A Transformer model for Dengue time series forecast

Detalhes bibliográficos
Ano de defesa: 2025
Autor(a) principal: Guedes, Henrique Berenger
Orientador(a): Coelho, Flávio Codeço
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: eng
Instituição de defesa: Não Informado pela instituição
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Inglês:
Time series forecasting
Transformer
Dengue
Deep Learning
Link de acesso: https://hdl.handle.net/10438/37785
Resumo: Dengue fever is a viral mosquito-borne disease that affects many countries, especially in the Latin American and Asian continents. During the past five years, its incidence has risen sharply in Brazil, with many municipalities that were previously non endemic now reporting sustained transmission. Accurate forecasts are therefore critical for early warning systems and for guiding the allocation of health care resources. This study examines the capacity of the Transformer architecture, a deep learning model originally developed for sequence modeling, to capture the complex temporal dynamics of dengue transmission. Weekly dengue case and climate covariates were compiled for 92 municipalities in the state of Rio de Janeiro and used to train and validate the model. All data used in this study were obtained from the Mosqlimate platform.
id FGV_2a2d97dbfc3c54f515b17500298d5ffa
oai_identifier_str oai:repositorio.fgv.br:10438/37785
network_acronym_str FGV
network_name_str Repositório Institucional do FGV (FGV Repositório Digital)
repository_id_str
spelling Guedes, Henrique BerengerEscolas::EMApCarvalho, Luiz Max Fagundes deBianchi, Lucas Monteiro Coelho, Flávio Codeço2025-10-13T15:03:31Z2025-10-13T15:03:31Z2025-09-08https://hdl.handle.net/10438/37785Dengue fever is a viral mosquito-borne disease that affects many countries, especially in the Latin American and Asian continents. During the past five years, its incidence has risen sharply in Brazil, with many municipalities that were previously non endemic now reporting sustained transmission. Accurate forecasts are therefore critical for early warning systems and for guiding the allocation of health care resources. This study examines the capacity of the Transformer architecture, a deep learning model originally developed for sequence modeling, to capture the complex temporal dynamics of dengue transmission. Weekly dengue case and climate covariates were compiled for 92 municipalities in the state of Rio de Janeiro and used to train and validate the model. All data used in this study were obtained from the Mosqlimate platform.A dengue é uma doença viral transmitida por mosquitos que afeta