计算机科学 ›› 2020, Vol. 47 ›› Issue (5): 225-229.doi: 10.11896/jsjkx.190400127

• 人工智能 • 上一篇    下一篇

基于单通道脑电信号的疲劳检测系统

王博石, 吴修诚, 胡馨艺, 张莉   

  1. 重庆大学电气工程学院 重庆400044
  • 收稿日期:2019-04-23 出版日期:2020-05-15 发布日期:2020-05-19
  • 通讯作者: 吴修诚(1215942547@qq.com)
  • 作者简介:493733680@qq.com

Fatigue Detection System Based on Single Channel EEG Signal

WANG Bo-shi, WU Xiu-cheng, HU Xin-yi, ZHANG Li   

  1. School of Electrical Engineering,Chongqing University,Chongqing 400044,China
  • Received:2019-04-23 Online:2020-05-15 Published:2020-05-19
  • About author:WANG Bo-shi,born in 1997,postgra-duate.His main research interests include brain-computer interface and so on.
    WU Xiu-cheng,born in 1998,postgra-duate.His main research interests include electrical engineering and automation.

摘要: 针对目前高强度劳动人群频繁猝死的情况,文中设计了一套基于单通道脑电信号(Electroencephalography,EEG)的疲劳检测系统,以实现对该类人群疲劳程度的准确判定,起到预警效果。系统利用TGAM(ThinkGearm AM)脑电模块采集原始EEG数据,通过蓝牙方式将数据传送至上位机,在上位机中提取EEG的4个基本节律成分(δ,θ,α,β),以节律信号的相对频带能量作为表征疲劳状态的脑电特征,并利用Fisher判别分析(Fisher Discriminant Analysis,FDA)和概率神经网络(Probabilistic Neural Network,PNN)两种方法对脑电特征进行分类,给出评估结果。实验结果表明,所设计的基于单通道EEG的疲劳检测系统能够实现准确率较高的疲劳状态检测。

关键词: EEG, FDA算法, GUI, TGAM脑电模块, 基本节律

Abstract: For sudden death in people with high labor intensity,this paper designs a fatigue detection system based on single-channel EEG to realize accurate judgment of the fatigue level in order to make a timely warning for this kind of people.The system uses the TGAM(ThinkGear AM) to collect the original EEG data,transmits the data to the host computer via Bluetooth,and extracts four basic rhythm components (δ,θ,α,β) of the EEG in the host computer.The relative frequency band energies of some rhythms are used as the EEG features characterizing fatigue state,and Fisher discriminant analysis(FDA) and probabilistic neural network(PNN) are used to classify EEG features.Finally,the evaluation results are given.The experimental results show that the designed single-channel EEG-based fatigue detection system can achieve high accuracy of fatigue state detection.

Key words: Basic rhythm, EEG, FDA algorithm, GUI, TGAM EEG module

中图分类号: 

