The objective of this paper is to examine the behavioural characteristics and patterns of pedestrians and vehicles in the context of emergency evacuation of car parks. Firstly, survey data is utilised to investigate the decision-making preferences of car park insiders in emergency evacuation scenarios. Secondly, the evacuation behaviours of pedestrians and vehicles are modelled using the XGBoost-SHAP model, with the objective of analysing the behavioural mechanisms in emergency evacuation situations. The results indicate that the density and distance of pedestrian exits are the primary factors influencing pedestrian choice. Furthermore, pedestrians with experience in emergency evacuation are more likely to select vehicle exits during emergency situations. With regard to vehicle choice, exit density was identified as the most significant influencing factor. In contrast, personal income and the presence of training were found to have a greater effect than exit distance. Concurrently, the selection of pedestrian and vehicle exits was influenced by a complex interaction of multiple factors.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Interpretable XGBoost-SHAP model for investigating car park pedestrian and vehicle emergency evacuation mechanisms


    Contributors:

    Conference:

    International Conference on Smart Transportation and City Engineering (STCE 2024) ; 2024 ; Chongqing, China


    Published in:

    Proc. SPIE ; 13575


    Publication date :

    2025-04-28





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Explainable Aircraft Crash Severity Prediction Using XGBoost and SHAP

    Benfaress, Ilyass / Bouhoute, Afaf / Zinedine, Ahmed | IEEE | 2025



    Road driving suitability evaluation method based on XGBoost-SHAP and random parameter multivariate Logit model

    YAO SIZHE / YU BO / CHEN YUREN et al. | European Patent Office | 2025

    Free access

    Extended Pedestrian Evacuation Model Considering Multiple Evacuation Behaviors

    Qinghua, Mao / Yang, Li / Rongfu, Yu et al. | Transportation Research Record | 2025