双分支图卷积网络用于可解释的运动 EEG 分类
A Dual-Branch Graph and Convolutional Network for Interpretable Movement EEG Classification
AI 导读
研究者提出一种结合 LGGNet 风格局部-全局图分支与 EEGNet 风格卷积分支的双分支架构，用于头皮 EEG 的运动-静息分类。在 Ofner 上肢运动数据集上采用留一被试交叉验证，平均 F1 分数为 0.74 ± 0.06。图分支将 61 个电极按解剖区域分组，被试间一致显示 Parietal Left Low 区域（P1、P3 电极）连接性最强，使解码器兼具可解释性与分类效果。
正文 · 原文
Abstract:Decoding upper-limb movements from scalp electroencephalography (EEG) is an important problem for brain-computer interfaces (BCIs), but many deep learning models provide limited insight into the brain regions underlying their predictions. We propose a two-branch architecture that combines an LGGNet-inspired local-global graph branch with an EEGNet-style convolutional branch for movement-versus-rest classification. The graph branch groups 61 EEG electrodes into anatomically informed regions and learns their spatial relationships, providing a direct representation of the regions emphasized by the model. We evaluate the proposed architecture using leave-one-subject-out cross-validation on the Ofner upper-limb movement dataset. The model achieves a mean F1-score of 0.74 +/- 0.06 across subjects. Beyond classification performance, we analyze the learned graph structure to identify the regions with the strongest connectivity. Across all held-out subjects, the highest connectivity is consistently observed in the Parietal Left Low region, corresponding to electrodes P1 and P3. This region is opposite to the performed right-arm movements and lies within the posterior parietal area previously associated with upper-limb movement processing. These results show that incorporating a region-based graph into the decoder can provide an anatomically interpretable representation while maintaining effective movement classification, offering a practical approach toward more transparent EEG-based BCIs.
| Subjects: | Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Signal Processing (eess.SP) |
| Cite as: | arXiv:2611.16609 [cs.AI] |
| (or arXiv:2611.16609v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16609 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Maryam Ostadsharif Memar [view email]
[v1]
Thu, 12 Nov 2026 10:47:37 UTC (146 KB)
来源：arXiv cs.AI · arxiv.org