Dynamic prediction method of route travel time based on interval velocity measurement system

Focusing on the dynamic travel time prediction for the intelligent transportation system (ITS), this paper proposes a new prediction method by introducing the particle filters algorithm. Based on the interval velocity measurement system, various traffic parameters of the highway are obtained, and a state model with these associated parameters is built for the travel time estimation. Then, the probability distribution of the system state is simulated by a set of particles according to Bayesian theory. The distribution of these particles is updated real-time based on the state transition model and re-sampling method at last. The estimated travel time is given based on the predicted system state distribution. The proposed method learns the system state transition model based on the history data derived from the interval velocity measurement system. And the introduction of the particle filters improves the proposed method greatly to handle the dynamic and uncertainty of the system. Simulation experiments are taken on the traffic data from the detection sensors on several road sections. The results show that the proposed method has much better prediction performance than some traditional methods, and validate this method can be applied on the route travel time prediction of a dynamic traffic flow.