Recently the research of traffic flow prediction with deep learning framework has be largely developed, whereas most current methods are still faced with the following shortcomings. For spatial feature extraction, studies have shown that both local and non-local correlations exist on traffic networks. Considering the temporal dependencies, short-term impending and longer periodic components are two most critical patterns of traffic data, which further provide different information for the prediction task. Furthermore, multi-source heterogeneous external data, which naturally holds semantic gap with traffic data, also have impact on traffic flow. To solve the above problems, this paper proposes an AutoMSNet (Multi-Source Spatio-Temporal Network via Automatic neural architecture search). The AutoMSNet is composed of an encoder-decoder structure. The encoder takes neighboring data as inputs, while the decoder captures long-term periodic patterns. Thus, different functions of two temporal features are simultaneously extracted. Moreover, a neural architecture search space is designed for spatial feature extraction. Through architecture search technique, graph convolutions with different receptive fields are automatically selected and combined to form an optimal module structure. Therefore, both local and non-local spatial features can be adaptively captured. Besides, a meta learning feature fusion strategy is proposed to integrate external data, which can alleviate the semantic gap between different data sources. Extensive experiments on three real-world traffic datasets evaluate the superiority of the proposed model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction


    Beteiligte:
    Fang, Shen (Autor:in) / Zhang, Chunxia (Autor:in) / Xiang, Shiming (Autor:in) / Pan, Chunhong (Autor:in)


    Erscheinungsdatum :

    01.03.2023


    Format / Umfang :

    3335216 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    MS-Net: Multi-Source Spatio-Temporal Network for Traffic Flow Prediction

    Fang, Shen / Prinet, Veronique / Chang, Jianlong et al. | IEEE | 2022


    Deep Spatio-Temporal Convolutional Neural Network for City Traffic Flow Prediction

    Zhou, Zhiyuan / Qin, Yanjun / Luo, Haiyong | IEEE | 2021


    Predicting Multiple Traffic Features using a Spatio-Temporal Neural Network Architecture

    Ichim, Bogdan / Iordache, Florin | TIBKAT | 2022

    Freier Zugriff

    Spatio-Temporal AutoEncoder for Traffic Flow Prediction

    Liu, Mingzhe / Zhu, Tongyu / Ye, Junchen et al. | IEEE | 2023


    Global spatio‐temporal dynamic capturing network‐based traffic flow prediction

    Haoran Sun / Yanling Wei / Xueliang Huang et al. | DOAJ | 2023

    Freier Zugriff