Recently, utilizing the traffic simulation models have been known as an efficient traffic control and management tool. However, all traffic micro-simulation models require a car-following model so that the simulations would be performed based on it. Many car-following methods have been proposed yet, but all these methods have several number of parameters to calibrate, in a way a little variation over them creates considerable disturbance. In this paper a new car following model was proposed using the Multi-variate Adaptive Regression Spline (MARS) method that do not need any calibration stage. The proposed model inputs are leading vehicle velocity, relative velocity of leading and following vehicles and spacing between them and the output is the acceleration of the following car. As a result of this paper, a car following model with the Mean Squared Error (MSE) equal to 0.004 and the correlation coefficient (R) equal to 0.98 was achieved using the function estimation method through the MARS method. Finally, the MARS output was compared with the results achieved by the Helly linear model, the GHR model and the Gipps model. Based on micro simulation experiment it was shown that the proposed method was more accurate than those models.
Poor Arab, M. (2019). Car following modeling based on multi-variate adaptive regression spline, Study area: A highway zone. Quarterly Journal of Transportation Engineering, (), -.
MLA
Mohsen Poor Arab. "Car following modeling based on multi-variate adaptive regression spline, Study area: A highway zone". Quarterly Journal of Transportation Engineering, , , 2019, -.
HARVARD
Poor Arab, M. (2019). 'Car following modeling based on multi-variate adaptive regression spline, Study area: A highway zone', Quarterly Journal of Transportation Engineering, (), pp. -.
VANCOUVER
Poor Arab, M. Car following modeling based on multi-variate adaptive regression spline, Study area: A highway zone. Quarterly Journal of Transportation Engineering, 2019; (): -.