Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)
计算机技术﹑电信技术     
分形维数结合RLS-ICA的脑电信号消噪
杨帮华,韩志军,王倩,何亮飞
上海大学 机电工程与自动化学院,上海 200072
Hybrid methodology combining fractal dimension and RLS-ICA for rejection of electroencephalography noise
YANG Bang-hua, HAN Zhi-jun, WANG Qian, HE liang-fei
School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072,China
 全文: PDF(2782 KB)   HTML
摘要：

针对脑机接口中脑电信号噪声的去除,提出将分形维数、递归式最小均方(RLS)-独立分量分析(ICA)相结合的方法.利用ICA对脑电信号进行盲源分离,得到源信号；采用分形维数自动识别源信号中的噪声信号；利用RLS自适应滤波器对已识别出来的噪声信号进行自适应滤波；通过信号重构,得到去除噪声的脑电信号.该方法有2个优点：一是通过对分形维数自动识别源信号中的噪声信号进行滤波,克服了RLS-ICA将所有源信号进行滤波,可能造成部分有用脑电信号被去除的缺点；二是通过分形维数减少RLS滤波的独立源,加快了运行速度.为了证明该方法的有效性,分别对2008年国际BCI竞赛数据和本实验室的数据进行处理.将该方法与RLS-ICA进行比较,结果显示,该方法的去噪效果明显优于RLS-ICA,单个样本的运行时间比RLS-ICA少007 s.采用提出的方法不仅能够去除一些常见的诸如眼电(EOG)、肌电(EMG)等噪声,而且能够去除一些未知的噪声.
Abstract:

A novel method combining fractal dimension and recursive least-squares (RLS)-independent component analysis (ICA) was presented in order to remove noise from electroencephalography (EEG) in the study on brain computer interfaces (BCIs). The ICA was used to decompose the contaminated EEG signals into independent components (ICs). Then the fractal dimension was used to automatically identify ICs containing noises. The RLS adaptive filters were applied to filter noise in the identified ICs further. The processed ICs were projected back to reconstruct the uncontaminated EEG signals. The proposed method has two obvious advantages. One is that it only filters ICs identified to contain noise by fractal dimension, which can overcome the shortage that RLS-ICA filters all the ICs to result in some useful EEG being deleted. The other is that it can accelerate the speed of RLS-ICA by decreasing the number of ICs to be filtered. The 2008 International BCI competition data and the laboratory data were preprocessed in order to verify the effectiveness of the proposed method. The proposed method was compared with RLS-ICA. Experimental results showed that the novel method had better performance than RLS-ICA in removing noise. The running time of one sample by the proposed method was 007 seconds shorter than that by the RLS-ICA in average. The proposed method can not only remove electrooculogram (EOG) and electromyography (EMG), but also remove some unknown noises．
出版日期: 2014-08-04
:  TN 912  
基金资助:

国家自然科学基金资助项目(60975079，31100709)；上海市教育委员会创新项目(11YZ19，12ZZ099)
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

杨帮华,韩志军,王倩,何亮飞. 分形维数结合RLS-ICA的脑电信号消噪[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2014.07.013.

YANG Bang-hua, HAN Zhi-jun, WANG Qian, HE liang-fei. Hybrid methodology combining fractal dimension and RLS-ICA for rejection of electroencephalography noise. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2014.07.013.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2014.07.013    或    http://www.zjujournals.com/eng/CN/Y2014/V48/I7/1234

