Machine Learning Group, Berlin Institute of Technology, Berlin, Germany.
Clin Neurophysiol. 2013 Sep;124(9):1824-34. doi: 10.1016/j.clinph.2013.03.009. Epub 2013 May 1.
Regardless of the paradigm used to implement a brain-computer interface (BCI), all systems suffer from BCI-inefficiency. In the case of patients the inefficiency can be high. Some solutions have been proposed to overcome this problem, however they have not been completely successful yet.
EEG from 10 healthy users was recorded during neuromuscular electrical stimulation (NMES) of hands and feet and during motor imagery (MI) of the same limbs. Features and classifiers were computed using part of these data to decode MI.
Offline analyses showed that it was possible to decode MI using a classifier based on afferent patterns induced by NMES and even infer a better model than with MI data.
Afferent NMES motor patterns can support the calibration of BCI systems and be used to decode MI.
This finding might be a new way to train sensorimotor rhythm (SMR) based BCI systems for healthy users having difficulties to attain BCI control. It might also be an alternative to train MI-based BCIs for users who cannot perform real movements but have remaining afferents (ALS, stroke patients).
无论使用哪种范式来实现脑机接口（BCI），所有系统都存在 BCI 效率低下的问题。对于患者来说，这种效率低下的情况可能会很严重。已经提出了一些解决方案来克服这个问题，但尚未完全成功。
记录 10 名健康使用者在手部和脚部神经肌肉电刺激（NMES）以及同一肢体运动想象（MI）期间的脑电图。使用这些数据的一部分计算特征和分类器，以解码 MI。
离线分析表明，使用基于 NMES 诱导的传入模式的分类器来解码 MI 是可能的，甚至可以推断出比使用 MI 数据更好的模型。
传入的 NMES 运动模式可以支持 BCI 系统的校准，并用于解码 MI。
这一发现可能为有困难获得 BCI 控制的健康使用者训练基于感觉运动节律（SMR）的 BCI 系统提供了一种新方法。对于无法进行实际运动但仍有传入神经（ALS、中风患者）的使用者，这也可能是训练基于 MI 的 BCI 的一种替代方法。
