文章摘要
邱天爽,武建.多参考信号的ICA方法及其在去除脑电伪差中应用[J].,2008,(5):740-743
多参考信号的ICA方法及其在去除脑电伪差中应用
ICA method with multi-references and its application to removing artifacts from brain signals
  
DOI:10.7511/dllgxb200805021
中文关键词: 独立分量分析  参考信号  伪差去除  脑电信号
英文关键词: independent component analysis (ICA)  reference signals  artifacts removing  electroencephalograph (EEG) signal
基金项目:〖JP2〗国家自然科学基金资助项目(305740753017025960372081);教育部博士学科点专项科研基金资助项目(20010141025).〖JP〗
作者单位
邱天爽,武建  
摘要点击次数: 794
全文下载次数: 1014
中文摘要:
      为消除脑电信号中的心电、眼电等伪差,在已有的不动点算法和带参考信号的独立分量分析算法的基础上,提出了一种多参考信号的独立分量分析方法.该方法通过计算各伪差在各路观测信号中的比重,去除伪差对观测信号的影响,从而得到较为纯净的脑电信号.所提方法相对于传统的fast ICA算法具有更小的计算量,并且不需要对分离的独立源进行人工干预,同时也是对ICA-R算法的一种扩展,解决了其只能提取单路源信号的缺点.仿真实验证明该方法更切合实际情况,而且能够更加有效地去除脑电信号中的多个伪差.
英文摘要:
      In order to eliminate the effect of artifacts in electroencephalograph (EEG) signals, such as electrocardiogram (ECG) and electrooculogram (EOG), etc., a new ICA (independent component analysis) method with multi-references is proposed based on the fixed-point algorithm and the ICA algorithm with references. After the proportions of artifacts in observation signals are calculated respectively, the comparatively pure EEGs are separated from the artifacts. Compared with fast ICA, the new method has less computational complexity and doesn′t need to dispose the independent sources. In addition, it can overcome the defect of ICA-R algorithm which just extracts single signal. Computer simulation demonstrates that the new method can effectively remove several artifacts from brain signals.
查看全文   查看/发表评论  下载PDF阅读器
关闭