{"id":"https://openalex.org/W4226151432","doi":"https://doi.org/10.1109/access.2022.3164192","title":"DBSCAN-Based Automatic De-Duplication for Software Quality Inspection Data","display_name":"DBSCAN-Based Automatic De-Duplication for Software Quality Inspection Data","publication_year":2022,"publication_date":"2022-04-01","ids":{"openalex":"https://openalex.org/W4226151432","doi":"https://doi.org/10.1109/access.2022.3164192"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3164192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3164192","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/09745940.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/ielx7/6287639/10005208/09745940.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102822894","display_name":"Chun-Hua Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4403386539","display_name":"Software Engineering Institute of Guangzhou","ror":"https://ror.org/0549ke970","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun-Hua Cao","raw_affiliation_strings":["Department of Network Engineering, South China Institute of Software Engineering, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2424-2656","affiliations":[{"raw_affiliation_string":"Department of Network Engineering, South China Institute of Software Engineering, Guangzhou, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4403386539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046069282","display_name":"Yana Tang","orcid":"https://orcid.org/0000-0003-3280-6976"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4403386539","display_name":"Software Engineering Institute of Guangzhou","ror":"https://ror.org/0549ke970","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya-Na Tang","raw_affiliation_strings":["Department of Network Engineering, South China Institute of Software Engineering, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Network Engineering, South China Institute of Software Engineering, Guangzhou, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4403386539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102293102","display_name":"Hua Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4403386539","display_name":"Software Engineering Institute of Guangzhou","ror":"https://ror.org/0549ke970","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Zhou","raw_affiliation_strings":["Department of Network Engineering, South China Institute of Software Engineering, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Network Engineering, South China Institute of Software Engineering, Guangzhou, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4403386539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101889877","display_name":"Yuli Li","orcid":"https://orcid.org/0000-0002-7189-8423"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4403386539","display_name":"Software Engineering Institute of Guangzhou","ror":"https://ror.org/0549ke970","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Li Li","raw_affiliation_strings":["Department of Network Engineering, South China Institute of Software Engineering, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Network Engineering, South China Institute of Software Engineering, Guangzhou, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4403386539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045937223","display_name":"Zbigniew Marsza\u0142ek","orcid":"https://orcid.org/0000-0002-6593-7158"},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Zbigniew Marsza\u0142ek","raw_affiliation_strings":["Faculty of Applied Mathematics, Silesian University of Technology, Gliwice, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Mathematics, Silesian University of Technology, Gliwice, Poland","institution_ids":["https://openalex.org/I119004910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1312,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49909986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"11","issue":null,"first_page":"17882","last_page":"17890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13567","display_name":"AI and Multimedia in Education","score":0.9916999936103821,"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"}},"topics":[{"id":"https://openalex.org/T13567","display_name":"AI and Multimedia in Education","score":0.9916999936103821,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9577000141143799,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7951055765151978},{"id":"https://openalex.org/keywords/dbscan","display_name":"DBSCAN","score":0.701783299446106},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6188499331474304},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.588117778301239},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5386711359024048},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4114794135093689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3798280358314514},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3010639548301697},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.1825222373008728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7951055765151978},{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.701783299446106},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6188499331474304},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.588117778301239},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5386711359024048},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4114794135093689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3798280358314514},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3010639548301697},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.1825222373008728},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3164192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3164192","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/09745940.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:06d30e222f734d8eacc95b14fba1a899","is_oa":true,"landing_page_url":"https://doaj.org/article/06d30e222f734d8eacc95b14fba1a899","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":"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 11, Pp 17882-17890 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3164192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3164192","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/09745940.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":[{"score":0.5699999928474426,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226151432.pdf","grobid_xml":"https://content.openalex.org/works/W4226151432.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2568154862","https://openalex.org/W2590387313","https://openalex.org/W2779640815","https://openalex.org/W2780813414","https://openalex.org/W2796154898","https://openalex.org/W2800529092","https://openalex.org/W2912456704","https://openalex.org/W2943966997","https://openalex.org/W3003545729","https://openalex.org/W3006100806","https://openalex.org/W3024934024","https://openalex.org/W3032749142","https://openalex.org/W3038721901","https://openalex.org/W3082776374","https://openalex.org/W3092561083","https://openalex.org/W3110078514","https://openalex.org/W3112404385","https://openalex.org/W3118658449","https://openalex.org/W3137539129"],"related_works":["https://openalex.org/W3176449234","https://openalex.org/W2045002201","https://openalex.org/W4225278791","https://openalex.org/W4322502698","https://openalex.org/W2394193399","https://openalex.org/W2954170735","https://openalex.org/W3022637481","https://openalex.org/W3144143113","https://openalex.org/W2054669762","https://openalex.org/W2767235736"],"abstract_inverted_index":{"Software":[0],"quality":[1,18,29,51,79,113,158],"inspection":[2,30,52,80,114],"will":[3],"generate":[4,49],"too":[5],"much":[6],"data,":[7],"and":[8,63,90,107,124,134,143],"removing":[9],"duplicate":[10],"data":[11,31,53,81,115,121],"can":[12,151],"improve":[13,153],"the":[14,23,68,108,132,144,154],"efficiency":[15,155],"of":[16,27,37,104,111,136,156],"software":[17,28,50,78,112,157],"inspection.":[19,159],"This":[20],"paper":[21],"studies":[22],"automatic":[24,109],"de-duplication":[25,110],"method":[26,138],"based":[32],"on":[33],"density-based":[34],"spatial":[35],"clustering":[36,102],"applications":[38],"with":[39],"noise":[40],"(DBSCAN)":[41],"clustering.":[42],"Intelligent":[43],"optimization":[44],"algorithm":[45,73,103],"is":[46,74,116,148],"used":[47,97],"to":[48,76,98],"by":[54,83,118],"initializing":[55],"individuals,":[56],"calculating":[57,87],"fitness":[58],"function":[59],"value,":[60],"improving":[61],"individuals":[62,65],"splitting":[64],"that":[66,131],"meet":[67],"conditions.":[69],"Local":[70],"linear":[71],"embedding":[72],"selected":[75],"extract":[77],"features":[82,95],"searching":[84],"neighborhood":[85],"points,":[86],"reconstruction":[88],"weight":[89],"projection":[91],"vector.":[92],"The":[93,127],"extracted":[94],"are":[96,139],"select":[99],"DBSCAN":[100],"multi-density":[101],"regional":[105],"division,":[106,120],"realized":[117],"grid":[119,125],"bin":[122],"dividing":[123],"merging.":[126],"experimental":[128],"results":[129],"show":[130],"precision":[133],"recall":[135],"this":[137],"higher":[140],"than":[141],"99%,":[142],"resource":[145],"consumption":[146],"rate":[147],"low,":[149],"which":[150],"effectively":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}