基于个性化行为模型的驾驶疲劳识别方法

doi:10.16265/j.cnki.issn1003-3033.2018.06.008

中国安全科学学报 ›› 2018, Vol. 28 ›› Issue (6): 43-48.doi: 10.16265/j.cnki.issn1003-3033.2018.06.008

基于个性化行为模型的驾驶疲劳识别方法

楚文慧^1,2, 吴超仲¹ 教授, 张晖^**1 副教授, 杨曼¹, 李思瑶¹

1 武汉理工大学智能交通系统研究中心,湖北武汉 430063;
2 武汉科技大学汽车与交通工程学院,湖北武汉 430081

收稿日期:2018-03-12 修回日期:2018-05-20 出版日期:2018-06-28 发布日期:2020-11-25
通讯作者: **张晖(1983—),男,安徽肥东人,博士,副教授、主要从事道路交通安全、驾驶行为等方面的研究。E-mail:zhanghuiits@whut.edu.cn。
作者简介:楚文慧(1990—),女,山东菏泽人,博士研究生,研究方向为汽车主动安全与驾驶行为。E-mail:chuwh@whut.edu.cn。
基金资助:
国家重点研发计划项目(2017YFC0804802);国家自然科学基金资助(51775396, 61603282);国家自然科学基金—联合基金资助(u1624262)。

Driver behavior model and its application in driver fatigue identification

CHU Wenhui ^1,2, WU Chaozhong ¹, ZHANG Hui ¹, YANG Man ¹, LI Siyao ¹

1 Intelligent Transportation Systems Research Center,Wuhan University of Technology,Wuhan Hubei 430063,China;
2 School of Automobile and Traffic Engineering,Wuhan University of Science and Technology,Wuhan Hubei 430081,China

Received:2018-03-12 Revised:2018-05-20 Online:2018-06-28 Published:2020-11-25

摘要/Abstract

摘要： 为提高疲劳驾驶状态的识别精度,应考虑驾驶人之间的个体差异。以实车驾驶试验条件下车道保持行为中的车速和车道偏离值为输入,以方向盘转角为输出,基于径向基(RBF)神经网络针对每个驾驶人构建正常驾驶状态下的车道保持行为模型,并根据残差对模型的拟合及预测效果进行评价;将疲劳驾驶状态下的车速和车道偏离值输入到上述驾驶行为模型中,可得到模型预测的方向盘转角值,通过分析预测值与实际方向盘转角之间的差异,研究疲劳对驾驶人行为的影响;将预测残差作为输入,建立基于支持向量机(SVM)的疲劳驾驶状态辨识模型。结果表明:所建立的RBF神经网络-SVM识别模型对不同驾驶人疲劳驾驶状态的平均识别率达85%。

关键词: 个性化驾驶, 径向基(RBF)神经网络, 驾驶行为建模, 疲劳驾驶, 支持向量机(SVM), 实车试验

Abstract: It is held by the authors that in order to improve the identification precision of fatigue driving condition,individual difference among drivers should be considered.A RBF neural network based modeling framework is developed to characterize the lane keeping behavior of a driver under normal driving conditions.The effectiveness of the model is analyzed by studying the residuals,i.e.,the differences between the actual and model-predicted driver actions.The model is then used in fatigue driving to predict the hypothetical actions of the driver.The difference between the predicted normal behavior and the actual fatigued behavior gives individual insight into how the driving behavior is affected by fatigue.The residuals were extracted as the input features of a SVM model,which was used to classify normal and fatigued driving conditions for each driver.The validation results show that the average identification accuracy of fatigued driving condition by the proposed model is 85%.

Key words: personalized driving, radial basis function (RBF) neural network, driver behavior modeling, fatigued driving, support vector machine (SVM), field test

中图分类号:

X910

楚文慧, 吴超仲, 张晖, 杨曼, 李思瑶. 基于个性化行为模型的驾驶疲劳识别方法[J]. 中国安全科学学报, 2018, 28(6): 43-48.

CHU Wenhui, WU Chaozhong, ZHANG Hui, YANG Man , LI Siyao. Driver behavior model and its application in driver fatigue identification[J]. China Safety Science Journal, 2018, 28(6): 43-48.

