{"id":"https://openalex.org/W2017663101","doi":"https://doi.org/10.1587/transinf.2014edp7292","title":"Proposing and Evaluating Clone Detection Approaches with Preprocessing Input Source Files","display_name":"Proposing and Evaluating Clone Detection Approaches with Preprocessing Input Source Files","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2017663101","doi":"https://doi.org/10.1587/transinf.2014edp7292","mag":"2017663101"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2014edp7292","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7292","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E98.D/2/E98.D_2014EDP7292/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E98.D/2/E98.D_2014EDP7292/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112421750","display_name":"Eunjong Choi","orcid":"https://orcid.org/0000-0002-2196-033X"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eunjong CHOI","raw_affiliation_strings":["Osaka University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102003982","display_name":"Norihiro Yoshida","orcid":"https://orcid.org/0000-0003-4910-1729"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norihiro YOSHIDA","raw_affiliation_strings":["Nagoya University","#N##TAB##TAB##TAB##TAB# Nagoya University#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Nagoya University#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024065727","display_name":"Yoshiki Higo","orcid":"https://orcid.org/0000-0002-8278-8975"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiki HIGO","raw_affiliation_strings":["Osaka University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102258593","display_name":"Katsuro Inoue","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuro INOUE","raw_affiliation_strings":["Osaka University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6253,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87861561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"E98.D","issue":"2","first_page":"325","last_page":"333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9994999766349792,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7762892246246338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7648435831069946},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7539320588111877},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.7126036286354065},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.46077224612236023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42963454127311707},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3573340177536011},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3460637331008911},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17128053307533264}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7762892246246338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648435831069946},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7539320588111877},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7126036286354065},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.46077224612236023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42963454127311707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3573340177536011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3460637331008911},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17128053307533264},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2014edp7292","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7292","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E98.D/2/E98.D_2014EDP7292/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2014edp7292","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7292","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E98.D/2/E98.D_2014EDP7292/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2017663101.pdf","grobid_xml":"https://content.openalex.org/works/W2017663101.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1508590353","https://openalex.org/W1572143836","https://openalex.org/W1598423581","https://openalex.org/W1980482639","https://openalex.org/W1983118588","https://openalex.org/W1983316175","https://openalex.org/W1990061958","https://openalex.org/W2009095932","https://openalex.org/W2074529754","https://openalex.org/W2101832700","https://openalex.org/W2104301886","https://openalex.org/W2109030668","https://openalex.org/W2109943392","https://openalex.org/W2127811329","https://openalex.org/W2128888088","https://openalex.org/W2131112324","https://openalex.org/W2138756793","https://openalex.org/W2164521341","https://openalex.org/W2171172203","https://openalex.org/W2172244770","https://openalex.org/W3003280364","https://openalex.org/W3147107715"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W4252684102","https://openalex.org/W2591697403","https://openalex.org/W2352307597","https://openalex.org/W1979633005","https://openalex.org/W2163724607","https://openalex.org/W4249277012","https://openalex.org/W2099969795","https://openalex.org/W3120493416","https://openalex.org/W2098192829"],"abstract_inverted_index":{"So":[0],"far,":[1],"many":[2,210],"approaches":[3,59,127,134,183,208],"for":[4,60],"detecting":[5,61],"code":[6,38,43,52,62,100,119,185],"clones":[7,63,101,186],"have":[8],"been":[9],"proposed":[10,126,182,207],"based":[11],"on":[12],"the":[13,48,51,81,93,96,142,152,156,175,189,198,203,206],"different":[14,34,70,162],"degrees":[15,29,71,163],"of":[16,20,26,30,36,72,107,112,144,158,164,169],"normalizations":[17,31,49,165],"(e.g.":[18],"removal":[19,168],"white":[21],"spaces,":[22],"tokenization,":[23],"and":[24,85,137],"regularization":[25],"identifiers).":[27],"Different":[28],"lead":[32],"to":[33,39,80,92],"granularities":[35],"source":[37,67,83],"be":[40,129],"detect":[41,184],"as":[42,167],"clones.":[44],"To":[45],"investigate":[46],"how":[47],"impact":[50],"clone":[53,120],"detection,":[54],"this":[55],"study":[56],"proposes":[57],"six":[58],"with":[64,135,161,200],"preprocessing":[65],"input":[66,82],"files":[68,84,94,108,147,160],"using":[69,116],"normalizations.":[73],"More":[74],"precisely,":[75],"each":[76,113],"normalization":[77],"is":[78,90,141,155,202],"applied":[79],"then":[86],"equivalence":[87,114],"class":[88,115],"partitioning":[89],"performed":[91],"in":[95,209],"preprocessing.":[97],"After":[98],"that,":[99],"are":[102,110],"detected":[103],"from":[104],"a":[105,117],"set":[106],"that":[109,180,191],"representatives":[111],"token-based":[118],"detection":[121,143,157],"tool":[122],"named":[123],"CCFinder.":[124,194],"The":[125,139],"can":[128],"categorized":[130],"into":[131],"two":[132],"types,":[133],"non-normalization":[136,201],"normalization.":[138,150],"former":[140],"only":[145,193],"identical":[146,159],"without":[148],"any":[149],"Meanwhile,":[151],"latter":[153],"category":[154],"such":[166],"all":[170],"lines":[171],"containing":[172],"macros.":[173],"From":[174],"case":[176],"study,":[177],"we":[178],"observed":[179],"our":[181],"faster":[187],"than":[188],"approach":[190,199],"uses":[192],"We":[195],"also":[196],"found":[197],"fastest":[204],"among":[205],"cases.":[211]},"counts_by_year":[{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}