基于听觉的脑机接口系统为视力减退或者无法控制眼球运动的闭锁综合症患者提供了一种新的交流通道,使其可以与外界环境进行简单的交流.为了实现在线二分类听觉脑机接口系统,采用包含两种靶刺激、一种非靶刺激的三音oddball范式作为听觉刺激,通过一维离散小波变换对所得脑电数据进行单次样本特征提取,选取低频的特征向量,并采用支持向量机(SVM)进行目标与非目标的识别.结果表明,利用小波变换可以有效地单次提取特征向量P300,相当于20次靶刺激响应的叠加结果,最终目标识别正确率可高达80％以上,达到与视觉诱发的BCI模式可比的效果,可以用于二分类的脑机接口系统.%Auditory brain-computer interfaces ( BCIs) provide a means of non-muscular communication for locked-in state (LIS) patients who have compromised vision or lose the control of their eye movement. In this paper, an auditory BCI based on a three-stimulus oddball paradigm was evaluated to make an online binary decision. One-dimensional discrete wavelet transform ( DWT) method were used to reduce noise and extract low-frequency feature. The target and non-target stimuli were classified by support vector machines ( SVM). Experiments showed that the P300 feature could be effectively extracted using the wavelet transform in a single trial, equivalent to the average result of original target signals for 20 times. The identification correct rates of 84% were acquired, which is comparable to the BCI based on visual.
展开▼
