Abstract Traffic crashes typically occur in a few seconds and real-time prediction can significantly benefit traffic safety management and the development of safety countermeasures. This paper presents a novel deep learning model for crash identification based on high-frequency, high-resolution continuous driving data. The method consists of feature engineering based on Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) and classification based on Extreme Gradient Boosting (XGBoost). The CNN-GRU architecture captures the time series characteristics of driving kinematics data. Compared to normal driving segments, safety-critical events (SCEs)—i.e., crashes and near-crashes (CNC)—are rare. The weighted categorical cross-entropy loss and oversampling methods are utilized to address this imbalance issue. An XGBoost classifier is utilized instead of the multi-layer perceptron (MLP) to achieve a high precision and recall rate. The proposed approach is applied to the Second Strategic Highway Research Program Naturalistic Driving Study (SHRP 2 NDS) data with 1,820 crashes, 6,848 near-crashes, and 59,997 normal driving segments. The results show that in a 3-class classification system (crash, near-crash, normal driving segments), the accuracy for the overall model is 97.5%, and the precision and recall for crashes are 84.7%, and 71.3% respectively, which is substantially better than benchmarks models. Furthermore, the recall of the most severe crashes is 98.0%. The proposed crash identification approach provides an accurate, highly efficient, and scalable way to identify crashes based on high frequency, high-resolution continuous driving data and has broad application prospects in traffic safety applications.

    Highlights Identify crashes and near-crashes using high-frequency kinematic driving data Use CNN-GRU DL architecture to catch the key features of crashes and near-crashes Use XGBoost to mitigate the class-weighted risk and sample selection bias issues Application to SHRP2 NDS showed distinct features and high prediction power


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Real-time driving risk assessment using deep learning with XGBoost


    Beteiligte:
    Shi, Liang (Autor:in) / Qian, Chen (Autor:in) / Guo, Feng (Autor:in)


    Erscheinungsdatum :

    2022-09-12




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    A feature learning approach based on XGBoost for driving assessment and risk prediction

    Shi, Xiupeng / Wong, Yiik Diew / Li, Michael Zhi-Feng et al. | Elsevier | 2019



    Real‐time detection of distracted driving based on deep learning

    Tran, Duy / Manh Do, Ha / Sheng, Weihua et al. | Wiley | 2018

    Freier Zugriff

    Real-time detection of distracted driving based on deep learning

    Tran, Duy / Manh Do, Ha / Sheng, Weihua et al. | IET | 2018

    Freier Zugriff

    Tackling Real-World Autonomous Driving using Deep Reinforcement Learning

    Maramotti, Paolo / Capasso, Alessandro Paolo / Bacchiani, Giulio et al. | IEEE | 2022