School of Electrical and Data Engineering, University of Technology Sydney, Ultimo, NSW 2007, Australia.
Department of Engineering, King's College London, London WC2R 2LS, UK.
Sensors (Basel). 2022 Feb 23;22(5):1750. doi: 10.3390/s22051750.
The brain-computer interface (BCI) has many applications in various fields. In EEG-based research, an essential step is signal denoising. In this paper, a generative adversarial network (GAN)-based denoising method is proposed to denoise the multichannel EEG signal automatically. A new loss function is defined to ensure that the filtered signal can retain as much effective original information and energy as possible. This model can imitate and integrate artificial denoising methods, which reduces processing time; hence it can be used for a large amount of data processing. Compared to other neural network denoising models, the proposed model has one more discriminator, which always judges whether the noise is filtered out. The generator is constantly changing the denoising way. To ensure the GAN model generates EEG signals stably, a new normalization method called sample entropy threshold and energy threshold-based (SETET) normalization is proposed to check the abnormal signals and limit the range of EEG signals. After the denoising system is established, although the denoising model uses the different subjects' data for training, it can still apply to the new subjects' data denoising. The experiments discussed in this paper employ the HaLT public dataset. Correlation and root mean square error (RMSE) are used as evaluation criteria. Results reveal that the proposed automatic GAN denoising network achieves the same performance as the manual hybrid artificial denoising method. Moreover, the GAN network makes the denoising process automatic, representing a significant reduction in time.
脑机接口（BCI）在各个领域都有许多应用。在基于 EEG 的研究中，信号去噪是一个重要的步骤。本文提出了一种基于生成对抗网络（GAN）的去噪方法，用于自动去噪多通道 EEG 信号。定义了一个新的损失函数，以确保滤波后的信号尽可能多地保留有效原始信息和能量。该模型可以模拟和集成人工去噪方法，从而减少处理时间，因此可以用于大量数据处理。与其他神经网络去噪模型相比，所提出的模型多了一个判别器，它始终判断是否滤除了噪声。生成器不断改变去噪方式。为了确保 GAN 模型生成 EEG 信号稳定，提出了一种新的归一化方法，称为基于样本熵阈值和能量阈值的（SETET）归一化，用于检查异常信号并限制 EEG 信号的范围。建立去噪系统后，尽管去噪模型使用不同的受试者数据进行训练，但仍可以应用于新受试者数据的去噪。本文讨论的实验使用 HaLT 公共数据集。相关性和均方根误差（RMSE）被用作评估标准。结果表明，所提出的自动 GAN 去噪网络与手动混合人工去噪方法具有相同的性能。此外，GAN 网络使去噪过程自动化，大大减少了时间。
