Large-scale network traffic analysis is crucial for many transport applications, ranging from estimation and prediction to control and planning. One of the key issues is how to integrate spatial and temporal analyses efficiently. Deep Learning is gaining momentum as a go-to approach for artificial vision, and transfer learning approaches allow to exploit pretrained models and apply them to new domains. In this paper, we encode traffic states as images and use a pretrained deep convolutional neural network as a feature extractor. Experimental results show how the extracted feature vectors cluster naturally into meaningful network traffic states and illustrate how these network states can be used for traffic state prediction.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Understanding Network Traffic States using Transfer Learning


    Beteiligte:
    Krishnakumari, Panchamy (Autor:in) / Perotti, Alan (Autor:in) / Pinto, Viviana (Autor:in) / Cats, Oded (Autor:in) / van Lint, Hans (Autor:in)


    Erscheinungsdatum :

    01.11.2018


    Format / Umfang :

    719140 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Cross-Domain Traffic Scene Understanding: A Dense Correspondence-Based Transfer Learning Approach

    Di, Shuai / Zhang, Honggang / Li, Chun-Guang et al. | IEEE | 2018



    Mining Dynamic Network-Wide Traffic States

    Paz, Alexander / Gaviria, Carlos / Arteaga, Cristian et al. | IEEE | 2018


    Comparing Deep Neural Network Architectures using Transfer Learning to Predict Cognitive States

    Nicholas J. Napoli / Mudit Paliwal / Victoria R. Rodrigues et al. | NTRS