Tarrahan Parseh Transportation Research Institute International Journal of Transportation Engineering 2322-259X 4 2 2016 10 01 Prediction of Car Following Behavior Based on the Instantaneous Reaction Time using an ANFIS-CART Based Model 109 126 40536 10.22119/ijte.2016.40536 EN Mohsen Poor Arab Moghadam MSc. Student in GIS Division, School of Surveying and Geospatial Eng., College of Engineering, University of Tehran, Tehran, Iran Parham Pahlavani Assistant Professor, Center of Excellence in Geomatics Engineering in Disaster Management, School of Surveying and Geospatial Engineering., College of Engineering, University of Tehran, Tehran, Iran Saber Naseralavi Assistant Professor, Department of Civil Engineering, Shahid Bahonar University of Kerman, Kerman, Iran. Journal Article 2016 03 15 Car-following models are among the most important components of micro traffic flow simulation which is studied<br />by transportation experts to evaluate new applications of intelligent transportation systems. Until now, several carfollowing<br />models have been proposed. An obvious disadvantage of the former models is the great number of parameters<br />which are difficult to calibrate. In this paper, a car-following model was modeled and developed by combining an<br />Adaptive Neuro-Fuzzy Inference System (ANFIS) and a Classification And Regression Tree (CART) to simulate and<br />predict future behavior of each driver-vehicle-unit (DVU). In this model, the reaction time was instantaneously calculated<br />based on the time interval between acceleration and relative velocity by the proposed model and was considered<br />as a new input. The results were compared with the fixed reaction time and the reaction time proposed by Ozaki. To<br />evaluate the performance of the model, we compared the proposed model's output data with real conditions and it was<br />found that the precision of the proposed model was significantly high with regard to the instantaneous reaction time.<br />According the implemented simulation, the proposed model reached a good validity on the basis of proximity to a real<br />situation of car-following. http://www.ijte.ir/article_40536_d2fd2442ea1065e9f10ef41766dbd0ec.pdf