Crash hotspot identification (HSID) is an essential component of traffic management authorities’ efforts to improve safety and allocate limited resources. This paper presents a method for identifying hotspots using self-organizing maps (SOM). The SOM method was used to identify high-risk areas based on five commonly used HSID methods: crash frequency, equivalent property damage only, crash rate, empirical Bayes, and the societal risk-based method. Crashes on a major road in Iran were examined using the proposed method. Based on these criteria, high-risk locations were grouped into six clusters, which provided appropriate criteria for each location depending on the importance of the cluster. The findings show that the identification of crash hotspots tends to focus on areas with more crashes and deaths, demonstrating that the research methodology was appropriate.


    Access

    Download


    Export, share and cite



    Title :

    Self-Organized Neural Network Method to Identify Crash Hotspots


    Contributors:


    Publication date :

    2023




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Spatial Multiresolution Analysis Approach to Identify Crash Hotspots and Estimate Crash Risk

    Katicha, Samer Wehbe / Khoury, John / Flintsch, Gerardo | ASCE | 2021


    Methods for Identifying Truck Crash Hotspots

    Wenrui Qu / Shaojie Liu / Qun Zhao et al. | DOAJ | 2020

    Free access

    The Temporal Dynamics of Road Traffic Crash Hotspots

    Resheff, Yehezkel S. / Sher, Mali / Adler, Nicole | IEEE | 2024


    Identifying Teen-Related Crash Hotspots and Outliers Using ArcGIS

    Mohammed, Hemin J. / Schrock, Steven D. | TIBKAT | 2020


    Hybrid-OD matrix based simulation approach to identify e-charging hotspots in transport network

    ElBanhawy, Eiman Y. / Dalton, Ruth / Shankar, Venky N. et al. | IEEE | 2014