Estimating link travel time correlation

An application of Bayesian smoothing splines

Byron J. Gajewski, Laurence R Rilett

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

The estimation and forecasting of travel times has become an increasingly important topic as Advanced Traveler Information Systems (ATIS) have moved from conceptualization to deployment. This paper focuses on an important, but often neglected, component of ATIS - the estimation of link travel time correlation. Natural cubic splines are used to model the mean link travel time. Subsequently, a Bayesian-based methodology is developed for estimating the posterior distribution of the correlation of travel times between links along a corridor. The approach is illustrated on a corridor in Houston, Texas, that is instrumented with an Automatic Vehicle Identification system.

Original languageEnglish (US)
Pages (from-to)53-70
Number of pages18
JournalJournal of Transportation and Statistics
Volume7
Issue number2-3
StatePublished - Jan 1 2005

Fingerprint

Smoothing Splines
Travel Time
Travel time
Splines
Advanced traveler information systems
travel
Information Systems
information system
Automatic vehicle identification
Cubic Spline
System Identification
Posterior distribution
Forecasting
time
Methodology
methodology

Keywords

  • Automatic vehicle identification
  • Gibbs Sampler
  • Intelligent transportation systems
  • Markov Chain Monte Carlo

ASJC Scopus subject areas

  • Statistics and Probability
  • Transportation

Cite this

Estimating link travel time correlation : An application of Bayesian smoothing splines. / Gajewski, Byron J.; Rilett, Laurence R.

In: Journal of Transportation and Statistics, Vol. 7, No. 2-3, 01.01.2005, p. 53-70.

Research output: Contribution to journalArticle

@article{37f3ac2ac78640e4b8f601f14685ffd2,
title = "Estimating link travel time correlation: An application of Bayesian smoothing splines",
abstract = "The estimation and forecasting of travel times has become an increasingly important topic as Advanced Traveler Information Systems (ATIS) have moved from conceptualization to deployment. This paper focuses on an important, but often neglected, component of ATIS - the estimation of link travel time correlation. Natural cubic splines are used to model the mean link travel time. Subsequently, a Bayesian-based methodology is developed for estimating the posterior distribution of the correlation of travel times between links along a corridor. The approach is illustrated on a corridor in Houston, Texas, that is instrumented with an Automatic Vehicle Identification system.",
keywords = "Automatic vehicle identification, Gibbs Sampler, Intelligent transportation systems, Markov Chain Monte Carlo",
author = "Gajewski, {Byron J.} and Rilett, {Laurence R}",
year = "2005",
month = "1",
day = "1",
language = "English (US)",
volume = "7",
pages = "53--70",
journal = "Journal of Transportation and Statistics",
issn = "1094-8848",
publisher = "Bureau of Transportation Statistics",
number = "2-3",

}

TY - JOUR

T1 - Estimating link travel time correlation

T2 - An application of Bayesian smoothing splines

AU - Gajewski, Byron J.

AU - Rilett, Laurence R

PY - 2005/1/1

Y1 - 2005/1/1

N2 - The estimation and forecasting of travel times has become an increasingly important topic as Advanced Traveler Information Systems (ATIS) have moved from conceptualization to deployment. This paper focuses on an important, but often neglected, component of ATIS - the estimation of link travel time correlation. Natural cubic splines are used to model the mean link travel time. Subsequently, a Bayesian-based methodology is developed for estimating the posterior distribution of the correlation of travel times between links along a corridor. The approach is illustrated on a corridor in Houston, Texas, that is instrumented with an Automatic Vehicle Identification system.

AB - The estimation and forecasting of travel times has become an increasingly important topic as Advanced Traveler Information Systems (ATIS) have moved from conceptualization to deployment. This paper focuses on an important, but often neglected, component of ATIS - the estimation of link travel time correlation. Natural cubic splines are used to model the mean link travel time. Subsequently, a Bayesian-based methodology is developed for estimating the posterior distribution of the correlation of travel times between links along a corridor. The approach is illustrated on a corridor in Houston, Texas, that is instrumented with an Automatic Vehicle Identification system.

KW - Automatic vehicle identification

KW - Gibbs Sampler

KW - Intelligent transportation systems

KW - Markov Chain Monte Carlo

UR - http://www.scopus.com/inward/record.url?scp=19644363207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=19644363207&partnerID=8YFLogxK

M3 - Article

VL - 7

SP - 53

EP - 70

JO - Journal of Transportation and Statistics

JF - Journal of Transportation and Statistics

SN - 1094-8848

IS - 2-3

ER -