具有多层次优化能力的EEG生成模型

基于生成对抗网络(generative adversarial networks, GAN)的脑电信号(electroencephalogram, EEG)生成技术存在生成样本特征单一、幅值差异过大以及拟合速度慢等问题, 其质量难以满足深度学习模型训练和优化的要求. 因此, 本文通过对WGAN-GP的优化, 使其更适应脑电信号生成, 从而解决以上问题. 具体而言: (1)在WGAN-GP网络的框架的基础上, 通过将长短期记忆网络(long short-term memory, LSTM)代替卷积神经网络(convolutional neural networks, CNN), 以保证时间相关特征的完整性, 从而解决脑电生成特征单一的问题; (2)将标准化处理后的真实脑电信号输入至判别器, 以解决幅值差异过大问题; (3)将脑电噪声部分作为先验知识输入至网络生成器, 以提高生成模型的拟合速度. 本文分别通过sliced Wasserstein distance (SWD)、mode score (MS) 以及EEGNet对生成模型做多层次定量评估. 与目前已有生成网络WGAN-GP相比较, 基于本模型的生成数据更为接近真实数据.

EEG Generation Model with Hierarchical Optimization

Electroencephalogram (EEG) generation via generative adversarial networks (GANs) suffers from various issues including invariant features of samples generated, large amplitude differences, and slow fitting speeds. The quality of signals thus generated fails to meet the requirements of deep-learning model training and optimization. To address the issues above, this study optimizes the Wasserstein GAN gradient penalty (WGAN-GP) so that it can perform better in EEG generation. The details are as follows: (1) On the basis of the framework of the WGAN-GP network, the convolutional neural network (CNN) is replaced by the long short-term memory (LSTM) network to ensure the integrity of time-dependent features and thereby solve the issue of invariant features; (2) real EEGs are normalized and then applied to the discriminator to reduce the amplitude differences; (3) the noisy parts of EEGs are applied to the generator as prior knowledge to increase the fitting speed of the generation model. Sliced Wasserstein distance (SWD), mode score (MS), and EEGNet are applied to evaluate the proposed generation model quantitatively and hierarchically. Compared with the current generative network WGAN-GP, the proposed model provides data closer to their real counterparts.