The invention relates to a traffic flow combination prediction method. The method comprises the following steps: S1, acquiring traffic flow data; s2, performing complete set empirical mode decomposition on the data to obtain a plurality of components with different stability and random features and a residual component; s3, calculating randomness and complexity of all the components obtained in the S2, and dividing all the components into two types according to a calculation result, namely a linear part and a nonlinear part; s4, inputting a component corresponding to the nonlinear part into the trained attention mechanism-time convolution network-bidirectional gating circulation unit neural network model to obtain a prediction result; s5, inputting a component corresponding to the linear part into an autoregressive translation average model to obtain a prediction result; and S6, adding the prediction result of S4 and the prediction result of S5 to obtain a final prediction result. Compared with the prior art, the method has the advantages of higher prediction accuracy and the like.

    本发明涉及一种交通流组合预测方法,方法包括以下步骤:S1、获取交通流数据;S2、将数据进行完备集合经验模态分解,得到多个稳定性和随机特征不同的分量和一个残差分量;S3、对S2得到的所有分量计算随机性和复杂度,并根据计算结果将所有分量分为两类,分别是线性部分和非线性部分;S4、将非线性部分对应的分量输入训练好的注意力机制‑时间卷积网络‑双向门控循环单元神经网络模型中,得到预测结果;S5、将线性部分对应的分量输入自回归平移平均模型,得到预测结果;S6、将S4的预测结果和S5的预测结果进行加和,得到最终的预测结果。与现有技术相比,本发明具有预测准确性更高等优点。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow combination prediction method


    Additional title:

    一种交通流组合预测方法


    Contributors:
    XIONG HAO (author) / ZHANG LI (author)

    Publication date :

    2023-11-14


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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



    Short-time traffic-flow combination prediction method

    YANG CHUNXIA / FU YIQIN / WU WENLU et al. | European Patent Office | 2015

    Free access

    Improved adaptive traffic flow combination prediction method

    YIN LISHENG / SHI CHENG / LIU PAN et al. | European Patent Office | 2024

    Free access

    Research on traffic flow prediction method based on combination models

    Nie, Jun / Xie, Weiqing / Zhang, Wen | SPIE | 2023


    Traffic flow prediction method based on improved combination model and application

    YIN LISHENG / LIU PAN / WU YANGYANG et al. | European Patent Office | 2022

    Free access