The invention provides a traffic flow time sequence prediction method based on double-domain normalization, which comprises the following steps of: dynamically capturing the distribution change of traffic flow data through normalization in a time domain and a frequency domain at the same time, eliminating non-stationary factors in time sequence data, performing prediction by utilizing a distribution prediction model, and performing a normalization removal process, so that the traffic flow time sequence prediction accuracy is improved. According to the method, the non-stationary information of the original data is reconstructed, and the prediction result can accurately reflect the non-stationary characteristics of the original data, so that the reliability and robustness of the prediction result are ensured, and the accuracy and stability of traffic flow time sequence prediction are remarkably improved. Specifically, frequency domain normalization decomposes a time sequence into high-frequency and low-frequency components to capture fast change and mutation information; the time domain normalization is to calculate local statistics, such as a mean value and a standard deviation, so as to dynamically reflect the rapid change of a time sequence. According to the method, the traffic flow prediction performance is remarkably improved, and superiority is shown in traffic flow prediction application.

    本发明提出一种基于双域归一化的交通流时间序列预测方法,通过同时在时间域和频率域内的归一化,动态捕捉交通流数据的分布变化,消除时间序列数据中的非平稳因素,然后利用分布预测模型进行预测,再进行去归一化过程,重构其非平稳信息,确保了预测结果能准确反映原始数据的非平稳性特征,从而保证了预测结果的可靠性与鲁棒性,显著提升了交通流时间序列预测的准确性和稳定性。具体而言,频率域归一化将时间序列分解为高频和低频成分,以捕捉快速变化和突变信息;时间域归一化则计算局部统计量,如均值和标准差,从而动态反映时间序列的快速变化。本发明方法显著提高了交通流预测性能,在交通流预测应用中展现出优越性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow time sequence prediction method based on double-domain normalization


    Weitere Titelangaben:

    一种基于双域归一化的交通流时间序列预测方法


    Beteiligte:
    LI NAIQI (Autor:in) / LIU PEIYUAN (Autor:in) / BAO JIGANG (Autor:in) / JIANG YONG (Autor:in) / XIA SHUTAO (Autor:in)

    Erscheinungsdatum :

    11.10.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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



    Traffic flow prediction method based on space-time sequence

    XIAO JUNBI / LIU TINGTING | Europäisches Patentamt | 2025

    Freier Zugriff

    Traffic flow prediction method based on group normalization and gridding cooperation

    BAO JIANMIN / ZHAI YINGMING / DING FEI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    CEEMDAN-RF-LSTM-based traffic flow time sequence data prediction method and system

    ZHOU ZHAOBIN / WANG HUIQING / CHEN ZHIDE et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Long-time-sequence traffic flow prediction method based on graph convolution-Informer model

    GUO ZIQIANG / CHENG BAOXI / YANG XIAOLEI et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Ship traffic flow long sequence space-time prediction method based on ST-Informer

    JIANG BAODE / LUO HAIYAN / JIANG YING | Europäisches Patentamt | 2023

    Freier Zugriff