说明：  BCI_MI_CSP_DNN是一种基于matlab的运动图像脑电信号分类程序。 基于matlab深度学习工具箱编写了BCI_MI_CSP_DNN程序 本程序的原理基于CSP和DNN算法 这个程序的性能是基于BCI竞赛II数据集II 提出了一种基于深度学习的运动图像脑电信号分类方法。在预处理原始脑电图信号的基础上，采用共空间模型(CSP)方法提取脑电图特征矩阵，并将其输入深度神经网络(DNN)进行训练和分类。我们的工作在BCI Competition II Dataset III上进行了实验测试，提出了最佳的DNN框架，准确率达到83.6%。
(In this study, our goal was to use deep learning methods to improve the classification performance of motor imagery EEG signals. Therefore, we propose a classification method based on deep learning for motor imagery EEG signals. Based on the pre-processed raw EEG signals, a co-space model (CSP) method is used to extract the EEG feature matrix, which is then fed to a deep neural network (DNN) for training and classification. Our work was tested experimentally on the BCI Competition II Dataset III dataset, and the best DNN framework was proposed, achieving an accuracy of 83.6%.)