Traffic congestion caused by either insufficient road capacity or unexpected events has been a major problem in urban transportation networks. To disseminate accurate traveler information and reduce congestion impact, it is desirable to develop an adaptive model to predict travel time. The proposed model is practically implementable to capture dynamic traffic patterns under various conditions, which integrates the features of exponential smoothing and the Kalman filter by utilizing both real-time and historic data. The model is simple in formulation while robust in performance in terms of accuracy and stability. With a constraint or nonconstraint smoothing factor, the proposed model is tested with both real world and simulated data and demonstrated itself a sound model that outperforms others (e.g., Kalman filter and simple exponential smoothing) specifically under recurring and nonrecurring congestion.
|Number of pages
|Journal of Advanced Transportation
|Published - Oct 1 2014
Bibliographical notePublisher Copyright:
Copyright © 2012 John Wiley & Sons, Ltd.
- Kalman filter
- simple exponential smoothing
- travel time
ASJC Scopus subject areas
- Automotive Engineering
- Economics and Econometrics
- Mechanical Engineering
- Computer Science Applications
- Strategy and Management