基于GSO-BP神经网络的城市轨道交通客流量短时间预测

Short time forecasting of passenger flow in urban railway using GSO-BPNN method

城市轨道交通作为公共交通客流量的分担措施之一,能够解决因客流量预测不准确而带来的资源浪费和低效益问题。建立一种新的GSO-BPNN方法,该方法在BP网络的基础上植入GSO算法,优化网络的初始权值和阈值,并以某城市轨道交通客流量为例,对比普通BP网络预测模型,结果显示GSO-BPNN方法的预测精度较高。

The urban railway is taken as one of the measures of partaking public transport passengers,in order to deal with the problems of the waste of resources and low efficiency,caused by the inaccurate urban traffic passenger forecasting.In this paper,a new method for GSO-BPNN is proposed.This method is a combination of BP neural network and GSO algorithm.Firstly,the initial weights and thresholds of BP neural network are optimized with GSO algorithm.Then the method is validated with an example of some urban railway passengers and compared with the common BP neural network.Finally,the result shows that this forecasting precision of GSO-BPNN method is preferable.