The invention belongs to the field of intelligent traffic, and particularly relates to a short-time traffic flow prediction method based on a space-time convolutional network. Comprising the following steps: acquiring traffic data from a traffic gate; calculating traffic checkpoint activeness according to the traffic data; extracting hidden features of the checkpoint nodes and fusing the traffic checkpoint activeness to obtain a hidden information matrix; generating a self-adaptive adjacency matrix according to the hidden information matrix, and inputting the self-adaptive adjacency matrix into a self-adaptive graph convolutional network module for processing to obtain initial traffic flow characteristics; processing the initial traffic flow characteristics by adopting a BiGRU network to obtain traffic space-time attribute characteristics; extracting external attribute features and generating an augmented matrix; inputting the augmented matrix into a BiGRU network and processing the augmented matrix by adopting an attention mechanism to generate an attention weight; predicting traffic flow according to the traffic time-space attribute characteristics and the attention weight to obtain a traffic flow prediction result; the traffic flow can be accurately predicted, and the method has a wide application prospect.

    本发明属于智能交通领域,具体涉及一种基于时空卷积网络的短时交通流量预测方法;包括:从交通卡口处获取交通数据;根据交通数据计算交通卡口活跃度;提取卡口节点的隐藏特征并融合交通卡口活跃度,得到隐藏信息矩阵;根据隐藏信息矩阵生成自适应邻接矩阵,将其输入到自适应图卷积网络模块进行处理,得到初始交通流量特征;采用BiGRU网络对初始交通流量特征进行处理,得到交通时空属性特征;提取外部属性特征并生成增广矩阵;将增广矩阵输入到BiGRU网络并采用注意力机制进行处理,生成注意力权重;根据交通时空属性特征和注意力权重预测交通流量,得到交通流量预测结果;本发明可实现对交通流量的准确预测,具有广阔的应用前景。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Short-term traffic flow prediction method based on space-time convolutional network


    Weitere Titelangaben:

    一种基于时空卷积网络的短时交通流量预测方法


    Beteiligte:
    JIA CHAOLONG (Autor:in) / KANG ZHEYI (Autor:in) / PENG GANG (Autor:in) / WANG RONG (Autor:in) / XIAO YUNPENG (Autor:in)

    Erscheinungsdatum :

    10.11.2023


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Traffic flow prediction method based on space-time diagram convolutional network

    JIANG YUNLIANG / XIA RENHUAN / ZHANG XIONGTAO et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Short-Term Traffic Flow Prediction Based on Graph Convolutional Network Embedded LSTM

    Huang, Yanguo / Zhang, Shuo / Wen, Junlin et al. | TIBKAT | 2020


    Short-Term Traffic Flow Prediction Based on Graph Convolutional Network Embedded LSTM

    Huang, Yanguo / Zhang, Shuo / Wen, Junlin et al. | ASCE | 2020



    Short-term traffic flow prediction method based on integrated graph convolutional neural network

    LIU LUYANG / LYU SHUAIQI / BAO XU | Europäisches Patentamt | 2024

    Freier Zugriff