{"id":"https://openalex.org/W2744822754","doi":"https://doi.org/10.18293/seke2017-043","title":"A Data Filtering Method Based on Agglomerative Clustering","display_name":"A Data Filtering Method Based on Agglomerative Clustering","publication_year":2017,"publication_date":"2017-07-05","ids":{"openalex":"https://openalex.org/W2744822754","doi":"https://doi.org/10.18293/seke2017-043","mag":"2744822754"},"language":"en","primary_location":{"id":"doi:10.18293/seke2017-043","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2017-043","pdf_url":"https://doi.org/10.18293/seke2017-043","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.18293/seke2017-043","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047060039","display_name":"Xiao Yu","orcid":"https://orcid.org/0000-0002-4473-3068"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Yu","raw_affiliation_strings":["State Key Lab. of Software Engineering, Computer School, Wuhan University, Wuhan, China","School of Computer Science and Information Engineering, HuBei University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab. of Software Engineering, Computer School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science and Information Engineering, HuBei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949972","display_name":"Peipei Zhou","orcid":"https://orcid.org/0000-0003-1370-5627"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peipei Zhou","raw_affiliation_strings":["School of Computer Science and Information Engineering, HuBei University, Wuhan, China","State Key Lab. of Software Engineering, Computer School, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, HuBei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]},{"raw_affiliation_string":"State Key Lab. of Software Engineering, Computer School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiansheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiansheng Zhang","raw_affiliation_strings":["School of Computer Science and Information Engineering, HuBei University, Wuhan, China","State Key Lab. of Software Engineering, Computer School, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, HuBei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]},{"raw_affiliation_string":"State Key Lab. of Software Engineering, Computer School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100642607","display_name":"Jin Liu","orcid":"https://orcid.org/0000-0001-7249-698X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Liu","raw_affiliation_strings":["State Key Lab. of Software Engineering, Computer School, Wuhan University, Wuhan, China","School of Computer Science and Information Engineering, HuBei University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab. of Software Engineering, Computer School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science and Information Engineering, HuBei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2017","issue":null,"first_page":"392","last_page":"397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9812999963760376,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9800000190734863,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7325505018234253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7204297184944153},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6860344409942627},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6103130578994751},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5484018921852112},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4812147915363312},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4705013930797577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41324034333229065},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2900952994823456}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7325505018234253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204297184944153},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6860344409942627},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6103130578994751},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5484018921852112},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4812147915363312},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4705013930797577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41324034333229065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2900952994823456},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18293/seke2017-043","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2017-043","pdf_url":"https://doi.org/10.18293/seke2017-043","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18293/seke2017-043","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2017-043","pdf_url":"https://doi.org/10.18293/seke2017-043","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G250828915","display_name":"\u57fa\u4e8e\u9690\u6027\u60c5\u5883\u6316\u6398\u7684API\u5fae\u73af\u5883\u7ec4\u5408\u670d\u52a1\u65b9\u6cd5\u548c\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61572374","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2819363858","display_name":"EDU:Collaborative: VACCS - Visualization and Analysis for C Code Security","funder_award_id":"1522883","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5675371398","display_name":null,"funder_award_id":"DGE-1522883","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5765857757","display_name":null,"funder_award_id":"U1135005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6466831794","display_name":null,"funder_award_id":"U163620068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324116","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2744822754.pdf","grobid_xml":"https://content.openalex.org/works/W2744822754.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W168970045","https://openalex.org/W1501959529","https://openalex.org/W1582810276","https://openalex.org/W1877763529","https://openalex.org/W1924689489","https://openalex.org/W1981771523","https://openalex.org/W1984800215","https://openalex.org/W2021688474","https://openalex.org/W2031770898","https://openalex.org/W2037691959","https://openalex.org/W2046830558","https://openalex.org/W2047338137","https://openalex.org/W2048456683","https://openalex.org/W2055949897","https://openalex.org/W2064330644","https://openalex.org/W2074218040","https://openalex.org/W2080521990","https://openalex.org/W2086184041","https://openalex.org/W2090854192","https://openalex.org/W2101227285","https://openalex.org/W2112658968","https://openalex.org/W2118283821","https://openalex.org/W2120457925","https://openalex.org/W2136706100","https://openalex.org/W2145793758","https://openalex.org/W2179590804","https://openalex.org/W2360967250","https://openalex.org/W2385483600","https://openalex.org/W2408200640","https://openalex.org/W2507665469","https://openalex.org/W2509246479","https://openalex.org/W2569856561","https://openalex.org/W2582885755","https://openalex.org/W4244437845","https://openalex.org/W6603376977","https://openalex.org/W6609917207","https://openalex.org/W6680356843","https://openalex.org/W6911028930"],"related_works":["https://openalex.org/W4255837520","https://openalex.org/W2387011115","https://openalex.org/W4298130764","https://openalex.org/W4234808182","https://openalex.org/W2804364458","https://openalex.org/W2382043075","https://openalex.org/W2809151339","https://openalex.org/W2360673138","https://openalex.org/W2132641928","https://openalex.org/W3200375535"],"abstract_inverted_index":{"Cross-company":[0],"defect":[1,45,69],"prediction":[2,11,46],"(CCDP)":[3],"is":[4],"a":[5,10,20,43,58,109],"practical":[6],"way":[7],"that":[8,128],"trains":[9],"model":[12,27,47],"by":[13],"exploiting":[14],"one":[15,96],"or":[16],"multiple":[17],"projects":[18],"of":[19],"source":[21],"company":[22],"and":[23,76,79,99,136,140],"then":[24],"applies":[25],"the":[26,101,105,119],"to":[28,41,84],"target":[29],"company.":[30],"Unfortunately,":[31],"larger":[32],"irrelevant":[33],"crosscompany":[34,44],"(CC)":[35],"data":[36,59,116],"usually":[37],"makes":[38],"it":[39],"difficult":[40],"build":[42],"with":[48,114],"high":[49],"performance.":[50],"To":[51],"address":[52],"such":[53],"issues,":[54],"this":[55],"paper":[56],"proposes":[57],"filtering":[60],"method":[61],"based":[62],"on":[63,122],"Agglomerative":[64,81],"Clustering":[65],"(DFAC)":[66],"for":[67],"cross-company":[68,77],"prediction.":[70],"First,":[71],"DFAC":[72,89,129],"combines":[73],"within-company":[74],"instances":[75,78,103],"uses":[80],"clustering":[82],"algorithms":[83],"group":[85],"these":[86],"instances.":[87],"Second,":[88],"selects":[90],"sub-clusters":[91,107],"which":[92],"consist":[93],"at":[94],"least":[95],"WC":[97],"instance,":[98],"collects":[100],"CC":[102,111],"in":[104],"selected":[106],"into":[108],"new":[110],"data.":[112],"Compared":[113],"existing":[115],"filter":[117],"methods,":[118],"experimental":[120],"results":[121],"15":[123],"public":[124],"PROMISE":[125],"datasets":[126],"show":[127],"increases":[130],"PD":[131],"value,":[132],"reduces":[133],"PF":[134],"value":[135],"achieves":[137],"higher":[138],"G-measure":[139],"AUC":[141],"values.":[142],"1":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}