一种混行环境下驾驶人认知分心识别方法

doi:10.13229/j.cnki.jdxbgxb20210215

吉林大学学报(工学版) ›› 2022, Vol. 52 ›› Issue (8): 1800-1807.doi: 10.13229/j.cnki.jdxbgxb20210215

• 交通运输工程·土木工程 • 上一篇

一种混行环境下驾驶人认知分心识别方法

华强¹(),金立生^1,²(),郭柏苍¹,张舜然¹,王禹涵¹

^1.吉林大学交通学院，长春 130022
^2.燕山大学车辆与能源学院，河北秦皇岛 066004

收稿日期:2021-03-18 出版日期:2022-08-01 发布日期:2022-08-12
通讯作者: 金立生 E-mail:huaqiang_lyf@163.com;jinls@ysu.edu.cn
作者简介:华强（1989-），男，博士研究生.研究方向：自动驾驶，驾驶人行为分析. E-mail： huaqiang_lyf@163.com
基金资助:
国家重点研发计划项目(2018YFB1600501)

A recognition method for driver's cognitive distraction in simulated mixed traffic environment

Qiang HUA¹(),Li-sheng JIN^1,²(),Bai-cang GUO¹,Shun-ran ZHANG¹,Yu-han WANG¹

^1.College of Transportation，Jilin University，Changchun 130022，China
^2.School of Vehicle and Energy，Yanshan University，Qinhuangdao 066004，China

Received:2021-03-18 Online:2022-08-01 Published:2022-08-12
Contact: Li-sheng JIN E-mail:huaqiang_lyf@163.com;jinls@ysu.edu.cn

摘要/Abstract

摘要：

面向智能网联车辆与非网联车辆的混行环境，研究了一种混行环境无信号交叉口下基于注意力机制的双向长短时记忆网络（Bi-LSTM）的认知分心识别模型。采集了60名驾驶人在混行环境下的模拟驾驶试验数据，采用支持向量机递归特征消除算法提取最优特征子集作为模型的输入。结果表明：该模型识别准确率高达96.58%，F₁值为96.24%，与SVM和决策树分心识别模型相比，准确率、召回率、F₁值和ROC曲线等模型性能方面均最优，可应用于智能车辆分心预警辅助系统，对提高道路安全性具有重要意义。

关键词: 分心驾驶, 混行环境, Bi-LSTM, 递归特征消除算法

Abstract:

To reduce traffic accidents in an environment where intelligent connected vehicle and non-connected vehicle are mixed， a cognitive distraction recognition model based on bi-directional long short-term memory（Bi-LSTM） with attention mechanism at unsignalized intersections was proposed in a mixed traffic environment. The driving simulator data of 60 drivers in the mixed traffic environment was collected and support vector machine recursive feature elimination algorithm（SVM-RFE） was adopted to extract the optimal feature subset as the input of the model. The results show that the recognition accuracy of the model is as high as 96.58% and the F₁-scores is 96.24%. Compared with SVM and decision tree distraction recognition models， this model has the best performance in terms of accuracy， recall， the F₁-scores and the ROC curve. The model can be applied to the autonomous driving distraction alarm assistance system， which is of great significance to improving road safety.

Key words: distracted driving, mixed traffic environment, Bi-LSTM model, recursive feature elimination algorithm

中图分类号:

U461.91

华强,金立生,郭柏苍,张舜然,王禹涵. 一种混行环境下驾驶人认知分心识别方法[J]. 吉林大学学报(工学版), 2022, 52(8): 1800-1807.

Qiang HUA,Li-sheng JIN,Bai-cang GUO,Shun-ran ZHANG,Yu-han WANG. A recognition method for driver's cognitive distraction in simulated mixed traffic environment[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(8): 1800-1807.

