The invention discloses a traffic flow prediction method based on a residual decomposition recurrent neural network, and the method comprises the steps: obtaining a road occupancy rate data set at continuous moments, and the road occupancy rate data set at continuous moments comprises a training set and a test set; constructing a residual decomposition recurrent neural network model, and inputting the training set into the residual decomposition recurrent neural network model for training to obtain a trained residual decomposition recurrent neural network model; and inputting the test set into the trained residual decomposition recurrent neural network model to obtain a traffic flow time sequence prediction trend. According to the method, modeling is carried out on an input road occupancy time sequence from the two perspectives of an autoregression method and a moving average method, the influence of a direct observation value of a past time point and a self residual error on the future trend of the sequence is considered at the same time, and the potential influence of a high-order residual error can be considered at the same time through the depth of a stacked network.

    本发明公开了一种基于残差分解循环神经网络的交通流量预测方法,包括:获取连续时刻的道路占用率数据集,其中,连续时刻的道路占用率数据集包括训练集和测试集;构建残差分解循环神经网络模型,将训练集输入所述残差分解循环神经网络模型进行训练,得到训练好的残差分解循环神经网络模型;将测试集输入训练好的残差分解循环神经网络模型,得到交通流量时间序列预测趋势。本发明从自回归法和滑动平均法两个角度对输入的道路占有率时间序列进行建模,同时考虑了过往时间点的直接观测值和自身残差对序列未来走向的影响,并可以通过堆叠网络深度同时考虑高阶残差的潜在影响。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow prediction method based on residual decomposition recurrent neural network


    Weitere Titelangaben:

    基于残差分解循环神经网络的交通流量预测方法


    Beteiligte:
    ZENG JUNCHENG (Autor:in) / ZENG YONGQIANG (Autor:in) / CHEN ZHIWEI (Autor:in) / LAN XINGRONG (Autor:in) / ZHAO HUI (Autor:in) / WU SHAOFENG (Autor:in) / GAN HONG (Autor:in)

    Erscheinungsdatum :

    12.12.2023


    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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



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

    PENG LIQUN / HE JIAMI / ZHOU TUQIANG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction based on residual neural network

    Huang, Yanguo / He, Xuan / Li, Luo et al. | SPIE | 2023


    Short-term Traffic Flow Prediction Based on Recurrent Neural Network

    Li, Zhijie / Li, Chenghao / Cui, Xu et al. | IEEE | 2021


    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. | Europäisches Patentamt | 2024

    Freier Zugriff