Chaos rapid identifying of traffic flow using neural networks with PSO
Pang Ming-bao, Jingjing Zhang, Fang Dong, Yanhu Wang · 2011
The problem of chaos rapid judging in traffic flow was studied using neural networks with particle swarm optimization (PSO). Based on analyzing the demand of intelligent transportation system and the problems of the existing methods of chaos identifying, the intelligent method of chaos rapid judging in traffic flow was proposed. The principle and the structure of the system are briefly introduced. There are online identifying module and offline identifying module mainly. Wolf method is used to calculate the largest Lyapunov exponent and judge chaos in offline identifying module. The online judging model was established using neural networks, which the wavelet packet energy features vector of the anterior time headway time series of traffic flow in every training sample were used as input variables. PSO was used to identify and update the parameters of the model. The simulation result shows that the method is correct and feasible. And it can satisfy the real-time requirement of chaos identifying in traffic flow.