{"id":"https://openalex.org/W2889366067","doi":"https://doi.org/10.1109/asap.2018.8445094","title":"Synthetic Data Approach for Classification and Regression","display_name":"Synthetic Data Approach for Classification and Regression","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2889366067","doi":"https://doi.org/10.1109/asap.2018.8445094","mag":"2889366067"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2018.8445094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2018.8445094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","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/A5051954504","display_name":"Yang Yue","orcid":"https://orcid.org/0000-0003-2752-7315"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Yue","raw_affiliation_strings":["School of Software and Microelectronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342640","display_name":"Ying Li","orcid":"https://orcid.org/0000-0001-7589-7295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["National Research Center of Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Center of Software Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032574264","display_name":"Kexin Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kexin Yi","raw_affiliation_strings":["National Research Center of Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Center of Software Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041563693","display_name":"Zhonghai Wu","orcid":"https://orcid.org/0000-0003-1268-836X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhonghai Wu","raw_affiliation_strings":["Academy for Advanced Interdisciplinary, Studies Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy for Advanced Interdisciplinary, Studies Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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":0.739068329334259},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.7355655431747437},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6228212118148804},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5849524736404419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5523041486740112},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5329357981681824},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5310618877410889},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5163329839706421},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4762827754020691},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4758855104446411},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.42105215787887573},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16263779997825623},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14325276017189026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.739068329334259},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.7355655431747437},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6228212118148804},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5849524736404419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5523041486740112},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5329357981681824},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5310618877410889},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5163329839706421},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4762827754020691},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4758855104446411},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.42105215787887573},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16263779997825623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14325276017189026},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2018.8445094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2018.8445094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W144784517","https://openalex.org/W157007071","https://openalex.org/W1766594731","https://openalex.org/W1937501050","https://openalex.org/W1993220166","https://openalex.org/W2099471712","https://openalex.org/W2104933073","https://openalex.org/W2148143831","https://openalex.org/W2166481425","https://openalex.org/W2565167788","https://openalex.org/W2739748921","https://openalex.org/W2963784072","https://openalex.org/W4255375128","https://openalex.org/W4320013936","https://openalex.org/W6640634549","https://openalex.org/W6675634716","https://openalex.org/W6720691552","https://openalex.org/W6741832134"],"related_works":["https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W3193043704","https://openalex.org/W2048488252","https://openalex.org/W4288365262","https://openalex.org/W2940614149","https://openalex.org/W4289884158","https://openalex.org/W2787485953","https://openalex.org/W3217432596","https://openalex.org/W4387323767"],"abstract_inverted_index":{"The":[0,179],"goal":[1],"of":[2,20,43,57,104,151,165,206],"this":[3],"paper":[4],"is":[5,195],"to":[6,11,15,65,94,132,147,169,202],"automatically":[7],"generate":[8,95,120,148],"synthetic":[9,96,140,145,149,174,185],"data":[10,13,62,116,150,175,186,200],"enable":[12],"analyzers":[14],"cope":[16],"with":[17],"the":[18,24,101,128,139,163,171,184,189,204],"problem":[19,205],"insufficient":[21,38,54,207],"data.":[22,97,178,208],"Taking":[23],"most":[25],"typical":[26],"machine":[27,44,166],"learning":[28,45,167],"tasks,":[29],"classification":[30,157],"and":[31,37,85,90,107,137,158,161,176],"regression,":[32,159],"as":[33],"an":[34,196],"example,":[35],"limited":[36],"samples":[39,122],"cause":[40],"low":[41],"generalization":[42],"models,":[46],"which":[47,192],"cannot":[48],"provide":[49],"reasonable":[50],"predictions.":[51],"Data":[52,81],"are":[53,63],"either":[55],"because":[56,61],"sample":[58],"rarity":[59],"or":[60,71],"impeded":[64],"be":[66],"accessed":[67],"for":[68,83,113,156,199],"privacy":[69],"concerns":[70],"confidential":[72],"protection.":[73],"To":[74],"overcome":[75,203],"this,":[76],"we":[77,119],"present":[78],"a":[79,109],"Synthetic":[80],"Approach":[82],"Classification":[84],"Regression,":[86],"adopting":[87],"probability":[88,102,125],"distribution":[89,103],"k-nearest":[91,110,129],"neighbor":[92,111,130],"model":[93,112,131],"We":[98,142],"first":[99],"estimate":[100],"each":[105],"feature":[106],"construct":[108],"all":[114],"original":[115,177,190],"samples.":[117,141],"Then":[118],"random":[121,135],"based":[123],"on":[124],"distributions,":[126],"adopt":[127],"validate":[133],"these":[134],"samples,":[136],"output":[138],"use":[143],"proposed":[144],"approaches":[146],"five":[152],"publicly":[153],"available":[154],"datasets":[155],"respectively,":[160],"evaluate":[162,170],"performance":[164],"models":[168],"resemblance":[172],"between":[173],"experimental":[180],"results":[181],"show":[182],"that":[183],"can":[187],"resemble":[188],"data,":[191],"indicates":[193],"it":[194],"effective":[197],"approach":[198],"analyzer":[201]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}