{"id":"https://openalex.org/W2913778214","doi":"https://doi.org/10.1109/ict-dm.2018.8636375","title":"An empirical study on optimization of training dataset in harmfulness prediction of code clone using ensemble feature selection model","display_name":"An empirical study on optimization of training dataset in harmfulness prediction of code clone using ensemble feature selection model","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913778214","doi":"https://doi.org/10.1109/ict-dm.2018.8636375","mag":"2913778214"},"language":"en","primary_location":{"id":"doi:10.1109/ict-dm.2018.8636375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ict-dm.2018.8636375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","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/A5111958681","display_name":"Sheng Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I22046295","display_name":"Inner Mongolia Normal University","ror":"https://ror.org/0497ase59","country_code":"CN","type":"education","lineage":["https://openalex.org/I22046295"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Yan","raw_affiliation_strings":["College of Computer and Information Engineering, Inner Mongolia Normal University Hohhot, Inner Mongolia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Inner Mongolia Normal University Hohhot, Inner Mongolia, China","institution_ids":["https://openalex.org/I22046295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426751","display_name":"Liping Zhang","orcid":"https://orcid.org/0000-0002-5613-5292"},"institutions":[{"id":"https://openalex.org/I22046295","display_name":"Inner Mongolia Normal University","ror":"https://ror.org/0497ase59","country_code":"CN","type":"education","lineage":["https://openalex.org/I22046295"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Zhang","raw_affiliation_strings":["College of Computer and Information Engineering, Inner Mongolia Normal University Hohhot, Inner Mongolia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Inner Mongolia Normal University Hohhot, Inner Mongolia, China","institution_ids":["https://openalex.org/I22046295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440896","display_name":"Dongsheng Liu","orcid":"https://orcid.org/0000-0001-5571-1932"},"institutions":[{"id":"https://openalex.org/I22046295","display_name":"Inner Mongolia Normal University","ror":"https://ror.org/0497ase59","country_code":"CN","type":"education","lineage":["https://openalex.org/I22046295"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Liu","raw_affiliation_strings":["College of Computer and Information Engineering, Inner Mongolia Normal University Hohhot, Inner Mongolia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Inner Mongolia Normal University Hohhot, Inner Mongolia, China","institution_ids":["https://openalex.org/I22046295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22046295"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.996999979019165,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.996999979019165,"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/T10260","display_name":"Software Engineering Research","score":0.9614999890327454,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9609000086784363,"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/classifier","display_name":"Classifier (UML)","score":0.7687864303588867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6979588270187378},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6702858805656433},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6029776930809021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6002004742622375},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5266292691230774},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5089101791381836},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47740259766578674},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4194391667842865}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7687864303588867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6979588270187378},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6702858805656433},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6029776930809021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6002004742622375},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5266292691230774},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5089101791381836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47740259766578674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4194391667842865}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ict-dm.2018.8636375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ict-dm.2018.8636375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1982621550","https://openalex.org/W1993220166","https://openalex.org/W2112076978","https://openalex.org/W2119887272","https://openalex.org/W2122195835","https://openalex.org/W2133462743","https://openalex.org/W2154151876","https://openalex.org/W2167101736","https://openalex.org/W2400516519","https://openalex.org/W2578863186","https://openalex.org/W4233434287"],"related_works":["https://openalex.org/W4388745254","https://openalex.org/W2889302474","https://openalex.org/W2980082554","https://openalex.org/W1517228774","https://openalex.org/W2767419625","https://openalex.org/W2389704471","https://openalex.org/W2117019857","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,58,76,101,118],"solve":[3],"the":[4,14,36,90,103,143,156,161],"problem":[5],"of":[6,16,38,84,146,160],"irrelevant":[7],"features":[8],"and":[9,31,131,158],"imbalanced":[10],"data":[11,50],"classification":[12],"in":[13,40,127],"process":[15],"clone":[17,120],"code":[18,119],"harmfulness":[19,121],"prediction,":[20],"an":[21],"integrated":[22,114,147],"classifier":[23,98,115,148],"algorithm":[24,71,116,149],"based":[25,72],"on":[26],"RUS":[27],"(Random":[28],"Under":[29],"Sampling)":[30],"Wrapper":[32,73],"was":[33,74,99,150],"proposed.":[34],"Firstly,":[35],"majority":[37],"samples":[39,57],"training":[41,62,85,106],"dataset":[42],"were":[43,53,87],"re-sampled":[44],"into":[45],"several":[46],"proportional":[47],"minority":[48,56],"class":[49],"set,":[51],"which":[52,154],"combined":[54],"with":[55,89,137],"create":[59],"multiple":[60],"different":[61,82],"sample":[63],"subsets;":[64,80,94],"Then,":[65],"a":[66],"sequential":[67],"floating":[68],"forward":[69],"search":[70],"proposed":[75],"select":[77],"optimal":[78,92],"feature":[79,93,163],"The":[81,108],"proportions":[83],"subsets":[86],"mapped":[88],"corresponding":[91],"Finally,":[95],"random":[96],"forest":[97],"used":[100],"evaluate":[102],"acquired":[104],"optimized":[105],"dataset.":[107],"experimental":[109],"results":[110],"showed":[111],"that":[112],"this":[113],"applied":[117],"prediction":[122],"increased":[123,151],"average":[124],"about":[125],"7%":[126],"accuracy,":[128],"F1":[129],"measure":[130],"AUC":[132,144],"evaluation":[133],"index.":[134],"And":[135],"compared":[136],"four":[138],"other":[139],"similar":[140],"optimization":[141],"methods,":[142],"value":[145],"by":[152],"10.3%,":[153],"expressed":[155],"feasibility":[157],"effectiveness":[159],"ensemble":[162],"selection":[164],"model.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}