{"id":"https://openalex.org/W2910372031","doi":"https://doi.org/10.1109/siu.2018.8404678","title":"Near duplicate detection in relational databases","display_name":"Near duplicate detection in relational databases","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2910372031","doi":"https://doi.org/10.1109/siu.2018.8404678","mag":"2910372031"},"language":"en","primary_location":{"id":"doi:10.1109/siu.2018.8404678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2018.8404678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11729/1446","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012244756","display_name":"Ahmet Tu\u011frul Bayrak","orcid":"https://orcid.org/0009-0009-6043-2765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmet Tu\u011frul Bayrak","raw_affiliation_strings":["ETSTUR, İstanbul, Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSTUR, İstanbul, Türkiye","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aykut \u0130nan Y\u0131lmaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aykut \u0130nan Y\u0131lmaz","raw_affiliation_strings":["ETSTUR, İstanbul, Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSTUR, İstanbul, Türkiye","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kemal Burak Y\u0131lmaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kemal Burak Y\u0131lmaz","raw_affiliation_strings":["ETSTUR, İstanbul, Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSTUR, İstanbul, Türkiye","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089441412","display_name":"Remzi D\u00fcza\u011fa\u00e7","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Remzi D\u00fcza\u011fa\u00e7","raw_affiliation_strings":["ETSTUR, İstanbul, Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSTUR, İstanbul, Türkiye","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034053831","display_name":"Veri Bilimi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Veri Bilimi","raw_affiliation_strings":["ETSTUR, İstanbul, Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSTUR, İstanbul, Türkiye","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114594458","display_name":"Analitik B\u00f6l\u00fcm\u00fc","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Analitik B\u00f6l\u00fcm\u00fc","raw_affiliation_strings":["ETSTUR, İstanbul, Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSTUR, İstanbul, Türkiye","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040262351","display_name":"Olcay Taner Y\u0131ld\u0131z","orcid":"https://orcid.org/0000-0001-5838-4615"},"institutions":[{"id":"https://openalex.org/I167234411","display_name":"I\u015f\u0131k University","ror":"https://ror.org/02j8k6t75","country_code":"TR","type":"education","lineage":["https://openalex.org/I167234411"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Olcay Taner Y\u0131ld\u0131z","raw_affiliation_strings":["Işık Üniversitesi Bilgisayar Mühendisliği Bölümü","Isik Universitesi, Istanbul, TR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Işık Üniversitesi Bilgisayar Mühendisliği Bölümü","institution_ids":[]},{"raw_affiliation_string":"Isik Universitesi, Istanbul, TR","institution_ids":["https://openalex.org/I167234411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9884999990463257,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9883999824523926,"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":0.7232147455215454},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.6716636419296265},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.6677437424659729},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5641767978668213},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5591031312942505},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.48743608593940735},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4499758183956146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19635623693466187},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05611526966094971}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232147455215454},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6716636419296265},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.6677437424659729},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5641767978668213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5591031312942505},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.48743608593940735},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4499758183956146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19635623693466187},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05611526966094971}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/siu.2018.8404678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2018.8404678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"},{"id":"pmh:oai:acikerisim.isikun.edu.tr:11729/1446","is_oa":true,"landing_page_url":"https://hdl.handle.net/11729/1446","pdf_url":null,"source":{"id":"https://openalex.org/S4306401174","display_name":"Akademik A\u00e7\u0131k Eri\u015fim (I\u015f\u0131k \u00dcniversitesi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I167234411","host_organization_name":"I\u015f\u0131k University","host_organization_lineage":["https://openalex.org/I167234411"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Object"},{"id":"pmh:oai:acikerisim.isikun.edu.tr:11729/1839","is_oa":true,"landing_page_url":"https://hdl.handle.net/11729/1839","pdf_url":null,"source":{"id":"https://openalex.org/S4306401174","display_name":"Akademik A\u00e7\u0131k Eri\u015fim (I\u015f\u0131k \u00dcniversitesi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I167234411","host_organization_name":"I\u015f\u0131k University","host_organization_lineage":["https://openalex.org/I167234411"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},{"id":"pmh:oai:localhost:11729/1446","is_oa":true,"landing_page_url":"http://hdl.handle.net/11729/1446","pdf_url":null,"source":{"id":"https://openalex.org/S4306401174","display_name":"Akademik A\u00e7\u0131k Eri\u015fim (I\u015f\u0131k \u00dcniversitesi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I167234411","host_organization_name":"I\u015f\u0131k University","host_organization_lineage":["https://openalex.org/I167234411"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"26th IEEE Signal Processing and Communications Applications Conference, SIU 2018","raw_type":"conferenceObject"}],"best_oa_location":{"id":"pmh:oai:acikerisim.isikun.edu.tr:11729/1446","is_oa":true,"landing_page_url":"https://hdl.handle.net/11729/1446","pdf_url":null,"source":{"id":"https://openalex.org/S4306401174","display_name":"Akademik A\u00e7\u0131k Eri\u015fim (I\u015f\u0131k \u00dcniversitesi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I167234411","host_organization_name":"I\u015f\u0131k University","host_organization_lineage":["https://openalex.org/I167234411"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Object"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1961147827","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2052390074","https://openalex.org/W2164456230","https://openalex.org/W2296107147"],"related_works":["https://openalex.org/W4281971614","https://openalex.org/W2390933768","https://openalex.org/W2467236363","https://openalex.org/W3175260668","https://openalex.org/W3122721839","https://openalex.org/W2953259538","https://openalex.org/W2184455175","https://openalex.org/W2292909562","https://openalex.org/W4309137527","https://openalex.org/W4375869232"],"abstract_inverted_index":{"While":[0],"data":[1,68,72],"amount":[2],"increases,":[3],"number":[4],"of":[5,27,47],"duplicate":[6,14,34,55,62],"records":[7,15,35,56],"in":[8,57],"relational":[9],"databases":[10],"increase":[11],"gradually.":[12],"The":[13,60],"might":[16],"cause":[17],"inconsistency":[18],"on":[19],"reports":[20],"and":[21,70],"analyzes.":[22],"To":[23],"reduce":[24],"the":[25,48,67,71],"effects":[26],"this":[28],"problem,":[29],"we":[30],"aim":[31],"to":[32,52],"detect":[33,53],"using":[36],"machine":[37],"learning":[38],"algorithms":[39],"with":[40],"features":[41],"that":[42],"are":[43,64],"produced":[44],"by":[45],"similarity":[46],"records.":[49,59],"We":[50],"achieved":[51],"28412":[54],"9301467":[58],"detected":[61],"rows":[63],"removed":[65],"from":[66],"source":[69],"become":[73],"more":[74],"consistent.":[75]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2019-01-25T00:00:00"}