{"id":"https://openalex.org/W4406458143","doi":"https://doi.org/10.1109/bigdata62323.2024.10825133","title":"Training Variational Autoencoders for Population Synthesis in Public Health with Missing Data","display_name":"Training Variational Autoencoders for Population Synthesis in Public Health with Missing Data","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458143","doi":"https://doi.org/10.1109/bigdata62323.2024.10825133"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","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/A5115904478","display_name":"Nathan Blackthorn","orcid":null},"institutions":[{"id":"https://openalex.org/I83683471","display_name":"University of West Florida","ror":"https://ror.org/002w4zy91","country_code":"US","type":"education","lineage":["https://openalex.org/I83683471"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nathan Blackthorn","raw_affiliation_strings":["University of West Florida,Department of Computer Science,Pensacola,FL,USA"],"affiliations":[{"raw_affiliation_string":"University of West Florida,Department of Computer Science,Pensacola,FL,USA","institution_ids":["https://openalex.org/I83683471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114494323","display_name":"Andrew Arash Mahyari","orcid":null},"institutions":[{"id":"https://openalex.org/I1335578998","display_name":"Florida Institute for Human and Machine Cognition","ror":"https://ror.org/02napvw46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1335578998"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Arash Mahyari","raw_affiliation_strings":["Florida Institute For Human and Machine Cognition (IHMC),Pensacola,FL,USA"],"affiliations":[{"raw_affiliation_string":"Florida Institute For Human and Machine Cognition (IHMC),Pensacola,FL,USA","institution_ids":["https://openalex.org/I1335578998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081004875","display_name":"Ashok Srinivasan","orcid":"https://orcid.org/0000-0003-0408-2886"},"institutions":[{"id":"https://openalex.org/I83683471","display_name":"University of West Florida","ror":"https://ror.org/002w4zy91","country_code":"US","type":"education","lineage":["https://openalex.org/I83683471"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok Srinivasan","raw_affiliation_strings":["University of West Florida,Department of Computer Science,Pensacola,FL,USA"],"affiliations":[{"raw_affiliation_string":"University of West Florida,Department of Computer Science,Pensacola,FL,USA","institution_ids":["https://openalex.org/I83683471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115904478"],"corresponding_institution_ids":["https://openalex.org/I83683471"],"apc_list":null,"apc_paid":null,"fwci":0.5561,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74381197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4969","last_page":"4973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10235","display_name":"Health disparities and outcomes","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/3306","display_name":"Health"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10235","display_name":"Health disparities and outcomes","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/3306","display_name":"Health"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12011","display_name":"Insurance, Mortality, Demography, Risk Management","score":0.958899974822998,"subfield":{"id":"https://openalex.org/subfields/3317","display_name":"Demography"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9567000269889832,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.6285710334777832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6146643757820129},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6092537641525269},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5419178605079651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5230744481086731},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.47172465920448303},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38140609860420227},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.14849543571472168},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08916610479354858},{"id":"https://openalex.org/keywords/environmental-health","display_name":"Environmental health","score":0.07267838716506958}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.6285710334777832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6146643757820129},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6092537641525269},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5419178605079651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5230744481086731},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.47172465920448303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38140609860420227},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.14849543571472168},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08916610479354858},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.07267838716506958},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2128248134","https://openalex.org/W2808094045","https://openalex.org/W2963185411","https://openalex.org/W3082373586","https://openalex.org/W3096831136","https://openalex.org/W3211207279","https://openalex.org/W4392026140","https://openalex.org/W6685352114","https://openalex.org/W6735926176"],"related_works":["https://openalex.org/W4380150146","https://openalex.org/W3024870410","https://openalex.org/W2410652950","https://openalex.org/W4283773154","https://openalex.org/W3139174110","https://openalex.org/W4289597203","https://openalex.org/W2085630472","https://openalex.org/W4285201053","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"The":[0],"importance":[1],"of":[2,5,62,75,181,194],"social":[3,24],"determinants":[4],"health":[6,11,32,97,201,217],"in":[7,94,184,196],"shaping":[8],"equitable":[9],"public":[10,31,96,216],"policies":[12],"is":[13,59,105],"gaining":[14],"increasing":[15],"recognition.":[16],"Emerging":[17],"data":[18,187,221],"sources,":[19],"such":[20,99],"as":[21,44,100],"mobility":[22],"and":[23,163,171],"media":[25],"data,":[26,43,102,132],"are":[27,48,142,207],"becoming":[28],"key":[29],"to":[30,40,50,56,88,108,135,160,214],"models.":[33],"However,":[34,93],"privacy":[35,69],"concerns":[36],"often":[37],"limit":[38],"access":[39,87],"these":[41],"sensitive":[42,113],"even":[45,203],"anonymized":[46],"datasets":[47,90,206],"vulnerable":[49],"deductive":[51],"disclosure.":[52],"A":[53],"promising":[54],"solution":[55,213],"this":[57,103,182],"challenge":[58],"the":[60,73,140,146,150,176,179,192],"use":[61],"synthetic":[63,83,165,198],"populations,":[64],"which":[65],"not":[66],"only":[67],"safeguard":[68],"but":[70],"also":[71],"enable":[72],"exploration":[74],"various":[76],"\"what-if\"":[77],"scenarios.":[78],"Most":[79],"existing":[80],"studies":[81,218],"on":[82,145],"populations":[84,199],"assume":[85],"full":[86],"complete":[89,205],"for":[91,125,154,174,200],"training.":[92],"many":[95],"applications,":[98],"census":[101],"assumption":[104],"unrealistic":[106],"due":[107],"incomplete":[109,131],"responses,":[110],"especially":[111],"regarding":[112],"questions":[114],"like":[115],"wealth":[116],"or":[117],"education.":[118],"This":[119,189],"paper":[120],"introduces":[121],"a":[122,211],"novel":[123],"approach":[124],"training":[126],"Variational":[127],"AutoEncoders":[128],"(VAEs)":[129],"with":[130],"without":[133],"resorting":[134],"missing":[136,186],"value":[137],"imputation.":[138],"Instead,":[139],"VAEs":[141,159,195],"trained":[143],"solely":[144],"observed":[147],"data.":[148],"Using":[149],"2019":[151],"PUMS":[152],"dataset":[153],"Florida,":[155],"we":[156],"successfully":[157],"train":[158],"generate":[161],"diverse":[162],"flexible":[164],"populations.":[166],"By":[167],"comparing":[168],"marginal":[169],"distributions":[170],"utilizing":[172],"t-SNE":[173],"analysis,":[175],"results":[177],"highlight":[178],"effectiveness":[180],"method":[183],"addressing":[185],"challenges.":[188],"work":[190],"demonstrates":[191],"potential":[193],"generating":[197],"research,":[202],"when":[204],"unavailable,":[208],"thereby":[209],"offering":[210],"robust":[212],"advance":[215],"while":[219],"preserving":[220],"privacy.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}