Abstract Extracting meaningful information from noisy high-dimensional data is attracting increasing attention as richer and higher resolution data is being collected and used for transportation system planning and management purposes. Discovering critical information via effective data representation learning not only helps reduce data dimension, it also enables a deeper understanding of the underlying properties of noisy data, which could then lead to better planning and operations decisions. In this study, we present a new perspective that, unlike most existing approaches in the general data science literature, the design of data representation should go beyond the data itself; it should incorporate an understanding of how the data is used in the domain-specific applications. We further argue that this design philosophy is particularly important for transportation data because of the high spatial correlations of transportation data brought by network interdependence. We propose a usage-aware representation learning framework by incorporating the information loss for downstream application into the data encoding-decoding process. The proposed approach is formulated as a Stiefel manifold optimization problem. The effectiveness of the proposed framework is demonstrated in two network applications: modeling transportation network flows and estimating network-level vehicular emissions. The performance of the learned representation from our approach is compared with existing approaches using multiple evaluation context, including data reconstruction quality, clustering, anomaly detection, and critical information identification, through case studies implemented in Sioux Falls, Boston, and San Jose networks. The good performance of our approach consistently observed in those experiments indicates the importance of incorporating the downstream data usage in the process of data representation learning.

    Highlights A usage-aware representation learning framework in transportation networks. Learning representations via optimizatin on manifold. Data reconstruction and anomaly detection capabilities in transportation network analysis. Network-level vehicular emission estimation through learned representations.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Usage-aware representation learning for critical information identification in transportation networks


    Beteiligte:
    Sun, Ran (Autor:in) / Fan, Yueyue (Autor:in)


    Erscheinungsdatum :

    2024-02-21




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Identification Methods of Critical Combination of Vulnerable Links in Transportation Networks

    Li, Lin / Ma, Jie / Li, Dawei | British Library Conference Proceedings | 2019




    Context-Aware Machine Learning for Intelligent Transportation Systems: A Survey

    Huang, Guang-Li / Zaslavsky, Arkady / Loke, Seng W. et al. | IEEE | 2023


    Identification of critical combination of vulnerable links in transportation networks – a global optimisation approach

    Wang, David Z. W. / Liu, Haoxiang / Szeto, W. Y. et al. | Taylor & Francis Verlag | 2016