PROJECT TITLE :

A Modified Car-Following Model Based on a Neural Network Model of the Human Driver Effects

ABSTRACT:

Today, among the microscopic traffic flow modeling approaches, the automotive-following models are increasingly utilized by transportation consultants to utilize acceptable intelligent transportation systems. Unlike previous works, where the reaction delay is considered to be fixed, during this paper, a changed neural network approach is proposed to simulate and predict the automotive-following behavior primarily based on the instantaneous reaction delay of the motive force-vehicle unit because the human effects. This reaction delay is calculated primarily based on a proposed plan, and also the model is developed based mostly on this feature as an input. During this modeling, the inputs and outputs are chosen with respect to the reaction delay to coach the neural network model. Using the field data, the performance of the model is calculated and compared with the responses of some existing neural network automobile-following models. Considering the distinction between the responses of the actual plant and the expected model because the error, comparison shows that the error in the proposed model is significantly smaller than that that in the opposite models.