  • TP391.4
[1]WANG R Y.Sports Physiology [M].Beijing:People's Sports Publishing House,2002.
[2]LIU Z Q,SONG X S,WANG P,et al.An Identification Method of Fatigue Driving Based on Eye Features[J].Journal of Chongqing University of Technology(Natural Science),2016,30(10):11-15,33.
[3]MORRIS T L,MILLER J C.Electrooculographic and perfor-mance indices of fatigue during simulated flight [J].Biological Psychology,1996,42(3):343-360.
[4]LAL S K L,CRAIG A.Phyasiological indicators of driver fatigue [C]//Rood Satety Research Policing & Bducation.2000.
[5]ZHANG C,WANG H,FU R.Automated Detection of DriverFatigue Based on Entropy and Complexity Measures [J].IEEE Transactions on Intelligent Transportation Systems,2014,15(1):168-177.
[6]ZHANG L Y,ZHENG C X.Study on the EEG Kolmogorov entropy measure for mental fatigue state [J].Chinese Journal of Biomedical Engineering,2007,2(2):170-176.
[7]ZHAO C L,ZHENG C X,ZHAO M.Research on driving mental fatigue grading based on kernel learning algorithm [J].Journal of Data Acquisition & Processing,2009,24(3):335-339.
[8]DU S X,WU T J.Support Vector Machine Method in Pattern Recognition [J].Journal of Zhejiang University(Engineering Science),2003,37(5):521-527.
[9]ZHAO H,RONG L L,LI X.A new method for designing hie-rarchical support vector machine multi-class classifiers [J].Journal of Computer Applications,2003(5):34-37.
[10]CHEN T,CHEN Z G,YUAN X H,et al.Emotion RecognitionMethod Based on Instantaneous Energy of Electroencephalography[J].Computer Engineering,2019,45(4):196-204.
[11]LIU J L.Design and research of brain-computer interface system based on steady-state visual evoked potential [J].Industrial Control Computer,2011(5):8-9.
[12]SUN Z D.Activate the sleeping brain [M].Heilongjiang Science and Technology Press,2010.
[13]XIAO Z H,YU H,WANG Y C.Unsupervised Machine Learning Based on the Sum of Squares of the Dynamic Deviations[J].Journal of Chongqing University of Technology(Natural Science),2018,32(11):134-139,186.
[14]ZHENG J H.Dictionary of Statistics [M].China StatisticsPress,1995:207.
[15]ZHOU Z H.Machine Learning [M].Tsinghua UniversityPress,2016:53.
[16]LI J J,DING Z S,ZHANG H Y.Analysis of Common Discriminant Classification Methods[J].Journal of Xi'an University of Science and Technology,2007,27(1):138-139.
[17]DING L,ZENG S L.HandwrittenMiaowen Recognition Re-search Based on Probabilistic Neural Network [J] .Journal of Dali University,2018(12).
[18]LIN W,WANG X,ZHENG Y H,et al.Study on feature extraction and recognition of partial discharge signals based on probabilistic neural network [J].Electrical Automation,2018,40(3):64-67.
[19]ZHANG M.Design of Communication Principle Demonstration System Based on Matlab GUI[J].Journal of Experimental Technology and Management,2013,30(9):111-113,127.
[1] 王皓亮,高建华.
GUI测试中多级形态模型的分割与应用
Segmentation and Application of Multilevel Morphology Model in GUI Testing
计算机科学, 2017, 44(9): 190-194. https://doi.org/10.11896/j.issn.1002-137X.2017.09.036
[2] 申晓宁,谢文武.
基于量子进化算法的移动机器人实时路径规划
Real-time Path Planning for Mobile Robots Based on Quantum Evolutionary Algorithm
计算机科学, 2013, 40(5): 229-232.
[3] 关菁华,刘大有.
一种挖掘概念漂移数据流的选择性集成算法
Selected Ensemble of Classifiers for Handling Concept-drifting Data Streams
计算机科学, 2010, 37(1): 205-207.
[4] 李炯 卢显良 董仕.
基于GridSim模拟器的网格资源调度算法研究

计算机科学, 2008, 35(8): 95-97.
[5] 裴玉.
基于SVG的自适应软件界面开发工具设计与实现

计算机科学, 2008, 35(1): 271-273.
[6] 尹文超 陈渝 康烁 杨晔 曾益.
SkyEye模拟器的LCD及TouchScreen模拟模块的设计、实现与验证

计算机科学, 2005, 32(6): 189-192.
[7] 张鹏 徐鹏.
GUI抽象描述模型研究

计算机科学, 2005, 32(11): 198-201.
[8] 乔健 陈彤兵 汪卫 施伯乐.
一种基于结构索引的XML模式匹配方法

计算机科学, 2005, 32(10): 95-99.
[9] 佟立峰.
应用设计模式设计可移植的、可扩充、简单灵活的嵌入式GUIToolkit

计算机科学, 2003, 30(10): 99-102.
[10] 王咏 徐贯东.
面向GUI的软件开发模型—I&F模型

计算机科学, 2000, 27(8): 47-49.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!