期刊文献+

跨海大桥交通事故严重程度预测分析方法 被引量:1

下载PDF
导出
摘要 本文以跨海大桥交通事故严重程度为研究对象,围绕交通事故发生时间、发生位置、事故形态、车辆因素和交通因素5个维度构建交通事故严重程度指标体系,提出了事故发生后交通因素的计算方法,并研究了9个相关因素。其次,基于极端梯度提升(XGBoost)预测模型建立跨海大桥交通事故严重程度预测模型,使用F-score值获得影响因素的重要性排序,结合SHAP归因算法揭示各因素与交通事故发生时严重程度的关系。预测分析结果表明,指标体系中交通因素、涉及车辆类型、位置因素、涉及车辆数等7种因素对事故严重程度影响较大。相较于传统的统计预测模型,XGBoost模型对于跨海大桥交通事故严重程度的预测准确率可达到85.4%,证明模型具有可行性。
出处 《中国公路》 2023年第11期153-157,共5页 China Highway
基金 广东省重点领域研发计划项目(2019B111106001)。
  • 相关文献

参考文献8

二级参考文献63

  • 1吕晓夫,杨亚东.回归分析方法在船舶交通事故预测中的应用[J].武汉理工大学学报(交通科学与工程版),2006,30(3):546-548. 被引量:22
  • 2Peter T, Savolainen P T, Fred L, et al. The statis- tical analysis of highway crash injury severities: A review and assessment of methodological alternatives [J]. Accident Analysis and Prevention, 2011, 43 (5) :1666-1676.
  • 3Chang H, Yeh T. Risk factors to driver fatalities in single-vehicle crashes: comparisons between non- motorcycle drivers and motorcyclists[J]. Journal of Transportation Engineering, 2006, 132 (3): 227- 236.
  • 4Malyshkina N, Mannering F. Empirical assessment of the impact of highway design exceptions on the frequency and severity of vehicle accidents[J]. Acci- dent Analysis and Prevention, 2010, 42(1): 131- 139.
  • 5Yamamoto T, Shankar V. Bivariate ordered-re- sponse probit model of driver's and passenger's inju- ry severities in collisions with fixed objects[J]. Ac- cident Analysis and Prevention, 2004, 36(5) : 869-876.
  • 6Helai H, Chor C, Haque M. Severity of driver inju- ry and vehicle damage in traffic crashes at intersec- tions: a Bayesian hierarchical analysis[J]. Accident Analysis and Prevention, 2008, 40(1): 45-54.
  • 7Lee J, Mannering F. Impact of roadside features on the frequency and severity of run-off-roadway acci- dents: an empirical analysis[J]. Accident Analysis and Prevention, 2002, 34(2): 149-161.
  • 8Eluru N, Bhat C, Hensher D. A mixed generalized ordered response model for examining pedestrian and bicyclist injury severity level in traffic crashes[J]. Accident Analysis and Prevention, 2008, 40 (3) : 1033-1054.
  • 9Ma Zhuang lin, Shao Chun-fu, Ma She qiang, et al. Constructing road safety performance indicators u- sing fuzzy delphi method and grey delphi method [J]. Expert Systems with Applications, 2011, 38(3):1509-1514.
  • 10Mussone L, Ferrari A, Oneta M. An analysis of ur ban collisions using an artificial intelligence model [J]. Accident Analysis & Prevention, 1999, 31 (6): 705 -718.

共引文献50

同被引文献11

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部