The invention provides a traffic flow prediction method and device fused with an autocorrelation mechanism. The prediction method comprises the following steps: acquiring a time sequence of traffic flow, and calculating an autocorrelation coefficient sequence of the time sequence; obtaining the first L + 1 peak values of the amplitude of the autocorrelation coefficient sequence, and taking L lag orders corresponding to the first L peak values not including the maximum peak value as periodic characteristics; splitting the time sequence based on each lagging order in the L lagging orders, and arranging a plurality of sub-sequences after splitting to obtain L original sequences; performing cyclic shift on each original sequence to obtain a plurality of rearranged sequences; taking each original sequence and the plurality of rearranged sequences as rows of a matrix, constructing L two-dimensional matrixes, and splicing the L two-dimensional matrixes to form a spliced matrix; and inputting the time sequence and the splicing matrix into a neural network model for training to obtain a trained target neural network model. The traffic flow prediction method provided by the invention can capture the periodic characteristics of the time sequence, and is high in prediction precision.

    本发明提供一种融合自相关机制的交通流预测方法、及装置。该预测方法包括:获取交通流的时间序列,并计算其自相关系数序列;获取自相关系数序列的幅值的前L+1个峰值,并将不包括最大峰值的前L个峰值对应的L个滞后阶数作为周期性特征;基于L个滞后阶数中的每个滞后阶数对时间序列进行拆分,将拆分后的多个子序列进行排列得到L个原始序列;对每个原始序列进行循环移位,获取多个重排序列;将每个原始序列和多个重排序列分别作为矩阵的行,构建得到L个二维矩阵,并拼接形成拼接矩阵;将时间序列和拼接矩阵输入神经网络模型进行训练,得到训练好的目标神经网络模型。本发明提供的交通流预测方法能够捕捉时间序列的周期性特征,预测精度高。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method and device fused with autocorrelation mechanism, and storage medium


    Additional title:

    融合自相关机制的交通流预测方法、装置及存储介质


    Contributors:
    ZHAO SHULI (author) / WANG WEIPING (author) / HE XUENING (author) / CHEN JINGYAO (author) / WU YONGJUN (author) / DENG TIANMIN (author) / ZHANG TESEN (author)

    Publication date :

    2024-04-26


    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



    Traffic flow prediction method and device and storage medium

    CAI XIAODONG / WANG XINLAN | European Patent Office | 2021

    Free access

    Traffic flow prediction method, equipment, storage medium and device

    LIU ZHEN / XIE DONGSHENG / LI MIN et al. | European Patent Office | 2023

    Free access

    Traffic flow prediction method and device, equipment and storage medium

    HAN XUAN / WANG WEI | European Patent Office | 2023

    Free access

    Traffic flow prediction method and device, equipment and storage medium

    WANG JUNBO / YUAN QING | European Patent Office | 2024

    Free access

    Traffic flow prediction method and device, equipment and storage medium

    LIU KAI / WANG JIAQIN / LI HANTAO et al. | European Patent Office | 2024

    Free access