Traffic crash risk prediction is pivotal for proactive traffic safety management but faces challenges due to the extreme imbalance between crash and non-crash data. This paper proposes integrating variational autoencoder into a generative adversarial network (VAE-GAN) for crash data augmentation without information loss. VAE-GAN generates higher-quality data due to its superior deep generative capabilities. For the crash occurrence risk prediction task, we utilize a convolutional neural network (CNN) trained on the balanced datasets generated by VAE-GAN. Two kinds of category determinations are tested for better prediction results by using prediction probability maximum and selecting threshold. The prediction model integrating variational autoencoder into a deep convolutional generative adversarial network (VAE-DCGAN) exhibits the best performance. Furthermore, we leverage Shapley additive explanations (SHAP) to interpret the key features and patterns impacting prediction results. This analysis gains insights into the underlying mechanisms of crash occurrences, and helps improve proactive traffic management and control strategies.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A crash occurrence risk prediction model based on variational autoencoder and generative adversarial network


    Additional title:

    TRANSPORTMETRICA B: TRANSPORT DYNAMICS
    W. ZHU ET AL.


    Contributors:


    Publication date :

    2024-12-31


    Size :

    24 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training

    Hou, Xianxu / Sun, Ke / Shen, Linlin et al. | ArXiv | 2019

    Free access

    Wasserstein Generative Adversarial Network to Address the Imbalanced Data Problem in Real-Time Crash Risk Prediction

    Man, Cheuk Ki / Quddus, Mohammed / Theofilatos, Athanasios et al. | IEEE | 2022


    Symmetric Variational Autoencoder and Connections to Adversarial Learning

    Chen, Liqun / Dai, Shuyang / Pu, Yunchen et al. | ArXiv | 2017

    Free access

    Variational autoencoder-based neural network model compression

    Cheng, Liang / Guan, Peiyuan / Taherkordi, Amir et al. | ArXiv | 2024

    Free access