Graduate Institute of Biomedical Informatics, Taipei Medical University, 250 Wu-Xin Street, Taipei 110, Taiwan.
Comput Biol Med. 2011 Aug;41(8):633-9. doi: 10.1016/j.compbiomed.2011.05.014. Epub 2011 Jun 17.
In this study, an adaptive electroencephalogram (EEG) analysis system is proposed for a two-session, single-trial classification of motor imagery (MI) data. Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the adaptive linear discriminant analysis (LDA) is used for classification of left- and right-hand MI data and for simultaneous and continuous update of its parameters. In addition to the original use of continuous wavelet transform (CWT) and Student's two-sample t-statistics, the 2D anisotropic Gaussian filter is proposed to further refine the selection of active segments. The multiresolution fractal features are then extracted from wavelet data by means of modified fractal dimension. The classification in session 2 is performed by adaptive LDA, which is trial-by-trial updated using the Kalman filter after the trial is classified. Compared with original active segment selection and non-adaptive LDA on six subjects from two data sets, the results indicate that the proposed method is helpful to realize adaptive BCI systems.
在这项研究中，提出了一种自适应脑电图（EEG）分析系统，用于对运动想象（MI）数据进行两阶段、单次试验分类。该系统应用从感觉运动皮质获得的事件相关脑电位（ERP）数据，采用自适应线性判别分析（LDA）对左、右手 MI 数据进行分类，并同时对其参数进行连续更新。除了原始的连续小波变换（CWT）和学生双样本 t 统计量外，还提出了二维各向异性高斯滤波器来进一步改进活动段的选择。然后通过修正的分形维数从小波数据中提取多分辨率分形特征。在第 2 阶段的分类中，使用卡尔曼滤波器对试验进行分类后，自适应 LDA 会逐次进行更新。与来自两个数据集的六位受试者的原始活动段选择和非自适应 LDA 相比，结果表明，该方法有助于实现自适应 BCI 系统。
