Xiong Wenjing, Ma Lin, Li Haifeng
Faculty of Computing, Harbin Institute of Technology, Harbin, China.
Front Neurosci. 2024 Jan 24;17:1258024. doi: 10.3389/fnins.2023.1258024. eCollection 2023.
Scalp electroencephalogram (EEG) analysis and interpretation are crucial for tracking and analyzing brain activity. The collected scalp EEG signals, however, are weak and frequently tainted with various sorts of artifacts. The models based on deep learning provide comparable performance with that of traditional techniques. However, current deep learning networks applied to scalp EEG noise reduction are large in scale and suffer from overfitting.
Here, we propose a dual-pathway autoencoder modeling framework named DPAE for scalp EEG signal denoising and demonstrate the superiority of the model on multi-layer perceptron (MLP), convolutional neural network (CNN) and recurrent neural network (RNN), respectively. We validate the denoising performance on benchmark scalp EEG artifact datasets.
The experimental results show that our model architecture not only significantly reduces the computational effort but also outperforms existing deep learning denoising algorithms in root relative mean square error (RRMSE)metrics, both in the time and frequency domains.
The DPAE architecture does not require a priori knowledge of the noise distribution nor is it limited by the network layer structure, which is a general network model oriented toward blind source separation.
头皮脑电图（EEG）分析与解读对于追踪和分析大脑活动至关重要。然而，所采集的头皮EEG信号微弱且常常受到各类伪迹的干扰。基于深度学习的模型与传统技术具有相当的性能。然而，当前应用于头皮EEG降噪的深度学习网络规模庞大且存在过拟合问题。
在此，我们提出一种名为双通路自动编码器（DPAE）的建模框架用于头皮EEG信号去噪，并分别在多层感知器（MLP）、卷积神经网络（CNN）和循环神经网络（RNN）上证明了该模型的优越性。我们在基准头皮EEG伪迹数据集上验证了去噪性能。
实验结果表明，我们的模型架构不仅显著减少了计算量，而且在时域和频域的均方根相对误差（RRMSE）指标上均优于现有的深度学习去噪算法。
DPAE架构不需要噪声分布的先验知识，也不受网络层结构的限制，是一种面向盲源分离的通用网络模型。
