arXiv：cs.LG· Lu Wang-N\"oth, Hai Huang, Philipp Heiler, Shuqiong Wu, Liyun Zhang, Helmut Mayer·· 4 小时前AI 评分23
弱监督标注细粒度 EEG 成分用于伪影衰减的概念验证研究
A Proof-of-Concept Study of Weakly Supervised Labeling of Fine-Grained EEG Components for Artifact Attenuation
AI 导读
研究提出一种结合频率感知高维表示与多实例学习的框架，将分离出的 EEG 成分展开为频率分辨的子成分，从而在仅有 epoch 级标签、无需细粒度真值的情况下学习每个子成分的伪影概率分数。该子成分分类器可支持细粒度 EMG 伪影检测与分数引导衰减；在留出受试者上，对下颌紧绷的伪影相关频谱偏差降低最明显，抬眉效果中等，皱眉效果有限。
正文
Abstract:Electroencephalography (EEG) is highly susceptible to electromyographic (EMG) artifacts, whose temporal heterogeneity and spatial-spectral overlap with neural activity can leave mixed sources after blind source separation. Existing artifact-removal methods are further limited by scarce reliable component-level ground truth: expert annotations are costly and subjective, while no established method provides realistic simulation-based ground truth for EMG contamination in multichannel scalp EEG. To address these limitations, we propose a framework combining a frequency-aware high-dimensional representation with Multi-Instance Learning. The representation unfolds separated components into frequency-resolved intra-components, creating a space in which mixed neural and muscular activity becomes more separable, while the weakly supervised learning formulation enables artifact-likelihood scores for individual intra-components to be learned from epoch-level labels without finer-grained ground truth. The resulting intra-component classifier supports fine-grained EMG artifact detection and score-guided attenuation. Experiments on held-out subjects show that the framework learns informative intra-component scores and reduces artifact-related spectral deviations most clearly for jaw tension, with moderate effects for raising eyebrows and limited effects for frowning.
| Subjects: | Machine Learning (cs.LG); Signal Processing (eess.SP) |
| Cite as: | arXiv:2610.09792 [cs.LG] |
| (or arXiv:2610.09792v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09792 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lu Wang-Nöth [view email]
[v1]
Wed, 7 Oct 2026 10:08:25 UTC (1,708 KB)
来源：arXiv：cs.LG · arxiv.org