Route choice model is important for Intelligent Transportation Systems. The most commonly used route choice models include seminal logit models and their extension re-cursive logit model. The advantage of these models is their interpretable parameters and thus useful for policy making. Recently, more accurate models have been proposed by using data-driven approaches such as deep neural networks, however, they generally lacks interpretabllity. In this study, we proposed a hybrid model of recursive logit model and Directed Graph Neural Network which has the advantage of interpletable pa-rameters as well as high accuracy of capturing complicated data in road network. Applying the model to actual travel trajectory data in Tokyo, our proposed model shows higher prediction accuracy compared to recursive logit model and a Residual Neural Network-based Recursive logit model. Moreover, the prediction accuracy and the interpretability can be balanced arbitrarily by adjusting the penalty coefficient.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Incorporating Graph Neural Network into Route Choice Model in Road Network


    Beteiligte:
    Yuxun, Ma (Autor:in) / Toru, Seo (Autor:in)


    Erscheinungsdatum :

    24.09.2024


    Format / Umfang :

    1167950 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Incorporating bounded rationality concept into route choice model for transportation network analysis

    Hato, E. / Asakura, Y. / Association for European Transport | British Library Conference Proceedings | 2000



    Improvement of Road Network Reliability Under Different Route Choice Principles

    Nakagawa, S. / Wakabayashi, H. / Iida, Y. et al. | British Library Conference Proceedings | 1996