Estimation of link speed distribution from probe vehicle data

Li, ZG; Cai, C; Menon, AK; Xu, Y; Chen, F

Estimation of link speed distribution from probe vehicle data

Li, ZG Cai, C Menon, AK Xu, Y Chen, F

Permalink

Publisher:: SAGE PUBLICATIONS INC
Publication Type:: Journal Article
Citation:: Transportation Research Record, 2016, 2595, (2595), pp. 98-107
Issue Date:: 2016-01-01

Closed Access

	Filename	Description	Size
	2595-11.pdf	Published version	5.84 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Li, ZG
dc.contributor.author	Cai, C
dc.contributor.author	Menon, AK
dc.contributor.author	Xu, Y
dc.contributor.author	Chen, F https://orcid.org/0000-0003-4971-8729
dc.date.accessioned	2022-08-01T20:32:01Z
dc.date.available	2022-08-01T20:32:01Z
dc.date.issued	2016-01-01
dc.identifier.citation	Transportation Research Record, 2016, 2595, (2595), pp. 98-107
dc.identifier.issn	0361-1981
dc.identifier.issn	2169-4052
dc.identifier.uri	http://hdl.handle.net/10453/159461
dc.description.abstract	Probes with GPS devices reveal useful information for traffc conditions, but the high level of noise and the sparsity of observations make it challenging to estimate speed distribution from the data collected. This paper proposes a Bayesian approach for estimating link speed distribution from GPS-equipped probe data. The key contribution of the study is a generic hierarchical Monte Carlo Markov chain algorithm for sampling from probe speed distribution, with Gaussian mixture models for probe speed clustering. The algorithm combines Gibbs sampling and Metropolis-Hastings sampling to improve convergence speed. A rigorous mathematical discussion is provided for the simulation approach. The algorithm is evaluated with synthetic data and real-world probe data and shows the feasibility of the approach. Results also confrm the computational advantages of the proposed algorithm and suggest its potential for real-time extension.
dc.language	English
dc.publisher	SAGE PUBLICATIONS INC
dc.relation.ispartof	Transportation Research Record
dc.relation.isbasedon	10.3141/2595-11
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0905 Civil Engineering, 1205 Urban and Regional Planning, 1507 Transportation and Freight Services
dc.subject.classification	Logistics & Transportation
dc.title	Estimation of link speed distribution from probe vehicle data
dc.type	Journal Article
utslib.citation.volume	2595
utslib.for	0905 Civil Engineering
utslib.for	1205 Urban and Regional Planning
utslib.for	1507 Transportation and Freight Services
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
dc.date.updated	2022-08-01T20:31:57Z
pubs.issue	2595
pubs.publication-status	Published
pubs.volume	2595
utslib.citation.issue	2595

Abstract:

Probes with GPS devices reveal useful information for traffc conditions, but the high level of noise and the sparsity of observations make it challenging to estimate speed distribution from the data collected. This paper proposes a Bayesian approach for estimating link speed distribution from GPS-equipped probe data. The key contribution of the study is a generic hierarchical Monte Carlo Markov chain algorithm for sampling from probe speed distribution, with Gaussian mixture models for probe speed clustering. The algorithm combines Gibbs sampling and Metropolis-Hastings sampling to improve convergence speed. A rigorous mathematical discussion is provided for the simulation approach. The algorithm is evaluated with synthetic data and real-world probe data and shows the feasibility of the approach. Results also confrm the computational advantages of the proposed algorithm and suggest its potential for real-time extension.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/159461