Objective . Brain Computer Interface (BCI) inefficiency indicates that there would be 10% to 50% of users are unable to operate Motor-Imagery-based BCI systems. Importantly, the almost all previous studieds on BCI inefficiency were based on tests of Sensory Motor Rhythm (SMR) feature. In this work, we assessed the occurrence of BCI inefficiency with SMR and Movement-Related Cortical Potential (MRCP) features. Approach . A pool of datasets of resting state and movements related EEG signals was recorded with 93 subjects during 2 sessions in separated days. Two methods, Common Spatial Pattern (CSP) and template matching, were used for SMR and MRCP feature extraction, and a winner-take-all strategy was applied to assess pattern recognition with posterior probabilities from Linear Discriminant Analysis to combine SMR and MRCP features. Main results . The results showed that the two types of features showed high complementarity, in line with their weak intercorrelat...

中文翻译：

---

通过结合感觉运动节律和与运动相关的皮层潜在功能来减少脑计算机接口的效率低下。

目标。脑计算机接口（BCI）效率低下表明，将有10％到50％的用户无法操作基于Motor-Imagery的BCI系统。重要的是，几乎以前所有关于BCI无效的研究都是基于感觉运动节律（SMR）功能的测试。在这项工作中，我们通过SMR和与运动有关的皮层电位（MRCP）功能评估了BCI无效的发生。方法。在分离的几天中的2个疗程中，与93名受试者记录了一组静息状态和与运动有关的EEG信号的数据集。SMR和MRCP特征提取使用两种方法，即公共空间模式（CSP）和模板匹配，然后应用赢家通吃策略评估线性判别分析中具有后验概率的模式识别，以结合SMR和MRCP特征。主要结果。