The invention discloses a traffic flow prediction method containing missing data, and the method comprises the steps: obtaining a traffic data set of a certain region, the traffic data set comprises the missing data, reconstructing the traffic data set into a traffic flow data matrix, inputting the traffic flow data matrix X into an orthogonal non-negative matrix factorization (ONMF) module of a trained space-time prediction model to form K clusters, filling data in each cluster by using a generalized matrix decomposition GMF module of a space-time prediction model to obtain a traffic flow data matrix after data filling; performing standardization processing on the traffic flow data matrix after data filling; and according to the historical step length H and the prediction window W, modeling the standardized traffic flow data matrix into a three-dimensional tensor, and inputting the three-dimensional tensor into a graph convolutional recurrent neural network GCRNN of the trained space-time prediction model to obtain prediction data Y '. The method has universality in the aspect of traffic prediction of missing data, and the spatial-temporal characteristics are learned in a finer-grained manner so as to realize more effective traffic flow prediction.

    本发明公开了一种含缺失数据的交通流预测方法,包括:获取某区域的交通数据集,其包含缺失数据,将该交通数据集重建模为交通流数据矩阵,将交通流数据矩阵X输入训练好的时空预测模型的正交非负矩阵分解ONMF模块形成K个簇,并在各簇中利用时空预测模型的广义矩阵分解GMF模块填充数据,以得到填充数据后的交通流数据矩阵对填充后的交通流数据矩阵进行标准化处理,并根据历史步长H和预测窗口W将标准化后的交通流数据矩阵建模为三维张量将三维张量输入训练好的时空预测模型的图卷积循环神经网络GCRNN,以得到预测数据Y′。本发明在对缺失数据的交通预测方面具有通用性,且更细粒度地学习时空特征以实现更有效地交通流预测。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method and system containing missing data


    Additional title:

    一种含缺失数据的交通流预测方法和系统


    Contributors:
    JIN YANI (author) / LIU CAIPING (author) / XIE KUN (author) / WEN JIGANG (author) / ZHANG DAFANG (author)

    Publication date :

    2023-02-07


    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



    VEHICLE TRAFFIC FLOW PREDICTION METHOD WITH MISSING DATA

    LI CHANGLE / YUE WENWEI / ZHANG HEHE et al. | European Patent Office | 2021

    Free access

    Vehicle traffic flow prediction method with missing data

    CHANGLE LI / WENWEI YUE / HEHE ZHANG et al. | European Patent Office | 2023

    Free access

    Vehicle traffic flow prediction method with missing data

    European Patent Office | 2021

    Free access

    Traffic flow data missing repair system evaluation and strategy design method

    ZHANG WEIHUA / AN SUNG-CHUN / OU JISHUN | European Patent Office | 2023

    Free access

    Traffic flow data restoration method based on missing judgment of traffic flow data acquisition equipment

    WU YINFENG / DONG YINGYUE / GUAN YICHENG et al. | European Patent Office | 2024

    Free access