Besio Walter G, Cao Hongbao, Zhou Peng
Biomedical Engineering Department, Louisiana Tech University, Ruston, LA 71272, USA.
IEEE Trans Neural Syst Rehabil Eng. 2008 Apr;16(2):191-4. doi: 10.1109/TNSRE.2007.916303.
For persons with severe disabilities, a brain-computer interface (BCI) may be a viable means of communication. Lapalacian electroencephalogram (EEG) has been shown to improve classification in EEG recognition. In this work, the effectiveness of signals from tripolar concentric electrodes and disc electrodes were compared for use as a BCI. Two sets of left/right hand motor imagery EEG signals were acquired. An autoregressive (AR) model was developed for feature extraction with a Mahalanobis distance based linear classifier for classification. An exhaust selection algorithm was employed to analyze three factors before feature extraction. The factors analyzed were 1) length of data in each trial to be used, 2) start position of data, and 3) the order of the AR model. The results showed that tripolar concentric electrodes generated significantly higher classification accuracy than disc electrodes.
对于重度残疾人士而言，脑机接口（BCI）可能是一种可行的交流方式。拉普拉斯脑电图（EEG）已被证明可提高EEG识别中的分类效果。在这项工作中，比较了三极同心电极和圆盘电极的信号作为BCI的有效性。采集了两组左/右手运动想象EEG信号。开发了一种自回归（AR）模型用于特征提取，并使用基于马氏距离的线性分类器进行分类。在特征提取之前，采用穷举选择算法分析三个因素。分析的因素为：1）每次试验中要使用的数据长度，2）数据的起始位置，以及3）AR模型的阶数。结果表明，三极同心电极产生的分类准确率明显高于圆盘电极。
