计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (6A): 250500107-7.doi: 10.11896/jsjkx.250500107

• 大数据&数据科学 • 上一篇    下一篇

基于双通道时空超图卷积网络的交通速度预测方法

陈洪峰1, 赵振振2   

  1. 1 浙江工业大学信息工程学院 杭州 310023
    2 浙江工业大学计算机科学与技术学院 杭州 310023
  • 出版日期:2026-06-16 发布日期:2026-06-12
  • 通讯作者: 赵振振(zhenzzhao97@zjut.edu.cn)
  • 作者简介:(2627003138@qq.com)
  • 基金资助:
    浙江省“领雁”研发攻关计划(2024C01214);国家自然科学基金(62476247)

Dual-channel Spatiotemporal Hypergraph Convolutional Network for Traffic Speed Prediction

CHEN Hongfeng1and ZHAO Zhenzhen2   

  1. 1 College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,China
    2 College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China
  • Published:2026-06-16 Online:2026-06-12
  • About author:CHEN Hongfeng,born in 2005,undergraduate.His main research interests include deep learning and big data ana-lysis.
    ZHAO Zhenzhen,born in 1997,Ph.D,research associate. His main research interests include intelligent traffic and spatio-temporal graph neural network.
  • Supported by:
    “Leading Goose” R & D Program of Zhejiang(2024C01214) and National Natural Science Foundation of China(62476247).

PDF (PC)

37

摘要： 交通速度预测在智能交通系统中的交通拥堵识别、信号控制等任务中起到至关重要的作用。然而,交通数据中包含着随时间动态变化的空间关系,导致路网中非直接相邻的道路节点中亦存在关联关系,从而衍生出跨区域的隐式协同特征。因此,提出了一种用于交通数据隐式特征提取的双通道时空超图卷积网络。具体而言,该网络应用聚类算法发现全局的空间特征。然后,建立超图与线图的双通道卷积方法来捕捉交通数据中的隐式空间关系。最后,应用卷积结构的长短期记忆网络捕获时间特征。在真实世界交通速度数据集中的实验表明,所提出框架的性能优于最先进的基线模型。

关键词: 交通数据, 时空特征, 超图卷积, 交通速度预测

Abstract: Traffic speed forecasting plays a vital role in tasks such as traffic congestion recognition and signal control in intelligent transportation systems.However,since traffic data contains spatial relationships that change dynamically over time,there are also correlations between non-directly adjacent road nodes in the road network,thus deriving implicit cross-regional collaborative features.Therefore,this paper proposes a dual-channel spatiotemporal hypergraph convolutional network for implicit feature extraction of traffic data to solve the above problems.Specifically,the network uses a clustering algorithm to discover global spatial features.Then,a dual-channel convolution method of hypergraph and line graph is established to capture the implicit spatial relationships in traffic data.Finally,a long short-term memory network with a convolutional structure is used to capture temporal features.Experiments in real scenarios show that the performance of this framework is better than the state-of-the-art baseline models.

Key words: Traffic data, Spatiotemporal features, Hypergraph convolution, Traffic speed prediction

中图分类号: 

