01031391

Component

https://doi.org/10.3141/1968-12

http://scholar.google.com...mons&publication_year=2006

A hybrid model for predicting urban arterial travel time on the basis of so-called state-space neural networks (SSNNs) and the extended Kalman filter (EKF) is presented. Previous research demonstrated that SSNNs can address complex nonlinear spatiotemporal problems. However, SSNN models require off-line training with large sets of input–output data, presenting three main drawbacks: (a) great amounts of time and effort are involved in collecting, preparing, and executing these training sessions; (b) as the input–output mapping changes over time, the model requires complete retraining; and (c) if a different input set becomes available (e.g., from inductive loops) and the input–output mapping has to be changed, then retraining the model is impossible until enough time has passed to compose a representative training data set. To improve SSNN effectiveness, the EKF is proposed to train the SSNN instead of conventional approaches. Moreover, this network topology is derived from the urban travel time prediction problem. Instead of treating the neural network as a “black-box” model, the design explicitly reflects the relationships that exist in physical traffic systems. It allows the interpretation of neuron weights and structure in terms of the inherent mechanism of the network process with clear physical meaning. Model performance was tested on a densely used urban arterial in the Netherlands. Performance of this proposed model is compared with that of two existing models. Results of the comparisons indicate that the proposed model predicts complex nonlinear urban arterial travel times with satisfying effectiveness, robustness, and reliability.

01037954

English

pp 99-108

2006

Transportation Research Record: Journal of the Transportation Research Board

0309099773

Print

Figures (6) ; References (22) ; Tables (3)

Arterial highways; Kalman filtering; Mathematical prediction; Neural networks; Travel time; Urban areas

Netherlands

Data and Information Technology; Highways; Planning and Forecasting; I72: Traffic and Transport Planning

TRIS, TRB, ATRI

Mar 3 2006 10:34AM

• Application of Genetic Neural Networks to Real-Time Intersection Accident Detection Using Acoustic Signals
• Applications of Artificial Intelligence Paradigms to Decision Support in Real-Time Traffic Management
• Forecasting Shared-Use Vehicle Trips with Neural Networks and Support Vector Machines
• Frameworks to Represent Uncertainty When Level of Service Is Determined
• Improving the Prediction of Annual Average Daily Traffic for Nonfreeway Facilities by Applying a Spatial Statistical Method
• Incorporating Wavelet Decomposition Technique to Compress TransGuide Intelligent Transportation System Data
• Kalman Filter-Based Tracking System for Automated Inventory of Roadway Signs
• Moments Analysis for Improving Decision Reliability Based on Travel Time
• Performance Evaluation of Sensor- and Image-Based Technologies for Automated Pavement Condition Surveys
• Predicting Directional Design Hourly Volume from Statutory Holiday Traffic
• Real-Time Detection of Crash-Prone Conditions at Freeway High-Crash Locations
• Travel Time Estimation with Correlation Analysis of Single-Loop Detector Data
• Unscented Kalman Filter Method for Speed Estimation Using Single Loop Detector Data