脑-机接口中新的脑电数据分类方法

New Method of Classifying EEG Signals in Brain-Computer Interfaces

根据自发脑电的特点,将HMM-AR模型算法运用到脑电状态的分类中,证明它是一种非常有用的分析脑-机接口方法。将Laplacian filter、ICA和HMM-AR方法相结合,用想象左右手运动的BCI数据进行识别,得到了很好的分类结果,有效地区分脑电中运动与非运动两种状态。该算法能够在运动开始后1 s内检验到脑电信号的变化,从而证明了该算法在BCI的实用性,达到了良好的识别效果。

Distinguishing the states of ＂movement＂ or ＂rest＂ in electroencephalogram （EEG） plays an important role in the domain of brain computer interface （BCI）. According to the electroencephalogram feature, Hidden Markov model （HMM）-AR might be a useful tool in EEG pattern classification. The method which jointly employs Laplacian filter, ICA transform, and HMM-AR is presented for EEG pattern classification. The hybrid method is confirmed through the classification of EEG that is recorded during the imagination of a left or right hand movement. The results illustrate the algorithm can availably classify the two brain states of movement and rest. The algorithm for cue movement determination has been designed resulting in detecting the movements within one second interval, it prove the algorithm feasibility in BCI data sets.