图/表 10

表1

图1

图2

表2

表3

图3

图4

表4

表5

图5

参考文献 21

1	Nee M, Contrand B, Orriols L, et al. Road safety and distraction, results from a responsibility case-control study among a sample of road users interviewed at the emergency room[J]. Accident Analysis and Prevention, 2019, 122: 19-24.
2	Metz B, Landau A, Just M. Frequency of secondary tasks in driving-results from naturalistic driving data[J]. Safety Science, 2014, 68: 195-203.
3	Klauer S G, Guo F, Simons-Morton B G, et al. Distracted driving and risk of road crashes among novice and experienced drivers[J]. The New England Journal of Medicine, 2014, 370(1): 54-59.
4	Haque M M, Washington S. A parametric duration model of the reaction times of drivers distracted by mobile phone conversations[J]. Accident Analysis and Prevention, 2014, 62: 42-53.
5	Ross V, Jongen E M, Wang W, et al. Investigating the influence of working memory capacity when driving behavior is combined with cognitive load: an LCT study of young novice drivers[J]. Accident Analysis and Prevention, 2014, 62: 377-387.
6	Strayer D L, Watson J M, Drews F A. Cognitive distraction while multitasking in the automobile[J], Psychology of Learning and Motivation, 2011, 54: 29-58.
7	Young K L, Salmon P M. Examining the relationship between driver distraction and driving errors: a discussion of theory, studies and methods[J]. Safety Science, 2012, 50(2): 165-174.
8	Sharma A, Ali Y, Saifuzzaman M. Human factors in modelling mixed traffic of traditional, connected, and automated vehicles[C]∥International Conference on Applied Human Factors and Ergonomics Springer, Brisbane, Australia, 2017: 262-273.
9	Strayer D L, Drews F A. Cell phone induced driver distraction[J]. Current Directions in Psychological Science, 2007, 16(3): 128-131.
10	孙健,张一豪,王俊骅. 基于自然驾驶数据的分心驾驶行为识别方法[J]. 中国公路学报, 2020, 33(9): 225-235.
	Sun Jian, Zhang Yi-hao, Wang Jun-hua. Detecting driver distraction behavior with naturalistic driving data[J]. China Journal of Highway and Transport, 2020, 33(9): 225-235.
11	张辉,钱大琳,邵春福,等.模拟驾驶环境下驾驶人分心状态判别[J]. 中国公路学报, 2018, 31(4): 47-55.
	Zhang Hui, Qian Da-lin, Shao Chun-fu, et al. Driver's distraction states identification in simulation driving environment[J]. China Journal of Highway and Transport, 2018, 31(4): 47-55.
12	Liao Y, Li S E, Wang W, et al. Detection of driver cognitive distraction: a comparison study of stop-controlled intersection and speed-limited highway[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(6): 1628-1637.
13	Liang Y, Lee J D. A hybrid bayesian network approach to detect driver cognitive distraction[J]. Transportation Research Part C, 2014, 38(1): 146-155.
14	Hua Q, Jin L S, Jiang Y Y, et al. Cognitive distraction state recognition of drivers at a nonsignalized intersection in a mixed traffic environment[J]. Advances in Civil Engineering, 2021(5): 1-16.
15	Zhou P, Shi W, Tian J. Attention-based bidirectional long short-term memory networks for relation classification[C]∥Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany, 2016: 207-213.
16	张健,吴坤润,杨敏,等.智能网联环境下交叉口双环自适应控制模型[J]. 吉林大学学报: 工学版, 2021, 51(2): 541-548.
	Zhang Jian, Wu Kun-run, Yang Min, et al. Double-ring adaptive control model of intersection during intelligent and connected environment[J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(2): 541-548.
17	Wu G, Sanderson B, Bittner V. The 6-minute walk test: how important is the learning effect?[J]. American Heart Journal, 2003, 146(1): 129-133.
18	Liao Y, Li S E, Wang W. The impact of driver cognitive distraction on vehicle performance at stop-controlled intersections[C]∥Intelligent Vehicles Symposium, Seoul, South Korea, 2015: 946-951.
19	裴玉龙,金英群,陈贺飞.基于脑电信号分析的不同年龄驾驶人疲劳特性[J]. 中国公路学报, 2018, 31(4): 59-65.
	Pei Yu-long, Jin Ying-qun, Chen He-fei. Fatigue characteristics in drivers of different ages based on analysis of EEG[J]. China Journal of Highway and Transport, 2018, 31(4): 59-65.
20	卢运梅. SVM-RFE算法在数据分析中的应用[D]. 长春: 吉林大学计算机科学与技术学院, 2009.
	Lu Yun-mei. The application of SVM-RFE algorithm to data analysis[D]. Changchun: College of Computer Science and Technology, Jilin University, 2009.
21	王芳荣,郭柏苍,金立生,等.次任务驾驶安全评价指标筛选及其权值计算[J]. 吉林大学学报: 工学版, 2017, 47(6): 1710-1715.
	Wang Fang-rong, Guo Bai-cang, Jin Li-sheng, et al. Selection of safe evaluation indexes and weight calculation for secondary task driving[J]. Journal of Jilin University(Engineering and Technology Edition), 2017, 47(6): 1710-1715.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

驾驶人特征		数量	比例/%	2019年中国司机总数的百分比/%
性别	男	42	70.0	70.00*
性别	女	18	30.0	30.00*
年龄	18~25	14	23.3	24.10*
	26~35	20	33.3	34.12*
	36~50	24	40.0	38.88*
	>60	2	3.3	2.90*
驾龄/年			4~15，均值=8，标准差=3.34
驾驶里程/万公里			均值=3.57，标准差=1.78

序号	符号	特征指标	指标类别
1	R_（_α₊_β_）	脑电指标R_（_α₊_β_）	脑电指标
2	R_（_α_/_β_）	脑电指标R_（_α_/_β_）
3	R_（_θ₊_β_）	脑电指标R_（_θ₊_β_）
4	Pupil_Mean	瞳孔直径均值	眼动指标
5	Fixation_X_Mean	注视点的水平位置均值
6	SacSP_Mean	扫视速度均值
7	Fixation_Y_Mean	注视点的垂直位置均值
8	SDLP	横向位移标准差	驾驶绩效指标
9	SDLA	横向加速度标准差
10	SDSWA	方向盘转角标准差
11	SP_Mean	车速均值
12	LonA_Mean	纵向加速度均值
13	LonD_Mean	纵向减速度均值
14	ThrottleP_Mean	油门开度均值
15	SWV_Mean	方向盘转角角速度均值
16	YawV_Mean	横摆角速度均值
17	BrakeP_Mean	制动踏板开度均值

重要度序号	指标描述	符号
1	脑电指标R_（_θ₊_β_）	R_（_θ₊_β_）
2	瞳孔直径均值	Pupil_Mean
3	横向位移标准差	SDLP
4	方向盘转角标准差	SDSWA
5	扫视速度均值	SacSP_Mean
6	车速均值	SP_Mean
7	注视点的水平位置均值	Fixation_X_Mean
8	注视点的垂直位置均值	Fixation_Y_Mean
9	横向加速度标准差	SDLA
10	脑电指标R_（_α₊_β_）	R_（_α₊_β_）
11	纵向加速度均值	LonA_Mean
12	方向盘转角角速度均值	SWV_Mean
13	横摆角速度均值	YawV_Mean
14	制动踏板开度均值	BrakeP_Mean
15	脑电指标R_（α/_β_）	R_（_α/β_）
16	纵向减速度均值	LonD_Mean
17	油门开度均值	ThrottleP_Mean

特征个数	准确率/%	精确率/%	召回率/%	F₁值/%
5	89.75	87.70	89.81	88.74
6	90.13	89.62	90.75	90.18
7	93.00	92.57	93.50	93.03
8	94.75	94.08	95.50	94.78
9	96.58	95.28	97.22	96.24
10	95.25	93.99	96.00	93.84
11	93.75	92.47	95.25	93.43

特征个数	准确率 /%	精确率 /%	召回率 /%	F₁值 /%	算法类别
9	96.58	95.28	97.22	96.24	Bi-LSTM+ Attention
9	93.36	92.38	92.94	92.66	SVM
9	92.17	90.84	91.85	91.34	决策树

一种混行环境下驾驶人认知分心识别方法

A recognition method for driver's cognitive distraction in simulated mixed traffic environment

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 21

相关文章 1

Metrics

本文评价

推荐阅读 0