基于独立分量分析的脑电噪声消除

Eliminating Artifacts of EEG Data Based on Independent Component Analysis

作为一种新的多元统计处理方法 ,独立分量分析 (ICA)是解决盲源分离 (BSS)问题的一个有效手段。在简要分析 ICA理论及其算法的基础上 ,提出将其应用到脑电中的眼电伪迹的去除任务。实际采集的生理信号大多由相互独立的成分线性迭加而成 ,符合 ICA要求源信号统计独立的基本假设。与传统方法相比 ,ICA这种空间滤波器不受信号频谱混迭的限制 ,消噪的同时能对有用信号的细节成分做到很好的保留 ,很大程度上弥补了时频域方法的不足。此外解混矩阵的逆可以用来反映独立源的空间分布模式 ,具有重要的生理意义。

As a new array processing technique, independent component analysis(ICA) is an effective means to resolve the blind source separation(BSS) problem. Based on the brief introductions of ICA theory and algorithm, we apply ICA to the removal of ocular artifacts from EEG recordings. The EEG data collected from the human scalp is actually the mixtures of some independent components. It is coincident with the basic assumptions of ICA. Compared with the traditional methods of artifacts elimination, ICA, a kind of spatial filter, is not restricted by the case of spectrum overlapping, and it has a good reservation of useful detail signals. In addition, the inverse weight matrix of ICA can be used to reflect the topographic structure of different independent sources of EEG.