［1］ 王兵,王柏祥. 脑电信号中伪迹去除的综合研究［D］. 杭州:浙江大学, 2010: 12．
WANG Bing, WANG Bai-xiang. Comprehensive study on removal of artifacts from EEG data ［D］. Hangzhou: Zhejiang University, 2010: 12．
［2］ GUERRERO-MOSQUERA C, NAVIA-VAZQUEZ A. Automatic removal of ocular artifacts using adaptive filtering and independent component analysis for electroencephalogram data ［J］. IET Signal Processing, 2012, 6(2): 99-106．
［3］ ZHU Dan-hua, TONG Ji-jun, CHEN Yu-quan. An ica-based method for automatic eye blink artifact correction in multi-channel EEG ［C］∥Proceeding of the 5th International Conference on Technology and Applications in Biomedicine.Shenzhen: IEEE, 2008: 338-341．
［4］ LI Yan-dong, MA Zhong-wei, LU Wen-kai, et al. Automatic removal of the eye blink artifact from EEG using an ica-based template matching approach ［J］. Physiological Measurement, 2006, 27(4): 425-436．
［5］ HE P, WILSON G, RUSSELL C. Removal of ocular artifacts from electro-encephalogram by adaptive filtering ［J］. Medical Biological Engineering and Computing, 2004, 42(3): 407-412．
［6］ 杜晓燕, 李颖洁, 朱贻盛. 脑电信号伪迹去除的研究进展［J］. 生物医学工程学杂志, 2008, 25(2): 464-467．
DU Xiao-yan, LI Ying-jie, ZHU Yi-sheng. Removal of artifacts from EEG signal ［J］. Journal of Biomedical Engineering, 2008, 25(2): 464-467．
［7］ 吴秀玲,张丽清. 基于独立分量分析算法的脑电诱发电位的特征提取［D］. 上海:上海交通大学, 2007: 24．
WU Xiu-ling, ZHANG Li-qing. Feature extraction of visual evoked potentials using independent component analysis ［D］. Shanghai:Shanghai Jiaotong University, 2007: 24．
［8］ WANG Qiang, OLGA Sourina, MINH Khoa-nguyen. EEG-based “serious” games design for medical applications ［C］∥2010 International Conference on Cyberworlds. Singapore: IEEE, 2010: 270-276．
［9］ GOMEZ-HERRERO G, DE CLERCQ W, ANWAR H, et al. Automatic removal of ocular artifacts in the EEG without an EOG reference channel ［C］∥Proceeding of the 7th Nordic Signal Processing Symposium. Rejkjavik: IEEE, 2006: 130-133．
［10］ 李伟平,张爱华.脑电信号自适应预处理方法的研究与应用［D］. 兰州: 兰州理工大学, 2004: 30．
LI Wei-ping, ZAHNG Ai-hua. Research and application of the EEG recording pre-processing ［D］. Lanzhou: Lanzhou University of Technology, 2004: 30．
［11］ KLAUS-ROBERT M, BENJAMIN B, CARMEN V,et al. BCI competition IV ［EB/OL］．［2012-11-06］. http:∥www.bbci.de/competition/iv/．
［12］ Mathworks ［EB/OL］．［2012-11-06］．http://www.mathworks.cn/cn/help/stats/lillietest.html．
［13］ 盛骤,谢式千,潘承毅. 概率论与数理统计［M］. 北京: 高等教育出版社, 2008: 184-187．
［14］ Mathworks ［EB/OL］．［2012-11-06］．http://www.mathworks.cn/cn/help/stats/ttest2.html．
［15］ KLADOS M A, PAPADELIS C, BRAUN C, et al. REG-ICA: a hybrid methodology combining blind source separation and regression techniques for the rejection of ocular artifacts ［J］. Biomedical Signal Processing and Control, 2011(6): 110．
［16］ 王兵,王魁,王柏祥.脑电信号中工频干扰去除的综合研究［J］.传感器学报, 2010, 23(1): 87-92．
WANG Bing, WANG Kui, WANG Bai-xiang. Comprehensive study on removal of power line Interference in EEG ［J］. Chinese Journal of Sensors and Actuators, 2010, 23(1): 87-92．
[1] 杨登舟,徐嘉明,刘加,夏善红. 说话人日志中可靠静音模型语音活动检测方法[J]. 浙江大学学报(工学版), 2016, 50(1): 151-157.
[2] 杨立春, 钱沄涛, 王文宏. 基于零陷谱减的GSC二元麦克风小阵列语音增强算法[J]. J4, 2013, 47(8): 1493-1499.
[3] 朱梦尧, 李东晓, 张明. 基于HRTF频谱特征优化MDCT域滤波[J]. J4, 2010, 44(9): 1730-1737.