Probabilistic travel time progression and its application to automatic vehicle identification data. (November 2015)

• Record Type: Journal Article
• Authors: Nantes, Alfredo; Ngoduy, Dong; Miska, Marc; Chung, Edward
• Is Part Of: Transportation research. Volume 81 Part 1 (2015)
• Page Start: 131
• Page End: 145
• Publication Date: 2015-11
• Subjects: Off-line travel time estimation -- Long corridor -- Automatic Vehicle Identification (AVI) -- Data impoverishment problem -- Probabilistic travel time progression; Transportation -- Research -- Periodicals; Transportation -- Mathematical models -- Periodicals
• DOI: 10.1016/j.trb.2015.09.001
• Languages: English
• ISSNs: 0191-2615

Abstract

Highlights: To extend the conventional deterministic travel time progression method to capture the random variables. To propose a polynomial-time implementation of our framework suitable for AVI data. To show how to effectively discern between normal and anomalous travel times within the AVI data. To provide a comprehensive analysis of accuracy and robustness of our method for the Brisbane case study. Abstract: Travel time has been identified as an important variable to evaluate the performance of a transportation system. Based on the travel time prediction, road users can make their optimal decision in choosing route and departure time. In order to utilise adequately the advanced data collection methods that provide real-time different types of information, this paper is aimed at a novel approach to the estimation of long roadway travel times, using Automatic Vehicle Identification (AVI) technology. Since the long roads contain a large number of scanners, the AVI sample size tends to reduce and, as such, computing the distribution for the total road travel time becomes difficult. In this work, we introduce a probabilistic framework that extends the deterministic travel time progression method to dependent random variables and enables the off-line estimation of road travel time distributions. In the proposed method, the accuracy of the estimation does not depend on the size of the sample over the entire corridor, but only on the amount of historical data that is available for each link. In practice, the system is also robust to small link samples and can be used to detect outliers within the AVI data.