Fusion of Spatio-Temporal and Multi-Scale Frequency Features for Dry Electrodes MI-EEG Decoding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910001006641152 |
|---|---|
| author | Gong, Tianyi Han, Can Wu, Junxi Qian, Dahong |
| author_facet | Gong, Tianyi Han, Can Wu, Junxi Qian, Dahong |
| contents | Dry-electrode Motor Imagery Electroencephalography (MI-EEG) enables fast, comfortable, real-world Brain Computer Interface by eliminating gels and shortening setup for at-home and wearable use.However, dry recordings pose three main issues: lower Signal-to-Noise Ratio with more baseline drift and sudden transients; weaker and noisier data with poor phase alignment across trials; and bigger variances between sessions. These drawbacks lead to larger data distribution shift, making features less stable for MI-EEG tasks.To address these problems, we introduce STGMFM, a tri-branch framework tailored for dry-electrode MI-EEG, which models complementary spatio-temporal dependencies via dual graph orders, and captures robust envelope dynamics with a multi-scale frequency mixing branch, motivated by the observation that amplitude envelopes are less sensitive to contact variability than instantaneous waveforms. Physiologically meaningful connectivity priors guide learning, and decision-level fusion consolidates a noise-tolerant consensus. On our collected dry-electrode MI-EEG, STGMFM consistently surpasses competitive CNN/Transformer/graph baselines. Codes are available at https://github.com/Tianyi-325/STGMFM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18424 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fusion of Spatio-Temporal and Multi-Scale Frequency Features for Dry Electrodes MI-EEG Decoding Gong, Tianyi Han, Can Wu, Junxi Qian, Dahong Human-Computer Interaction Machine Learning Dry-electrode Motor Imagery Electroencephalography (MI-EEG) enables fast, comfortable, real-world Brain Computer Interface by eliminating gels and shortening setup for at-home and wearable use.However, dry recordings pose three main issues: lower Signal-to-Noise Ratio with more baseline drift and sudden transients; weaker and noisier data with poor phase alignment across trials; and bigger variances between sessions. These drawbacks lead to larger data distribution shift, making features less stable for MI-EEG tasks.To address these problems, we introduce STGMFM, a tri-branch framework tailored for dry-electrode MI-EEG, which models complementary spatio-temporal dependencies via dual graph orders, and captures robust envelope dynamics with a multi-scale frequency mixing branch, motivated by the observation that amplitude envelopes are less sensitive to contact variability than instantaneous waveforms. Physiologically meaningful connectivity priors guide learning, and decision-level fusion consolidates a noise-tolerant consensus. On our collected dry-electrode MI-EEG, STGMFM consistently surpasses competitive CNN/Transformer/graph baselines. Codes are available at https://github.com/Tianyi-325/STGMFM. |
| title | Fusion of Spatio-Temporal and Multi-Scale Frequency Features for Dry Electrodes MI-EEG Decoding |
| topic | Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2601.18424 |