[1]郭兰英,张晓静,程 鑫.基于改进决策树的道路交通事故成因耦合分析[J].计算机技术与发展,2022,32(06):156-161.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 026]
　GUO Lan-ying,ZHANG Xiao-jing,CHENG Xin.Coupling Analysis of Causes of Road Traffic Accidents Based on Improved Decision Tree[J].,2022,32(06):156-161.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 026]
点击复制

基于改进决策树的道路交通事故成因耦合分析()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年06期
页码:
156-161
栏目:
应用前沿与综合
出版日期:
2022-06-10

文章信息/Info

Title:
Coupling Analysis of Causes of Road Traffic Accidents Based on Improved Decision Tree
文章编号:
1673-629X(2022)06-0156-06
作者:
郭兰英; 张晓静; 程 鑫
长安大学 信息工程学院,陕西 西安 710064
Author(s):
GUO Lan-ying; ZHANG Xiao-jing; CHENG Xin
School of Information Engineering,Chang’an University,Xi’an 710064,China
关键词:
交通事故; GBDT-RFE; 事故严重程度; 决策树; 多因素耦合
Keywords:
traffic accident; GBDT-RFE; severity of accident; decision tree; multi-factor coupling
分类号:
TP181
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 06. 026
摘要:
道路交通事故的发生充满不确定性,为尽可能减轻事故损害,研究分析其成因具有重要意义。 该文提出了一种基于改进决策树的道路交通事故成因耦合分析算法。 算法采取数据清洗、方差过滤、相关性分析、数据重采样等方法预处理西安市历史事故数据,分析道路交通事故特征中的时间特性及道路环境特性,发现交通事故的严重程度易受交通特征影响。 以事故严重程度为目标, 初步选取道路因素及环境因素在内的 17 个交通特征候选自变量, 以梯度提升决策树(gradient boosting decision tree,GBDT) 为基模型,结合递归特征消除法( recursive feature elimination,RFE)探究不同交通特征对事故等级的影响。 利用 GBDT-RFE 模型筛选出道路类型、道路横断面位置、交通信号方式、路侧防护设施类型、道路线型、照明条件作为主要特征变量,以此构建决策树模型,提取易引发重大事故且置信度较高的多因素耦合模式作为重点情境防范,为事故安全预警提供参考。
Abstract:
The occurrence of road traffic accidents is full of uncertainty. In order to reduce the accident damage as much as possible,it isof great significance to study and analyze its causes. We present an algorithm for coupling analysis of the causes of road traffic accidentsbased on improved decision trees. The algorithm uses data cleaning, variance filtering, correlation analysis, data resampling and othermethods to preprocess historical accident data in Xi’an,analyze the time characteristics of road traffic accident characteristics and road environment characteristics,and find that the severity of traffic accidents is easily affected by traffic characteristics. Aiming at the severity ofthe accident,17 traffic feature candidate independent variables including road factors and environmental factors are initially selected,andthe gradient boosting decision tree ( GBDT) is used as the base model,combined with the recursive feature elimination method ( RFE)explore the impact of different traffic characteristics on the level of accidents. Use the GBDT-RFE model to screen out the road type,road cross- section location, traffic signal mode, roadside protection facility type, road alignment, and lighting conditions as the mainfeature variables,and build a decision tree model to extract the high-confidence multi-factor coupling mode that is likely to cause majoraccidents as key situation prevention and provides a reference for accident safety early warning.

相似文献/References:

[1]陈异,戴琳,寇鹏.零膨胀泊松回归模型及其在交通事故中的应用[J].计算机技术与发展,2013,(10):163.
　CHEN Yi,DAI Lin,KOU Peng.Zero-inflated Poisson Regression Model and Its Application in Traffic Accident[J].,2013,(06):163.
[2]钱刚,蒋珉,柴干.高速公路事故影响范围的研究[J].计算机技术与发展,2014,24(06):83.
　QIAN Gang[],JIANG Min[],CHAI Gan[].Study on Expressway Traffic Accident Influence Scope[J].,2014,24(06):83.
[3]孙振华,王转转,肖 鑫.用 LSTM 对市级周交通事故量预测方法研究[J].计算机技术与发展,2023,33(02):195.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 029]
　SUN Zhen-hua,WANG Zhuan-zhuan,XIAO Xin.Approach of Predicting Number of Citywide Traffic Accidents Using Long Short-term Memory Neural Network[J].,2023,33(06):195.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 029]

更新日期/Last Update: 2022-06-10