{"id":"https://openalex.org/W3043767303","doi":"https://doi.org/10.1109/access.2020.3009414","title":"Semi-Stream Similarity Join Processing in a Distributed Environment","display_name":"Semi-Stream Similarity Join Processing in a Distributed Environment","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3043767303","doi":"https://doi.org/10.1109/access.2020.3009414","mag":"3043767303"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3009414","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3009414","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09141233.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09141233.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055181817","display_name":"Hong-Ji Kim","orcid":"https://orcid.org/0000-0001-8755-2550"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hong-Ji Kim","raw_affiliation_strings":["School of Computer and Information Engineering, Kwangwoon University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Kwangwoon University, Seoul, South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091742813","display_name":"Kihoon Lee","orcid":"https://orcid.org/0000-0003-4661-0982"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ki-Hoon Lee","raw_affiliation_strings":["School of Computer and Information Engineering, Kwangwoon University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Kwangwoon University, Seoul, South Korea","institution_ids":["https://openalex.org/I161024014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055181817"],"corresponding_institution_ids":["https://openalex.org/I161024014"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1103,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8049573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"130194","last_page":"130204"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9829000234603882,"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/join","display_name":"Join (topology)","score":0.9061580896377563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7704806327819824},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6433321237564087},{"id":"https://openalex.org/keywords/hash-join","display_name":"Hash join","score":0.5515720844268799},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5383272171020508},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5030185580253601},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4711766839027405},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4345259666442871},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36646220088005066},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3465209901332855},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.2593309283256531},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12592098116874695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1209682822227478},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10354256629943848}],"concepts":[{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.9061580896377563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704806327819824},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6433321237564087},{"id":"https://openalex.org/C188805328","wikidata":"https://www.wikidata.org/wiki/Q4060691","display_name":"Hash join","level":3,"score":0.5515720844268799},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5383272171020508},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5030185580253601},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4711766839027405},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4345259666442871},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36646220088005066},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3465209901332855},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.2593309283256531},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12592098116874695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1209682822227478},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10354256629943848},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3009414","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3009414","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09141233.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ed6d6b77f90f4b47a582ee8fe4f788fc","is_oa":true,"landing_page_url":"https://doaj.org/article/ed6d6b77f90f4b47a582ee8fe4f788fc","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 130194-130204 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3009414","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3009414","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09141233.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2820426551","display_name":null,"funder_award_id":"NRF-2018R1D1A1B0704","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5830618976","display_name":null,"funder_award_id":"NRF-2018R1D1A1B07043","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6225209897","display_name":null,"funder_award_id":"2018R1D1A1B0704","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7497119234","display_name":null,"funder_award_id":"NRF-2018R1D1A1B07043727","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8011125346","display_name":null,"funder_award_id":"2018R1D1A1B0","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G982292920","display_name":null,"funder_award_id":"NRF-20","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321374","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3043767303.pdf","grobid_xml":"https://content.openalex.org/works/W3043767303.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W9924853","https://openalex.org/W1960131443","https://openalex.org/W1973001156","https://openalex.org/W1979666709","https://openalex.org/W2001700730","https://openalex.org/W2014868275","https://openalex.org/W2038281398","https://openalex.org/W2104599107","https://openalex.org/W2108991785","https://openalex.org/W2131975293","https://openalex.org/W2132399973","https://openalex.org/W2151930506","https://openalex.org/W2152565070","https://openalex.org/W2157355837","https://openalex.org/W2164634022","https://openalex.org/W2169387919","https://openalex.org/W2294331997","https://openalex.org/W2328380634","https://openalex.org/W2393639016","https://openalex.org/W2513214219","https://openalex.org/W2525769010","https://openalex.org/W2576109540","https://openalex.org/W2586025740","https://openalex.org/W2616120155","https://openalex.org/W2706966281","https://openalex.org/W2752274179","https://openalex.org/W2755880841","https://openalex.org/W2883952940","https://openalex.org/W2888868755","https://openalex.org/W2900972923","https://openalex.org/W2922169274","https://openalex.org/W2937574645","https://openalex.org/W2951438725","https://openalex.org/W2954727071","https://openalex.org/W2964013013","https://openalex.org/W2974377501","https://openalex.org/W2997804184","https://openalex.org/W3012776781","https://openalex.org/W3146259567","https://openalex.org/W6600373641","https://openalex.org/W6679815717","https://openalex.org/W6711975443"],"related_works":["https://openalex.org/W2381211091","https://openalex.org/W2091359263","https://openalex.org/W4283362132","https://openalex.org/W2469706965","https://openalex.org/W1589496614","https://openalex.org/W4234452035","https://openalex.org/W2159860101","https://openalex.org/W3187487646","https://openalex.org/W4205996836","https://openalex.org/W1981952567"],"abstract_inverted_index":{"Similarity":[0],"join":[1,38,61,81,89],"has":[2,26],"become":[3],"very":[4,125],"important":[5],"for":[6,58,109],"semi-":[7],"or":[8],"un-structured":[9],"data":[10,41,66],"processing":[11,78],"and":[12,42,83,120,137],"analysis.":[13],"Although":[14],"several":[15],"studies":[16],"have":[17],"been":[18,27],"conducted":[19],"on":[20],"the":[21,52,65,85,128,132],"similarity":[22,32,37,60,138],"join,":[23,33],"little":[24],"attention":[25],"paid":[28],"to":[29,127],"a":[30,36,43,72,75],"semi-stream":[31,59],"which":[34],"is":[35,118,123],"between":[39,87],"stream":[40,77],"large":[44,110],"disk-based":[45],"relation.":[46],"In":[47],"this":[48],"study,":[49],"we":[50],"propose":[51],"first":[53],"distributed":[54,76],"solution":[55],"called":[56],"DSim-Join":[57,63,99,117],"problem.":[62],"minimizes":[64],"transmission,":[67],"reduces":[68],"database":[69],"accesses":[70],"using":[71,94],"cache":[73],"in":[74],"engine,":[79],"parallelizes":[80],"processing,":[82],"balances":[84],"load":[86],"parallel":[88],"threads.":[90],"Experimental":[91],"results":[92,113],"obtained":[93],"real-world":[95],"datasets":[96],"show":[97,115],"that":[98,116],"yields":[100],"significantly":[101],"improved":[102],"throughput":[103],"compared":[104],"with":[105],"state-of-the-art":[106],"methods,":[107],"especially":[108],"datasets.":[111],"The":[112],"also":[114],"scalable":[119],"stable;":[121],"it":[122],"not":[124],"sensitive":[126],"parameters":[129],"such":[130],"as":[131],"micro-batch":[133],"interval,":[134,136],"checkpoint":[135],"threshold.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}