Traffic hazardous events seriously threaten human lives. Effectively predicting a hazardous event can improve traffic safety and decrease traffic incidents. We have investigated data from 30 commercial drivers in Shanghai from 2014 to 2015. We have selected time windows corresponding to the traffic incidents, and labeled the data based on parameters from multiple vehicle sensors. Then, we divided the data into training data and validation data. Some classical models have been applied in modeling, prediction, analysis, and interpretation of the traffic risk. The experimental results indicate that the vehicle parameters have appreciable influences on the criticality of a traffic incident. The model with high accuracy rate of prediction has been validated and evaluated based on the validation data and the frequently-used indexes. As a conclusion, the proposed model could contribute to effective early warning of hazardous events during driving.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Predicting Traffic Hazardous Events Based on Naturalistic Driving Data


    Beteiligte:
    Sun, Ping (Autor:in) / Gao, Junhao (Autor:in) / Fan, Hongfei (Autor:in) / Wang, Xuesong (Autor:in)

    Kongress:

    18th COTA International Conference of Transportation Professionals ; 2018 ; Beijing, China


    Erschienen in:

    CICTP 2018 ; 1866-1874


    Erscheinungsdatum :

    2018-07-02




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch






    Screening Naturalistic Driving Study Data for Safety-Critical Events

    Wu, Kun-Feng / Jovanis, Paul P. | Transportation Research Record | 2013