Abstract: In a traffic flow prediction based fuzzy neural network, the optimization of the parameters of the nodes is very critical. An improved particle swarm optimization method was used to optimize the fuzzy neural network parameters to improve the precision and speed of vehicle prediction by fuzzy neural networks. Simulation results show that the accuracyof method is faster and accuracy is more accurate than PSO and BP algorithm, and the fuzzy neural network prediction model based on IPSO is an effective method for traffic flow prediction.

Key words: Fuzzy neural network, Particle swarm optimization, Traffic flow prediction