基于随机森林的电动自行车骑行者事故伤害程度影响因素分析

交通运输系统工程与信息 ›› 2021, Vol. 21 ›› Issue (1): 196-200.

基于随机森林的电动自行车骑行者事故伤害程度影响因素分析

李英帅^*1，张旭²，王卫杰¹，居潇凡¹

1. 南京工业大学，交通运输工程学院，南京 211816；2. 重庆交通大学，交通运输学院，重庆 400074

收稿日期:2020-07-29 修回日期:2020-09-22 出版日期:2021-02-25 发布日期:2021-02-25
作者简介:李英帅(1985- )，男，山东临沂人，讲师，博士。
基金资助:
道路交通安全公安部重点实验室开放课题/Open Project of the Key Laboratory of Road Traffic Safety Ministry of Public Security(2017ZDSYSKFKT01)；南京工业大学青年教师科研启动基金/High Level Introduction of Talent Research Start-up Fund by Nanjing Tech University(3827400205)。

Factors Affecting Electric Bicycle Rider Injury in Accident Based on Random Forest Model

LI Ying-shuai^*1, ZHANG Xu², WANG Wei-jie¹, JU Xiao-fan¹

1. School of Transportation Engineering, Nanjing Tech University, Nanjing 211816, China; 2. College of Traffic & Transportation, Chongqing Jiaotong University, Chongqing 400074, China

Received:2020-07-29 Revised:2020-09-22 Online:2021-02-25 Published:2021-02-25

摘要/Abstract

摘要：

为研究电动自行车道路交通事故对骑行者伤害程度影响因素的重要性排序，分析电动自行车骑行者事故伤害程度的影响因素。收集某市2013-2015年电动自行车交通事故数据，对其进行描述性统计分析，从中选出与交通事故严重程度相关的22个影响因素。利用随机森林模型对电动自行车骑行者受伤严重程度进行预测，并对相关因素的重要程度进行排序。研究表明，影响电动自行车骑行者受伤严重程度的最主要因素依次为车辆间事故类型、受伤部位、道路物理隔离类型等。针对交通事故相关因素提出改进建议，研究结论可为电动自行车事故预防提供决策参考。

关键词: 交通工程, 影响因素, 随机森林, 电动自行车, 事故伤害程度

Abstract:

This study analyzed the crucial factors that affect the injury degree of electric bicycle riders in the accident and ranked the factors based on their significance. The study collected electric bicycle traffic accident data in a city from 2013 to 2015, and then performed the descriptive statistical analysis. 22 factors related to the severity of traffic accidents were selected for analysis. The random forest model was used to predict the severity of electric bicycle rider injuries, and then rank the significance of the impact factors. The result indicates that the most significant factors affecting the severity of electric bicycle rider injuries in the accident are as follows: the type of accident, the injury is on which part of the body, and the separation type on the road, etc. The study also puts forward suggestions to improve bicycle rider's safety in terms of related factors, which provide reference for prevention of electric bicycle accident and relevant decision-makings in the safety management.

Key words: traffic engineering, impact factors, random forest, electric bicycles, accident injury degree

中图分类号:

U491.31

李英帅，张旭，王卫杰，居潇凡. 基于随机森林的电动自行车骑行者事故伤害程度影响因素分析[J]. 交通运输系统工程与信息, 2021, 21(1): 196-200.

LI Ying-shuai, ZHANG Xu, WANG Wei-jie, JU Xiao-fan. Factors Affecting Electric Bicycle Rider Injury in Accident Based on Random Forest Model[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(1): 196-200.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract20205.shtml

http://www.tseit.org.cn/CN/Y2021/V21/I1/196

参考文献

[1] WEBER T, SCARAMUZZA G, SCHMITT K U. Evaluation of E- bike accidents in Switzerland[J]. Accident Analysis and Prevention, 2014, 73: 47.

[2] HAUSTEIN S, MØLLER M. E- bike safety: Individuallevel factors and incident characteristics[J]. Journal of Transport & Health, 2016, 3(3): 386-394.

[3] SCHEPERS J P, FISHMAN E, HERTOG P D, et al. The safety of electrically assisted bicycles compared to classic bicycles[J]. Accident: Analysis and Prevention, 2014, 73(73): 174.

