汽车工程学报2024，Vol.14Issue(5)：898-910,13.DOI:10.3969/j.issn.2095‒1469.2024.05.16
基于时空注意力机制的网约车出行需求预测模型
A Travel Demand Prediction Model for Ride-Hailing Services Based on Spatio-Temporal Attention Mechanism
摘要
Abstract
The paper aims to solve the problem of forecasting passenger travel demand in e-hailing car operations,thereby reducing vehicle idle rates and minimizing passenger waiting times.Considering the dynamic spatiotemporal dependencies of passenger travel demand,this study proposes a method based on spatial data visualization and the Granger causality test for analyzing the spatial dependency.A spatiotemporal graph convolutional neural network model incorporating attention mechanisms is established to predict passenger travel demand.The case study shows that this model effectively captures the dynamic characteristics of the time-space dependencies of passenger travel demand,improves the prediction performance of the model,and achieves high accuracy and practicability.关键词
出行需求预测/注意力机制/时空依赖性/时空图卷积神经网络Key words
travel demand forecasting/attention mechanism/spatiotemporal dependence/attention based spatial temporal graph convolutional networks分类
交通工程引用本文复制引用
王宁,马洪恩..基于时空注意力机制的网约车出行需求预测模型[J].汽车工程学报,2024,14(5):898-910,13.基金项目
同济大学学科交叉联合攻关项目(2023-4-YB-04) （2023-4-YB-04）
