The invention discloses a traffic flow prediction method based on a diffusion space-time residual multi-graph convolutional network, and the method comprises the steps: collecting and preprocessing traffic flow data, obtaining noiseless traffic flow data, and dividing the noisy traffic flow data and the noiseless traffic flow data into a training set and a test set; a de-noising diffusion space-time residual multi-graph convolution network is constructed, the de-noising diffusion space-time residual multi-graph convolution network comprises a de-noising diffusion module and a space-time residual multi-graph convolution module, the de-noising diffusion module is used for acquiring original features in the noisy traffic flow data, and the space-time residual multi-graph convolution module is used for enhancing space-time features of the noiseless traffic flow data and outputting a predicted value; and training the de-noising diffusion space-time residual multi-graph convolutional network, and carrying out traffic flow prediction by using the trained network. According to the method, the denoising diffusion module is introduced to prevent the preprocessed noiseless traffic flow data from losing original features, and the space-time residual multi-graph convolution module is utilized to enhance the space-time feature extraction of the noiseless traffic flow data, so that the prediction performance of the traffic flow can be improved.

    本发明公开一种基于扩散时空残差多图卷积网络的交通流预测方法,包括:采集交通流量数据并预处理,得到无噪声交通流量数据,将有噪声和无噪声交通流量数据拆分为训练集和测试集;构建去噪扩散时空残差多图卷积网络,包括去噪扩散模块和时空残差多图卷积模块,去噪扩散模块用于获取有噪声交通流量数据中的原始特征,时空残差多图卷积模块用于增强无噪声交通流量数据的时空特征并输出预测值;训练去噪扩散时空残差多图卷积网络,利用训练好的网络进行交通流预测。本发明通过对引入去噪扩散模块来避免经过预处理的无噪声交通流量数据丢失原始特征,并利用时空残差多图卷积模块增强对无噪声交通流量数据的时空特征提取,有利于提高交通流的预测性能。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method based on de-noising diffusion space-time residual multi-graph convolutional network


    Additional title:

    基于去噪扩散时空残差多图卷积网络的交通流预测方法


    Contributors:
    SHI QUAN (author) / BAO YINXIN (author) / CAO CHENYANG (author) / SHEN QINQIN (author) / YU XIAN (author) / CAO YANG (author)

    Publication date :

    2024-05-03


    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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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




    Urban traffic flow space-time prediction scheme based on graph convolutional neural network

    ZHANG RONGQING / WANG HANQIU / LI BING | European Patent Office | 2021

    Free access

    Traffic flow prediction method of attention-based deep residual space-time diagram convolutional network

    XU SHIJIAN / ZHANG XUHONG / WU YUEDONG et al. | European Patent Office | 2023

    Free access

    Traffic flow prediction method of space-time attention graph convolutional network based on multi-feature fusion

    CHEN YAJUN / DING ZHIMING / GUO LIMIN | European Patent Office | 2023

    Free access

    Multi-view fusion space-time dynamic graph convolutional network urban traffic flow prediction method

    YUAN GUAN / ZHAO WENZHU / ZHANG YANMEI et al. | European Patent Office | 2023

    Free access