Abstract:

Aiming at the multi?classification problem for Motor Imagery ElectroEncephaloGraphy （MI?EEG）， Lightweight convolutional neural Network （L?Net） and Lightweight Hybrid Network （LH?Net） based on deep separable convolution were built on the basis of existing research. Experiments and analyses were carried out on the BCI competition IV-2a data set. It was shown that L?Net could fit the data faster than LH?Net， and the training time was shorter. However， LH?Net is more stable than L?Net and has better robustness in classification performance on the test set， the average accuracy and average Kappa coefficient of LH?Net were increased by 3.6% and 4.8%， respectively compared with L?Net. In order to further improve the classification performance of the model， a new method of adding Gaussian noise based on the time?frequency domain was adopted to apply Data Augmentation （DA） on the training samples， and simulation verification of the noise intensity was carried out， thus the optimal noise intensity ranges of the two models were inferred. With the DA method， the average accuracies of the two models were increased by at least 4% in the simulation results， the four classification effects were significantly improved.

Key words: electroencephalography, motor imagery, deep learning, depth separable convolution, data augmentation

摘要：

针对运动想象脑电（MI?EEG）多分类问题，在已有研究的基础上进行改进，构建了基于深度可分离卷积的轻量级卷积神经网络（L?Net）和轻量级混合网络（LH?Net），并在BCI竞赛Ⅳ-2a四分类数据集上进行了实验和分析，结果表明：L?Net比LH?Net可以更快地拟合数据，训练时间更短；但LH?Net的稳定性比L?Net更好，在测试集上的分类性能具有更好的稳健性，平均准确率和平均Kappa系数比L?Net分别提高了3.6个百分点和4.8个百分点。为了进一步提升模型分类性能，采用了基于时频域的高斯噪声添加新方法对训练样本进行数据增强（DA），并针对噪声的强度进行了仿真验证，推测出了两种模型的最优噪声强度的取值范围。仿真结果表明使用了该数据增强方法后，两种模型的平均准确率最少提高了4个百分点，四分类效果均得到了明显提升。

关键词: 脑电信号, 运动想象, 深度学习, 深度可分离卷积, 数据增强