Highlights Developed an integrated data- and theory-driven crash severity model. Interpretable embedding representations for discretized variables. Behaviorally meaningful outputs that can be used for crash severity analysis.

    Abstract For crash severity modeling, researchers typically view theory-driven models and data-driven models as different or even conflicting approaches. The reason is that the machine-learning models offer good predictability but weak interpretability, while the latter has robust interpretability but moderate predictability. In order to alleviate the tension between them, this study proposes an integrated data- and theory-driven crash-severity model, known as Embedded Fusion model based on Text Vector Representations (TVR-EF), by leveraging the complementary strengths of both. The model specification consists of two parts. (i) the data-driven component not only mitigate the deficiencies of traditional econometric models, where one-hot encoding is frequently used and makes it impossible to observe semantic relatedness between variable categories, but also enhances the interpretability for the relationship between crash severity and potential influencing factors using the learned embedding weight matrix. (ii) In the theory-driven component, the multinomial logit model is implemented as a 2D-Convolutional Neural Network (2D-CNN) to increase flexibility and decrease dependency on prior knowledge for different crash-severity outcomes. A crash dataset from Guangdong Province, China, is utilized to estimate the TVR-EF model, which is then benchmarked against two traditional econometric models and three widely used machine-learning models. Results indicate that TVR-EF model does not only improve the predictive performance but also makes it easier to interpret.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An integrated data- and theory-driven crash severity model


    Contributors:
    Liu, Dongjie (author) / Li, Dawei (author) / Sze, N.N. (author) / Ding, Hongliang (author) / Song, Yuchen (author)


    Publication date :

    2023-09-01




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Crash severity sensing

    Stuetzler, F.-J. / Meissner, P. | British Library Conference Proceedings | 1998


    Method for Modeling Crash Severity with Observable Crash Data

    Ray, Malcolm H. / Carrigan, Christine E. / Plaxico, Chuck A. | Transportation Research Record | 2014


    Data mining approach to model bus crash severity in Australia

    Samerei, Seyed Alireza / Aghabayk, Kayvan / Mohammadi, Amin et al. | Elsevier | 2020


    Alternative Crash Severity Ranking Measures and the Implications on Crash Severity Ranking Results

    Campbell, J. R. / Knapp, K. K. / Institute of Transportation Engineers | British Library Conference Proceedings | 2006