This paper introduces a novel deep learning architecture for identifying outliers in the context of intelligent transportation systems. The use of a convolutional neural network with decomposition is explored to find abnormal behavior in maritime data. The set of maritime data is first decomposed into similar clusters containing homogeneous data, and then a convolutional neural network is used for each data cluster. Different models are trained (one per cluster), and each model is learned from highly correlated data. Finally, the results of the models are merged using a simple but efficient fusion strategy. To verify the performance of the proposed framework, intensive experiments were conducted on marine data. The results show the superiority of the proposed framework compared to the baseline solutions in terms of several accuracy metrics.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Intelligent Deep Fusion Network for Anomaly Identification in Maritime Transportation Systems


    Beteiligte:


    Erscheinungsdatum :

    01.02.2023


    Format / Umfang :

    841463 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Intelligent guidance in collision avoidance of maritime transportation

    Perera, L. P. / Carvalho, J. P. / Soares, C. Guedes | TIBKAT | 2012


    Maritime Transportation System Safety – Modeling and Identification

    Przemyslaw Dziula / Krzysztof Kolowrocki / Joanna Soszynska-Budny | DOAJ | 2013

    Freier Zugriff

    Maritime transportation

    International Conference on Maritime Transport | TIBKAT | 2020