{"id":"https://openalex.org/W4415362373","doi":"https://doi.org/10.7717/peerj-cs.3228","title":"Empirical copula-based data augmentation for mixed-type datasets: a robust approach for synthetic data generation","display_name":"Empirical copula-based data augmentation for mixed-type datasets: a robust approach for synthetic data generation","publication_year":2025,"publication_date":"2025-10-20","ids":{"openalex":"https://openalex.org/W4415362373","doi":"https://doi.org/10.7717/peerj-cs.3228"},"language":"en","primary_location":{"id":"doi:10.7717/peerj-cs.3228","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj-cs.3228","pdf_url":null,"source":{"id":"https://openalex.org/S4210178049","display_name":"PeerJ Computer Science","issn_l":"2376-5992","issn":["2376-5992"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7717/peerj-cs.3228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088758808","display_name":"Mohsen Ben Hassine","orcid":null},"institutions":[{"id":"https://openalex.org/I179097149","display_name":"University of Carthage","ror":"https://ror.org/057x6za15","country_code":"TN","type":"education","lineage":["https://openalex.org/I179097149"]},{"id":"https://openalex.org/I4210110695","display_name":"Universit\u00e9 Tunis Carthage","ror":"https://ror.org/01xf5pq20","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210110695"]},{"id":"https://openalex.org/I4210120884","display_name":"Institut Sup\u00e9rieur des \u00c9tudes Technologiques en Communications de Tunis","ror":"https://ror.org/02rfbsc53","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210120884"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Mohsen Ben Hassine","raw_affiliation_strings":["Computer Sciences, Universit\u00e9 Tunis Carthage, Ariana, Ariana, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Sciences, Universit\u00e9 Tunis Carthage, Ariana, Ariana, Tunisia","institution_ids":["https://openalex.org/I179097149","https://openalex.org/I4210110695","https://openalex.org/I4210120884"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073678278","display_name":"Lamine Mili","orcid":"https://orcid.org/0000-0001-6134-3945"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lamine Mili","raw_affiliation_strings":["Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University (Virginia Tech), Virginia, Virginia, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University (Virginia Tech), Virginia, Virginia, United States","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088758808"],"corresponding_institution_ids":["https://openalex.org/I179097149","https://openalex.org/I4210110695","https://openalex.org/I4210120884"],"apc_list":{"value":1395,"currency":"USD","value_usd":1395},"apc_paid":{"value":1395,"currency":"USD","value_usd":1395},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32106234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"e3228","last_page":"e3228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9927999973297119,"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/T10282","display_name":"Financial Risk and Volatility Modeling","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.7228999733924866},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5745000243186951},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.426800012588501},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4244000017642975},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.36550000309944153},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.3644999861717224},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.3474999964237213},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.32499998807907104}],"concepts":[{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.7228999733924866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217000126838684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6244999766349792},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4088999927043915},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.7717/peerj-cs.3228","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj-cs.3228","pdf_url":null,"source":{"id":"https://openalex.org/S4210178049","display_name":"PeerJ Computer Science","issn_l":"2376-5992","issn":["2376-5992"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/140607","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/140607","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:e7968981563c4f64b464e122acbb4f5d","is_oa":true,"landing_page_url":"https://doaj.org/article/e7968981563c4f64b464e122acbb4f5d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PeerJ Computer Science, Vol 11, p e3228 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.7717/peerj-cs.3228","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj-cs.3228","pdf_url":null,"source":{"id":"https://openalex.org/S4210178049","display_name":"PeerJ Computer Science","issn_l":"2376-5992","issn":["2376-5992"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1817128614","https://openalex.org/W2148143831","https://openalex.org/W2741280792","https://openalex.org/W2789942385","https://openalex.org/W2949736877","https://openalex.org/W2954996726","https://openalex.org/W3120369609","https://openalex.org/W3152268000","https://openalex.org/W3158382876","https://openalex.org/W3174167721","https://openalex.org/W3203429447","https://openalex.org/W4225349722","https://openalex.org/W4285722178","https://openalex.org/W4287686870","https://openalex.org/W4297796148","https://openalex.org/W4300980427","https://openalex.org/W4310895557","https://openalex.org/W4319996951","https://openalex.org/W4360860566","https://openalex.org/W4361285594","https://openalex.org/W4389671650","https://openalex.org/W4392971772","https://openalex.org/W4397028113","https://openalex.org/W4402230126","https://openalex.org/W4403623300","https://openalex.org/W4404967466","https://openalex.org/W6891856102"],"related_works":[],"abstract_inverted_index":{"Data":[0],"augmentation":[1],"is":[2,144],"a":[3,54],"critical":[4],"technique":[5],"for":[6,47,59],"enhancing":[7],"model":[8],"performance":[9],"in":[10,146],"scenarios":[11],"with":[12],"limited,":[13],"sparse,":[14],"or":[15,31],"imbalanced":[16],"datasets.":[17],"While":[18],"existing":[19],"methods":[20],"often":[21],"focus":[22],"on":[23],"homogeneous":[24],"data":[25,38,49,62,83],"types":[26,39],"(":[27],"e.g":[28],".,":[29],"continuous-only":[30],"categorical-only),":[32],"real-world":[33],"datasets":[34,110],"frequently":[35],"contain":[36],"mixed":[37],"(continuous,":[40],"integer,":[41],"and":[42,67,71,87,107,116,153],"categorical),":[43],"posing":[44],"significant":[45],"challenges":[46],"synthetic":[48,61,106,130],"generation.":[50],"This":[51],"article":[52],"introduces":[53,88],"novel":[55],"empirical":[56],"copula-based":[57],"framework":[58],"generating":[60],"that":[63,132],"preserves":[64],"both":[65],"marginal":[66],"joint":[68],"probability":[69],"distributions":[70],"dependencies":[72],"of":[73,102,137],"mixed-type":[74],"features.":[75],"Our":[76],"method":[77,143],"addresses":[78],"missing":[79],"values,":[80],"handles":[81],"heterogeneous":[82],"through":[84],"type-specific":[85],"transformations,":[86],"controlled":[89],"noise":[90],"to":[91,127],"enhance":[92],"diversity":[93],"while":[94],"maintaining":[95],"statistical":[96,135],"fidelity.":[97],"We":[98],"demonstrate":[99],"the":[100,113,117,134,138],"efficacy":[101],"this":[103],"approach":[104],"using":[105],"experimental":[108],"benchmark":[109],"such":[111],"as":[112],"Census":[114],"Income":[115],"Wisconsin":[118],"Diagnostic":[119],"Breast":[120],"Cancer":[121],"(WDBC)":[122],"dataset,":[123],"demonstrating":[124],"its":[125],"ability":[126],"generate":[128],"realistic":[129],"samples":[131],"retain":[133],"properties":[136],"original":[139],"data.":[140],"The":[141],"proposed":[142],"implemented":[145],"an":[147],"open-source":[148],"Python":[149],"class,":[150],"ensuring":[151],"reproducibility":[152],"scalability.":[154]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-21T00:00:00"}