01125511

Component

https://doi.org/10.3141/2105-15

http://scholar.google.com...ylen&publication_year=2009

This paper presents the Bayesian evidence framework that enables a unified way of constructing and training committees of an arbitrary number of models. The main contribution the paper makes is an expansion of this framework for recurrent neural networks, which involves analytically deriving the gradient and the Hessian of the network. State-space neural networks (SSNNs), a special type of recurrent neural networks, are compared with feed-forward neural networks (FFNNs), and the effect of the Bayesian framework on both types is investigated using data from a densely used freeway in the Netherlands. From a cross-validation procedure, it can be concluded that, for a short time horizon, both Bayesian training and recurrency do not lead to improvements, but that, for a longer horizon, both techniques are beneficial. It is shown that the use of a committee leads to improved performance; furthermore, the correlation of the evidence factor, which follows from Bayesian model-fitting, and the generalization performance is compared against the training error and the generalization performance. It is found that the evidence has lower correlation, which is an indication that (a) the data set may be too small, (b) bias exists, (c) the mapping between the input and output data is difficult, and (d) the approximation of the evidence is imperfect. Future research will need to resolve these issues. However, the Bayesian framework will already be beneficial to more complex problems and lead to estimations of error bars on the predictions, which may be useful for many applications.

01141653

09-0023

English

pp 118-126

2009

Transportation Research Record: Journal of the Transportation Research Board

9780309126205

Print

Figures (2) ; References (43) ; Tables (2)

Mathematical prediction; Neural networks; Traffic data; Traffic models; Travel time

Bayesian approach

Netherlands

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

TRIS, TRB, ATRI

Jan 30 2009 4:18PM

• A Semidirective Interview Method to Analyze Behavioral Changes: A Focus on Two Case Studies
• Development of Geolocation Data Compression for Transportation Target Identification
• Distributed Approach for Estimation of Dynamic Origin–Destination Demand
• Driver-Assisted Bus Interview: Passive Transit Travel Survey with Smart Card Automatic Fare Collection System and Applications
• Efficiency and Effectiveness of Cell Phone Samples in Transportation Surveys
• Forecasting Network Data: Spatial Interpolation of Traffic Counts from Texas Data
• Generating Internationally Comparable Figures on Long-Distance Travel for Europe
• Household Travel Surveys with GPS: An Experiment
• Improving the Usability of a Complex Household Travel Survey: An Evaluation of User Requirements
• Kinematic Terrestrial Light-Detection and Ranging System for Scanning
• Measuring and Estimating Suppressed Travel with Enhanced Activity–Travel Diaries
• Model-Based Synthesis of Household Travel Survey Data in Small and Midsize Metropolitan Areas
• Participatory Geographic Information Systems and Active Transportation: Collecting Data and Creating Change
• Processing Raw Data from Global Positioning Systems Without Additional Information
• Transport and Surveillance Aspects of Location-Based Services
• Vehicle Detection from Satellite Images: Intensity-, Chromaticity-, and Lane-Based Method