Evaluation of the Use of an Intelligent System in the Calibration of a Refined Car-Following Model

This paper aims to extract the computational logic of a hybrid method for online calibration of car-following models and apply it to a refined car-following model that incorporates the behavior of vehicles moving on the adjacent traffic lanes. This calibration method combines the concept of Kalman filters with the Takag-Sugeno Fuzzy Inference System (T-S FIS). Furthermore, this paper analyzes the influence of the lane change behavior on the calibration process. The testing of the hybrid calibration method in the case of a refined car-following model uses real traffic data and it is followed by a discussion of the results based on day/night traffic behaviors.