Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | |
Tipo de documento: | Tese |
Idioma: | por |
Título da fonte: | Biblioteca Digital de Teses e Dissertações da UERJ |
Texto Completo: | http://www.bdtd.uerj.br/handle/1/18970 |
Resumo: | The predictions of deaths from COVID-19 are useful for the formulation of public policies, allowing the use of more effective social isolation strategies with less economic and social impact, in addition to promoting indicators of how the population adheres to vaccines. The objective of this work is to explore a broad set of prediction methods to identify the best models without vaccination coverage (Case 1) and with vaccination coverage (Case 2) in Brazil. The methods of Artificial Intelligence and the classical methods of econometrics were considered. The cross-validation technique for time series was implemented, thus providing an accurate estimate to assess the predictive capacity of the models. Each model was adjusted considering an initial training base of 30 values. In Case 1, daily and cumulative deaths from the Oxford COVID-19 Government Response Tracker database were used. In Case 2, the dataset comes from Our World in Data, where the seven-day moving average was adopted as a reference to improve data quality. In Case 1 the models were trained and tested with 266 samples considering a forecast horizon of 7 days. In Case 2 the models were trained and tested 494 times considering a forecast horizon of seven days, 486 times considering a horizon of 15 days, and 471 times assuming a horizon of 30 days. Models of different classes were adopted: ETS algorithms, ARIMA, regression, and machine learning. The forecasts were compared using the average results of the forecast metrics: R2, RMSE, MAE, and MAPE. In Case 1, the accumulated forecasts offered better results than the daily ones, as the models are less influenced by the components of the time series: cycle and seasonality. The best results for the prediction of daily deaths were obtained by the Ridge regression method (R2 = 0.772, RMSE = 136, and MAE = 113). The best results for predicting cumulative deaths were obtained by the Cubist regression method (R2 = 0.993, RMSE = 468, and MAE = 409). In Case 2, the ARIMA model with one differentiation showed the best results for a seven-day horizon (RMSE = 74 and MAE = 64). |
id |
UERJ_a724ee40e24b95bfb79bfbaf140d8045 |
---|---|
oai_identifier_str |
oai:www.bdtd.uerj.br:1/18970 |
network_acronym_str |
UERJ |
network_name_str |
Biblioteca Digital de Teses e Dissertações da UERJ |
repository_id_str |
2903 |
spelling |
Luna, Aderval Severinohttp://lattes.cnpq.br/0294676847895948Xavier, Vinicius Layterhttp://lattes.cnpq.br/9683190447704675Costa, André Luiz Hemerlyhttp://lattes.cnpq.br/8951119580894280Tôrres, Alexandre Rodrigueshttp://lattes.cnpq.br/1294795998541584Campos, Eduardo Limahttp://lattes.cnpq.br/6118194123564577Amaral, Marcelo Rubens dos Santos dohttp://lattes.cnpq.br/4387513899931248http://lattes.cnpq.br/9034649150495481Provenza, Marcello Montillomprovenza@gmail.com2023-01-27T12:31:56Z2022-09-23PROVENZA, Marcello Montillo. Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia. 2022. 52 f. Tese (Doutorado em Engenharia Química) - Instituto de Química, Universidade do Estado do Rio de Janeiro, Rio de Janeiro, 2022.http://www.bdtd.uerj.br/handle/1/18970The predictions of deaths from COVID-19 are useful for the formulation of public policies, allowing the use of more effective social isolation strategies with less economic and social impact, in addition to promoting indicators of how the population adheres to vaccines. The objective of this work is to explore a broad set of prediction methods to identify the best models without vaccination coverage (Case 1) and with vaccination coverage (Case 2) in Brazil. The methods of Artificial Intelligence and the classical methods of econometrics were considered. The cross-validation technique for time series was implemented, thus providing an accurate estimate to assess the predictive capacity of the models. Each model was adjusted considering an initial training base of 30 values. In Case 1, daily and cumulative deaths from the Oxford COVID-19 