A traffic flow prediction method based on multi-feature extraction and fusion obtains an accurate traffic flow prediction model by analyzing historical traffic flow data, thereby achieving the purpose of traffic flow prediction. According to the method, nonlinear features in traffic flow data are extracted by using a related convolutional network, spatial features are extracted by means of Transform, and time features are extracted by means of an LSTM network; a Kalman filter is used for extracting linear features, a difference value between a prediction result obtained by nonlinear features and a true value is used as input of a Kalman filtering model, the Kalman filtering model is constructed, linear features are obtained, and finally, a nonlinear prediction result and a linear prediction result are fused to obtain a final result. According to the method, the defect of feature extraction by means of RNN and CNN networks is overcome, and better prediction accuracy is achieved.

    一种基于多特征提取及融合的交通流预测方法,通过对历史交通流数据进行分析得到一个准确的交通流预测模型,从而达到实现交通流预测的目的。本发明利用相关卷积网络来提取交通流数据中的非线性特征,借助Transformer来提取空间特征,借助LSTM网络来提取时间特征;利用卡尔曼滤波器来提取线性特征,将非线性特征得到的预测结果与真值的差值作为卡尔曼滤波模型的输入,构造一个卡尔曼滤波模型,得到线性特征,并且最终融合非线性预测结果与线性预测结果得到最终结果。本方法克服了借助RNN、CNN网络提取特征时的缺点,达到了更好的预测准确性。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method based on multi-feature extraction and fusion


    Additional title:

    一种基于多特征提取及融合的交通流预测方法


    Contributors:
    TANG YUNXIAO (author) / LI DINGCHENG (author) / LIN ZE (author)

    Publication date :

    2024-04-12


    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 / 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



    Traffic flow prediction method based on multi-feature fusion

    LIU CONG'AI / QIN YUHUA / ZHANG XIAOJING | European Patent Office | 2024

    Free access

    Multi-modal traffic flow prediction method based on multi-source data feature fusion

    CHEN LULU / LI SHIJIE / JIANG HUAIGUANG et al. | European Patent Office | 2025

    Free access

    Traffic flow prediction method of multi-network feature random fusion based on residual connection

    MAO ZHAOYONG / WANG YICHEN / SHEN JUNGE et al. | European Patent Office | 2023

    Free access

    A Traffic Prediction Model Based on Multi Stream Feature Fusion

    Musike, Mahipal Reddy / Tiwari, Rajesh / Shrivastava, Rajeev | Springer Verlag | 2024


    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