|本期目录/Table of Contents|

[1]叶 春,高 浩.基于Morlet小波的EEG疲劳程度的识别研究[J].绵阳师范学院学报,2017,(08):89-94,120.
 YE Chun,GAO Hao.Recognition of EEG Fatigue Degree Based on Morlet Wavelet Transform[J].Journal of Mianyang Normal University,2017,(08):89-94,120.
点击复制

基于Morlet小波的EEG疲劳程度的识别研究(PDF)
分享到:

《绵阳师范学院学报》[ISSN:1672-612X/CN:51-1670/G]

卷:
期数:
2017年08期
页码:
89-94,120
栏目:
计算机与网络技术
出版日期:
2017-08-15

文章信息/Info

Title:
Recognition of EEG Fatigue Degree Based on Morlet Wavelet Transform
文章编号:
1672-612X(2017)08-0089-06
作者:
叶 春1高 浩2
1.江苏信息职业技术学院,江苏无锡 214001;
2.南京邮电大学自动化学院,江苏南京 210003
Author(s):
YE Chun1GAO Hao2
Jiangsu Vocational College of Information and Techninology,Wuxi 214001, China;
College of Automation,Nanjing University of Posts and Telecommunications,Nanjing 210023, China
关键词:
Morlet小波变换 脑电信号 特征提取
Keywords:
Morlet wavelet transform EEG signal feature extraction
分类号:
TP391
DOI:
-
文献标志码:
A
摘要:
为了识别人类疲劳程度,文中提出一种基于Morlet小波变换的EEG脑电信号测量方法来分析受测者的眼动信号,通过时域信号的特征值筛选来识别疲劳状态,进而了解受测者的疲劳程度.本研究使用非侵入式脑电信号测量仪,进行脑电信号原始数据的采集,使用Matlab程序对于脑电信号进行Morlet小波变换(Morlet Wavelet transform, MWT)将信号分解,再将数据转化为特征值之后,使用支持向量机(Support vector machine, SVM)与反向传播类神经网络(Back propagation neural network, BPNN)进行疲劳的状态分析.该方法对400名测试者在不同疲劳程度状态下进行测试,结果显示脑电信号识别的正确率平均达到96.15%.
Abstract:
In order to identify the degree of human fatigue, an EEG signal measurement method based on Morlet wavelet transform was proposed to analyze the eye movement signal of the subject, and the fatigue state was identified by the eigenvalue screening of the time domain signal to understand the fatigue of the subject degree. In this study, we used the non-invasive EEG signal measuring instrument to collect the original data of EEG signal. Morlet wavelet transform(Morlet Wavelet transform, MWT)was used to decompose the signal and then transform the data into eigenvalues, Thenthe state analysis of fatigue was carried out using Support Vector Machine(SVM)and Back Propagation Neural Network(BPNN). This method tested 400 testers at different degrees of fatigue. The results showed that the correct rate of EEG identification was 96.15%.

参考文献/References:

[1] Murata A,Uetake A,Takasawa Y.Evaluation of mental fatigue using feature parameter extracted from event-related potential[J].International Journal of Industrial Ergonomics,2015,36(14):165—180.
[2] Rainer Guttkuhn,Acacia Aguirre etc.Technologies for the Monitoring and Prevention of driver Fatigue. Anneke Heitmann[J].Driver Assessment Training and Vehicle Design,2014,24(12):424—430.
[3] Jung T.P.,Makeig S,Stensmo M.et al.Estimating Alertness from the EEG Power Spectrum[J].IEEE Transactions on Bio-medical Engineering,2013,12(3):234—242.
[4] Blankertz B,Tomioka R,Lemm S,et al.Optimizing spatial filters for robust EEG single-trial analysis[J].IEEE Signal Processing Maga-zine,2015,36(11):348—390.
[5] Lin C T,Wu R C,Liang S F,et al. EEG-based drowsinessestimation for safety driving using independent componentanalysis[J].IEEE Transactions on Circuits and Systems,2015,12(4):598—599.
[6] 王斐,王少楠,王惜慧,彭莹,杨乙丁.基于脑电图识别结合操纵特征的驾驶疲劳检测[J].仪器仪表学报,2014,12(12):158—160.
[7] 王福旺,王宏,罗旭.基于EEG与EOG信号的疲劳驾驶状态综合分析[J].东北大学学报(自然科学版),2014,12(05):66—69.
[8] 施锦河,沈继忠,王攀.四类运动想象脑电信号特征提取与分类算法[J].浙江大学学报(工学版),2012,12(11):52—55.
[9] 袁翔,孙香梅.疲劳驾驶检测方法研究进展[J].汽车工程学报,2012,6(2):245—266.
[10] 颜世玉,王宏,刘冲,赵海滨.基于小波方差的运动想象脑电信号特征提取[J].东北大学学报(自然科学版),2012,12(07):145—156.

相似文献/References:

备注/Memo

备注/Memo:
基金项目: 国家自然科学基金(61571236,61602255,61203196); 中国博士后基金(2014M551632)资助项目; 江苏省博士后基金(1402018A),江苏省省科技厅产学研资金/前瞻性联合研究项目(BY2013017); 江苏高校品牌专业建设工程资助项目(PPZY2015C239)
第一作者简介:叶春(1979—)男,江苏无锡人,硕士,讲师,计算机学会CCF专业会员(65418M),研究方向:模式识别,神经网络研究
高浩(1976—)男,安徽蚌埠人,博士,教授
更新日期/Last Update: 2017-08-15