The invention discloses a short traffic flow prediction method based on an ARIMA and LSTM hybrid neural network, and the method comprises the steps: respectively collecting original traffic flow datafrom an initial time period to a t time period, determining a differential order d, an autoregression order p and a movement regression order q in an ARIMA model, obtaining an ARIMA(p, d, q) model ofa calibration parameter, and training the ARIMA (p, d, q) model by using the original traffic flow sequence from the initial time period to the t time period to obtain preliminary prediction flow dataof the t time period, and extracting AR(p) part data and MA(q) part data from the trained ARIMA(p, d, q) model, training an ARIMA-LSTM hybrid neural network model by taking the AR (p) partial data and MA (q) partial data of the preliminary prediction stream data of the t period as input and taking a traffic stream data true value of the t period as output to obtain a prediction model; and obtaining the prediction input data of the prediction time period, inputting the prediction input data into the prediction model, obtaining the prediction traffic flow data of the prediction time period, sothat the accuracy of the obtained prediction traffic flow data is high.

    本发明公开了一种基于ARIMA和LSTM混合神经网络的短交通流预测方法,分别采集初始时段至t时段的原始交通流数据,确定ARIMA模型中差分阶数d,自回归阶数p和移动回归阶数q,得到标定参数的ARIMA(p,d,q)模型,使用初始时段至t时段的原始交通流序列训练ARIMA(p,d,q)模型,得到t时段的初步预测流数据从训练后的ARIMA(p,d,q)模型中提取AR(p)部分数据和MA(q)部分数据,以t时段的初步预测流数据AR(p)部分数据和MA(q)部分数据作为输入,以t时段的交通流数据真实值作为输出训练ARIMA‑LSTM混合神经网络模型,得到预测模型,获取预测时段的预测输入数据,将预测输入数据输入所述预测模型,得到预测时段的预测交通流数据,所得到的预测交通流数据准确性高。


    Access

    Download


    Export, share and cite



    Title :

    Short traffic flow prediction method based on ARIMA and LSTM hybrid neural network


    Additional title:

    基于ARIMA和LSTM混合神经网络的短交通流预测方法


    Contributors:
    WANG WEI (author) / ZHOU WEI (author) / HUA XUEDONG (author) / QIN SHAOYANG (author)

    Publication date :

    2021-03-19


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Short-term traffic flow prediction with LSTM recurrent neural network

    Kang, Danqing / Lv, Yisheng / Chen, Yuan-yuan | IEEE | 2017



    Prediction of ship track based on ARIMA-LSTM

    Yu, Chen / Fu, Yuhui | SPIE | 2022


    Short-Time Traffic Flow Prediction with ARIMA-GARCH Model

    Chen, C. / Hu, J. / Meng, Q. et al. | British Library Conference Proceedings | 2011


    Prediction of ship track based on ARIMA-LSTM

    Yu, Chen / Fu, Yuhui | British Library Conference Proceedings | 2022