Use este identificador para citar ou linkar para este item: http://www.repositorio.ufc.br/handle/riufc/31645
Título: A dynamic linear model for the estimation of time-varying origin–destination matrices from link counts
Autor(es): Pitombeira Neto, Anselmo Ramalho
Loureiro, Carlos Felipe Grangeiro
Palavras-chave: Transportes
Modelos lineares (Estatística)
Matrizes
Dynamic linear models
Matrices
Data do documento: 2016
Editor: JOURNAL OF ADVANCED TRANSPORTATION
Citação: PITOMBEIRA NETO, A. R.; LOUREIRO, C. F. G. A dynamic linear model for the estimation of time-varying origin–destination matrices from link counts. J. Adv. Transp., v. 50, p. 2116-2129, 2016.
Abstract: We propose a dynamic linear model (DLM) for the estimation of day-to-day time-varying origin– destination (OD) matrices from link counts. Mean OD flows are assumed to vary over time as a locally constant model. We take into account variability in OD flows, route flows, and link volumes. Given a time series of observed link volumes, sequential Bayesian inference is applied in order to estimate mean OD flows. The conditions under which mean OD flows may be estimated are established, and computational studies on two benchmark transportation networks from the literature are carried out. In both cases, the DLM converged to the unobserved mean OD flows when given sufficient observations of traffic link volumes despite assuming uninformative prior OD matrices. We discuss limitations and extensions of the proposed DLM. Copyright © 2017 John Wiley & Sons, Ltd.
URI: http://www.repositorio.ufc.br/handle/riufc/31645
ISSN: 0197-6729
Aparece nas coleções:DET - Artigos publicados em revista científica

Arquivos associados a este item:
Arquivo Descrição TamanhoFormato 
2016_art_cfgloureiro_dynamic.pdf719,3 kBAdobe PDFVisualizar/Abrir


Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.