  • TP391
[1] NAGY A M,SIMON V.Survey on traffic prediction in smartcities[J].Pervasive and Mobile Computing,2018,50:148-163.
[2] KONG X,WU Y,WANG H,et al.Edge computing for internet of everything:A survey[J].IEEE Internet of Things Journal,2022,9(23):23472-23485.
[3] MA X,TAO Z,WANG Y,et al.Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J].Transportation Research Part C:Emerging Technologies,2015,54:187-197.
[4] LIU Y,ZHENG H,FENG X,et al.Short-term traffic flow prediction with Conv-LSTM[C]//2017 9th International Confe-rence on Wireless Communications and Signal Processing(WCSP).IEEE,2017:1-6.
[5] KIPF T N,WELLING M.Semi-Supervised Classification withGraph Convolutional Networks[C]//International Conference on Learning Representations.2017.
[6] MENG X F,XU R H.City Traffic Flow Prediction MethodBased on Dynamic Spatio-Temporal Neural Network[J].Computer Science,2023,50(S1):602-608.
[7] WILLIAMS B M,HOEL L A.Modeling and forecasting vehic-ular traffic flow as a seasonal ARIMA process:Theoretical basis and empirical results[J].Journal of Transportation Enginee-ring,2003,129(6):664-672.
[8] ZIVOT E,WANG J.Vector autoregressive models for multi-variate time series[J/OL].https://faculty.washington.edu/ezivot/econ584/notes/varModels.pdf.
[9] CHEN R,LIANG C Y,HONG W C,et al.Forecasting holiday daily tourist flow based on seasonal support vector regression with adaptive genetic algorithm[J].Applied Soft Computing,2015,26:435-443.
[10] JOHANSSON U,BOSTRÖM H,LÖFSTRÖM T,et al.Regression conformal prediction with random forests[J].Machine Learning,2014,97:155-176.
[11] YU B,YIN H,ZHU Z.Spatio-temporal graph convolutional networks:a deep learning framework for traffic forecast-ing[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence.2018:3634-3640.
[12] ZHAO L,SONG Y,ZHANG C,et al.T-GCN:A temporal graph convolutional network for traffic prediction[J].IEEE Transactions on Intelligent Transportation Systems,2019,21(9):3848-3858.
[13] WU Z,PAN S,LONG G,et al.Graph wavenet for deep spa-tial-temporal graph modeling[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence.2019:1907-1913.
[14] ZHENG C,FAN X,WANG C,et al.Gman:A graph mul-ti-attention network for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:1234-1241.
[15] BAI L,YAO L,LI C,et al.Adaptive graph convolutional recurrent network for traffic forecasting[J].Advances in Neural Information Processing Systems,2020,33:17804-17815.
[16] HUANG L,LIU X X,HUANG S Q,et al.Temporal hierarchical graph attention network for traffic prediction[J].ACM Transactions on Intelligent Systems and Technology(TIST),2021,12(6):1-21.
[17] YU L,DU B,HU X,et al.Deep spatio-temporal graph convolutional network for traffic accident prediction[J].Neurocompu-ting,2021,423:135-147.
[18] ORESHKIN B N,AMINI A,COYLE L,et al.FC-GAGA:Fully connected gated graph architecture for spatio-temporal traffic forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:9233-9241.
[19] SHUMAN D I,NARANG S K,FROSSARD P,et al.The emerging field of signal processing on graphs:Extending high-dimensional data analysis to networks and other ir-regular domains[J].IEEE Signal Processing Magazine,2013,30(3):83-98.
[20] GUO S,LIN Y,FENG N,et al.Attention based spa-tial-temporal graph convolutional networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:922-929.
[21] HAN X,SHEN G,YANG X,et al.Congestion recognition for hybrid urban road systems via digraph convolutional net-work[J].Transportation Research Part C:Emerging Technologies,2020,121:102877.
[22] SHEN G,HAN X,CHIN K S,et al.An attention-based digraph convolution network enabled framework for congestion recognition in three-dimensional road networks[J].IEEE Transactions on Intelligent Transportation Systems,2021,23(9):14413-14426.
[23] YADATI N,NIMISHAKAVI M,YADAV P,et al.Hypergcn:A new method for training graph convolutional networks on hy-pergraphs[C]//Advances in Neural Information Processing Systems 32.2019.
[24] FU S,LIU W,ZHOU Y,et al.Hplapgcn:Hypergraph p-laplacian graph convolutional networks[J].Neurocomputing,2019,362:166-174.
[25] FENG Y,YOU H,ZHANG Z,et al.Hypergraph neural net-works[C]//Proceedings of the AAAI conference on artificial intelligence.2019:3558-3565.
[26] JIANG J,WEI Y,FENG Y,et al.Dynamic hypergraph neural networks[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence.2019:2635-2641.
[27] BANDYOPADHYAY S,DAS K,MURTY M N.Line hypergraph convolution network:Applying graph convolution for hy-pergraphs[J].arXiv:2002.03392,2020.
[28] XIA X,YIN H,YU J,et al.Self-supervised hypergraph convolutional networks for session-based recommenda-tion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021,35(5):4503-4511.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发