ANFIS based modeling and prediction car following behavior in real traffic flow based on instantaneous reaction delay

Nowadays, car following models, as the most popular microscopic traffic flow modeling, are increasingly being used by transportation experts to evaluate new Intelligent Transportation System (ITS) applications. This paper presents a car-following model that was developed using an adaptive neuro fuzzy inference system (ANFIS) to simulate and predict the future behavior of a Driver-Vehicle-Unit (DVU). This model was developed based on new idea for calculate and estimate the instantaneous reaction of DVU. This idea was used in selection of inputs and outputs in train of ANFIS model. Integration of the driver's reaction time delay and omission of the necessity of regime classification are considered while developing the model. The model's performance was evaluated based on field data and compared to a number of existing car following models. The results showed that new model based on instantaneous reaction delay outperformed the other car-following models. The model was validated at the microscopic level, and the results showed very close agreement between field data and model outputs. The proposed model can be recruited in Drier Assistant devices, Safe Distance Keeping Observers, Collision Prevention systems and other ITS applications.