Nonparametric traffic flow prediction using kernel estimator
Type de document
CHAPITRE D'OUVRAGE (CO)
Résumé / Abstract
In this paper, we consider a nonparametric short-term traffic flow prediction model based on functional estimation techniques, using the kernel smoother for the auto regression function. This model is designed for nonlinear statistical prediction. The application to traffic flow forecasting motivates the analysis, and shows the ability of this model to be turned in different ways for different specific applications. Performance of the proposed model has been evaluated using measured data for a ZELT test area at Toulouse. A preliminary result indicates a greater predictive accuracy of this model.