基于深度卷积神经网络的运动想象分类及其在脑控外骨骼中的应用

Motor Imagery Classification Based on Deep Convolutional Neural Network and Its Application in Exoskeleton Controlled by EEG

基于运动想象的脑机接口技术已经广泛的应用于康复外骨骼领域.由于脑电信号的信噪比低,使得脑机接口分类率很难提高.因此,有效的脑电特征提取与分类方法成为现在的研究热点.该文创新地采用基于深度学习理论的卷积神经网络对单次运动想象脑电信号进行特征提取和分类.首先,根据脑电信号时间和空间特征相结合的特性,针对性地设计了一个5层的CNN结构来进行运动想象分类;其次,基于想象左手运动和脚运动设计了运动想象实验范式,获得运动想象实验数据;再次,将该方法应用于公共数据集和实验数据集并建立分类模型,同时与其它3种方法(功率值+SVM、CSP+SVM和MRA+LDA)相比较;最后,将从实验数据集中获得的分类模型(具有最好分类表现)应用于上肢康复外骨骼的实时控制中,验证该文提出方法的可行性.实验结果表明,卷积神经网络方法可以提高分类识别率:卷积神经网络方法应用在公共数据集(90.75%±2.47%)和实验数据集(89.51%±2.95%)中的平均识别率均高于其它3种方法;在上肢康复外骨骼的实时控制中,也验证了CNN方法的可行性:所有被试的平均识别率为88.75%±3.42%.该文提出的方法可实现运动想象的精确识别,为脑机接口技术在康复外骨骼领域的应用提供了理论基础与技术支持.

Brain-Computer Interface （BCI） based on motor imagery （MI） has been applied in the rehabilitation exoskeleton widely. In the practical use, the low signal-noise ratio of electroen- cephalogram （EEG） signal results in the low classification accuracy in BCI. Therefore, many studies have focused on the improvement of feature extraction and classification algorithms. In this paper, we proposed an original method based on the deep convolutional neural network （CNN） to perform feature extraction and classification for single-trial MI EEG signal. Firstly, according to the EEG signal＇s characteristic that combining time and space information, we constructed a 5-layer CNN model to classify the MI; secondly, MI experimental paradigm was designed based on imagining left hand movement and foot movement, and the experimental data of MI were collected; thirdly, the proposed method was used in the public data set and experimental data set to build classification model, compared with the other three methods （power＋ SVM, CSP＋SVM and MRA＋LDA）; finally, the classification model which achieved the best classification performance was applied in real-time control of upper-limb exoskeleton to verify the effectiveness of our proposed method. The results demonstrate that CNN can further improve classification performance, the average accuracies of public data set （90.75% ± 2.47%） and experimental data set （89.51%±2.95%） using CNN are both higher than that using the other three methods. Furthermore, in real-time control of upper-limb exoskeleton, the average accuracy of all subjects reaches to 88.75%±3.42%, which verifies the effectiveness of the CNN method. The proposed method can recognize MI, and provides theoretical basis and technical support for BCI applications in the field of rehabilitation exoskeleton.