Passenger Flow Forecast Using Wavelet Neural Network Model

Wavelet neural network (WNN), combining with wavelet analysis and neural network, brings forth a high-accuracy performance in identification and approximation. Passenger flow forecast plays an important role in transit scheduling and an improved WNN model is constructed to actualize dynamic forecast, in which Morlet wavelet is selected as the activation function. Input data series surveyed from No. 609 line in Xi'an, China, is pre-processed via a fuzzy operator before transferred to train and test the constructed network. A hybrid genetic algorithm and identical dimension recurrence idea are performed to optimize the structure and shape of WNN dynamically to enhance its forecast accuracy. The result indicates the proposed WNN model can accelerate the convergence speed, improve the global generalization ability and possess the practicality in dynamic transit scheduling.