用自回归白化滤波器提取脑-机接口信号VEP

利用脑-计算机接口这种新颖的人-机交互模式构建一种脑控拼写装置,其主要问题是实时、准确地从头皮电极记录到的脑电背景信号中提取视觉诱发电位,以决定用户选择按键。由于在一个短时程内可以认为自发脑电是平稳的,利用靶刺激出现前记录到的非靶刺激信号计算自回归模型参数,构造一个白化滤波器,再将实时信号通过白化滤波器滤波,使自发脑电得以白化,然后采用小波分析方法滤除白噪信号。结果表明靶刺激信号更加突出,提高了后续模式分类的正确率。采用模拟自然阅读诱发模式使短时信号的平稳性得到了保障,利用白化滤波器去除自发脑电是可行的。

The Extraction of VEP in Ongoing Electroencephalogram by Auto Regressive Whitening Filter

Exploiting the novel human-machine interaction paradigm called brain-computer interface,a mental speller for those with neuromuscular disorders and motor disabilities was constructed.One of the key issues was to precisely recognize the visual evoked potentials from spontaneous electroencephalogram(EEG) background which were recorded from scalp electrodes,and this was utilized to determine which key was "pressed"by user.As the spontaneous EEG could be regarded as a stationary random process in a short period,a whiten filter was constructed by using the AR parameters calculated from those non-target signals.In succession,real-time signals were input to the filter where the spontaneous EEGs were whitened.Finally,a wavelet method was used to have the white signals filtered.The results showed that classification accuracy was improved by enhancing the target signals.The hypothesis of evoked potential regarded as with stationarity in a short period is feasible by using "imitating-natural-reading" paradigm,and the spontaneous EEG can be removed by whiten filter.