注意力引导的条件对抗学习用于单通道脑电中的肌电伪迹抑制
Attention Guided Conditional Adversarial Learning for EMG Artifact Suppression in Single Channel EEG
浏览论文内容
中文总结 AI 辅助
本文提出P2P Trans条件对抗去噪器，结合注意力机制与PatchGAN，在单通道脑电肌电伪迹抑制中取得最优相关系数0.8645，适用于低信噪比场景。
中文摘要 AI 辅助
肌电活动可在宽频率范围内主导头皮脑电信号，并掩盖与分析及脑机接口相关的神经结构。本文评估了P2P Trans，一种条件对抗去噪器，其结合了U形编码器-解码器、瓶颈处的多头自注意力、交叉注意力引导的跳跃融合以及PatchGAN判别器。所报告的实验使用EEGdenoiseNet片段，表示为1024个样本序列，在从-7到2 dB的十个信噪比下合成配对混合，并评估了50000个训练样本和5980个测试样本。与五个卷积编码器-解码器基线相比，P2P Trans实现了最佳的平均相关系数0.8645和最低的平均频谱RRMSE 0.3596。其平均时间RRMSE为0.5797，未领先于比较，这表明在频谱抑制和逐点波形保真度之间存在权衡。其优势在严重污染下最为显著。结果支持注意力引导的对抗性恢复作为低信噪比下的有用方法，同时也指出了对受试者独立评估、直接一维建模和下游任务验证的需求。
英文摘要
Electromyographic activity can dominate scalp electroencephalography across a broad frequency range and obscure neural structure that is relevant to analysis and brain computer interfaces. This paper evaluates P2P Trans, a conditional adversarial denoiser that combines a U shaped encoder decoder, multi head self attention at the bottleneck, cross attention guided skip fusion, and a PatchGAN discriminator. The reported experiment used EEGdenoiseNet segments represented as 1024 sample sequences, synthesized paired mixtures at ten signal to noise ratios from minus 7 to 2 dB, and evaluated 50000 training examples and 5980 test examples. Against five convolutional encoder decoder baselines, P2P Trans achieved the best mean correlation coefficient of 0.8645 and the lowest mean spectral RRMSE of 0.3596. Its mean temporal RRMSE was 0.5797 and did not lead the comparison, which indicates a tradeoff between spectral suppression and pointwise waveform fidelity. The advantage was strongest under severe contamination. The results support attention guided adversarial restoration as a useful low SNR approach, while also identifying the need for subject independent evaluation, direct one dimensional modeling, and downstream task validation.
发表机构
- Columbia University（哥伦比亚大学）
- Xi’an University of Posts and Telecommunications（西安邮电大学）
- The University of Tokyo（东京大学）
机构由 AI 辅助整理，请以论文原文为准。
