TriRouter improves EEG motor imagery decoding with missing electrodes
TriRouter: Sparse-to-Dense Electrode-Space Routing for Robust EEG Motor Imagery Decoding
Machine Learning
Summary
EEG devices reading brain signals often lose some of their sensors, making it hard to understand what the brain is imagining. The authors created TriRouter, a method that can work well even when many electrode signals are missing or corrupted. It smartly uses available signals to keep decoding brain activity accurate, outperforming previous methods especially when up to 75% of electrodes are not usable. This helps brain-computer interfaces stay reliable even with practical sensor problems.
What this means in practice
- •For brain-computer interface developers: Improve decoding accuracy of EEG motor imagery when some electrodes fail or data is corrupted in wearable BCI devices.
- •For clinical neurotechnology teams: Maintain reliable EEG signal interpretation despite hardware limitations or electrode loss during patient monitoring.
Authors
Ying Zhou, Yaoxin, Mengting Liu
Abstract
Motor imagery brain-computer interfaces require reliable decoding from multichannel EEG, but practical acquisition often yields sparse or corrupted electrode montages. We propose TriRouter, an electrode-space routing framework with discriminative-preservation, mask-robustness, and latent-compensation paths. A validation-calibrated router uses observable channel availability to allocate path contributions, preserving complete-channel discrimination while increasing representation recovery under severe missingness. In BNCI2014-001, TriRouter outperforms standard public backbones and a dynamic-spatial-filtering corrupted-EEG baseline. It improves accuracy over the strongest corrupted-EEG baseline by 3.68, 4.02, and 6.46 percentage points at nominal 25%, 50%, and 75% missing settings, and remains effective under structured regional missingness and additional low-channel dataset evaluation.