Institute of Knowledge Discovery, Graz University of Technology, 8010 Graz, Austria.
IEEE Trans Neural Syst Rehabil Eng. 2012 May;20(3):313-9. doi: 10.1109/TNSRE.2012.2189584. Epub 2012 Apr 3.
System calibration and user training are essential for operating motor imagery based brain-computer interface (BCI) systems. These steps are often unintuitive and tedious for the user, and do not necessarily lead to a satisfactory level of control. We present an Adaptive BCI framework that provides feedback after only minutes of autocalibration in a two-class BCI setup. During operation, the system recurrently reselects only one out of six predefined logarithmic bandpower features (10-13 and 16-24 Hz from Laplacian derivations over C3, Cz, and C4), specifically, the feature that exhibits maximum discriminability. The system then retrains a linear discriminant analysis classifier on all available data and updates the online paradigm with the new model. Every retraining step is preceded by an online outlier rejection. Operating the system requires no engineering knowledge other than connecting the user and starting the system. In a supporting study, ten out of twelve novice users reached a criterion level of above 70% accuracy in one to three sessions (10-80 min online time) of training, with a median accuracy of 80.2 ± 11.3% in the last session. We consider the presented system a positive first step towards fully autocalibrating motor imagery BCIs.
系统校准和用户培训对于操作基于运动想象的脑机接口 (BCI) 系统至关重要。这些步骤对于用户来说通常是不直观和繁琐的，并且不一定能达到令人满意的控制水平。我们提出了一种自适应 BCI 框架，在双分类 BCI 设置中，仅在自动校准几分钟后就提供反馈。在操作过程中，系统会反复重新选择仅从 Laplacian 推导的 C3、Cz 和 C4 上的六个预定义对数频带功率特征（10-13 和 16-24 Hz）中的一个，即表现出最大可区分性的特征。然后，系统会在所有可用数据上重新训练线性判别分析分类器，并使用新模型更新在线范例。每次重新训练步骤之前都会进行在线异常值拒绝。操作该系统除了连接用户并启动系统外，不需要其他工程知识。在一项支持性研究中，在 10-80 分钟的在线时间内，12 名新手用户中的 10 名在 1-3 次训练会话中达到了准确率高于 70%的标准，最后一次会话的准确率中位数为 80.2±11.3%。我们认为所提出的系统是朝着完全自适应运动想象 BCI 迈出的积极的第一步。
