FA-BP Neural Network-Based Forecast for Railway Passenger Volume
The research presents a long-term forecast model based on the use of a back-propagation (BP) neural network. Firstly, a brief overview of the forecast models and BP neural network model is demonstrated. Then the improved BP model based on factor analysis (FA-BP) and algorithmfor solving the model are presented. At last, a numerical case study is shown.As the current statistic yearbook only provides the volume data of Jing-Hu corridor, the notion of economical relation intensityis applied to process the original data. The results show that FA-BP neural network is effective in forecast. The proposed model providesa reference in the forefront field of integrated regional transportation planning.
Xun Wu, Weizhen Chen, Weijun Yang and Jianguo Liang
M. T. Li et al., "FA-BP Neural Network-Based Forecast for Railway Passenger Volume", Applied Mechanics and Materials, Vols. 641-642, pp. 673-677, 2014