muitos países, especialmente nos continentes latino-americano e asiático. Nos últimos cinco anos, sua incidência aumentou significativamente no Brasil, com muitos municípios que antes não eram endêmicos agora registrando transmissão sustentada. Previsões precisas são, portanto, essenciais para sistemas de alerta precoce e para orientar a alocação de recursos de saúde. Este estudo examina a capacidade da arquitetura Transformer — um modelo de aprendizado profundo originalmente desenvolvido para modelagem de sequências — de capturar as complexas dinâmicas temporais da transmissão da dengue. Casos semanais de dengue e variáveis climáticas foram compilados para 92 municípios do estado do Rio de Janeiro e utilizados para treinar e validar o modelo. Todos os dados utilizados neste estudo foram obtidos na plataforma Mosqlimate.engTime series forecastingTransformerDengueDeep LearningMatemáticaDengueEpidemiologia - Modelos matemáticosAprendizado profundo (Aprendizado do computador)Doenças - PrevençãoAprendizado do computadorA Transformer model for Dengue time series forecastinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional do FGV (FGV Repositório Digital)instname:Fundação Getulio Vargas (FGV)instacron:FGVORIGINALDissertação_final.pdfDissertação_final.pdfPDFapplication/pdf2434071https://repositorio.fgv.br/bitstreams/85690ee7-ea3d-41e4-b123-507a3879591e/downloada4753fba2d2c413ddd987dad3e93fdd9MD51trueAnonymousREADLICENSElicense.txtlicense.txttext/plain; charset=utf-85112https://repositorio.fgv.br/bitstreams/3419cf56-56ab-4b24-afe1-fd759466e491/download2a4b67231f701c416a809246e7a10077MD52falseAnonymousREADTEXTDissertação_final.pdf.txtDissertação_final.pdf.txtExtracted texttext/plain62129https://repositorio.fgv.br/bitstreams/c824a46f-eb1f-4ab9-aa74-0f83bbd04648/download0cb519d6ddbb8524f21689f6d6b07bdbMD53falseAnonymousREADTHUMBNAILDissertação_final.pdf.jpgDissertação_final.pdf.jpgGenerated Thumbnailimage/jpeg2565https://repositorio.fgv.br/bitstreams/36212b8e-43b2-4a1d-a186-3a76eb48eb5e/download16f3ee414dfa6bddf67195c302d64170MD54falseAnonymousREAD10438/377852025-11-25 12:28:29.246open.accessoai:repositorio.fgv.br:10438/37785https://repositorio.fgv.brRepositório InstitucionalPRIhttp://bibliotecadigital.fgv.br/dspace-oai/requestbiblioteca.digital@fgv.bropendoar:39742025-11-25T12:28:29Repositório Institucional do FGV (FGV Repositório Digital) - Fundação Getulio Vargas (FGV)falseVGVybW8gZGUgTGljZW5jaWFtZW50bwpIw6EgdW0gw7psdGltbyBwYXNzbzogcGFyYSByZXByb2R1emlyLCB0cmFkdXppciBlIGRpc3RyaWJ1aXIgc3VhIHN1Ym1pc3PDo28gZW0gdG9kbyBvIG11bmRvLCB2b2PDqiBkZXZlIGNvbmNvcmRhciBjb20gb3MgdGVybW9zIGEgc2VndWlyLgoKQ29uY29yZGFyIGNvbSBvIFRlcm1vIGRlIExpY2VuY2lhbWVudG8sIHNlbGVjaW9uYW5kbyAiRXUgY29uY29yZG8gY29tIG8gVGVybW8gZGUgTGljZW5jaWFtZW50byIgZSBjbGlxdWUgZW0gIkZpbmFsaXphciBzdWJtaXNzw6NvIi4KClRFUk1PUyBMSUNFTkNJQU1FTlRPIFBBUkEgQVJRVUlWQU1FTlRPLCBSRVBST0RVw4fDg08gRSBESVZVTEdBw4fDg08gUMOaQkxJQ0EgREUgQ09OVEXDmkRPIMOAIEJJQkxJT1RFQ0EgVklSVFVBTCBGR1YgKHZlcnPDo28gMS4yKQoKMS4gVm9jw6osIHVzdcOhcmlvLWRlcG9zaXRhbnRlIGRhIEJpYmxpb3RlY2EgVmlydHVhbCBGR1YsIGFzc2VndXJhLCBubyBwcmVzZW50ZSBhdG8sIHF1ZSDDqSB0aXR1bGFyIGRvcyBkaXJlaXRvcyBhdXRvcmFpcyBwYXRyaW1vbmlhaXMgZS9vdSBkaXJlaXRvcyBjb25leG9zIHJlZmVyZW50ZXMgw6AgdG90YWxpZGFkZSBkYSBPYnJhIG9yYSBkZXBvc2l0YWRhIGVtIGZvcm1hdG8gZGlnaXRhbCwgYmVtIGNvbW8gZGUgc2V1cyBjb21wb25lbnRlcyBtZW5vcmVzLCBlbSBzZSB0cmF0YW5kbyBkZSBvYnJhIGNvbGV0aXZhLCBjb25mb3JtZSBvIHByZWNlaXR1YWRvIHBlbGEgTGVpIDkuNjEwLzk4IGUvb3UgTGVpIDkuNjA5Lzk4LiBOw6NvIHNlbmRvIGVzdGUgbyBjYXNvLCB2b2PDqiBhc3NlZ3VyYSB0ZXIgb2J0aWRvLCBkaXJldGFtZW50ZSBkb3MgZGV2aWRvcyB0aXR1bGFyZXMsIGF1dG9yaXphw6fDo28gcHLDqXZpYSBlIGV4cHJlc3NhIHBhcmEgbyBkZXDDs3NpdG8gZSBkaXZ1bGdhw6fDo28gZGEgT2JyYSwgYWJyYW5nZW5kbyB0b2RvcyBvcyBkaXJlaXRvcyBhdXRvcmFpcyBlIGNvbmV4b3MgYWZldGFkb3MgcGVsYSBhc3NpbmF0dXJhIGRvcyBwcmVzZW50ZXMgdGVybW9zIGRlIGxpY2VuY2lhbWVudG8sIGRlIG1vZG8gYSBlZmV0aXZhbWVudGUgaXNlbnRhciBhIEZ1bmRhw6fDo28gR2V0dWxpbyBWYXJnYXMgZSBzZXVzIGZ1bmNpb27DoXJpb3MgZGUgcXVhbHF1ZXIgcmVzcG9uc2FiaWxpZGFkZSBwZWxvIHVzbyBuw6NvLWF1dG9yaXphZG8gZG8gbWF0ZXJpYWwgZGVwb3NpdGFkbywgc2VqYSBlbSB2aW5jdWxhw6fDo28gw6AgQmlibGlvdGVjYSBWaXJ0dWFsIEZHViwgc2VqYSBlbSB2aW5jdWxhw6fDo28gYSBxdWFpc3F1ZXIgc2VydmnDp29zIGRlIGJ1c2NhIGUgZGlzdHJpYnVpw6fDo28gZGUgY29udGXDumRvIHF1ZSBmYcOnYW0gdXNvIGRhcyBpbnRlcmZhY2VzIGUgZXNwYcOnbyBkZSBhcm1hemVuYW1lbnRvIHByb3ZpZGVuY2lhZG9zIHBlbGEgRnVuZGHDp8OjbyBHZXR1bGlvIFZhcmdhcyBwb3IgbWVpbyBkZSBzZXVzIHNpc3RlbWFzIGluZm9ybWF0aXphZG9zLgoKMi4gQSBhc3NpbmF0dXJhIGRlc3RhIGxpY2Vuw6dhIHRlbSBjb21vIGNvbnNlccO8w6puY2lhIGEgdHJhbnNmZXLDqm5jaWEsIGEgdMOtdHVsbyBuw6NvLWV4Y2x1c2l2byBlIG7Do28tb25lcm9zbywgaXNlbnRhIGRvIHBhZ2FtZW50byBkZSByb3lhbHRpZXMgb3UgcXVhbHF1ZXIgb3V0cmEgY29udHJhcHJlc3Rhw6fDo28sIHBlY3VuacOhcmlhIG91IG7Do28sIMOgIEZ1bmRhw6fDo28gR2V0dWxpbyBWYXJnYXMsIGRvcyBkaXJlaXRvcyBkZSBhcm1hemVuYXIgZGlnaXRhbG1lbnRlLCByZXByb2R1emlyIGUgZGlzdHJpYnVpciBuYWNpb25hbCBlIGludGVybmFjaW9uYWxtZW50ZSBhIE9icmEsIGluY2x1aW5kby1zZSBvIHNldSByZXN1bW8vYWJzdHJhY3QsIHBvciBtZWlvcyBlbGV0csO0bmljb3MsIG5vIHNpdGUgZGEgQmlibGlvdGVjYSBWaXJ0dWFsIEZHViwgYW8gcMO6YmxpY28gZW0gZ2VyYWwsIGVtIHJlZ2ltZSBkZSBhY2Vzc28gYWJlcnRvLgoKMy4gQSBwcmVzZW50ZSBsaWNlbsOnYSB0YW1iw6ltIGFicmFuZ2UsIG5vcyBtZXNtb3MgdGVybW9zIGVzdGFiZWxlY2lkb3Mgbm8gaXRlbSAyLCBzdXByYSwgcXVhbHF1ZXIgZGlyZWl0byBkZSBjb211bmljYcOnw6NvIGFvIHDDumJsaWNvIGNhYsOtdmVsIGVtIHJlbGHDp8OjbyDDoCBPYnJhIG9yYSBkZXBvc2l0YWRhLCBpbmNsdWluZG8tc2Ugb3MgdXNvcyByZWZlcmVudGVzIMOgIHJlcHJlc2VudGHDp8OjbyBww7pibGljYSBlL291IGV4ZWN1w6fDo28gcMO6YmxpY2EsIGJlbSBjb21vIHF1YWxxdWVyIG91dHJhIG1vZGFsaWRhZGUgZGUgY29tdW5pY2HDp8OjbyBhbyBww7pibGljbyBxdWUgZXhpc3RhIG91IHZlbmhhIGEgZXhpc3Rpciwgbm9zIHRlcm1vcyBkbyBhcnRpZ28gNjggZSBzZWd1aW50ZXMgZGEgTGVpIDkuNjEwLzk4LCBuYSBleHRlbnPDo28gcXVlIGZvciBhcGxpY8OhdmVsIGFvcyBzZXJ2acOnb3MgcHJlc3RhZG9zIGFvIHDDumJsaWNvIHBlbGEgQmlibGlvdGVjYSBWaXJ0dWFsIEZHVi4KCjQuIEVzdGEgbGljZW7Dp2EgYWJyYW5nZSwgYWluZGEsIG5vcyBtZXNtb3MgdGVybW9zIGVzdGFiZWxlY2lkb3Mgbm8gaXRlbSAyLCBzdXByYSwgdG9kb3Mgb3MgZGlyZWl0b3MgY29uZXhvcyBkZSBhcnRpc3RhcyBpbnTDqXJwcmV0ZXMgb3UgZXhlY3V0YW50ZXMsIHByb2R1dG9yZXMgZm9ub2dyw6FmaWNvcyBvdSBlbXByZXNhcyBkZSByYWRpb2RpZnVzw6NvIHF1ZSBldmVudHVhbG1lbnRlIHNlamFtIGFwbGljw6F2ZWlzIGVtIHJlbGHDp8OjbyDDoCBvYnJhIGRlcG9zaXRhZGEsIGVtIGNvbmZvcm1pZGFkZSBjb20gbyByZWdpbWUgZml4YWRvIG5vIFTDrXR1bG8gViBkYSBMZWkgOS42MTAvOTguCgo1LiBTZSBhIE9icmEgZGVwb3NpdGFkYSBmb2kgb3Ugw6kgb2JqZXRvIGRlIGZpbmFuY2lhbWVudG8gcG9yIGluc3RpdHVpw6fDtWVzIGRlIGZvbWVudG8gw6AgcGVzcXVpc2Egb3UgcXVhbHF1ZXIgb3V0cmEgc2VtZWxoYW50ZSwgdm9jw6ogb3UgbyB0aXR1bGFyIGFzc2VndXJhIHF1ZSBjdW1wcml1IHRvZGFzIGFzIG9icmlnYcOnw7VlcyBxdWUgbGhlIGZvcmFtIGltcG9zdGFzIHBlbGEgaW5zdGl0dWnDp8OjbyBmaW5hbmNpYWRvcmEgZW0gcmF6w6NvIGRvIGZpbmFuY2lhbWVudG8sIGUgcXVlIG7Do28gZXN0w6EgY29udHJhcmlhbmRvIHF1YWxxdWVyIGRpc3Bvc2nDp8OjbyBjb250cmF0dWFsIHJlZmVyZW50ZSDDoCBwdWJsaWNhw6fDo28gZG8gY29udGXDumRvIG9yYSBzdWJtZXRpZG8gw6AgQmlibGlvdGVjYSBWaXJ0dWFsIEZHVi4KCjYuIENhc28gYSBPYnJhIG9yYSBkZXBvc2l0YWRhIGVuY29udHJlLXNlIGxpY2VuY2lhZGEgc29iIHVtYSBsaWNlbsOnYSBDcmVhdGl2ZSBDb21tb25zIChxdWFscXVlciB2ZXJzw6NvKSwgc29iIGEgbGljZW7Dp2EgR05VIEZyZWUgRG9jdW1lbnRhdGlvbiBMaWNlbnNlIChxdWFscXVlciB2ZXJzw6NvKSwgb3Ugb3V0cmEgbGljZW7Dp2EgcXVhbGlmaWNhZGEgY29tbyBsaXZyZSBzZWd1bmRvIG9zIGNyaXTDqXJpb3MgZGEgRGVmaW5pdGlvbiBvZiBGcmVlIEN1bHR1cmFsIFdvcmtzIChkaXNwb27DrXZlbCBlbTogaHR0cDovL2ZyZWVkb21kZWZpbmVkLm9yZy9EZWZpbml0aW9uKSBvdSBGcmVlIFNvZnR3YXJlIERlZmluaXRpb24gKGRpc3BvbsOtdmVsIGVtOiBodHRwOi8vd3d3LmdudS5vcmcvcGhpbG9zb3BoeS9mcmVlLXN3Lmh0bWwpLCBvIGFycXVpdm8gcmVmZXJlbnRlIMOgIE9icmEgZGV2ZSBpbmRpY2FyIGEgbGljZW7Dp2EgYXBsaWPDoXZlbCBlbSBjb250ZcO6ZG8gbGVnw612ZWwgcG9yIHNlcmVzIGh1bWFub3MgZSwgc2UgcG9zc8OtdmVsLCB0YW1iw6ltIGVtIG1ldGFkYWRvcyBsZWfDrXZlaXMgcG9yIG3DoXF1aW5hLiBBIGluZGljYcOnw6NvIGRhIGxpY2Vuw6dhIGFwbGljw6F2ZWwgZGV2ZSBzZXIgYWNvbXBhbmhhZGEgZGUgdW0gbGluayBwYXJhIG9zIHRlcm1vcyBkZSBsaWNlbmNpYW1lbnRvIG91IHN1YSBjw7NwaWEgaW50ZWdyYWwuCgpBbyBjb25jbHVpciBhIHByZXNlbnRlIGV0YXBhIGUgYXMgZXRhcGFzIHN1YnNlccO8ZW50ZXMgZG8gcHJvY2Vzc28gZGUgc3VibWlzc8OjbyBkZSBhcnF1aXZvcyDDoCBCaWJsaW90ZWNhIFZpcnR1YWwgRkdWLCB2b2PDqiBhdGVzdGEgcXVlIGxldSBlIGNvbmNvcmRhIGludGVncmFsbWVudGUgY29tIG9zIHRlcm1vcyBhY2ltYSBkZWxpbWl0YWRvcywgYXNzaW5hbmRvLW9zIHNlbSBmYXplciBxdWFscXVlciByZXNlcnZhIGUgbm92YW1lbnRlIGNvbmZpcm1hbmRvIHF1ZSBjdW1wcmUgb3MgcmVxdWlzaXRvcyBpbmRpY2Fkb3Mgbm8gaXRlbSAxLCBzdXByYS4KCkhhdmVuZG8gcXVhbHF1ZXIgZGlzY29yZMOibmNpYSBlbSByZWxhw6fDo28gYW9zIHByZXNlbnRlcyB0ZXJtb3Mgb3UgbsOjbyBzZSB2ZXJpZmljYW5kbyBvIGV4aWdpZG8gbm8gaXRlbSAxLCBzdXByYSwgdm9jw6ogZGV2ZSBpbnRlcnJvbXBlciBpbWVkaWF0YW1lbnRlIG8gcHJvY2Vzc28gZGUgc3VibWlzc8Ojby4gQSBjb250aW51aWRhZGUgZG8gcHJvY2Vzc28gZXF1aXZhbGUgw6AgYXNzaW5hdHVyYSBkZXN0ZSBkb2N1bWVudG8sIGNvbSB0b2RhcyBhcyBjb25zZXHDvMOqbmNpYXMgbmVsZSBwcmV2aXN0YXMsIHN1amVpdGFuZG8tc2UgbyBzaWduYXTDoXJpbyBhIHNhbsOnw7VlcyBjaXZpcyBlIGNyaW1pbmFpcyBjYXNvIG7Do28gc2VqYSB0aXR1bGFyIGRvcyBkaXJlaXRvcyBhdXRvcmFpcyBwYXRyaW1vbmlhaXMgZS9vdSBjb25leG9zIGFwbGljw6F2ZWlzIMOgIE9icmEgZGVwb3NpdGFkYSBkdXJhbnRlIGVzdGUgcHJvY2Vzc28sIG91IGNhc28gbsOjbyB0ZW5oYSBvYnRpZG8gcHLDqXZpYSBlIGV4cHJlc3NhIGF1dG9yaXphw6fDo28gZG8gdGl0dWxhciBwYXJhIG8gZGVww7NzaXRvIGUgdG9kb3Mgb3MgdXNvcyBkYSBPYnJhIGVudm9sdmlkb3MuCgpQYXJhIGEgc29sdcOnw6NvIGRlIHF1YWxxdWVyIGTDunZpZGEgcXVhbnRvIGFvcyB0ZXJtb3MgZGUgbGljZW5jaWFtZW50byBlIG8gcHJvY2Vzc28gZGUgc3VibWlzc8OjbywgY2xpcXVlIG5vIGxpbmsgIkZhbGUgY29ub3NjbyIuCgpTZSB2b2PDqiB0aXZlciBkw7p2aWRhcyBzb2JyZSBlc3RhIGxpY2Vuw6dhLCBwb3IgZmF2b3IgZW50cmUgZW0gY29udGF0byBjb20gb3MgYWRtaW5pc3RyYWRvcmVzIGRvIFJlcG9zaXTDs3Jpby4K
dc.title.eng.fl_str_mv A Transformer model for Dengue time series forecast
title A Transformer model for Dengue time series forecast
spellingShingle A Transformer model for Dengue time series forecast
Guedes, Henrique Berenger
Time series forecasting
Transformer
Dengue
Deep Learning
Matemática
Dengue
Epidemiologia - Modelos matemáticos
Aprendizado profundo (Aprendizado do computador)
Doenças - Prevenção
Aprendizado do computador
title_short A Transformer model for Dengue time series forecast
title_full A Transformer model for Dengue time series forecast
title_fullStr A Transformer model for Dengue time series forecast
title_full_unstemmed A Transformer model for Dengue time series forecast
title_sort A Transformer model for Dengue time series forecast
author Guedes, Henrique Berenger
author_facet Guedes, Henrique Berenger
author_role author
dc.contributor.unidadefgv.por.fl_str_mv Escolas::EMAp
dc.contributor.member.none.fl_str_mv Carvalho, Luiz Max Fagundes de
Bianchi, Lucas Monteiro
dc.contributor.author.fl_str_mv Guedes, Henrique Berenger
dc.contributor.advisor1.fl_str_mv Coelho, Flávio Codeço
contributor_str_mv Coelho, Flávio Codeço
dc.subject.eng.fl_str_mv Time series forecasting
Transformer
Dengue
Deep Learning
topic Time series forecasting
Transformer
Dengue
Deep Learning
Matemática
