The invention belongs to the technical field of traffic, and particularly relates to a multi-scale traffic flow prediction model and method based on contextual feature injection. A traditional trafficflow prediction method has certain one-sidedness, and a good effect cannot be achieved in prediction precision and stability degree. The invention provides a multi-scale traffic flow prediction modelbased on contextual feature injection. The model sequentially comprises an input layer, a learning layer, an injection fusion layer and an output layer, wherein the learning layer comprises a deep recurrent neural network layer and a deep belief network layer, the input layer, the deep recurrent neural network layer and the injection fusion layer are arranged in sequence, and the input layer, thedeep belief network layer and the injection fusion layer are arranged in sequence. By injecting the contextual features into the time sequence features, the accuracy of an existing traffic flow prediction model is improved, and comprehensive simulation, evaluation and prediction of a traffic flow mode are achieved.

    本申请属于交通技术领域,特别是涉及一种语境特征注入的多尺度交通流预测模型及方法。传统的交通流预测方法具有一定的片面性,在预测精度和稳定程度上不能达到很好的效果。本申请提供了一种语境特征注入的多尺度交通流预测模型,所述模型依次包括输入层,学习层、注入融合层和输出层,所述学习层包括深度循环神经网络分层和深度置信网络分层,所述输入层、所述深度循环神经网络分层和所述注入融合层依次排列,所述输入层、所述深度置信网络分层和所述注入融合层依次排列。通过将语境特征注入到时间序列特征之中,提高现有交通流预测模型的准确率,实现对交通流模式全面地仿真、评估和预测。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Multi-scale traffic flow prediction model and method based on contextual feature injection


    Weitere Titelangaben:

    一种语境特征注入的多尺度交通流预测模型及方法


    Beteiligte:
    QU LICHENG (Autor:in) / LYU JIAO (Autor:in) / WANG HAIFEI (Autor:in) / QU YIHUA (Autor:in) / ZHANG MINGHAO (Autor:in) / LI XIANG (Autor:in) / LI ZHAOLU (Autor:in) / ZHANG ZHUANGZHUANG (Autor:in)

    Erscheinungsdatum :

    11.08.2020


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Traffic flow prediction method based on multi-scale spatial feature mining

    SONG YUN / BAI XINKE / DENG ZELIN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method based on multi-feature fusion

    LIU CONG'AI / QIN YUHUA / ZHANG XIAOJING | Europäisches Patentamt | 2024

    Freier Zugriff

    Traffic flow prediction method based on multi-feature extraction and fusion

    TANG YUNXIAO / LI DINGCHENG / LIN ZE | Europäisches Patentamt | 2024

    Freier Zugriff

    Multi-modal traffic flow prediction method based on multi-source data feature fusion

    CHEN LULU / LI SHIJIE / JIANG HUAIGUANG et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    A Traffic Prediction Model Based on Multi Stream Feature Fusion

    Musike, Mahipal Reddy / Tiwari, Rajesh / Shrivastava, Rajeev | Springer Verlag | 2024