The invention belongs to the technical field of traffic transportation, and particularly relates to a traffic prediction method based on multi-graph gating convolution and Conv-LSTM, which comprises the following steps: calculating the similarity between time sequences through a DTWN similarity value filling module, and taking K data average values with higher similarity to fill missing so as to ensure the integrity of traffic data. The method comprises the following steps: decomposing traffic data through DWT, and dividing the traffic data into an approximation coefficient and a detail coefficient; the approximation coefficient reflects the long-term trend of the traffic flow, the detail coefficient comprises short-term fluctuation information, and the data obtained by processing the DWT by combining and using different models. The detail coefficients are processed through multi-graph gating cavity convolution MGDCN to capture short-term fluctuation; the approximation coefficients are processed by Conv-LSTM to capture long term trends. Compared with an existing traffic prediction model, missing data can be fully filled, short-term fluctuation and long-term trend of traffic can be captured, errors in traffic prediction can be effectively reduced, and traffic prediction accuracy is improved.

    本发明属于交通运输技术领域,具体涉及一种基于多图门控卷积与Conv‑LSTM的交通预测方法,通过DTWN相似值填充模块计算时间序列之间的相似性,取K个相似性较高的数据平均值进行填充缺失,确保交通数据的完整性。通过DWT分解交通数据,将其分为近似系数和细节系数。近似系数反映了交通流量的长期趋势,而细节系数则包含了短期波动信息,通过结合使用不同的模型来处理DWT得到的数据。通过多图门控空洞卷积MGDCN处理细节系数来捕获短期波动;通过Conv‑LSTM处理近似系数来捕捉长期趋势。与现有交通预测模型相比,本发明能充分填补缺失数据,捕获交通的短期波动和长期趋势,能有效减少交通预测中的误差,提高交通预测准确性。


    Access

    Download


    Export, share and cite



    Title :

    Traffic prediction method based on multi-graph gating convolution and Conv-LSTM


    Additional title:

    一种基于多图门控卷积与Conv-LSTM的交通预测方法


    Contributors:
    ZHANG LINLIANG (author) / XU SHUYUN (author) / LI SHUO (author) / PAN LIHU (author) / YAO TAO (author) / GONG SU (author) / LIU ZHENXING (author) / LUO JIANBAO (author) / WANG NING (author) / LUO HAOYANG (author)

    Publication date :

    2025-03-25


    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



    Instant traffic flow prediction method based on Conv-LSTM

    WU LIJUN | European Patent Office | 2023

    Free access


    Conv-Bi-LSTM model-based ship heaving motion prediction system and prediction method

    ZHANG YA / FAN SHIWEI / PING BAOJIN et al. | European Patent Office | 2023

    Free access