The invention relates to the technical field of traffic flow prediction, in particular to a traffic flow prediction method for a space-time diagram auto-encoder. Comprising the steps of 1, smoothing given traffic flow sample data by using an improved HA-RTS algorithm; step 2, encoding the traffic flow sample data processed in the step 1 by an Encode layer, wherein the encoding means that each module outputs input data as hidden features containing prediction information through parameter learning; and step 3, decoding the hidden features obtained in the Encode layer in the step 2 into a predicted value by a Decode layer constructed by a multi-layer attention network module, a memory gating convolution module and a full connection layer, thereby obtaining a traffic flow prediction result. According to the method, the multi-layer attention neural network and the gated memory convolutional neural network are integrated, and the influence of observation noise in model training is removed. The accuracy and robustness of traffic flow prediction are effectively improved, and the problem that traffic flow time-space dependence modeling is complex and difficult is solved.

    本发明涉及交通流量预测技术领域,具体地涉及一种面向时空图自编码器的交通流量预测方法。包括:步骤1:使用改进的HA‑RTS算法平滑处理给定的交通流样本数据;步骤2:由Encode层对步骤1处理的交通流样本数据进行编码,编码是指各模块通过参数学习将输入数据输出为包含了预测信息的隐藏特征;步骤3:由多层注意力网络模块、记忆门控卷积模块和全连接层构建的Decode层对步骤2的Encode层中得到的隐藏特征解码为预测值,由此得到交通流量预测结果。本发明集成了多层注意力神经网络和门控记忆卷积神经网络,并去除了模型训练中所受观测噪声影响。有效地提高交通流量预测的准确性和鲁棒性,解决了交通流时空依赖性建模复杂困难的问题。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method for space-time diagram auto-encoder


    Additional title:

    一种面向时空图自编码器的交通流量预测方法


    Contributors:
    XIA DAWEN (author) / BAI DEWEI (author) / LI HUAQING (author) / HUANG DAN (author) / ZHANG WENYONG (author) / SHEN BINGQI (author) / HUO YUJIA (author) / GENG JIAN (author) / XU HAILONG (author) / WU JING (author)

    Publication date :

    2023-03-28


    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



    Traffic flow prediction method of space-time diagram convolutional network

    TENG FEI / WANG ZIDAN / QIAO LU et al. | European Patent Office | 2024

    Free access

    Traffic flow prediction method based on space-time diagram transfer learning

    LI YUN / GAO YA / YAO ZHIXIU et al. | European Patent Office | 2023

    Free access

    Traffic flow prediction method based on space-time diagram convolutional network

    JIANG YUNLIANG / XIA RENHUAN / ZHANG XIONGTAO et al. | European Patent Office | 2022

    Free access

    Traffic flow prediction method based on space-time diagram convolutional network

    JIANG CONG / SONG YUN / DENG ZELIN et al. | European Patent Office | 2023

    Free access

    Traffic flow prediction method based on Transform space-time diagram convolutional network

    ZHENG LINJIANG / CHEN YILING / LIU WEINING et al. | European Patent Office | 2022

    Free access