Government Response Tracker database were used. In Case 2, the dataset comes from Our World in Data, where the seven-day moving average was adopted as a reference to improve data quality. In Case 1 the models were trained and tested with 266 samples considering a forecast horizon of 7 days. In Case 2 the models were trained and tested 494 times considering a forecast horizon of seven days, 486 times considering a horizon of 15 days, and 471 times assuming a horizon of 30 days. Models of different classes were adopted: ETS algorithms, ARIMA, regression, and machine learning. The forecasts were compared using the average results of the forecast metrics: R2, RMSE, MAE, and MAPE. In Case 1, the accumulated forecasts offered better results than the daily ones, as the models are less influenced by the components of the time series: cycle and seasonality. The best results for the prediction of daily deaths were obtained by the Ridge regression method (R2 = 0.772, RMSE = 136, and MAE = 113). The best results for predicting cumulative deaths were obtained by the Cubist regression method (R2 = 0.993, RMSE = 468, and MAE = 409). In Case 2, the ARIMA model with one differentiation showed the best results for a seven-day horizon (RMSE = 74 and MAE = 64).As previsões de óbitos por COVID-19 são úteis para a formulação de políticas públicas, permitindo a utilização de estratégias de isolamento social mais eficazes e com menor impacto econômico e social, além de promover indicadores de como a população adere às vacinas. O objetivo deste trabalho é explorar um amplo conjunto de métodos de previsão para identificar os melhores modelos sem cobertura vacinal (Caso 1) e com cobertura vacinal (Caso 2) no Brasil. Foram considerados os métodos de Inteligência Artificial e os métodos clássicos de econometria. A técnica de validação cruzada para séries temporais foi implementada, fornecendo assim uma estimativa precisa para avaliar a capacidade preditiva dos modelos. Cada modelo foi ajustado considerando uma base inicial de treinamento de 30 valores. No Caso 1, foram usadas as mortes diárias e acumuladas da base Oxford COVID-19 Government Response Tracker. No Caso 2, o conjunto de dados provém do Our World in Data, onde a média móvel de sete dias foi adotada como referência para melhorar a qualidade dos dados. No Caso 1 os modelos foram treinados e testados com 266 amostras considerando um horizonte de previsão de 7 dias. No Caso 2 os modelos foram treinados e testados 494 vezes considerando um horizonte de revisão de sete dias, 486 vezes considerando um horizonte de 15 dias e 471 vezes considerando um horizonte de 30 dias. Foram adotados modelos de diferentes classes: algoritmos ETS, ARIMA, regressão e aprendizado de máquina. A comparação entre as previsões foi feita utilizando os resultados médios das métricas de previsão: R2, RMSE, MAE e MAPE. No Caso 1, as previsões acumuladas ofereceram melhores resultados do que as diárias, pois os modelos são menos influenciados pelas componentes da série temporal: ciclo e sazonalidade. Os melhores resultados para a predição de óbitos diários foram obtidos pelo método de regressão de Ridge (R2 = 0,772, RMSE = 136 e MAE = 113). Os melhores resultados para predição de óbitos acumulados foram obtidos pelo método de regressão Cubist (R2 = 0,993, RMSE = 468 e MAE = 409). No Caso 2, o modelo ARIMA com uma diferenciação apresentou os melhores resultados para um horizonte de sete dias (RMSE = 74 e MAE = 64).Submitted by Ana Rachel CTC/Q (ana.teles@uerj.br) on 2023-01-27T12:31:56Z No. of bitstreams: 1 Tese - Marcello Montillo Provenza - 2022 - Completa.pdf: 1276605 bytes, checksum: 377db2774e0e3b6aacda62d26069fa22 (MD5)Made available in DSpace on 2023-01-27T12:31:56Z (GMT). No. of bitstreams: 1 Tese - Marcello Montillo Provenza - 2022 - Completa.pdf: 1276605 bytes, checksum: 377db2774e0e3b6aacda62d26069fa22 (MD5) Previous issue date: 2022-09-23application/pdfporUniversidade do Estado do Rio de JaneiroPrograma de Pós-Graduação em Engenharia QuímicaUERJBrasilCentro de Tecnologia e Ciências::Instituto de QuímicaTime seriesDeathsStatistical modelsMachine learningEngenharia químicaProcessamento de dadosCOVID-19 (Doença)Séries