Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Tese |
Idioma: | eng |
Título da fonte: | Biblioteca Digital de Teses e Dissertações da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/258394 |
Resumo: | Robust artificial intelligence models have been criticized for their lack of uncertainty control and inability to explain feature importance, which has limited their adoption. However, probabilistic machine learning and explainable artificial intelligence have shown great scientific and technical advances, and have slowly permeated other areas, such as Traffic Engineering. This thesis fulfils a literature gap related to probabilistic traffic breakdown forecasting. We propose a traffic breakdown probability calculation methodology based on probabilistic speed predictions. Since the probabilistic characteristic is absent in traditional formulations of neural networks, we suggest using Variational LSTMs to make the speed forecasts. This Recurrent Neural Network uses Dropout to produce a Bayesian approximation and generate probabilistic outputs. This thesis also investigates the effects of inclement weather on traffic breakdown probability and methods for identifying traffic breakdowns. The proposed methodology produces great control over the probability of congestion, which could not be achieved using deterministic models, resulting in important theoretical and practical contributions. |
id |
URGS_d9dd4cff7939802fef3dde43255107e7 |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/258394 |
network_acronym_str |
URGS |
network_name_str |
Biblioteca Digital de Teses e Dissertações da UFRGS |
repository_id_str |
1853 |
spelling |
Zechin, DouglasCybis, Helena Beatriz Bettella2023-05-23T03:27:46Z2023http://hdl.handle.net/10183/258394001167921Robust artificial intelligence models have been criticized for their lack of uncertainty control and inability to explain feature importance, which has limited their adoption. However, probabilistic machine learning and explainable artificial intelligence have shown great scientific and technical advances, and have slowly permeated other areas, such as Traffic Engineering. This thesis fulfils a literature gap related to probabilistic traffic breakdown forecasting. We propose a traffic breakdown probability calculation methodology based on probabilistic speed predictions. Since the probabilistic characteristic is absent in traditional formulations of neural networks, we suggest using Variational LSTMs to make the speed forecasts. This Recurrent Neural Network uses Dropout to produce a Bayesian approximation and generate probabilistic outputs. This thesis also investigates the effects of inclement weather on traffic breakdown probability and methods for identifying traffic breakdowns. The proposed methodology produces great control over the probability of congestion, which could not be achieved using deterministic models, resulting in important theoretical and practical contributions.application/pdfengControle de tráfegoModelos de previsãoRedes neuraisRodoviasTraffic breakdownTraffic forecastingNeural networksInclement weatherBayesian statisticsProbabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisUniversidade Federal do Rio Grande do SulEscola de EngenhariaPrograma de Pós-Graduação em Engenharia de Produção e TransportesPorto Alegre, BR-RS2023doutoradoinfo:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001167921.pdf.txt001167921.pdf.txtExtracted Texttext/plain195676http://www.lume.ufrgs.br/bitstream/10183/258394/2/001167921.pdf.txt30dd81c9ce96f60b027e805341df6381MD52ORIGINAL001167921.pdfTexto completo (inglês)application/pdf5270991http://www.lume.ufrgs.br/bitstream/10183/258394/1/001167921.pdfd36ba1ef319ed0697cf5410c990c7af7MD5110183/2583942023-05-28 03:33:35.541993oai:www.lume.ufrgs.br:10183/258394Biblioteca Digital de Teses e Dissertaçõeshttps://lume.ufrgs.br/handle/10183/2PUBhttps://lume.ufrgs.br/oai/requestlume@ufrgs.br||lume@ufrgs.bropendoar:18532023-05-28T06:33:35Biblioteca Digital de Teses e Dissertações da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs |
title |
Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs |
spellingShingle |
Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs Zechin, Douglas Controle de tráfego Modelos de previsão Redes neurais Rodovias Traffic breakdown Traffic forecasting Neural networks Inclement weather Bayesian statistics |
title_short |
Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs |
title_full |
Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs |
title_fullStr |
Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs |
title_full_unstemmed |
Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs |
title_sort |
Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs |
author |
Zechin, Douglas |
author_facet |
Zechin, Douglas |
author_role |
author |
dc.contributor.author.fl_str_mv |
Zechin, Douglas |
dc.contributor.advisor1.fl_str_mv |
Cybis, Helena Beatriz Bettella |
contributor_str_mv |
Cybis, Helena Beatriz Bettella |
dc.subject.por.fl_str_mv |
Controle de tráfego Modelos de previsão Redes neurais Rodovias |
topic |
Controle de tráfego Modelos de previsão Redes neurais Rodovias Traffic breakdown Traffic forecasting Neural networks Inclement weather Bayesian statistics |
dc.subject.eng.fl_str_mv |
Traffic breakdown Traffic forecasting Neural networks Inclement weather Bayesian statistics |
description |
Robust artificial intelligence models have been criticized for their lack of uncertainty control and inability to explain feature importance, which has limited their adoption. However, probabilistic machine learning and explainable artificial intelligence have shown great scientific and technical advances, and have slowly permeated other areas, such as Traffic Engineering. This thesis fulfils a literature gap related to probabilistic traffic breakdown forecasting. We propose a traffic breakdown probability calculation methodology based on probabilistic speed predictions. Since the probabilistic characteristic is absent in traditional formulations of neural networks, we suggest using Variational LSTMs to make the speed forecasts. This Recurrent Neural Network uses Dropout to produce a Bayesian approximation and generate probabilistic outputs. This thesis also investigates the effects of inclement weather on traffic breakdown probability and methods for identifying traffic breakdowns. The proposed methodology produces great control over the probability of congestion, which could not be achieved using deterministic models, resulting in important theoretical and practical contributions. |
publishDate |
2023 |
dc.date.accessioned.fl_str_mv |
2023-05-23T03:27:46Z |
dc.date.issued.fl_str_mv |
2023 |
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.uri.fl_str_mv |
http://hdl.handle.net/10183/258394 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001167921 |
url |
http://hdl.handle.net/10183/258394 |
identifier_str_mv |
001167921 |
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.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Biblioteca Digital de Teses e Dissertações da UFRGS |
collection |
Biblioteca Digital de Teses e Dissertações da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/258394/2/001167921.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/258394/1/001167921.pdf |
bitstream.checksum.fl_str_mv |
30dd81c9ce96f60b027e805341df6381 d36ba1ef319ed0697cf5410c990c7af7 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
lume@ufrgs.br||lume@ufrgs.br |
_version_ |
1810085617928765440 |