Anderson Charles W, Knight James N, O'Connor Tim, Kirby Michael J, Sokolov Artem
Department of Computer Science, Colorado State University, Fort Collins, CO 80523, USA.
IEEE Trans Neural Syst Rehabil Eng. 2006 Jun;14(2):142-6. doi: 10.1109/TNSRE.2006.875527.
Generalized singular-value decomposition is used to separate multichannel electroencephalogram (EEG) into components found by optimizing a signal-to-noise quotient. These components are used to filter out artifacts. Short-time principal components analysis of time-delay embedded EEG is used to represent windowed EEG data to classify EEG according to which mental task is being performed. Examples are presented of the filtering of various artifacts and results are shown of classification of EEG from five mental tasks using committees of decision trees.
广义奇异值分解用于将多通道脑电图（EEG）分离为通过优化信噪比找到的成分。这些成分用于滤除伪迹。对时延嵌入EEG进行短时主成分分析，以表示加窗EEG数据，从而根据正在执行的心理任务对EEG进行分类。文中给出了各种伪迹的滤波示例，并展示了使用决策树委员会对五项心理任务的EEG进行分类的结果。
