The invention discloses a traffic flow prediction method based on a Fourier-recursive neural network. The method comprises the following steps of: (1) preprocessing traffic flow data; (2) setting a window sliding distance S and a window size T, setting a window function G, and segmenting traffic flow historical data; (3) performing short-time Fourier transform on each section of traffic flow historical data, and converting the traffic flow historical data from a time domain to a frequency domain; (4) building a recursive neural network model, and inputting a traffic flow historical data sampleinto the model for training; (5) judging whether the number of training times reaches the maximum number of training times or not; and (6) calculating a traffic flow prediction result according to the trained Fourier-recursive neural network model. The method is more accurate in long-time prediction of traffic flow data with periodicity rules, and still has better performance when the sequence islonger and the data volume is larger.

    本发明公开了一种基于傅里叶递归神经网络的交通流预测方法,包括以下步骤:(1)对交通流数据进行预处理;(2)设置窗口滑动距离S、窗口大小T、设置窗口函数G,将交通流历史数据分段;(3)对每段交通流历史数据进行短时傅里叶变换,从时间域转变换到频率域;(4)搭建递归神经网络模型,将交通流历史数据样本输入模型进行训练;(5)判断训练次数是否达到最大训练次数;(6)根据训练得到的傅里叶‑递归神经网络模型,计算交通流预测结果。本发明对于具有周期性规律的交通流数据的长时间预测更加准确,当序列较长、数据量较大时仍有较好的表现。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method based on Fourier-recursive neural network


    Additional title:

    一种基于傅里叶-递归神经网络的交通流预测方法


    Contributors:
    WANG CUN (author) / DONG XIAOFEI (author)

    Publication date :

    2020-07-28


    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



    Recursive Prediction of Traffic Conditions with Neural Network Models

    Zhang, H. M. | British Library Online Contents | 2000



    Traffic flow prediction method based on neural network

    GUO TANGYI / DENG HONG / YANG YONG et al. | European Patent Office | 2020

    Free access

    Traffic flow prediction method based on graph neural network

    PENG LAIHU / WU BAOWEN / QI YUBAO et al. | European Patent Office | 2024

    Free access

    Traffic flow prediction method based on space-time neural network

    YANG YU / GUO GUIBING | European Patent Office | 2024

    Free access