Application of Fuzzy Neural Network for speed prediction in the highway networks

A route guidance system is one of the most important services of advanced traveler information systems (ATIS) for drivers,which aims to inform the state of the highway’s traffic to a group of drivers using variable message sign (VMS), web sites, medias and etc. Dynamic travel time information is one of the major components of the dynamic route guidance system which can increase the highway networks reliability, lighten the traffic flow and create dynamic route guidance for drivers. In this paper different methods are reviewed and the results of neuro-fuzzy neural networks and perceptron neural networks are compared. Comparing the results of these methods for predicting the data collected from the Chamran to Niyayesh ramp in Tehran highway network, shows that fuzzy-neural approach can achieve more accurate results.