Highlights We explored the spatio-temporal evolution of urban traffic accidents and established models for urban traffic accident predictions using spatio-termporal deep learning techniques. The proposed SST-DHL outperforms SVM, ConvLSTM, ST-Transformer, DCRNN, ASTGCN and AdapGL in both numerical indicators and predictive performance. Demonstrated stable predictive capabilities across diverse, sparse datasets, including multi-time scale, heterogeneous traffic accident data from New York City and London. Our proposed dynamic hypergraph structure enhances the interpretability of deep learning models and captures the high-order spatial correlations of urban traffic accidents.

    Abstract Traffic accidents have emerged as one of the most public health safety matters, raising concerns from both the public and urban administrators. The ability to accurately predict traffic accident not only supports the governmental decision-making in advance but also enhances public confidence in safety measures. However, the efficacy of traditional spatio-temporal prediction models are compromised by the skewed distributions and sparse labeling of accident data. To this end, we propose a Sparse Spatio-Temporal Dynamic Hypergraph Learning (SST-DHL) framework that captures higher-order dependencies in sparse traffic accidents by combining hypergraph learning and self-supervised learning. The SST-DHL model incorporates a multi-view spatiotemporal convolution block to capture local correlations and semantics of traffic accidents, a cross-regional dynamic hypergraph learning model to identify global spatiotemporal dependencies, and a two-supervised self-learning paradigm to capture both local and global spatiotemporal patterns. Through experimentation on New York City and London accident datasets, we demonstrate that our proposed SST-DHL exhibits significant improvements compared to optimal baseline models at different sparsity levels. Additionally, it offers enhanced interpretability of results by elucidating complex spatio-temporal dependencies among various traffic accident instances. Our study demonstrates the effectiveness of the SST-DHL framework in accurately predicting traffic accidents, thereby enhancing public safety and trust.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Advancing urban traffic accident forecasting through sparse spatio-temporal dynamic learning


    Beteiligte:
    Cui, Pengfei (Autor:in) / Yang, Xiaobao (Autor:in) / Abdel-Aty, Mohamed (Autor:in) / Zhang, Jinlei (Autor:in) / Yan, Xuedong (Autor:in)


    Erscheinungsdatum :

    2024-03-29




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch






    Short-Term Forecasting of Urban Traffic Using Spatio-Temporal Markov Field

    Furtlehner, Cyril / Lasgouttes, Jean-Marc / Attanasi, Alessandro et al. | IEEE | 2022


    Han Ning Highway Traffic Accident Spatio-Temporal Analysis

    Wang, Chen ;Du, Kai ;Jin, Yin Li | Trans Tech Publications | 2011


    Han Ning Highway Traffic Accident Spatio-Temporal Analysis

    Wang, Chen / Du, Kai / Jin, Yin-Li et al. | Tema Archiv | 2011