[4] GUO Y, LIU P, BAI L, et al. Red light running behavior of electric bicycles at signalized intersections in China [J]. Transportation Research Record Journal of the Transportation Research Board, 2014, 2468(1): 28-37.

[5] 何庆, 马建菲, 李洋, 等. 基于122警情的电动自行车交通事故特征研究[J]. 交通信息与安全, 2018, 36(5): 132- 138. [HE Q, MA J F, LI Y, et al. A study of characteristics of road accidents involve electric bicycles based on 122 emergency number[J]. Journal of Transport Information and Safety, 2018, 36(5): 132-138.]

[6] 王涛, 黎文皓, 李文勇. 电动自行车交通事故严重程度影响因素分析[J]. 广西大学学报 ( 自然科学版), 2017, 42(6): 2080- 2088. [WANG T, LI W H, LI W Y. Influence factors and injury severity in electric bicycles traffic crashes[J]. Journal of Guangxi University (Nat Sci Ed), 2017, 42(6): 2080-2088.]

[7] ALI B, FRED M. The effect of passengers on driverinjury severities in single- vehicle crashes: A random parameters heterogeneity- in- means approach[J]. Analytic Methods in Accident Research, 2017, 14: 41- 53.

[8] 孙轶轩, 邵春福, 赵丹, 等. 交通事故严重程度 C5.0 决策树预测模型[J]. 长安大学学报(自然科学版), 2014, 5: 109-116. [SUN Y X, SHAO C F, ZHAO D, et al. C5.0 decision tree prediction model for traffic accident severity [J]. Journal of Chang'an University (Natural Science Edition), 2014, 5: 109-116.]

[9] 李成志, 李洋, 何庆, 等. 电动自行车交通事故中骑车人伤害程度的影响因素分析[J]. 交通工程, 2019, 4: 37- 43. [LI C Z, LI Y, HE Q, et al. Analysis of the influencing factors of the injury degree of cyclists in electric bicycle traffic accidents[J]. Traffic Engineering, 2019, 4: 37-43.]

[10] 赵玮, 徐良杰, 冉斌, 等. 基于Adaptive Lasso及RF算法的冰雪天气交通事故分析[J]. 中国安全科学学报, 2017, 27(2): 98-103. [ZHAO W, XU L J, RAN B, et al. Analyzing traffic crash under iced snow weather condition based on Adaptive Lasso and RF[J]. China Safety Science Journal, 2017, 27(2): 98-103.]

[11] 中国标准出版社, GA/T 946.3-2011, 道路交通管理信息采集规范[S]. 中国: 中国标准出版社, 2011. [China Standard Press, GA/T 946.3-2011, Specification for road traffic management information collection[S]. China: China Standard Press, 2011.]

[12] KUMAR S. Severity analysis of powered two wheeler traffic accidents in Uttarakhand，India[J]. European Transport Research Review, 2017, 9(2): 1-10.

[13] ONA J. Analysis of traffic accidents on rural highways using latent class clustering and Bayesian networks[J]. Accident Analysis and Prevention, 2013, 51(2): 1-10．

[14] 程政, 陈贤富. 基于随机森林模型的短时交通流预测方法[J]. 微型机与应用, 2016(10): 46-49. [CHENG Z, CHEN X F. Short- term traffic flow prediction method based on random forest model[J]. Microcomputers and Applications, 2016(10): 46-49.]

[15] 张雷, 王琳琳, 张旭东, 等. 随机森林算法基本思想及其在生态学中的应用: 以云南松分布模拟为例[J]. 生态学报, 2014(3): 650- 659. [ZHANG L, WANG L L, ZHANG X D, et al. The basic idea of random forest algorithm and its application in ecology: Taking Yunnan pine distribution simulation as an example[J]. Acta Ecologica Sinica, 2014(3): 650-659.]

[16] 曹正凤. 随机森林算法优化研究[D]. 北京: 首都经济贸易大学, 2014. [CAO Z F. Research on random forest algorithm optimization[D]. Beijing: Capital University of Economics and Business, 2014.]