华东交通大学学报2025，Vol.42Issue(3)：77-86,10.
参数优化的图卷积门控循环网络地铁客流预测
Parameter Optimization of Graph Convolution Gated Recurrent Neural Network for Subway Passenger Flow Prediction
摘要
Abstract
Fully exploiting the spatial correlation of passenger flow between related stations in the subway net-work has a positive effect on the improvement of subway passenger flow prediction accuracy.Capturing and quantifying spatial patterns in passenger flow data is difficult due to the difficulty of learning and transferring spatial correlations between metro stations.An improved graph-convolution gated recurrent neural network(GC-GRU)metro passenger flow prediction model was proposed to enhance the model's ability to handle different data types by integrating multivariate spatio-temporal data.The spider wasp optimisation(SWO)algorithm based on Tent chaotic mapping and Levy flight disturbance strategy was used to dynamically adjust the model structural parameters in order to optimize the hidden layer structure of the gated recurrent neural network.The ex-perimental results show that the prediction accuracy of the model is significantly higher on weekdays than on week-ends,and the root mean square error,mean absolute error,and mean absolute percentage error are reduced by 13 percentage points,12 percentage points,and 0.08 percentage points,respectively,during weekdays compared to weekends.Dynamic optimization of the hidden structure of gated recurrent networks can lead to better convergence of the prediction model and higher prediction accuracy.关键词
门控循环神经网络/图卷积运算/注意力机制/莱维飞行扰动策略/地铁客流预测Key words
gated recurrent neural network/graph convolution operation/attention mechanism/Levy flight dis-turbance/subway passenger flow prediction分类
交通工程引用本文复制引用
张阳,李露玢,陈燕玲..参数优化的图卷积门控循环网络地铁客流预测[J].华东交通大学学报,2025,42(3):77-86,10.基金项目
福建省自然科学基金项目(2023J01946) （2023J01946）