temporaisÓbitosModelos estatísticosAprendizado de máquinaEconometriaCOVID-19COVID 19ENGENHARIAS::ENGENHARIA QUIMICAPrevisão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemiaTime series forecast for deaths in Brazil caused by COVID-19 in the context of the pandemicinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisinfo:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da UERJinstname:Universidade do Estado do Rio de Janeiro (UERJ)instacron:UERJORIGINALTese - Marcello Montillo Provenza - 2022 - Completa.pdfTese - Marcello Montillo Provenza - 2022 - Completa.pdfapplication/pdf1276605http://www.bdtd.uerj.br/bitstream/1/18970/2/Tese+-+Marcello+Montillo+Provenza+-+2022+-+Completa.pdf377db2774e0e3b6aacda62d26069fa22MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82123http://www.bdtd.uerj.br/bitstream/1/18970/1/license.txte5502652da718045d7fcd832b79fca29MD511/189702024-02-27 15:35:57.026oai:www.bdtd.uerj.br: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Biblioteca Digital de Teses e Dissertaçõeshttp://www.bdtd.uerj.br/PUBhttps://www.bdtd.uerj.br:8443/oai/requestbdtd.suporte@uerj.bropendoar:29032024-02-27T18:35:57Biblioteca Digital de Teses e Dissertações da UERJ - Universidade do Estado do Rio de Janeiro (UERJ)false |
dc.title.por.fl_str_mv |
Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia |
dc.title.alternative.eng.fl_str_mv |
Time series forecast for deaths in Brazil caused by COVID-19 in the context of the pandemic |
title |
Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia |
spellingShingle |
Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia Provenza, Marcello Montillo Time series Deaths Statistical models Machine learning Engenharia química Processamento de dados COVID-19 (Doença) Séries temporais Óbitos Modelos estatísticos Aprendizado de máquina Econometria COVID-19 COVID 19 ENGENHARIAS::ENGENHARIA QUIMICA |
title_short |
Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia |
title_full |
Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia |
title_fullStr |
Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia |
title_full_unstemmed |
Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia |
title_sort |
Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia |
author |
Provenza, Marcello Montillo |
author_facet |
Provenza, Marcello Montillo mprovenza@gmail.com |
author_role |
author |
author2 |
mprovenza@gmail.com |
author2_role |
author |
dc.contributor.advisor1.fl_str_mv |
Luna, Aderval Severino |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/0294676847895948 |
dc.contributor.advisor2.fl_str_mv |
Xavier, Vinicius Layter |
dc.contributor.advisor2Lattes.fl_str_mv |
http://lattes.cnpq.br/9683190447704675 |
dc.contributor.referee1.fl_str_mv |
Costa, André Luiz Hemerly |
dc.contributor.referee1Lattes.fl_str_mv |
http://lattes.cnpq.br/8951119580894280 |
dc.contributor.referee2.fl_str_mv |
Tôrres, Alexandre Rodrigues |
dc.contributor.referee2Lattes.fl_str_mv |
http://lattes.cnpq.br/1294795998541584 |
dc.contributor.referee3.fl_str_mv |
Campos, Eduardo Lima |
dc.contributor.referee3Lattes.fl_str_mv |
http://lattes.cnpq.br/6118194123564577 |
dc.contributor.referee4.fl_str_mv |
Amaral, Marcelo Rubens dos Santos do |
dc.contributor.referee4Lattes.fl_str_mv |
http://lattes.cnpq.br/4387513899931248 |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/9034649150495481 |
dc.contributor.author.fl_str_mv |
Provenza, Marcello Montillo mprovenza@gmail.com |
contributor_str_mv |
Luna, Aderval Severino Xavier, Vinicius Layter Costa, André Luiz Hemerly Tôrres, Alexandre Rodrigues Campos, Eduardo Lima Amaral, Marcelo Rubens dos Santos do |
dc.subject.eng.fl_str_mv |
Time series Deaths Statistical models Machine learning |
topic |
Time series Deaths Statistical models Machine learning Engenharia química Processamento de dados COVID-19 (Doença) Séries temporais Óbitos Modelos estatísticos Aprendizado de máquina Econometria COVID-19 COVID 19 ENGENHARIAS::ENGENHARIA QUIMICA |
dc.subject.por.fl_str_mv |
Engenharia química Processamento de dados COVID-19 (Doença) Séries temporais Óbitos Modelos estatísticos Aprendizado de máquina Econometria COVID-19 COVID 19 |
dc.subject.cnpq.fl_str_mv |
