.png){kind=icon}
返回
A priority based multi-level heterogeneity modelling framework for vulnerable road users
.png){kind=icon}
PRE
AI
DOI：10.1080/23249935.2025.2516817.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Vulnerable road users in the United States have experienced record-high fatalities in recent years. To support improved safety planning, this study analyzes six years (2014–2019) of crash data involving pedestrians and bicyclists in North Carolina, USA. A priority-based framework is developed to identify high-risk locations across space and time using the space–time cube method, while addressing fundamental crash modeling specification challenges. Results show that while traffic control indicators, high-speed limits, and driver sobriety remain significant predictors of crash severity, their influence has declined over time. In contrast, the effects of daylight conditions and vulnerable road user sobriety have worsened. Overall, the combined impact of statistically significant factors indicates modest safety improvements at identified hotspots, with the probability of severe crashes gradually decreasing in recent years. The proposed framework offers practical guidance for transportation engineers and safety planners aiming to enhance safety outcomes for vulnerable road users.
Keyword:
Partially temporally constrained
Temporal Instability
Crash severity
Binary logit
XGBoost
Unobserved heterogeneity
期刊
IF:
3.1
论文数:
941
被引数:
2.2K
机构
引用论文
A temporal statistical assessment of the effectiveness of bicyclist safety helmets in mitigating injury severities in vehicle/ bicyclist crashes对自行车安全头盔在减轻车辆/自行车撞车事故中伤害严重程度的有效性进行时间统计评估
.png){kind=icon}
PREAI
分享收藏
分享收藏Highway accident severities and the mixed logit model: An exploratory empirical analysis公路事故严重程度和混合logit模型: 探索性实证分析
PREAI
分享收藏
查看更多内容