Browse by author
Lookup NU author(s): Professor Margaret Carol Bell CBE
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
This paper analyzes the characteristics of vehicle breakdown duration and the relationship between the duration and vehicle type, time, location, and reporting mechanisms. Two models, one based on fuzzy logic (FL) and the other on artificial neural networks (ANN), were developed to predict the vehicle breakdown duration. One advantage of these methods is that few inputs are needed in the modeling. Moreover, the distribution of the duration does not affect the results of the prediction. Predictions were compared with the actual breakdown durations demonstrating that the ANN model performs better than the FL model. In addition, the paper advocates for a standard way to collect data to improve the accuracy of duration prediction.
Author(s): Wang W, Chen H, Bell MC
Publication type: Article
Publication status: Published
Journal: Journal of Transportation and Statistics
ISSN (print): 1094-8848