This paper explores how geometric characteristics, accesses, infrastructures and road environment influence crash prediction and safety performance of rural roads in the Dutch province of Gelderland. More than 500km two-way two-lane rural road segments in Gelderland were investigated and 4968 groups of data were collected with length unit of 100m. Safety performance of these roadway segments was evaluated and classified based on ten-year observed crash data. Mechanical language and Naive Bayes classifier were applied to the crash prediction model and a 10-fold cross-validation was conducted to evaluate the performance of the model under the guarantee that it was not over fitted. The results reveal how road conditions and environmental elements, especially access elements and object elements, contribute to road safety. It provides a new prospective to improve road safety performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Crash Prediction and Safety Performance of Two-Way Two-Lane Rural Roads in Gelderland


    Contributors:
    Wang, Yue (author) / Yao, Yutian (author)

    Conference:

    15th COTA International Conference of Transportation Professionals ; 2015 ; Beijing, China


    Published in:

    CICTP 2015 ; 3071-3080


    Publication date :

    2015-07-13




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Safety Improvements on Two-Lane Rural Roads

    Bruehning, E. | British Library Conference Proceedings | 2000


    Safety Improvements for Two-Lane Rural Roads

    K. R. Agent / J. G. Pigman / N. Stamatiadis | NTIS | 2000


    Crash Modification Functions for Passing Relief Lanes on Two-Lane Rural Roads

    Persaud, Bhagwant / Anarkooli, Alireza Jafari / Almasi, Shahram et al. | Transportation Research Record | 2020