[论文解读] Reconstructing ERP Signals Using Generative Adversarial Networks for Mobile Brain-Machine Interface

Young Eun Lee, Minji Lee+1 more|arXiv (Cornell University)|May 18, 2020

EEG and Brain-Computer Interfaces参考文献 34被引用 7

一句话总结

该论文提出了一种基于生成对抗网络（GAN）的框架，用于从行走过程中采集的噪声EEG数据中重建事件相关电位（ERP）信号，采用预训练的卷积编码器和学习生成ERP样波形的生成模型。该方法显著提升了信噪比（SNR）和分类准确率，即使在移动条件下也能恢复关键ERP成分（N200和P300）。

ABSTRACT

Practical brain-machine interfaces have been widely studied to accurately detect human intentions using brain signals in the real world. However, the electroencephalography (EEG) signals are distorted owing to the artifacts such as walking and head movement, so brain signals may be large in amplitude rather than desired EEG signals. Due to these artifacts, detecting accurately human intention in the mobile environment is challenging. In this paper, we proposed the reconstruction framework based on generative adversarial networks using the event-related potentials (ERP) during walking. We used a pre-trained convolutional encoder to represent latent variables and reconstructed ERP through the generative model which shape similar to the opposite of encoder. Finally, the ERP was classified using the discriminative model to demonstrate the validity of our proposed framework. As a result, the reconstructed signals had important components such as N200 and P300 similar to ERP during standing. The accuracy of reconstructed EEG was similar to raw noisy EEG signals during walking. The signal-to-noise ratio of reconstructed EEG was significantly increased as 1.3. The loss of the generative model was 0.6301, which is comparatively low, which means training generative model had high performance. The reconstructed ERP consequentially showed an improvement in classification performance during walking through the effects of noise reduction. The proposed framework could help recognize human intention based on the brain-machine interface even in the mobile environment.

研究动机与目标

• 为解决运动伪影在移动脑机接口（BMI）中降低EEG信号质量的挑战。
• 开发一种鲁棒的信号重建框架，确保在动态条件下仍能保留关键ERP成分（N200和P300）。
• 提升在原始EEG受伪影严重污染的移动环境中ERP信号的分类性能。
• 探索GAN不仅用于数据生成，还用于EEG中端到端的降噪与信号重建。
• 使用真实世界行走EEG数据结合奇偶刺激ERP范式，验证该框架的有效性。

提出的方法

• 采用预训练的卷积编码器从行走过程中的噪声EEG信号中提取潜在表征。
• 设计生成模型，通过学习编码器潜在空间的逆映射来重建ERP样波形。
• 利用判别模型验证重建信号的真实性，确保其与静止状态下的ERP信号相似。
• 使用对抗损失与均方误差（MSE）损失的组合来训练GAN框架，以稳定训练过程并提升重建保真度。
• 将该框架应用于32导联EEG数据，数据采集于1.6 m/s的跑步机行走过程中，采用奇偶刺激ERP范式。
• 通过低MSE损失（0.6301）优化生成模型，表明其具备高质量的重建性能。

实验结果

研究问题

• RQ1 基于GAN的信号重建能否有效从行走过程中采集的噪声EEG信号中恢复ERP成分（N200和P300）？
• RQ2 所提出的GAN框架在移动环境中在多大程度上提升了ERP信号的信噪比（SNR）？
• RQ3 重建后的EEG信号是否具备足够的质量，以在移动BMI系统中可靠分类用户意图？
• RQ4 与原始噪声信号和干净静止状态信号相比，重建信号的分类性能如何？
• RQ5 生成模型能否产生多样化但生理上合理的ERP波形，同时保留关键神经特征？

主要发现

• 重建后的EEG信号成功保留了N200和P300成分，与静止状态下记录的ERP波形高度相似。
• 重建EEG的信噪比（SNR）显著高于原始行走EEG（p < 0.01），甚至超过静止状态信号的SNR。
• 尽管源自噪声行走数据，重建信号的分类准确率（AUC）与干净静止状态EEG相当。
• 生成模型实现了低均方误差（MSE）损失0.6301，表明重建保真度高且训练稳定。
• 视觉检查确认，重建信号保留了真实ERP反应的时间结构和振幅特征。
• 该框架在生成样本中表现出多样性，表明模型已学会从不同输入噪声信号中生成多样化但逼真的ERP波形。