《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (8): 2618-2625.DOI: 10.11772/j.issn.1001-9081.2023081226

• 前沿与综合应用 • 上一篇    下一篇

基于时空多图融合的交通流量预测

顾焰杰1, 张英俊1,2,3(), 刘晓倩1, 周围1,4, 孙威1   

  1. 1.北京交通大学 计算机与信息技术学院,北京 100044
    2.交通数据分析与挖掘北京市重点实验室(北京交通大学),北京 100044
    3.北京交通大学 智慧高铁系统前沿科学中心,北京 100044
    4.交通大数据与人工智能教育部重点实验室(北京交通大学),北京 100044
  • 收稿日期:2023-09-08 修回日期:2023-10-19 接受日期:2023-11-02 发布日期:2024-08-22 出版日期:2024-08-10
  • 通讯作者: 张英俊
  • 作者简介:顾焰杰(1999—),男,河北邢台人,硕士研究生,CCF会员,主要研究方向:机器学习、时间序列预测
    张英俊(1980—),男,内蒙古呼和浩特人,副教授,博士,CCF会员,主要研究方向:数据挖掘 zhangyj@bjtu.edu.cn
    刘晓倩(1996—),女,甘肃靖远人,博士研究生,主要研究方向:数据挖掘、进化学习、模糊认知图
    周围(1973—),女,河北石家庄人,研究员,博士,CCF会员,主要研究方向:数据挖掘、人工智能、计算机教育
    孙威(1998—),男,山东枣庄人,博士研究生,CCF会员,主要研究方向:数据挖掘、时序因果学习。
  • 基金资助:
    中央高校基本科研业务费专项(科技领军人才团队项目)(2022JBQY009)

Traffic flow forecasting via spatial-temporal multi-graph fusion

Yanjie GU1, Yingjun ZHANG1,2,3(), Xiaoqian LIU1, Wei ZHOU1,4, Wei SUN1   

  1. 1.College of Computer and Information Technology,Beijing Jiaotong University,Beijing 100044,China
    2.Beijing Key Laboratory of Traffic Data Analysis and Mining (Beijing Jiaotong University),Beijing 100044,China
    3.Frontiers Science Center for Smart High?speed Railway System,Beijing Jiaotong University,Beijing 100044,China
    4.Key Laboratory of Big Data & Artificial Intelligence in Transportation,Ministry of Education (Beijing Jiaotong University),Beijing 100044,China
  • Received:2023-09-08 Revised:2023-10-19 Accepted:2023-11-02 Online:2024-08-22 Published:2024-08-10
  • Contact: Yingjun ZHANG
  • About author:GU Yanjie, born in 1999, M. S. candidate. His research interests include machine learning, time series prediction.
    LIU Xiaoqian, born in 1996, Ph. D. candidate. Her research interests include data mining, evolutionary learning, fuzzy cognitive maps.
    ZHOU Wei, born in 1973, Ph. D., research fellow. Her research interests include data mining, artificial intelligence, computer education.
    SUN Wei, born in 1998, Ph. D. candidate. His research interests include data mining, temporal causal learning.
  • Supported by:
    Fundamental Research Funds for Central Universities(2022JBQY009)

摘要:

交通预测是智能交通系统(ITS)的核心任务,准确的交通流量预测(TFF)可以大幅提高公共资源的利用效率。针对现有多图神经网络模型对上下文信息使用不足、图融合方法不平衡和只考虑静态空间关系等问题,提出基于时空多图融合(STMGF)的TFF模型。首先,通过融合空间图、语义图和空间语义图提取不同区域的不同空间相关性,并利用空间注意力机制和图注意力机制融合不同的图结构以动态学习不同邻居的重要性;然后,使用多核时间注意力机制同时捕获局部时间依赖性和全局时间依赖性;最后,使用多层感知机预测交通流量,得到最终预测值。在NYCTaxi和NYCBike数据集验证模型的有效性。实验结果表明,在NYCBike数据集的36步预测任务中,与时空图卷积神经网络(STGCN)、基于时空注意力的图神经网络(ASTGNN)、元图卷积递归网络(MegaCRN)相比,所提模型的均方根误差(RMSE)分别降低了8.46%、2.70%和2.20%。

关键词: 多图融合, 多核注意力, 空间注意力, 图注意力, 深度学习

Abstract:

Traffic prediction is a fundamental task in Intelligent Transportation System (ITS), as accurate Traffic Flow Forecasting (TFF) can significantly improve the utilization efficiency of public resources. To address the limitations of insufficient utilization of contextual information, imbalanced graph fusion techniques, and consideration of only static spatial relationships in existing multi-graph neural network models, a TFF model based on Spatio-Temporal Multi-Graph Fusion (STMGF) was proposed. Firstly, different spatial correlations across different regions were extracted by the model through the fusion of spatial graphs, semantic graphs, and spatial-semantic graphs. Spatial attention mechanism and graph attention mechanism were utilized to dynamically learn the importance of different graph structures for different neighbors. Then, a multi-kernel temporal attention mechanism was employed to capture both local and global temporal dependencies. Finally, a multi-layer perceptron was utilized to predict traffic flow, obtaining the final prediction values. The validity of the model was verified on NYCTaxi dataset and NYCBike dataset. Experimental results showed that the Root Mean Square Errors (RMSE) of the proposed model STMGF were 8.46%, 2.70%, and 2.20% lower than those of Spatio-Temporal Graph Convolutional Network (STGCN), Attention based Spatial-Temporal Graph Neural Network (ASTGNN), and Meta-graph Convolutional Recurrent Network (MegaCRN), respectively in the 36 steps forecast task of the NYCBike dataset.

Key words: multi-graph fusion, multi-kernel attention, spatial attention, graph attention, deep learning

中图分类号: