{"id":"https://openalex.org/W2921662080","doi":"https://doi.org/10.1109/bigdata47090.2019.9006460","title":"An \u201cOn The Fly\u201d Framework for Efficiently Generating Synthetic Big Data Sets","display_name":"An \u201cOn The Fly\u201d Framework for Efficiently Generating Synthetic Big Data Sets","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2921662080","doi":"https://doi.org/10.1109/bigdata47090.2019.9006460","mag":"2921662080"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.06798","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088726212","display_name":"Karl Mason","orcid":"https://orcid.org/0000-0002-8966-9100"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karl Mason","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027070789","display_name":"Sadegh Vejdan","orcid":"https://orcid.org/0000-0002-9401-7262"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sadegh Vejdan","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074866066","display_name":"Santiago Grijalva","orcid":"https://orcid.org/0000-0001-8601-4662"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santiago Grijalva","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01986294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3379","last_page":"3387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9915000200271606,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9915000200271606,"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":0.9909999966621399,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9871000051498413,"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":0.7998324036598206},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7206695675849915},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.6200135946273804},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5745185613632202},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5472518801689148},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.540168046951294},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5089869499206543},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4844346344470978},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.48119884729385376},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4756336212158203},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4567405581474304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1932353675365448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998324036598206},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7206695675849915},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.6200135946273804},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5745185613632202},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5472518801689148},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.540168046951294},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5089869499206543},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4844346344470978},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.48119884729385376},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4756336212158203},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4567405581474304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1932353675365448},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.06798","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.06798","pdf_url":"https://arxiv.org/pdf/1903.06798","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2921662080","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1903.06798","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1903.06798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.06798","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.06798","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.06798","pdf_url":"https://arxiv.org/pdf/1903.06798","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2921662080.pdf","grobid_xml":"https://content.openalex.org/works/W2921662080.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1544148736","https://openalex.org/W1549869922","https://openalex.org/W2002541641","https://openalex.org/W2002825548","https://openalex.org/W2011430131","https://openalex.org/W2026360117","https://openalex.org/W2029501294","https://openalex.org/W2060747549","https://openalex.org/W2072750586","https://openalex.org/W2076063813","https://openalex.org/W2079697937","https://openalex.org/W2081406187","https://openalex.org/W2099471712","https://openalex.org/W2145287260","https://openalex.org/W2200122354","https://openalex.org/W2210543184","https://openalex.org/W2417056346","https://openalex.org/W2553567329","https://openalex.org/W2606508169","https://openalex.org/W2610135452","https://openalex.org/W2622826443","https://openalex.org/W2765356101","https://openalex.org/W2789345518","https://openalex.org/W2789712627","https://openalex.org/W2795993366","https://openalex.org/W2802770308","https://openalex.org/W2808980893","https://openalex.org/W2888875162","https://openalex.org/W2903970876","https://openalex.org/W2962977206","https://openalex.org/W6632476604","https://openalex.org/W6677477928"],"related_works":["https://openalex.org/W3157873259","https://openalex.org/W3164045371","https://openalex.org/W2088083083","https://openalex.org/W2463547599","https://openalex.org/W1982516027","https://openalex.org/W2753841819","https://openalex.org/W2973291463","https://openalex.org/W2495432222","https://openalex.org/W3167736128","https://openalex.org/W2796163979","https://openalex.org/W2952173606","https://openalex.org/W3096531182","https://openalex.org/W3008795670","https://openalex.org/W2339685823","https://openalex.org/W1808694123","https://openalex.org/W2320507227","https://openalex.org/W2997502132","https://openalex.org/W2945519417","https://openalex.org/W2890932039","https://openalex.org/W2182043445"],"abstract_inverted_index":{"Collecting,":[0],"analyzing":[1],"and":[2,48,82,120],"gaining":[3],"insight":[4],"from":[5],"large":[6,35,92],"volumes":[7,36],"of":[8,19,37,126,131,142,164,173],"data":[9,40,51,60,68,74,84,93,107,112,155,176],"is":[10,85,116,135],"now":[11],"the":[12,100,132,153,170,175],"norm":[13],"in":[14,73,161,178],"an":[15,98],"ever":[16],"increasing":[17],"number":[18],"industries.":[20],"Data":[21],"analytics":[22,52,113],"techniques,":[23],"such":[24,50],"as":[25],"machine":[26],"learning,":[27],"are":[28,42,63],"powerful":[29],"tools":[30],"used":[31],"to":[32,46,57,65,70,122,169],"analyze":[33],"these":[34,111],"data.":[38],"Synthetic":[39],"sets":[41,61,75],"routinely":[43],"relied":[44],"upon":[45],"train":[47],"develop":[49],"methods":[53],"for":[54,103,110],"several":[55],"reasons:":[56],"generate":[58,66],"larger":[59],"than":[62],"available,":[64],"diverse":[67,124],"sets,":[69,108],"preserve":[71],"anonymity":[72],"with":[76,138],"sensitive":[77],"information,":[78],"etc.":[79],"Processing,":[80],"transmitting":[81],"storing":[83],"a":[86,123,139,159],"key":[87],"issue":[88],"faced":[89],"when":[90,167],"handling":[91],"sets.":[94],"This":[95],"paper":[96],"presents":[97],"\u201cOn":[99],"fly\u201d":[101],"framework":[102,134,157],"generating":[104,174],"big":[105],"synthetic":[106],"suitable":[109],"methods,":[114],"that":[115,152],"both":[117],"computationally":[118],"efficient":[119],"applicable":[121],"set":[125,177],"problems.":[127],"An":[128],"example":[129],"application":[130],"proposed":[133,154],"presented":[136],"along":[137],"mathematical":[140],"analysis":[141],"its":[143,147],"computational":[144,162],"efficiency,":[145],"demonstrating":[146],"effectiveness.":[148],"Empirical":[149],"results":[150],"indicate":[151],"generation":[156],"provides":[158],"reduction":[160],"time":[163],"\u2248":[165],"33%":[166],"compared":[168],"alternative":[171],"approach":[172],"full.":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}