Traffic plays a key role in evaluating a country’s development. Urbanization, road construction, and vehicle numbers have increased worldwide, adding to the risk of accidents. Traffic accidents on freeways tend to cause more severe damage than accidents on other types of roads. Identifying collision hotspots on freeways is the first step to preventing crashes. In addition, governments need to allocate funding for safety legislation and supervision. Intelligent methods, such as smartphones, big data, and cloud computing, can be used for traffic safety, identifying hotspots by investigating traffic exposure, road attributes, and weather conditions. This paper analyzes the risk from aggressive driving behavior (ADB), including sudden accelerating, braking, and turning. Data is acquired from a Chinese smartphone application, Amap, owned by AutoNavi Software Company. A big amount of data is used by virtue of cloud computing technology. Results show the reliability of such algorithms to identify traffic accident hotspots on freeways.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Collision Hotspots Identification Based on Big Data about Aggressive Driving Behaviors


    Beteiligte:
    Bi, Chaofan (Autor:in) / Su, Yuelong (Autor:in) / Wang, Yujing (Autor:in) / Dong, Zhenning (Autor:in)

    Kongress:

    19th COTA International Conference of Transportation Professionals ; 2019 ; Nanjing, China


    Erschienen in:

    CICTP 2019 ; 3397-3409


    Erscheinungsdatum :

    02.07.2019




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Iterative DBSCAN (I-DBSCAN) to Identify Aggressive Driving Behaviors within Unlabeled Real-World Driving Data

    Marks, Charles / Jahangiri, Arash / Machiani, Sahar Ghanipoor | IEEE | 2019


    Identification of Autonomous Driving Volatility Hotspots on Urban Roads

    Lee, Hoyoon / Jee, Jeonghoon / Oh, Cheol et al. | IEEE | 2025