The invention relates to a navigation reminding method for short-term traffic flow prediction based on IGWO-LSTM, which comprises the following steps: firstly training and optimizing an LSTM model, then when a prediction model is used, preprocessing collected historical traffic flow data, inputting the preprocessed data into the trained and optimized LSTM model, and outputting a short-term traffic flow prediction result by the LSTM model; and finally, publishing the prediction result of the short-time traffic flow on navigation software and displaying the prediction result in the road section in different colors according to the traffic flow, wherein the displayed information is used as congestion reference for a driver, and a travel is reasonably planned and a navigation route is selected according to the displayed information. When the LSTM model is trained and optimized, historical traffic flow data are collected, preprocessed and divided into a training set and a test set, and then the IGWO algorithm and the training set are adopted to train and optimize the LSTM model; and the preprocessing comprises interpolation and normalization processing of missing data. According to the method, the prediction effect is more accurate, and accurate navigation reminding is brought to a vehicle owner, so that a travel route is reasonably selected.

    本发明涉及一种基于IGWO‑LSTM的短时交通流预测的导航提醒方法,首先训练及优化LSTM模型,然后在使用预测模型时,将采集到的历史交通流数据经过预处理后,输入到训练及优化后的LSTM模型中,由其输出短时交通流的预测结果,最后将短时交通流的预测结果发布在导航软件上,并根据交通流量的大小以不同颜色展示在路段中,展示的信息供司机用于拥堵性参考,并以此合理规划出行,选择导航路线;训练及优化LSTM模型时,先采集历史交通流数据,并对其进行预处理后划分为训练集和测试集,再采用IGWO算法和训练集训练并优化LSTM模型;预处理包括缺失数据的插补及归一化处理。本发明的方法预测效果更精确,给车主带来准确的导航提醒,以便合理选择出行路线。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Navigation reminding method for short-term traffic flow prediction based on IGWO-LSTM


    Weitere Titelangaben:

    一种基于IGWO-LSTM的短时交通流预测的导航提醒方法


    Beteiligte:
    LI HONGLIANG (Autor:in) / MENG SITAO (Autor:in) / ZHOU WUNENG (Autor:in)

    Erscheinungsdatum :

    03.08.2021


    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




    Short-Term Traffic Flow Prediction: Using LSTM

    Poonia, Pregya / Jain, V. K. | IEEE | 2020


    Short-term traffic flow prediction method based on improved LSTM

    GAN YONGHUA / JIANG XUEFENG / HU JINGSONG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Short-term traffic flow prediction method based on Spearman-LSTM model

    ZANG JINGFENG / JIA QINGYANG / LIU SHUANGLIN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Short-term traffic flow prediction method based on Conv1D-LSTM model

    ZHANG ZHIPENG / LIU YUHANG / DAI LEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff