Highlights A method is designed to extract driving behaviour features and predict risk levels. Massive driving behaviour features are extracted from real vehicle trajectory data. Key features are identified by feature importance ranking and recursive elimination. XGBoost can achieve satisfactory results of behaviour-based crash risk prediction.

    Abstract This study designs a framework of feature extraction and selection, to assess vehicle driving and predict risk levels. The framework integrates learning-based feature selection, unsupervised risk rating, and imbalanced data resampling. For each vehicle, about 1300 driving behaviour features are extracted from trajectory data, which produce in-depth and multi-view measures on behaviours. To estimate the risk potentials of vehicles in driving, unsupervised data labelling is proposed. Based on extracted risk indicator features, vehicles are clustered into various groups labelled with graded risk levels. Data under-sampling of the safe group is performed to reduce the risk-safe class imbalance. Afterwards, the linkages between behaviour features and corresponding risk levels are built using XGBoost, and key features are identified according to feature importance ranking and recursive elimination. The risk levels of vehicles in driving are predicted based on key features selected. As a case study, NGSIM trajectory data are used in which four risk levels are clustered by Fuzzy C-means, 64 key behaviour features are identified, and an overall accuracy of 89% is achieved for behaviour-based risk prediction. Findings show that this approach is effective and reliable to identify important features for driving assessment, and achieve an accurate prediction of risk levels.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

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


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    2019-05-05


    Format / Umfang :

    10 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Real-time driving risk assessment using deep learning with XGBoost

    Shi, Liang / Qian, Chen / Guo, Feng | Elsevier | 2022


    PV Power Prediction Based on XGBoost Algorithm

    Hong, Yufan / Yang, Jingxian / Yang, Zhen et al. | IEEE | 2023


    Traffic accident prediction system based on Ada-XGBoost

    CHANG RUNQI | Europäisches Patentamt | 2021

    Freier Zugriff