WICA算法在脑电α波增强中的应用  

Application of αWave Enhancement from EEG Based on uniting Wavelet Transform with Independent Component Analysis

作　　者：王亚[1] 傅伟[1] 

机构地区：[1]江苏财经职业技术学院,江苏淮安223003

出　　处：《廊坊师范学院学报（自然科学版）》2013年第1期20-24,共5页Journal of Langfang Normal University(Natural Science Edition)

基　　金：江苏省高校科研成果产业化推进工程项目(JH10-42);淮安市科技支撑计划(HAG09006;HAG2010049;SN12048);淮安市创新载体平台建设计划(HAP201010)

摘　　要：随着脑电信号处理技术的发展,脑诱发电位的提取更广泛地应用于神经精神科以及其他领域。但是,目前一系列脑电分析方法都存在一定的缺陷。而根据脑电信号以及信号分析方法各自的特点,把小波变换(WT)和独立分量(ICA)结合的方法(WICA)应用到脑电α波增强中,小波变换可以增强待检测信号成分,削弱非目标信号成分和噪声的干扰,经过小波变换后子带重组的多道ICA输入信号中,非目标信号成分和干扰信号成分己变得较弱,因此,WICA算法能有效地分离出相对较强的目标信号成分。实验结果表明,WICA算法在脑电α波增强中可取得比较好的效果。With the development of the brain electrical signal processing technology, the extraction of brain evoked po-tential has been widely used in the neurology department and other domains. But a series of recently electrical signal pro-cessing technology have not enough perfect. According to the respective characteristic of the brain electrical signal and the signal analysis method, applies in extracting brain evoked potential by wavelet （WT） and the Independent Component Analysis（ICA） union method （WICA）. The wavelet transformation may strengthen the examination signal ingredient, weakens the non-target signal ingredient and the noise disturbance; In after the sub - belt reorganization multi-channel ICA input signal, the non-target signal ingredient and the unwanted signal ingredient generally changes weakly, there-fore, the ICA algorithm can effectively separate stronger target signal ingredient. The results showed that, the WICA al-gorithm is very efficient on the brain electrical signal α wave enhancement.

关 键 词：小波变换 独立分量分析 脑信号 特征增强 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]