Dengue
Epidemiologia - Modelos matemáticos
Aprendizado profundo (Aprendizado do computador)
Doenças - Prevenção
Aprendizado do computador
dc.subject.area.por.fl_str_mv Matemática
dc.subject.bibliodata.por.fl_str_mv Dengue
Epidemiologia - Modelos matemáticos
Aprendizado profundo (Aprendizado do computador)
Doenças - Prevenção
Aprendizado do computador
description Dengue fever is a viral mosquito-borne disease that affects many countries, especially in the Latin American and Asian continents. During the past five years, its incidence has risen sharply in Brazil, with many municipalities that were previously non endemic now reporting sustained transmission. Accurate forecasts are therefore critical for early warning systems and for guiding the allocation of health care resources. This study examines the capacity of the Transformer architecture, a deep learning model originally developed for sequence modeling, to capture the complex temporal dynamics of dengue transmission. Weekly dengue case and climate covariates were compiled for 92 municipalities in the state of Rio de Janeiro and used to train and validate the model. All data used in this study were obtained from the Mosqlimate platform.
publishDate 2025
dc.date.accessioned.fl_str_mv 2025-10-13T15:03:31Z
dc.date.available.fl_str_mv 2025-10-13T15:03:31Z
dc.date.issued.fl_str_mv 2025-09-08
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/10438/37785
url https://hdl.handle.net/10438/37785
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.source.none.fl_str_mv reponame:Repositório Institucional do FGV (FGV Repositório Digital)
instname:Fundação Getulio Vargas (FGV)
instacron:FGV
instname_str Fundação Getulio Vargas (FGV)
instacron_str FGV
institution FGV
reponame_str Repositório Institucional do FGV (FGV Repositório Digital)
collection Repositório Institucional do FGV (FGV Repositório Digital)
bitstream.url.fl_str_mv https://repositorio.fgv.br/bitstreams/85690ee7-ea3d-41e4-b123-507a3879591e/download
https://repositorio.fgv.br/bitstreams/3419cf56-56ab-4b24-afe1-fd759466e491/download
https://repositorio.fgv.br/bitstreams/c824a46f-eb1f-4ab9-aa74-0f83bbd04648/download
https://repositorio.fgv.br/bitstreams/36212b8e-43b2-4a1d-a186-3a76eb48eb5e/download
bitstream.checksum.fl_str_mv a4753fba2d2c413ddd987dad3e93fdd9
2a4b67231f701c416a809246e7a10077
0cb519d6ddbb8524f21689f6d6b07bdb
16f3ee414dfa6bddf67195c302d64170
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional do FGV (FGV Repositório Digital) - Fundação Getulio Vargas (FGV)
repository.mail.fl_str_mv biblioteca.digital@fgv.br
_version_ 1866368972124848128

Registros relacionados