Traffic Safety Assessment and Injury Severity Analysis for Undivided Two-Way Highway–Rail Grade Crossings
The safety and reliability of undivided two-way highway–rail grade crossings (HRGCs) are of paramount importance in transportation systems. Utilizing crash data from the Federal Railroad Administration between 2020 and 2021, this study aims to predict crash injury severity outcomes and investigate v...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/12/4/519 |
_version_ | 1797297608544223232 |
---|---|
author | Qiaoqiao Ren Min Xu Bojian Zhou Sai-Ho Chung |
author_facet | Qiaoqiao Ren Min Xu Bojian Zhou Sai-Ho Chung |
author_sort | Qiaoqiao Ren |
collection | DOAJ |
description | The safety and reliability of undivided two-way highway–rail grade crossings (HRGCs) are of paramount importance in transportation systems. Utilizing crash data from the Federal Railroad Administration between 2020 and 2021, this study aims to predict crash injury severity outcomes and investigate various factors influencing injury severities. The χ<sup>2</sup> test was first used to select variables that were significantly associated with injury outcomes. By employing the eXtreme Gradient Boosting (XGBoost) model and interpretable SHapley Additive exPlanations (SHAP), a cross-category safety assessment that offers an evidence-based hierarchy and statistical inference of risk factors associated with crashes, crossings, vehicles, drivers, and environment was provided for killed, injured, and uninjured outcomes. Some significant predictors overlapped between the killed and injured models, such as old driver, driver was in vehicle, main track, went around the gate, adverse crossing surface, and truck, while the other different significant factors revealed that the model could distinguish between different severity levels. Additionally, the results suggested that the model has varying performances in predicting different injury severities, with the killed model having the highest accuracy of 93.36%. The SHAP dependency plots for the top three features also ensure reliable predictions and inform potential interventions aimed at strengthening traffic safety and risk management practices, such as enhanced warning systems and targeted educational campaigns for older drivers. |
first_indexed | 2024-03-07T22:23:09Z |
format | Article |
id | doaj.art-c4409d9e7b7944fd97d61c6e5a869e2b |
institution | Directory Open Access Journal |
issn | 2227-7390 |
language | English |
last_indexed | 2024-03-07T22:23:09Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Mathematics |
spelling | doaj.art-c4409d9e7b7944fd97d61c6e5a869e2b2024-02-23T15:26:02ZengMDPI AGMathematics2227-73902024-02-0112451910.3390/math12040519Traffic Safety Assessment and Injury Severity Analysis for Undivided Two-Way Highway–Rail Grade CrossingsQiaoqiao Ren0Min Xu1Bojian Zhou2Sai-Ho Chung3Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, ChinaDepartment of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, ChinaSchool of Transportation, Southeast University, Nanjing 210096, ChinaDepartment of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, ChinaThe safety and reliability of undivided two-way highway–rail grade crossings (HRGCs) are of paramount importance in transportation systems. Utilizing crash data from the Federal Railroad Administration between 2020 and 2021, this study aims to predict crash injury severity outcomes and investigate various factors influencing injury severities. The χ<sup>2</sup> test was first used to select variables that were significantly associated with injury outcomes. By employing the eXtreme Gradient Boosting (XGBoost) model and interpretable SHapley Additive exPlanations (SHAP), a cross-category safety assessment that offers an evidence-based hierarchy and statistical inference of risk factors associated with crashes, crossings, vehicles, drivers, and environment was provided for killed, injured, and uninjured outcomes. Some significant predictors overlapped between the killed and injured models, such as old driver, driver was in vehicle, main track, went around the gate, adverse crossing surface, and truck, while the other different significant factors revealed that the model could distinguish between different severity levels. Additionally, the results suggested that the model has varying performances in predicting different injury severities, with the killed model having the highest accuracy of 93.36%. The SHAP dependency plots for the top three features also ensure reliable predictions and inform potential interventions aimed at strengthening traffic safety and risk management practices, such as enhanced warning systems and targeted educational campaigns for older drivers.https://www.mdpi.com/2227-7390/12/4/519transportation systemtraffic safetyreliability estimation and mathematical statisticsrisk managementinjury severityHRGC crashes |
spellingShingle | Qiaoqiao Ren Min Xu Bojian Zhou Sai-Ho Chung Traffic Safety Assessment and Injury Severity Analysis for Undivided Two-Way Highway–Rail Grade Crossings Mathematics transportation system traffic safety reliability estimation and mathematical statistics risk management injury severity HRGC crashes |
title | Traffic Safety Assessment and Injury Severity Analysis for Undivided Two-Way Highway–Rail Grade Crossings |
title_full | Traffic Safety Assessment and Injury Severity Analysis for Undivided Two-Way Highway–Rail Grade Crossings |
title_fullStr | Traffic Safety Assessment and Injury Severity Analysis for Undivided Two-Way Highway–Rail Grade Crossings |
title_full_unstemmed | Traffic Safety Assessment and Injury Severity Analysis for Undivided Two-Way Highway–Rail Grade Crossings |
title_short | Traffic Safety Assessment and Injury Severity Analysis for Undivided Two-Way Highway–Rail Grade Crossings |
title_sort | traffic safety assessment and injury severity analysis for undivided two way highway rail grade crossings |
topic | transportation system traffic safety reliability estimation and mathematical statistics risk management injury severity HRGC crashes |
url | https://www.mdpi.com/2227-7390/12/4/519 |
work_keys_str_mv | AT qiaoqiaoren trafficsafetyassessmentandinjuryseverityanalysisforundividedtwowayhighwayrailgradecrossings AT minxu trafficsafetyassessmentandinjuryseverityanalysisforundividedtwowayhighwayrailgradecrossings AT bojianzhou trafficsafetyassessmentandinjuryseverityanalysisforundividedtwowayhighwayrailgradecrossings AT saihochung trafficsafetyassessmentandinjuryseverityanalysisforundividedtwowayhighwayrailgradecrossings |