基于时窗复杂度序列的睡眠脑电分析

运用时窗复杂度序列来分析睡眠脑电,减少了非平稳性及状态空间的不均匀性造成的脑状态信息的丢失,在一定程度上克服了复杂度的自身的局限,有助于不同睡眠期状态特征的提取.另外本文采用ICA、小波变换等方法对脑电进行预处理,实验表明它们能有效地去除脑电中的一些生理干扰,有利于提高复杂度算法在睡眠分期应用中的精确度.

Analysis of sleep staging by Time-Window complexity sequence of EEG

In this paper an approach of time-window complexity sequence is applied to sleep EEG analysis. This method can reduce the loss of state information due to the nonstationarity of EEG signals and the unevenness of state space, and overcome certain limitations of complexity itself in some extent. It will help to extract the state features of EEG in different sleep stages. In addition, we preprocess EEG by adopting ICA and wavelet transform (WT). The results show that some physiological artifacts in EEG can be eliminated effectively by these methods, and sleep staging based on sleep EEG data will therefore become more exact.