{"id":"https://openalex.org/W4214503032","doi":"https://doi.org/10.1145/3510834","title":"Distance-based Probabilistic Data Augmentation for Synthetic Minority Oversampling","display_name":"Distance-based Probabilistic Data Augmentation for Synthetic Minority Oversampling","publication_year":2021,"publication_date":"2021-11-30","ids":{"openalex":"https://openalex.org/W4214503032","doi":"https://doi.org/10.1145/3510834"},"language":"en","primary_location":{"id":"doi:10.1145/3510834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3510834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3510834","source":{"id":"https://openalex.org/S4210185969","display_name":"ACM/IMS Transactions on Data Science","issn_l":"2577-3224","issn":["2577-3224","2691-1922"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM/IMS Transactions on Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3510834","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020655064","display_name":"Joel Goodman","orcid":"https://orcid.org/0000-0002-7980-1104"},"institutions":[{"id":"https://openalex.org/I1288214837","display_name":"United States Naval Research Laboratory","ror":"https://ror.org/04d23a975","country_code":"US","type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joel Goodman","raw_affiliation_strings":["US Naval Research Laboratory, Washington, DC"],"affiliations":[{"raw_affiliation_string":"US Naval Research Laboratory, Washington, DC","institution_ids":["https://openalex.org/I1288214837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113984418","display_name":"Sharham Sarkani","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharham Sarkani","raw_affiliation_strings":["The George Washington University, Washington, DC"],"affiliations":[{"raw_affiliation_string":"The George Washington University, Washington, DC","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050432319","display_name":"Thomas A. Mazzuchi","orcid":"https://orcid.org/0000-0002-4584-4018"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Mazzuchi","raw_affiliation_strings":["The George Washington University, Washington, DC"],"affiliations":[{"raw_affiliation_string":"The George Washington University, Washington, DC","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020655064"],"corresponding_institution_ids":["https://openalex.org/I1288214837"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79019506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2","issue":"4","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11443","display_name":"Advanced Statistical Process Monitoring","score":0.9736999869346619,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9711999893188477,"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/oversampling","display_name":"Oversampling","score":0.993664026260376},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6884368658065796},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6375582814216614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5616741180419922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5496323704719543},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5424765348434448},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5109683275222778},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5011823177337646},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4911637008190155},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4895709455013275},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.43154042959213257},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3568735718727112},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3436378836631775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2832747995853424}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.993664026260376},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6884368658065796},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6375582814216614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5616741180419922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496323704719543},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5424765348434448},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5109683275222778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5011823177337646},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4911637008190155},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4895709455013275},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.43154042959213257},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3568735718727112},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3436378836631775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2832747995853424},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3510834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3510834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3510834","source":{"id":"https://openalex.org/S4210185969","display_name":"ACM/IMS Transactions on Data Science","issn_l":"2577-3224","issn":["2577-3224","2691-1922"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM/IMS Transactions on Data Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3510834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3510834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3510834","source":{"id":"https://openalex.org/S4210185969","display_name":"ACM/IMS Transactions on Data Science","issn_l":"2577-3224","issn":["2577-3224","2691-1922"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM/IMS Transactions on Data Science","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4214503032.pdf","grobid_xml":"https://content.openalex.org/works/W4214503032.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W10885063","https://openalex.org/W587473303","https://openalex.org/W600585464","https://openalex.org/W1100975233","https://openalex.org/W1496056137","https://openalex.org/W1517113043","https://openalex.org/W1581587400","https://openalex.org/W1967127231","https://openalex.org/W1985442349","https://openalex.org/W1993220166","https://openalex.org/W2015681982","https://openalex.org/W2040010062","https://openalex.org/W2047555270","https://openalex.org/W2076272581","https://openalex.org/W2087240369","https://openalex.org/W2096479881","https://openalex.org/W2096945460","https://openalex.org/W2104933073","https://openalex.org/W2118020555","https://openalex.org/W2118978333","https://openalex.org/W2120636621","https://openalex.org/W2132791018","https://openalex.org/W2139986471","https://openalex.org/W2150559772","https://openalex.org/W2150879893","https://openalex.org/W2172165257","https://openalex.org/W2295598076","https://openalex.org/W2460759951","https://openalex.org/W2520599539","https://openalex.org/W2562319768","https://openalex.org/W2772832743","https://openalex.org/W2795485111","https://openalex.org/W2810502617","https://openalex.org/W2896805537","https://openalex.org/W2899434936","https://openalex.org/W2909588969","https://openalex.org/W2969674096","https://openalex.org/W2991755410","https://openalex.org/W3021199811","https://openalex.org/W3026559324","https://openalex.org/W3035874221","https://openalex.org/W4212863985"],"related_works":["https://openalex.org/W2774028126","https://openalex.org/W4225392367","https://openalex.org/W3055496383","https://openalex.org/W2071785112","https://openalex.org/W3158316258","https://openalex.org/W3214103303","https://openalex.org/W4280583325","https://openalex.org/W4225984852","https://openalex.org/W2356149660","https://openalex.org/W4214503032"],"abstract_inverted_index":{"Class":[0],"imbalance":[1,20],"can":[2,28,71],"adversely":[3],"affect":[4],"the":[5,18,44,63,68,88,102,107,114],"performance":[6,130],"of":[7,46,109],"machine":[8],"learning":[9],"for":[10],"prediction":[11],"and":[12,48,93,126,134],"classification.":[13],"One":[14],"approach":[15,81,111],"to":[16],"address":[17],"class":[19,57,91],"problem":[21],"is":[22],"synthetic":[23,136],"minority":[24,51,69,90,137],"oversampling.":[25],"Oversampling":[26],"approaches":[27,41,61],"be":[29,72],"broadly":[30],"categorized":[31],"as":[32],"either":[33],"being":[34],"structural":[35,135],"or":[36],"statistical":[37,60,133],"in":[38,101],"nature.":[39],"Structural":[40],"generally":[42],"have":[43],"advantage":[45],"identifying":[47],"oversampling":[49,138],"those":[50,97],"data":[52,116],"points":[53],"that":[54,82],"best":[55],"facilitate":[56],"separation,":[58],"while":[59],"model":[62],"underlying":[64,89],"distribution":[65,92],"from":[66,118],"which":[67],"samples":[70,84,99],"drawn.":[73],"In":[74],"this":[75],"article,":[76],"we":[77],"formulate":[78],"a":[79],"distance-based":[80],"generates":[83],"by":[85,94,120],"both":[86,132],"modeling":[87],"geometrically":[95],"considering":[96],"borderline":[98],"entangled":[100],"majority":[103],"class.":[104],"We":[105],"demonstrate":[106],"efficacy":[108],"our":[110],"operating":[112],"on":[113],"Class-Imbalance":[115],"set":[117],"UCI":[119],"comparing":[121],"its":[122],"mean":[123],"accuracy,":[124],"AUC":[125],"F":[127],"1":[128],"-score":[129],"against":[131],"methods.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}