OBJECTIVE
Electroencephalography (EEG) is widely used in brain-computer interfaces (BCIs), but its microvolt-level signals are easily contaminated by electromyography (EMG), electrooculography (EOG), and mixed physiological artifacts. This study develops an EEG denoising framework that suppresses artifacts while preserving information used by downstream biomedical artificial intelligence (AI) tasks. Approach. We propose MTGNet, a task-oriented and spectrally guided EEG denoising framework. MTGNet combines Low-Rank Adaptation (LoRA)-based Task-Aware Consistency Regularization (TACR), a spectrally aware Guidance Network, and parallel Mamba-Transformer backbone. A pretrained 11.97M-parameter backbone learns to preserve intrinsic EEG characteristics from paired noisy-clean data, while 0.33M LoRA parameters enable task-specific adaptation without requiring paired clean EEG references. Main results. On EEGDenoiseNet, MTGNet reduces spectral relative root-mean-square error (S-RRMSE) by over 18.9%, 31.5%, and 14.0% for EMG, EOG, and hybrid artifacts, respectively (p<0.001). On a real-world fatigue EEG dataset, it improves classification accuracy by 6.20-6.69 percentage points compared with unprocessed inputs (p<0.05). Ablation, cross-classifier, and cross-dataset analyses validate the proposed components and support the transferability of MTGNet across the evaluated settings. Significance. The proposed framework provides a practical approach to task-aware EEG denoising, while future work should further validate its applicability across real-world EEG settings involving diverse tasks, artifact types, and acquisition conditions.
Jin-Cheng Hu, Zhongke Gao, Yushi Hao et al.· Journal of Neural Engineerin...· 0 citations
Accurate decoding of motor imagery electroencephalography (MI-EEG) signals is critical for practical brain-computer interface (BCI) systems. However, conventional approaches typically rely on dense multi-channel recordings, which not only introduce data redundancy but may also incorporate noise, thereby hindering real-world deployment. To address this challenge, we propose a graph neural network-based co-optimization framework that simultaneously performs channel selection and MI classification. The framework comprises two core components: one is the Key Channel Locator (KCL), which models EEG electrodes as graph nodes and identifies a subject-specific, fixed-size subset of informative channels through a dual-perspective evaluation that integrates graph convolutional topology with self-attention-derived feature importance, and the other is the UniEEG-Net, which efficiently decodes MI tasks from the selected channels using multi-scale temporal convolutions, depthwise separable spatial projection, and a self-attention mechanism. We extensively validate the proposed method on three datasets, including BCI Competition IV 2a, High Gamma, and a newly collected dataset. Experimental results demonstrate that our approach achieves performance comparable to that obtained with all channels while using significantly fewer electrodes. Moreover, UniEEG-Net exhibits classification accuracy surpassing current state-of-the-art models. The entire system is thus well-suited for real-world BCI applications, particularly in neurorehabilitation.
Hao-Yu Li, Wei-Dong Dang, Lei Liu et al.· Chaos· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
