The invention provides a CNN-LSTM-based urban road average speed prediction method and system, and relates to the technical field of urban vehicle speed prediction.The CNN and LSTM models are combined, firstly, historical traffic data and historical weather data are collected and normalized, road space features and weather influence features are extracted through the two-channel CNN, and the road space features and the weather influence features are extracted through the two-channel CNN; the method comprises the steps that a weather influence feature matrix and a road space feature matrix are fused through a cross-modal attention mechanism to generate a fusion matrix, then an LSTM is constructed for training, the fusion matrix serves as input, the urban road average speed at the future moment serves as output, and effective prediction of the urban road average speed is achieved.

    本发明提供基于CNN‑LSTM的城市道路平均速度预测方法及系统,涉及城市车速预测技术领域,本发明结合CNN和LSTM模型,首先,采集并归一化历史交通数据和历史天气数据,利用双通道CNN提取道路空间特征和天气影响特征,通过跨模态注意力机制融合天气影响特征矩阵和道路空间特征矩阵生成融合矩阵,然后,构建LSTM进行训练,以融合矩阵作为输入,未来时刻的城市道路平均速度作为输出,实现对城市道路平均速度的有效预测。


    Access

    Download


    Export, share and cite



    Title :

    CNN-LSTM-based urban road average speed prediction method and system


    Additional title:

    基于CNN-LSTM的城市道路平均速度预测方法及系统


    Contributors:
    WANG XUEMEI (author) / ZHU HAIMIN (author) / ZHANG DONGMING (author) / GUO KUANG (author)

    Publication date :

    2024-11-29


    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 / 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



    Urban-Road Average-Speed Prediction Method Based on Graph Convolutional Networks

    Wang, Xuemei / Chen, Ying / Zhang, Jinlei | Transportation Research Record | 2023


    Research on Urban Road Mean Speed Prediction Method Based on LSTM-CNN Model

    Zhao, Ke / Yuan, Shaoxin / Wang, Zhuanzhuan et al. | IEEE | 2022


    Urban road vehicle speed prediction method

    FAN ZIDE / HUANG FEILONG / SUN YI et al. | European Patent Office | 2023

    Free access

    Road average passing time prediction method

    CUI ZHENYU / LIU YING / XIE WEIHONG et al. | European Patent Office | 2020

    Free access

    D-LSTM: Short-Term Road Traffic Speed Prediction Model Based on GPS Positioning Data

    Meng, Xianwei / Fu, Hao / Peng, Liqun et al. | IEEE | 2022