Based on historical accident data of three waterways in the lower reaches of Yangtze River, the real-time navigation safety in the waterways was judged, and the important variables were screened by Random Forest model and Support Vector Machine model (SVM) was constructed. The real-time traffic accident state was predicted by the established model, and the results showed that the prediction effects of the three models were all good. Transferability test results show that the three models have good transferability, and the model can be directly used for real-time traffic risk prediction of other waterways after adjusting parameter values by the ten-fold cross-validation method, which indirectly proves that the model has good universal applicability.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Real-Time Traffic Safety Prediction Model for the Lower Reaches of Yangtze River


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Zhang, Zhenyuan (editor) / Zhang, Shukui (author) / Tao, Si (author) / Ding, Zhenguo (author)

    Conference:

    International Conference on Intelligent Transportation Engineering ; 2021 ; Beijing, China October 29, 2021 - October 31, 2021



    Publication date :

    2022-06-01


    Size :

    8 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English