The invention discloses an attribute-enhanced perceptual sequence diagram convolutional network traffic speed prediction method, and the method comprises the steps: carrying out the processing and integration of speed data II, an adjacent matrix G, static external information alpha and dynamic external information beta through an attribute enhancement unit in an attribute enhancement layer; the spatial information extraction layer carries out spatial dependency extraction on the integrated information integrated by the attribute enhancement unit through a GAT unit, outputs a feature matrix after information extraction, inputs the feature matrix into the time information extraction layer, carries out time sequence information extraction on the feature matrix through a GRU unit, and splices feature data calculated by the GRU unit; and as the input of the full-connection layer, the full-connection layer calculates a final network output result, namely a predicted speed value. Through the above mode, according to the attribute-enhanced perception time sequence diagram convolutional network traffic speed prediction method of the invention, time-space information and periodicity are considered at the same time, and through utilization of external factors, perception of a model on data time sequence is improved, and prediction efficiency is improved.

    本发明公开了一种属性增强的感知时序图卷积网络交通速度预测方法,利用属性增强层中的属性增强单元对速度数据II、邻接矩阵G、静态外部信息α和动态外部信息β进行处理整合,空间信息提取层通过GAT单元对属性增强单元整合后的整合信息进行空间依赖性提取,输出信息提取后的特征矩阵,将特征矩阵输入时间信息提取层,通过GRU单元对特征矩阵进行时序信息提取,将GRU单元计算的特征数据进行拼接,作为全连接层的输入,全连接层计算最终网络输出结果,即预测速度值。通过上述方式,本发明所述的属性增强的感知时序图卷积网络交通速度预测方法,同时考虑时空信息和周期性,通过对外部因素的利用,提升模型对数据时序性的感知,并提高预测效能。


    Access

    Download


    Export, share and cite



    Title :

    Attribute-enhanced perceptual sequence diagram convolutional network traffic speed prediction method


    Additional title:

    一种属性增强的感知时序图卷积网络交通速度预测方法


    Contributors:
    SONG YAOFENG (author) / LUO RUIKANG (author)

    Publication date :

    2023-12-12


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    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 / 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 speed prediction method based on multi-space-time diagram fusion convolutional network

    GU ZHAOLING / ZHANG ANQIN / CHEN JINGJING | European Patent Office | 2023

    Free access

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

    SUN YONG / ZHANG ANQIN / CHEN JINGJING | European Patent Office | 2023

    Free access


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

    JIANG YUNLIANG / XIA RENHUAN / ZHANG XIONGTAO et al. | European Patent Office | 2022

    Free access

    Traffic flow prediction method of space-time diagram convolutional network

    TENG FEI / WANG ZIDAN / QIAO LU et al. | European Patent Office | 2024

    Free access