参考文献

[1] HULBERT S.Effects of driver fatigue:in TW Forbes (Ed.),human factors in highway traffic safety research[J].Applied Ergonomics,1974,5(3):173-173.
[2] DINGUS T A,HARDEE L,WIERWILLE W W.Development of impaired driver detection measures[R].USA Department Report 8504.Blacksburg:Department of Industrial Engineering and Operations Research,Virginia Polytechnic Institute and State University,1985.
[3] INGRE M,ÉKERSTEDT T,PETERS B,et al.Subjective sleepiness,simulated driving performance and blink duration:examining individual differences[J].Journal of Sleep Research,2006,15(1):47-53.
[4] 吴超仲,张晖,毛喆,等.基于驾驶操作行为的驾驶员疲劳状态识别模型研究[J].中国安全科学学报,2007,17(4):162-165.
WU Chaozhong,ZHANG Hui,MAO Zhe,et al.A model for identifying fatigue status of vehicle drivers based on driving operation[J].China Safety Science Journal,2007,17(4):162-165.
[5] LI Zuojin,LI Shengbo,LI Renjie,et al.Online detection of driver fatigue using steering wheel angles for real driving conditions[J].Sensors,2017,17(3):495-506.
[6] ZHANG Hui,WU Chaozhong,HUANG Zhen,et al.Sensitivity of lane position and steering angle measurements to driver fatigue[J].Transportation Research Record Journal of the Transportation Research Board,2016,2585:67-76.
[7] LIN N,ZONG C,TOMIZUKA M,et al.An overview on study of identification of driver behavior characteristics for automotive control[J/OL].Mathematical Problems in Engineering,2014.https://doi.org/10.1155/2014/569109.
[8] 吕能超,任泽远,段至诚,等.Near-crash事件中驾驶人行为特征分析[J].中国安全科学学报,2017,27(6):19-24.
LYU Nengchao,REN Zeyuan,DUAN Zhicheng,et al.Analysis of driving behavior characteristics of drivers in Near-crash events[J].China Safety Science Journal,2017,27(6):19-24.
[9] MIYAJIMA C,NISHIWAKI Y,OZAWA K,et al.Driver modeling based on driving behavior and its evaluation in driver identification[J].Proceedings of the IEEE,2007,95(2):427-437.
[10] ERSAL T,FULLER H J A,TSIMHONI O,et al.Model-based analysis and classification of driver distraction under secondary tasks[J].IEEE Transactions on Intelligent Transportation Systems,2010,11(3):692-701.
[11] GONZLEZ A B R,WILBY M R,DAZ J J V,et al.Modeling and detecting aggressiveness from driving signals[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(4):1419-1428.
[12] ENEV M,TAKAKUWA A,KOSCHER K,et al.Automobile driver fingerprinting[J].Proceedings on Privacy Enhancing Technologies,2016,2016(1):34-50.
[13] GILLBERG M,KECKLUND G,AKERSTEDT T.Relations between performance and subjective ratings of sleepiness during a night awake.[J].Sleep,1994,17(3):236-241.
[14] 丁洁云.自适应驾驶员特性的车道保持辅助控制[D].北京:清华大学,2015.
DING Jieyun.Lane keeping auxiliary control with adaptive driver characteristics[D].Beijing:Tsinghua University,2015.
[15] 彭金栓,付锐,郭应时.自然驾驶条件下驾驶人换道行为实时预测[J].哈尔滨工业大学学报,2015,47(9):119-123.
PENG Jinshuan,FU Rui,GUO Yingshi.Real-time prediction of driver's lane change under natural driving conditions[J].Journal of Harbin Institute of Technology,2015,47(9):119-123.
[16] VAPNIK V N.An overview of statistical learning theory[J].IEEE Transactions on Neural Networks,1999,10(5):988-999.
[17] BYUN H,LEE S.A survey on pattern recognition applications of support vector machines[J].International Journal of Pattern Recognition & Artificial Intelligence,2002,17(3):459-486.
[18] LIANG Y,REYES M L,LEE J D.Real-time detection of driver cognitive distraction using support vector machines[J].IEEE Transactions on Intelligent Transportation Systems,2007,8(2):340-350.

基于个性化行为模型的驾驶疲劳识别方法

Driver behavior model and its application in driver fatigue identification

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杨文臣, 周燕宁, 田毕江, 郭凤香, 胡澄宇. 基于聚类分析和SVM的二级公路交通事故严重度预测[J]. 中国安全科学学报, 2022, 32(5): 163-169.
[2]	丁茜, 赵晓东, 吴鑫俊, 张泰丽, 徐振涛. 基于RBF核的多分类SVM滑塌易发性评价模型[J]. 中国安全科学学报, 2022, 32(3): 194-200.
[3]	吴孟龙, 叶义成, 胡南燕, 王其虎, 李文, 江慧敏. 基于模糊信息粒化的矿业安全生产态势区间预测^*[J]. 中国安全科学学报, 2021, 31(9): 119-127.
[4]	赵挺生, 庞奇志, 姜雯茜. 基于数据库与支持向量机的施工升降机安全风险预测[J]. 中国安全科学学报, 2021, 31(4): 11-17.
[5]	刘阳, 张建经, 罗宏森, 于海莹, 向波. 基于贝叶斯网络的Fuzzy-SVM路基震害预测模型^*[J]. 中国安全科学学报, 2021, 31(11): 171-178.
[6]	郑晓亮, 来文豪, 薛生. MI和SVM算法在煤与瓦斯突出预测中的应用[J]. 中国安全科学学报, 2021, 31(1): 75-80.
[7]	乔建刚, 郭蕊, 李维东. 穿城镇道路驾驶员眼动特性分析[J]. 中国安全科学学报, 2020, 30(7): 13-18.
[8]	马辉, 吕航, 栾瑞斌. 基于空间单元分析的装配式建筑施工安全预警模型[J]. 中国安全科学学报, 2020, 30(5): 27-32.
[9]	武琳玉, 梁伟, 沙夺林. 油气站场典型设备的焊缝缺陷检测与识别方法[J]. 中国安全科学学报, 2020, 30(11): 108-113.
[10]	马英楠, 吕子阳, 高星, 王勇毅. 基于SVM的居家老人跌倒预测方法研究[J]. 中国安全科学学报, 2019, 29(6): 43-48.
[11]	马杰, 刘琪, 张春玮, 刘克中, 张煜. 基于AIS的数据时空分析及船舶会遇态势提取方法[J]. 中国安全科学学报, 2019, 29(5): 111-116.
[12]	王岩韬, 赵嶷飞. 基于多算法协作的航班运行风险辨识研究[J]. 中国安全科学学报, 2018, 28(6): 166-172.
[13]	胡剑锋, 王涛涛. 基于脑电信号模糊熵的驾驶疲劳检测分析[J]. 中国安全科学学报, 2018, 28(4): 13-18.
[14]	邵良杉, 周玉. QGA-RFR模型在导水裂隙带高度预测中的应用[J]. 中国安全科学学报, 2018, 28(3): 19-24.
[15]	毛志勇, 黄春娟, 路世昌. 基于PSO-SVM的砂土地震液化预测模型[J]. 中国安全科学学报, 2018, 28(3): 25-30.