Author(s)

Jun Ding

Corresponding Author

Jun Ding

ABSTRACT

In order to improve the prediction accuracy of BP neural network prediction model, a prediction method based on Improved Particle Swarm Optimization BP neural network is proposed. The adaptive mutation operator is introduced to mutate the particles trapped in the local optimum, and the optimization performance of the particle swarm optimization algorithm is improved. The weight and threshold of BP neural network are optimized by improved particle swarm optimization algorithm. Then BP neural network prediction is trained. The model obtains the optimal solution. The forecasting method is applied to the time series of measured traffic flow to validate its validity. The results show that the method has better non-linear fitting ability and higher forecasting accuracy for short-term traffic flow.

KEYWORDS

BP neural network, particle swarm optimization, mutation operator, traffic flow prediction