ENGENHARIAS::ENGENHARIA QUIMICA |
description |
The predictions of deaths from COVID-19 are useful for the formulation of public policies, allowing the use of more effective social isolation strategies with less economic and social impact, in addition to promoting indicators of how the population adheres to vaccines. The objective of this work is to explore a broad set of prediction methods to identify the best models without vaccination coverage (Case 1) and with vaccination coverage (Case 2) in Brazil. The methods of Artificial Intelligence and the classical methods of econometrics were considered. The cross-validation technique for time series was implemented, thus providing an accurate estimate to assess the predictive capacity of the models. Each model was adjusted considering an initial training base of 30 values. In Case 1, daily and cumulative deaths from the Oxford COVID-19 Government Response Tracker database were used. In Case 2, the dataset comes from Our World in Data, where the seven-day moving average was adopted as a reference to improve data quality. In Case 1 the models were trained and tested with 266 samples considering a forecast horizon of 7 days. In Case 2 the models were trained and tested 494 times considering a forecast horizon of seven days, 486 times considering a horizon of 15 days, and 471 times assuming a horizon of 30 days. Models of different classes were adopted: ETS algorithms, ARIMA, regression, and machine learning. The forecasts were compared using the average results of the forecast metrics: R2, RMSE, MAE, and MAPE. In Case 1, the accumulated forecasts offered better results than the daily ones, as the models are less influenced by the components of the time series: cycle and seasonality. The best results for the prediction of daily deaths were obtained by the Ridge regression method (R2 = 0.772, RMSE = 136, and MAE = 113). The best results for predicting cumulative deaths were obtained by the Cubist regression method (R2 = 0.993, RMSE = 468, and MAE = 409). In Case 2, the ARIMA model with one differentiation showed the best results for a seven-day horizon (RMSE = 74 and MAE = 64). |
publishDate |
2022 |
dc.date.issued.fl_str_mv |
2022-09-23 |
dc.date.accessioned.fl_str_mv |
2023-01-27T12:31:56Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
PROVENZA, Marcello Montillo. Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia. 2022. 52 f. Tese (Doutorado em Engenharia Química) - Instituto de Química, Universidade do Estado do Rio de Janeiro, Rio de Janeiro, 2022. |
dc.identifier.uri.fl_str_mv |
http://www.bdtd.uerj.br/handle/1/18970 |
identifier_str_mv |
PROVENZA, Marcello Montillo. Previsão de séries temporais para os óbitos no Brasil causados pela COVID-19 no âmbito da pandemia. 2022. 52 f. Tese (Doutorado em Engenharia Química) - Instituto de Química, Universidade do Estado do Rio de Janeiro, Rio de Janeiro, 2022. |
url |
http://www.bdtd.uerj.br/handle/1/18970 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade do Estado do Rio de Janeiro |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Engenharia Química |
dc.publisher.initials.fl_str_mv |
UERJ |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Centro de Tecnologia e Ciências::Instituto de Química |
publisher.none.fl_str_mv |
Universidade do Estado do Rio de Janeiro |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da UERJ instname:Universidade do Estado do Rio de Janeiro (UERJ) instacron:UERJ |
instname_str |
Universidade do Estado do Rio de Janeiro (UERJ) |
instacron_str |
UERJ |
institution |
UERJ |
reponame_str |
Biblioteca Digital de Teses e Dissertações da UERJ |
collection |
Biblioteca Digital de Teses e Dissertações da UERJ |
bitstream.url.fl_str_mv |
http://www.bdtd.uerj.br/bitstream/1/18970/2/Tese+-+Marcello+Montillo+Provenza+-+2022+-+Completa.pdf http://www.bdtd.uerj.br/bitstream/1/18970/1/license.txt |
bitstream.checksum.fl_str_mv |
377db2774e0e3b6aacda62d26069fa22 e5502652da718045d7fcd832b79fca29 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da UERJ - Universidade do Estado do Rio de Janeiro (UERJ) |
repository.mail.fl_str_mv |
bdtd.suporte@uerj.br |
_version_ |
1792352372474773504 |