[1]段锁林,徐亭婷,庄 玮.基于小波包和ICA的ERD/ERS脑电信号特征提取[J].常州大学学报(自然科学版),2014,(02):38-42.[doi:10.3969/j.issn.2095-0411.2014.02.010]
　DUAN Suo-lin,XU Ting-ting,ZHUANG Wei.Feature Extraction of ERD/ERS Signal Basedon the Wavelet Package and ICA[J].Journal of Changzhou University(Natural Science Edition),2014,(02):38-42.[doi:10.3969/j.issn.2095-0411.2014.02.010]
点击复制

基于小波包和ICA的ERD/ERS脑电信号特征提取()
分享到：

常州大学学报(自然科学版)[ISSN:2095-0411/CN:32-1822/N]

卷:
期数:
2014年02期
页码:
38-42
栏目:
出版日期:
2014-04-30

文章信息/Info

Title:
Feature Extraction of ERD/ERS Signal Based on the Wavelet Package and ICA
作者:
段锁林; 徐亭婷; 庄 玮
常州大学 机器人研究所,江苏 常州 213164
Author(s):
DUAN Suo-lin; XU Ting-ting; ZHUANG Wei
Institute of Intelligent Robots,Changzhou University,Changzhou 213164,China
关键词:
脑电信号; 运动想象; 小波包; 独立成分分析; ERD/ERS系数
Keywords:
EEG;  motor imagery;  wavelet package;  independent component analysis(ICA);  event related desynchronization/ event related synchronization(ERD/ERS)coefficient
分类号:
TP242
DOI:
10.3969/j.issn.2095-0411.2014.02.010
文献标志码:
A
摘要:
在脑机接口研究中,针对运动想象脑电信号的特征提取,采用了一种优化的基于小波包的ICA(独立成分分析)法,用于提取大脑在想象动作时产生事件相关去同步/同步(Event Related Desynchronization or Event Related Synchronization ERD / ERS)信号。利用小波包对脑电信号进行分解去除不同脑电信号之间的统计相关性,抽取包含ERD/ERS现象的特征频带,对每个特征频带分别进行ICA分解,获取与ERD/ERS现象相关的μ节律和β节律。最后引入ERD / ERS 系数作为量化指标进行想象动作的识别。分类仿真结果表明,上述方法能够显著增强运动想象脑电信号的ERD/ERS 特征信息,对比与独立使用某一种方法,两种方法结合更能有效的提取脑电信号特征波。
Abstract:
In the study of braincomputer interface(BCI),a novel method of extracting electroencephalography(EEG)features based on wavelet package combined with ICA(Independent Component Analysis)was adopted to extract event related desynchronization or event related synchronization(ERD/ERS)signals produced by imaginary movement.First, in order to avoid the statistical correlation between different EEG rhythms,the EEG signal was decomposed to five levels by wavelet packet. At the same time some subband with notable ERD/ERS phenomenon were remained. Then ICA was separately applied on the subband components to obtain theμband and β band corresponding to the ERD/ERS phenomenon. Finally,ERD/ERS coefficient was introduced as a quantity index for the recognition of imaginary movements.The calculated results show that the adopted method can significantly enhance the feature information of ERD/ERS produced by imaginary movement.Compared with applying the two methods separately,the method combined wavelet package with ICA is more efficient to extract feature wave.

参考文献/References:

[1] Pfurtscheller G,Neuper C,Schlogl A,et al.Separability of EEG signals recorded during right and left motor imaginary using adaptive autoregressive parameters[J].IEEE Trans Rehabil Eng,1998(6):316-325.
[2] Wolpaw J R,McFarland D J,Vaughan T M,et al.Brain computer interface research at the Wadsworth Center[J].IEEE Trans Rehabil Eng,2000(8):222-225.
[3] 张爽.基于左右手运动想象的脑-机接口的算法研[D].天津:天津大学,2007.
[4] 王攀,沈继忠,施锦河.想象左右手运动的脑电特征提取[J].传感技术学报,2010,23(9):1220-1225.
[5] 李明爱,王蕊,郝冬梅.想象左右手运动的脑电特征提取及分类研究[J].中国生物医学工程学报,2009,28(2):166-170.
[6] 葛哲学,沙威.小波分析理论与MATLAB R2007实现[M].北京:电子工业出版社,2007:120-121.
[7] Pfurtscheller G, Lopes da Silva F H.Event-related EEG/MEG synchronization and desynchronization: basic principles[J].Clinical Neurophysiology,1999,110:1842-1857.
[8] 万柏坤,周仲兴,刘哑伟,等.基于ICA与PSD的ERD/ERS信号检测[J].天津大学学报,2008,41(11):1383-1390.
[9] 杨淑莹.模式识别与智能计算——Matlab技术实现[M].北京:电子工业出版社,2008:50-100.

备注/Memo

备注/Memo:
基金项目:机器人技术与系统国家重点实验室开放基金重点项(SKLRS20102D09)。 作者简介:段锁林(1956-),男,陕西岐山人,博士,教授,主要从事机器视觉与智能移动机器人控制研究。
更新日期/Last Update: 2014-04-20