Short-term urban traffic prediction is of great importance to improve travel and material transportation efficiency. It provides the basis of navigation planning, traffic configuration, and traffic management. The early traffic prediction methods are mainly based on machine learning methods. Due to the popularization of big data technology and the Internet of Things technology, the current traffic prediction method mainly leverages deep learning methods. However, deep learning methods have many choices for short-term traffic city prediction. There is no research to show which deep learning method is suitable for short-term urban traffic prediction. We conducted a systematic map study on 29 papers selected in the short-term urban traffic prediction in the past five years. And analyzed which deep learning methods can be applied to short-term urban traffic forecasting, and find out which methods are more suitable for traffic forecasting, and finally discuss the development trend of traffic prediction methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Short-term urban traffic prediction based on deep learning: A systematic map


    Beteiligte:
    Chen, Mingong (Autor:in) / Huang, Yuxiang (Autor:in) / Liang, Zhihong (Autor:in) / Qin, Mingming (Autor:in) / Guo, Zhichang (Autor:in) / Zhong, Cong (Autor:in)


    Erscheinungsdatum :

    22.11.2021


    Format / Umfang :

    19538456 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Short-Term Traffic Prediction Based on Deep Learning

    Huang, Ming-Xia / Li, Wen-Tao / Wang, Lu et al. | ASCE | 2020


    Short Term Traffic Flow Prediction Based on Deep Learning

    Li, JiaWen / Wang, JingSheng | ASCE | 2019


    Deep Learning for Short-Term Traffic Flow Prediction

    Polson, Nicholas | Online Contents | 2016



    Short-term traffic flow prediction method based on deep learning

    XIAO HONGBO / XIAO JIANHUA / DING LIMING et al. | Europäisches Patentamt | 2025

    Freier Zugriff