Motion Intention Decoding and Training Effect Evaluation in Robot-assisted Upper Limb Rehabilitation based on MR-BCI

The interaction between stroke patients and rehabilitation training robots is difficult because the motion intention cannot be exacted by limbs due to their weak motor ability. Although brain-computer interaction(BCI) is beneficial for perceiving the motion of patients, it cannot solve the problem independently without receiving enough data about the effectiveness of the robotic assistance. This study proposes a BCI method that integrates rehabilitation training and training effect evaluation in a mixed reality(MR) environment. Three EEG experimental paradigms were designed, using motor imagery to convert the four-classification problem of motor execution into three binary classification problems. An EEG classification model of a multi-scale convolution residual network based on a multi-head attention mechanism was built, consisting of a multi-head attention mechanism layer, four convolutional layers, and a pooling layer. The highest accuracy and best Kappa coefficient of 12 participants on the testing dataset were recorded. The average classification accuracy of MI, ME1, and ME2 achieves 80.35%, 87.52%, and 86.51%, respectively, proving the proposed classification method has sufficient decoding accuracy. Comparing the hemodynamic response curves of the participants’ upper limbs before and after robotic assistance during rehabilitation training, hemodynamic response curves were analyzed quantitatively. With the paired-sample t-test to compare the hemodynamics of a single participant, the significance of the overall mean difference was calculated to evaluate the influence of robotic assistance on enhancing local tissue blood oxygen, improving tissue function, and accelerating local tissue repair. The study verifies the effectiveness of robotic rehabilitation training and helps develop new types of BCI with better coordination between motion intention perception and motor ability.