{"id":"https://openalex.org/W3010602977","doi":"https://doi.org/10.1109/icsai48974.2019.9010154","title":"The Detection Algorithms for Similar Duplicate Data","display_name":"The Detection Algorithms for Similar Duplicate Data","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010602977","doi":"https://doi.org/10.1109/icsai48974.2019.9010154","mag":"3010602977"},"language":"en","primary_location":{"id":"doi:10.1109/icsai48974.2019.9010154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai48974.2019.9010154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 6th International Conference on Systems and Informatics (ICSAI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5112999838","display_name":"Jinyu Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin-yu Song","raw_affiliation_strings":["College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101517339","display_name":"Quan Yu","orcid":"https://orcid.org/0000-0002-4486-2070"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Yu","raw_affiliation_strings":["College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079180503","display_name":"Ruo-yu Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruo-yu Bao","raw_affiliation_strings":["College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210163363"],"apc_list":null,"apc_paid":null,"fwci":0.3329,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61231226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1534","last_page":"1542"},"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":0.9983999729156494,"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":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.8428336381912231},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.696139931678772},{"id":"https://openalex.org/keywords/dbscan","display_name":"DBSCAN","score":0.6876304149627686},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6830291748046875},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6201266050338745},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5932461619377136},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5357477068901062},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.5194751620292664},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4965360760688782},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46934545040130615},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.4314885139465332},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4306219816207886},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4109859764575958},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.21389400959014893},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16561287641525269},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14307105541229248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13918966054916382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13152837753295898},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.12725523114204407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8428336381912231},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.696139931678772},{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.6876304149627686},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6830291748046875},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6201266050338745},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5932461619377136},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5357477068901062},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.5194751620292664},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4965360760688782},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46934545040130615},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.4314885139465332},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4306219816207886},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4109859764575958},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.21389400959014893},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16561287641525269},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14307105541229248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13918966054916382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13152837753295898},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.12725523114204407},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsai48974.2019.9010154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai48974.2019.9010154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 6th International Conference on Systems and Informatics (ICSAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W158528365","https://openalex.org/W1569123402","https://openalex.org/W1673310716","https://openalex.org/W2024770506","https://openalex.org/W2065753378","https://openalex.org/W2131576956","https://openalex.org/W2203070563","https://openalex.org/W2320361084","https://openalex.org/W2334767787","https://openalex.org/W2349733666","https://openalex.org/W2353238921","https://openalex.org/W2360195242","https://openalex.org/W2362155272","https://openalex.org/W2379593863","https://openalex.org/W2576379123","https://openalex.org/W3111526966","https://openalex.org/W4254788633","https://openalex.org/W6606527289","https://openalex.org/W6633966005","https://openalex.org/W6637131181","https://openalex.org/W6979852455"],"related_works":["https://openalex.org/W2908348257","https://openalex.org/W4392178020","https://openalex.org/W2994182992","https://openalex.org/W2350549588","https://openalex.org/W2085265870","https://openalex.org/W2362374543","https://openalex.org/W3206496585","https://openalex.org/W2187267622","https://openalex.org/W2351942115","https://openalex.org/W2922989628"],"abstract_inverted_index":{"This":[0],"paper":[1,57,105,124,141],"studied":[2],"and":[3,32,66,79,101,128],"analyzed":[4],"three":[5,107,130],"algorithms":[6,26,108,131],"which":[7],"can":[8],"be":[9],"used":[10,22],"to":[11,72,121,146],"detect":[12],"similar":[13],"duplicate":[14,23],"data":[15,24,77,138],"records.":[16],"Among":[17],"them,":[18],"the":[19,64,74,81,89,92,95,144],"two":[20,87],"commonly":[21],"detection":[25],"are":[27,39],"basic":[28],"sorted-neighborhood":[29],"method":[30],"(SNM)":[31],"priority":[33],"queue":[34,102],"algorithm.":[35],"Both":[36],"of":[37,51,68,76,86,91,97,136],"them":[38],"based":[40,111],"on":[41,112],"sorting-merger":[42],"thought.":[43],"The":[44,56,104,123,140],"third":[45],"one":[46],"is":[47],"Density-Based":[48],"Spatial":[49],"Clustering":[50],"Applications":[52],"with":[53],"Noise":[54],"(DBSCAN).":[55],"also":[58],"discussed":[59],"some":[60,118],"key":[61],"problems":[62],"in":[63],"application":[65],"implementation":[67],"algorithms,":[69],"including":[70],"how":[71],"choose":[73],"attributes":[75,85],"records":[78],"calculate":[80],"similarity":[82],"between":[83],"these":[84,148],"records,":[88],"choice":[90],"sort":[93],"algorithm,":[94],"setting":[96],"sliding":[98],"window":[99],"size":[100],"length.":[103],"realized":[106],"by":[109,132],"programming":[110],"Matlab":[113],"platform,":[114],"as":[115,117],"well":[116],"technologies":[119],"related":[120,126],"algorithms.":[122,149],"verified":[125],"conclusions":[127],"evaluated":[129],"testing":[133],"a":[134],"lot":[135],"loaded":[137],"sets.":[139],"finally":[142],"provided":[143],"instruction":[145],"apply":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
