The invention discloses a time-space convolution short-time traffic flow prediction method based on complementary integrated empirical mode decomposition. The method comprises the steps of obtaining original traffic flow data and performing data preprocessing; and inputting the traffic flow data into the pre-constructed CEEMD-GAT-LSTM model to carry out short-term traffic flow prediction. Wherein the constructed prediction model comprises the steps of performing signal decomposition on traffic flow data by adopting CEEMD, fully mining spatial features of the data by adopting GAT, and fully mining time features of the data by adopting LSTM, so that the learning efficiency of the neural network is improved. According to the method, the prediction precision of short-time traffic flow prediction can be effectively improved, and favorable reference values are provided for traffic departments.

    本发明公开了基于互补集成经验模分解的时空卷积短时交通流预测方法,包括:获取原始交通流数据并进行数据预处理;将交通流数据输入到预构建的CEEMD‑GAT‑LSTM模型中进行短时交通流预测。其中,构建的预测模型包括:采用CEEMD对交通流数据进行信号分解、采用GAT充分挖掘数据的空间特征、采用LSTM充分挖掘数据的时间特征,从而提高神经网络的学习效率。本发明能够有效提高短时交通流预测的预测精度,为交通部门提供有利的参考价值。


    Access

    Download


    Export, share and cite



    Title :

    Space-time convolution short-time traffic flow prediction method based on complementary integrated empirical mode decomposition


    Additional title:

    基于互补集成经验模分解的时空卷积短时交通流预测方法


    Contributors:
    ZHANG LINGYUN (author) / ZHANG KAI (author) / DING YUJIE (author) / LU HAIPENG (author) / LIU HONG (author) / ZHANG DONG (author) / SUN KAIQIANG (author) / SUN ZHIYING (author) / WEI MING (author)

    Publication date :

    2022-12-16


    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 short-term prediction optimization application method based on time convolution network

    CUI TIANZE / DOU XUN / LUO HAIFENG et al. | European Patent Office | 2021

    Free access

    Attention-based dynamic space-time diagram convolution traffic flow prediction system and method

    JI ZHENYUAN / HUAN YUEHUI / YANG GENKE et al. | European Patent Office | 2023

    Free access

    Short-term traffic flow prediction method based on time series decomposition

    WANG WEI / ZHOU WEI / HUA XUEDONG | European Patent Office | 2020

    Free access

    Short-time traffic flow prediction method based on integrated evaluation

    LENG SUPENG / ZHANG QUANFENG / DUAN JINGSHAN et al. | European Patent Office | 2015

    Free access

    Traffic prediction method based on dual dynamic space-time diagram convolution

    SUN YANFENG / JIANG XIANGHENG / HU YONGLI et al. | European Patent Office | 2022

    Free access