Highlights We used Bayesian updating to improve transferability of real-time crash risk models. Real-time Crash risk models cannot be directly transferred across time and space. Bayesian updating can improve transferability even when new data are limited. Prediction accuracy of the updated model increases as new data sample size increases. Updating an existing model is better than developing a model when data are limited.
Abstract This study aimed to improve the spatial and temporal transferability of the real-time crash risk prediction models by using the Bayesian updating approach. Data from California’s I-880N freeway in 2002 and 2009 and the I-5N freeway in 2009 were used. The crash risk models for these three datasets are quite different from each other. The model parameters do not remain stable over time or space. The transferability evaluation results show that the crash risk models cannot be directly transferred across time and space. The updating results indicate that the Bayesian updating approach is effective in improving both spatial and temporal transferability even when new data are limited. The predictive performance of the updated model increases with an increase in the sample size of the new data. In addition, when limited new data are available, updating an existing model is better than developing a model using the limited new data.
Using the Bayesian updating approach to improve the spatial and temporal transferability of real-time crash risk prediction models
Tramsportation Research, Part C: Emerging Technologies ; 38 ; 167-176
2013-11-18
10 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Temporal transferability and updating of zonal level accident prediction models
Online Contents | 2006
|Transportation Research Record | 2022
|