In order to solve the problem of imprecise alarm of foreign objects in railway encroachment, realize foreign object risk stratification and early warning. The main purpose of this paper is to analyze the trespasser factors, environmental factors and track factors associated with the severity of injuries in railway trespassing accidents from the perspective of trespasser, so as to identify features that rail monitoring needed, and propose optimization measures for accident prevention. This paper uses the Multinomial logit model to identify the factors and characteristics of trespasser injury severity based on Federal Railroad Administration accident record data. The pre-accident acts and location are the most important factors influencing the severity of the accident. Driving is the most common acts in trespassing incidents, while lying, standing and walking have a significant relationship with fatality outcomes. Combinations of some different behaviors and orbital locations can lead to polarization of accident risk with a higher risk of death, and it should be pay more attention when monitoring these features. This paper can be used to determine the relative level of risk for of each feature of illegal trespassing accidents and infer the severity of accident casualties, so as to construct an evaluation index system for foreign body characteristics. This paper helps to improve the detection and early warning accuracy of intrusion accidents by considering trespassers’ acts, weather and track scene types in the framework of railway foreign object video detection, which has practical significance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Analysis of Risk Factors of Railway Trespassing Accidents Based on Multinomial Logit Model


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Qin, Yong (editor) / Jia, Limin (editor) / Yang, Jianwei (editor) / Diao, Lijun (editor) / Yao, Dechen (editor) / An, Min (editor) / Wang, Xu (author) / Ma, Xiaoping (author) / Zhang, Hanqing (author) / Chen, Fei (author)

    Conference:

    International Conference on Electrical and Information Technologies for Rail Transportation ; 2023 ; Beijing, China October 19, 2023 - October 21, 2023



    Publication date :

    2024-02-03


    Size :

    12 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Bayesian Multinomial Logit

    Washington, Simon / Congdon, Peter / Karlaftis, Matthew G. et al. | Transportation Research Record | 2009


    Multinomial Logit Regression

    Retherford, Robert D. / Choe, Minja Kim | Wiley | 1993


    Appendix F: Multinomial Logit Model

    Kumar, V. / Petersen, J. Andrew | Wiley | 2012



    Multinomial Logit model based on Gumbel Copula

    Huamin, L. / Haijun, H. / Huiwen, W. | British Library Online Contents | 2009