The invention discloses a short-term traffic flow prediction method based on a CASSA-LSTM algorithm, and the method comprises the following steps: S1, selecting historical traffic flow data as a data set, and dividing the data set into a training set and a test set; s2, data preprocessing: extracting time data in the table, if the data after statistics is interrupted, performing value compensation by using an averaging method, and then performing normalized compression on a data set; s3, a chaotic sequence generated by chaotic mapping is used for updating the position of a population leader, and a nonlinear decreasing adaptive inertia weight method is added in a follower formula to improve precision and obtain an optimization algorithm CASSA of SSA; s4, taking parameters of the LSTM neural network model as optimization objects of a CASSA algorithm, taking a mean square error value of the model on a test set as a fitness value, and according to the mean square error value, using a position updating formula by the CASSA to obtain optimal parameters; and S5, obtaining an optimal model of the CASSA-LSTM neural network, and predicting the traffic flow according to the optimal model. According to the invention, the short-time traffic flow prediction precision can be improved.

    本发明公开了一种基于CASSA‑LSTM算法的短时交通流预测方法,包括以下步骤:S1:选取历史车流量数据作为数据集,并对数据集划分训练集和测试集;S2:数据预处理:提取表中的时间数据,若统计后的数据出现间断的现象,就用均值法进行补值,然后对数据集进行归一化压缩;S3:使用混沌映射产生的混沌序列用于更新种群领导者的位置,并在追随者公式中加入了非线性递减自适应惯性权重方法提高精度得到SSA的优化算法CASSA;S4:将LSTM神经网络模型的参数作为CASSA算法的优化对象,以模型在测试集上的均方误差值作为适应度值,根据均方误差值,CASSA利用位置更新公式得到最优的参数;S5:得到CASSA‑LSTM神经网络的最优模型,根据最优模型对车流量进行预测。本发明能够提高短时交通流预测精度。


    Access

    Download


    Export, share and cite



    Title :

    Short-term traffic flow prediction method based on CASSA-LSTM algorithm


    Additional title:

    一种基于CASSA-LSTM算法的短时交通流预测方法


    Contributors:
    PENG YU'ANG (author) / YANG XIAOJIAN (author) / CHEN XUEYUAN (author) / HE SHUHUA (author) / DING HUI (author)

    Publication date :

    2022-08-30


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    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 / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    LSTM short-term traffic flow prediction method based on improved PSO algorithm

    JING GUOSHENG / ZHOU ZHIHUA / ZHANG WEI et al. | European Patent Office | 2021

    Free access

    Short-term traffic flow prediction method based on improved LSTM

    GAN YONGHUA / JIANG XUEFENG / HU JINGSONG et al. | European Patent Office | 2021

    Free access

    Expressway Short-Term Traffic Flow Prediction Based on CNN-LSTM

    Ye, Ting / Zou, Fumin / Guo, Feng | Springer Verlag | 2024


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

    ZHANG ZHIPENG / LIU YUHANG / DAI LEI et al. | European Patent Office | 2023

    Free access

    Application of LSTM in Short-term Traffic Flow Prediction

    Kang, Chuanli / Zhang, Zhenyu | IEEE | 2020