计算机科学 ›› 2016, Vol. 43 ›› Issue (7): 314-318.doi: 10.11896/j.issn.1002-137X.2016.07.058

• 图形图像与模式识别 • 上一篇    下一篇

基于脉搏IMF时频特征和SVDD的驾驶员疲劳检测

蒋建春,蒋丽,唐慧,张卓鹏,吴雪刚   

  1. 重庆邮电大学重庆高校汽车电子与嵌入式系统工程研究中心 重庆400065,重庆邮电大学重庆高校汽车电子与嵌入式系统工程研究中心 重庆400065,重庆邮电大学重庆高校汽车电子与嵌入式系统工程研究中心 重庆400065,重庆邮电大学重庆高校汽车电子与嵌入式系统工程研究中心 重庆400065,重庆大学通信工程学院 重庆400044
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受城市交通车路协同控制仿真系统开发项目(cstc2014yykfb40001),重庆市教委科学技术研究项目(KJ1500442),国家自然科学基金项目(91438104)资助

Driver Fatigue Detection Based on IMF Time-frequency Features of Pulse Signal and SVDD

JIANG Jian-chun, JIANG Li, TANG Hui, ZHANG Zhuo-peng and WU Xue-gang   

  • Online:2018-12-01 Published:2018-12-01

摘要: 针对传统时频特征难以很好地描述脉搏这类非平稳信号与驾驶员疲劳脉搏样本相对较少的问题,提出一种基于脉搏信号本征模函数(IMF)时频特征和支持向量数据描述(SVDD)的驾驶员疲劳检测方法。该方法充分利用了IMF适合表征非平稳信号和SVDD擅长处理不平衡样本分类问题的优势。首先,将脉搏信号进行经验模态分解;然后,提取各IMF时频特征:归一化能量、最大瞬时频率和瞬时幅值平均值;最后,用SVDD分类器对驾驶员疲劳状况做出判别并给出疲劳等级。对比实验表明,该方法能有效检测出驾驶员的疲劳状况。

关键词: 疲劳驾驶,脉搏信号,本征模函数,支持向量数据描述

Abstract: To address the problems of traditional time-frequency features’ being hard to characterize the non-stationary signal (e.g.,pulse signal) and the fewer samples of driver fatigue pulses,an approach was proposed to detect driver’s fatigue based on the time-frequency features of intrinsic mode function (IMF) of pulse signal and support vector data description (SVDD).This approach makes full use of the advantages of the IMF’ being suitable for characterizing non-stationary signal and SVDD’ being good at addressing the classification with unbalanced samples.First,the pulse signals are decomposed by using empirical mode decomposition method to obtain multiple IMF components.Then,the time-frequency features of IMF are extracted,which consists of the normalized energy,the maximum instantaneous frequency and the average of instantaneous amplitude.Finally,the SVDD classifier is used to detect the fatigue status of drivers and give corresponding fatigue level.Comparison experiments suggest that this approach can effectively detect the fatigue status of drivers.

Key words: Fatigue driving,Pulse signal,Intrinsic mode function,Support vector data description

[1] 疲劳驾驶案例.http://www.js.xinhuanet.com/2015-01/28/c_1114157388.htm
[2] Mitesh P,Sara L,Diarmuid K,et al.Fatigue detection usingcomputer vision[J].International Journal of Electronics and Telecommunications,2010,6(4):457-461
[3] Begum S.Intelligent driver monitoring systems based on physiological sensor signals:A Review[C]∥16th International IEEE Conference on Intelligent Transportation Systems.2013:282-289
[4] He Q,Li W,Fan X.Driver fatigue evaluation model with integration of multi-indicators based on dynamic bayesian network[J].IET Intelligent Transport Systems,2015,9(5):547-554
[5] Bundele M M,Banerjee R.Detection of fatigue of vehicular dri-ver using skin conductance and oximetry pulse:A neural network approach[C]∥The 11th International Conference on Information Integration and Web-based Applications and Services.2009:739-744
[6] Veena S L,MTech I.Efficient method of driver alertness using hybrid approach of eye movements and bio-signals[C]∥2014 International Conference on Intelligent Computing Applications.2014:78-80
[7] Qian S,Yu Z,Shen X.The Design and research of the vehicle in-telligent system of avoiding sleeping based on pulse[C]∥Industrial Engineering,Machine Design and Automation & Computer Science and Application.2015:458-465
[8] Bundele M M,Banerjee R.An SVM classifier for fatigue-detection using skin conductance for use in the BITS-lifeguard wearable computing system[C]∥2009 2nd International Conference on Emerging Trends in Engineering and Technology.2009:934-939
[9] Zhang A H,Zhao Z Y,Yang H.Visual Fatigue State Recognition Based on ECG Pulse Feature[J].Computer Engineering,2011,7(7):279-281(in Chinese) 张爱华,赵治月,杨华.基于心电脉搏特征的视觉疲劳状态识别[J].计算机工程,2011,7(7):279-281
[10] Li Y P.Visualized Pulse Signal Detecting Method for MentalFatigue Recognition[D].Lanzhou:Lanzhou University of Technolog,2008(in Chinese) 李永平.脉搏图像化监测方法对精神疲劳状态的识别[D].兰州:兰州理工大学,2008
[11] Huang N E.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proc.R.Soc.Lond.A.,1998,4:903-995
[12] Tal O,Adi R.Road characteristics and driver fatigue:A Simulator Study[J].Traffic Injury Prevention,2007(8):281-289
[13] Xie X L.Study on Driving Fatigue Formation Mechanism[D].Beijing:Beijing University of Technology,2010(in Chinese) 谢晓莉.驾驶疲劳生成机理研究[D].北京:北京工业大学,2010
[14] Zhang H L.Researeh of Emotion Recognition Based on PulseSignal[D].Chongqing:Southwest University,2011(in Chinese) 张慧玲.基于脉搏信号的情感识别研究[D].重庆:西南大学,2011
[15] Kim S,Choi Y,Lee M.Deep learning with support vector data description [J].Neurocomputing,2015,5:111-117
[16] Wu Z,Huang N E.Ensemble empirical mode decomposition:A noise-assisted data analysis method[J].Advances in Adaptive Data Analysis,2009,1(1):1-41
[17] Wang W H,Chen S W,Zhang S Q,et al.Feature-Preserving I-mage Denoising Method Combining EMD and Wavelet Analysis[J].Computer Science,2013,0(10):265-268(in Chinese) 王卫红,程时伟,张素琼,等.EMD与小波分析结合的特征保持图像去噪方法[J].计算机科学,2013,0(10):265-268
[18] Cao X N,Cai X D,Zheng S B.Analysis of Acceleration of Train Axle Box Based on Hilbert-Huang Transformation[J].Instrument Technique and Sensor,2015(3):92-95(in Chinese) 曹西宁,柴晓冬,郑树彬.基于Hilbert-Huang 变换的轨道车辆轴箱加速度信号分析[J].仪表技术与传感器,2015(3):92-95
[19] Tax D M J,Duin R P W.Support vector data description[J].Machine Learning,2004,4(1):45-66
[20] Xing H J,Zhao H X.Feature Extraction and Parameter Selection of SVDD Using Simulated Annealing Approach[J].Computer Science,2013,0(1):302-305(in Chinese) 邢红杰,赵浩鑫.基于模拟退火的SVDD特征提取和参数选择[J].计算机科学,2013,0(1):302-305

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!