast-growing":[7],"assets":[8],"most":[10,62],"real-world":[11,54,168],"applications.":[12],"This":[13,77],"increases":[14],"rate":[16],"human":[18],"errors":[19],"such":[20],"as":[21,145],"duplication":[22],"records,":[24],"misspellings,":[25],"and":[26,122,201],"erroneous":[27],"transpositions,":[28],"among":[29],"other":[30],"data":[31,44,75,101],"quality":[32],"issues.":[33],"Entity":[34,64],"Resolution":[35,65],"is":[36,67],"an":[37],"ETL":[38],"process":[39],"that":[40,138,182,203],"aims":[41,79],"to":[42,51,71,80,93,129,176],"resolve":[43],"inconsistencies":[45],"by":[46,116],"ensuring":[47,68],"entities":[48],"are":[49],"referring":[50],"same":[53,143],"objects.":[55],"One":[56],"main":[59],"challenges":[60],"traditional":[63],"systems":[66,140],"their":[69],"scalability":[70,160],"meet":[72],"rising":[74],"needs.":[76],"research":[78],"refactor":[81],"a":[82,165,173,189],"working":[83],"proof-of-concept":[84],"entity":[85],"resolution":[86],"system":[87,163,185,198,205],"called":[88],"Washing":[91,114,126,149,192],"Machine":[92,115,127,150],"be":[94],"highly":[95],"scalable":[96],"using":[97,117,151,164],"Apache":[98],"Spark":[99],"distributed":[100],"processing":[102],"framework.":[103],"We":[104,136,156,194],"solve":[105],"single-threaded":[107],"design":[108,128],"problem":[109],"legacy":[112,147],"PySpark's":[118],"Resilient":[119],"Distributed":[120],"Dataset":[121],"improve":[123],"use":[130],"intrinsic":[131],"metadata":[132],"information":[133],"from":[134,172],"references.":[135],"prove":[137],"our":[139,162,183,197,204],"achieve":[141],"results":[144,180],"18":[152],"synthetically":[153],"generated":[154],"datasets.":[155],"also":[157,195],"test":[158],"variety":[166],"benchmark":[169],"ER":[170],"datasets":[171],"few":[174],"thousand":[175],"millions.":[177],"Our":[178],"experimental":[179],"show":[181],"proposed":[184],"performs":[186],"better":[187],"than":[188],"MapReduce-based":[190],"Machine.":[193],"compared":[196],"with":[199],"Famer":[200],"concluded":[202],"can":[206],"find":[207],"more":[208],"clusters":[209],"when":[210],"given":[211],"optimal":[212],"starting":[213],"parameters":[214],"for":[215],"clustering.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}