The invention discloses a short-time traffic volume prediction method based on an improved grey wolf algorithm. The method comprises the following steps: importing intersection data into an Oracle database from an urban intersection database, and carrying out the data preprocessing of the stored intersection data through NumPy and Pands; converting the data after data preprocessing into features and labels required by a supervised learning model; carrying out data standardization processing on the processed data by using deviation standardization; constructing a short-time traffic volume prediction model of the intersection based on a GRU neural network, inputting the standardized data into the model for training, and achieving the prediction of the traffic volume of the intersection at acertain moment in the future; and performing model optimization on the short-time traffic volume prediction model based on the improved grey wolf algorithm so that precision and stability can be enhanced. The method has the operation process of screening and selecting the intersection data, and by screening and selecting the intersection data, the accuracy of predicting the intersection traffic flow can be effectively improved.

    本发明公开的一种基于改进灰狼算法的短时交通量预测方法,包括如下步骤:从城市交叉路口数据库将交叉路口数据导入至Oracle数据库,通过NumPy、Pandas对存入的路口数据进行数据预处理;将数据预处理完成的数据转化为监督学习模型需要的特征与标签;使用离差标准化对处理后的数据进行数据标准化处理;基于GRU神经网络构建路口的短时交通量预测模型,将标准化数据输入模型进行训练,实现对未来某时刻交叉路口车流量的预测;基于改进灰狼算法对短时交通量预测模型进行模型优化,提高精度与稳定性。本发明具有对路口数据进行筛选和选择的操作过程,通过对路口数据的筛选和选择,本发明方法可有效提高对路口车流量预测的准确率。


    Access

    Download


    Export, share and cite



    Title :

    Short-term traffic volume prediction method based on improved grey wolf algorithm


    Additional title:

    一种基于改进灰狼算法的短时交通量预测方法


    Contributors:
    SHI QUAN (author) / DAI JUNMING (author) / CAO YANG (author) / SHEN QINQIN (author) / SU YONGJIE (author) / LI YUNBO (author)

    Publication date :

    2020-10-13


    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



    An improved method of short-term traffic prediction

    Hongfei, J. / Ming, T. / Zhongxiang, H. et al. | British Library Conference Proceedings | 2005




    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