Goal. Stroke patients are usually accompanied by motor dysfunction, which greatly affects daily life. Electroacupuncture is a kind of nondrug therapy that can effectively improve motor function. However, the effect of electroacupuncture is hard to be measured immediately in clinic. This paper is aimed to reveal the instant changes in brain activity of three groups of stroke patients before, during, and after the electroacupuncture treatment by the EEG analysis in the alpha band and beta band. Methods. Seven different functional connectivity indicators including Pearson correlation coefficient, spectral coherence, mutual information, phase locking value, phase lag index, partial directed coherence, and directed transfer function were used to build the BCI-based brain network in stroke patients. Results and Conclusion. The results showed that the brain activity based on the alpha band of EEG decreased after the electroacupuncture treatment, while in the beta band of EEG, the brain activity decreased only in the first two groups. Significance. This method could be used to evaluate the effect of electroacupuncture instantly and quantitatively. The study will hopefully provide some neurophysiological evidence of the relationship between changes in brain activity and the effects of electroacupuncture. The study of BCI-based brain network changes in the alpha and beta bands before, during, and after electroacupuncture in stroke patients of different periods is helpful in adjusting and selecting the electroacupuncture regimens for different patients. The trial was registered on the Chinese clinical trial registry (ChiCTR2000036959).

Objective. BCI based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a new framework is proposed to solve the MI-EEG binary classification problem. Approach. Electrophysiological source imaging (ESI) technology is used to solve the influence of volume conduction effect and improve spatial resolution. Continuous wavelet transform (CWT) and best time of interest (TOI) are combined to extract the optimal discriminant spatial-frequency features. Finally, a CNN network with seven convolution layers is used to classify the features. In addition, we also validated several new data augment methods to solve the problem of small data sets and reduce network over-fitting. Main results. The model achieved an average classification accuracy of 93.2% and 95.4% on the BCI Competition III IVa and high-gamma data sets, which is better than most of the published advanced algorithms. By selecting the best TOI for each subject, the classification accuracy rate increased by about 2%. The effects of 4 data augment methods on the classification results were also verified. Among them, the noise addition and overlap methods are better than the other two, and the classification accuracy is improved by at least 4%. On the contrary, the rotation and flip data augment methods reduced the classification accuracy. Significance. Decoding motor imagery tasks can benefited from combing the ESI technology and the data augment technology, which is used to solve the problem of low spatial resolution and small samples of EEG signals, respectively. Based on the results, the model proposed has higher accuracy and application potential in the task of MI-EEG binary classification.