The invention discloses a traffic flow prediction method and system based on an incremental output decomposition recurrent neural network, and is applied to the technical field of intelligent traffic. Comprising the following steps: performing multi-feature extraction on point observation data and surface observation data in a road network as input data; the method comprises the following steps of: performing twice affine transformation on multi-feature space-time diagram input data to form a single-feature output form, inputting the single-feature output form into an encoder, using a double-head self-attention layer in the encoder so as to obtain two different increment sub-states, and respectively taking the two different increment sub-states as an increment size and a prediction basic value; according to the increment size and the prediction basic value, an uncertainty increment and prediction output are obtained based on a gating circulation unit structure; coupling with a decoder by using a long-term cross attention mechanism; and using the shift divergence difference as a delay degree evaluation index of the traffic flow prediction result. The delay phenomenon of traffic flow prediction can be effectively relieved, and an effective and stable prediction result is obtained.

    本发明公开了基于增量输出分解循环神经网络的交通流预测方法及系统,应用于智能交通技术领域。包括以下步骤:对道路路网中的点观测数据和面观测数据进行多特征提取作为输入数据;将多特征时空图输入数据进行两次仿射变换成为单特征输出形式输入到编码器中,在编码器中使用双头自注意力层,从而获取两个不同的增量子状态,并将两个不同的增量子状态分别作为增量大小和预测基础值;根据增量大小和预测基础值,基于门控循环单元结构得到不确定性增量和预测输出;使用长期交叉注意力机制与解码器耦合;使用移位散度差作为交通流预测结果的延迟程度评估指标。本发明能够有效缓解交通流预测的延迟现象,得到有效稳定的预测结果。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method and system based on incremental output decomposition recurrent neural network


    Additional title:

    基于增量输出分解循环神经网络的交通流预测方法及系统


    Contributors:
    PENG LIQUN (author) / HE JIAMI (author) / ZHOU TUQIANG (author) / LIU KAIFENG (author)

    Publication date :

    2023-04-11


    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 flow prediction method based on residual decomposition recurrent neural network

    ZENG JUNCHENG / ZENG YONGQIANG / CHEN ZHIWEI et al. | European Patent Office | 2023

    Free access

    Traffic accident severity prediction method based on recurrent neural network

    XU XUECAI / QIAN CHENG / XIAO DAIQUAN | European Patent Office | 2024

    Free access

    Short-term traffic flow prediction with LSTM recurrent neural network

    Kang, Danqing / Lv, Yisheng / Chen, Yuan-yuan | IEEE | 2017


    Short-term traffic flow prediction method based on graph convolution recurrent neural network

    GU JUNHUA / GUO RUIZHE / HE WENYING et al. | European Patent Office | 2024

    Free access