The invention discloses an urban road network traffic speed prediction method based on graph convolutional network node association degree. The method comprises the steps of 1 determining a road network range needing to be predicted, and aggregating vehicle speed on each road as a characteristic value of a road node; preprocessing the vehicle speed, and splitting a data set; 2 analyzing road sections in the road network, and constructing a correlation degree matrix by using a correlation analysis method; 3 constructing an urban road network traffic speed prediction model based on the graph convolutional network node association degree, and determining a network structure; 4 determining each parameter of the model, and performing training optimization and testing on the model by using the split data set; and 5 analyzing the performance of the model by using different evaluation indexes. According to the method, the spatial correlation between long-distance road sections in the global road network is considered, the correlation degree matrix is embedded into the graph convolutional network, the capability of capturing the spatial dependence of the urban road network is improved, and thus the model prediction performance is improved.

    本发明公开了一种基于图卷积网络节点关联度的城市路网交通速度预测方法,步骤如下:1.确定需要进行预测的路网范围,聚合每条道路上的车辆速度作为该道路节点的特征值。对车辆速度进行预处理并拆分数据集;2.对路网中的路段进行分析,利用相关性分析方法构造关联度矩阵;3.构建基于图卷积网络节点关联度的城市路网交通速度预测模型,确定网络结构;4.确定模型的各个参数,利用拆分好的数据集对模型进行训练优化及测试;5.利用不同的评价指标对模型性能进行分析。本发明考虑全局路网中远距离路段间的空间相关性,将关联度矩阵嵌入到图卷积网络中,提高对城市路网空间依赖性捕获的能力,从而提高模型预测性能。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Urban road network traffic speed prediction method based on graph convolutional network node association degree


    Weitere Titelangaben:

    基于图卷积网络节点关联度的城市路网交通速度预测方法


    Beteiligte:
    SHI ZHENQUAN (Autor:in) / FENG SIYUN (Autor:in) / SHI QUAN (Autor:in) / CAO YANG (Autor:in) / SHAO YEQIN (Autor:in) / CAO ZHICHAO (Autor:in)

    Erscheinungsdatum :

    2021-06-18


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES



    Topological Graph Convolutional Network-Based Urban Traffic Flow and Density Prediction

    Qiu, Han / Zheng, Qinkai / Msahli, Mounira et al. | IEEE | 2021


    Spatial–Temporal Tensor Graph Convolutional Network for Traffic Speed Prediction

    Xu, Xuran / Zhang, Tong / Xu, Chunyan et al. | IEEE | 2023


    Graph attention temporal convolutional network for traffic speed forecasting on road networks

    Zhang, Ke / He, Fang / Zhang, Zhengchao et al. | Taylor & Francis Verlag | 2021


    Graph Attention Convolutional Network: Spatiotemporal Modeling for Urban Traffic Prediction

    Song, Qingyu / Ming, RuiBo / Hu, Jianming et al. | IEEE | 2020


    Urban-Road Average-Speed Prediction Method Based on Graph Convolutional Networks

    Wang, Xuemei / Chen, Ying / Zhang, Jinlei | Transportation Research Record | 2023