EEG is often contaminated by ocular (EOG) and muscle (EMG) artifacts, yet many pipelines apply uniform denoising, risking distortion of clean neural activity. We propose a two-head, single-channel regressor that estimates EOG and EMG noise-to-signal ratio (NSR, dB) from short segments and test whether it can guide selective artifact reduction, including downstream BCI decoding. Approach. Using EEGdenoiseNet clean EEG and artifact exemplars, we synthesised 2-s single-channel mixtures with known EOG/EMG NSR spanning -10 to +10 dB and trained several model families to jointly regress both NSRs. Generalisation was evaluated on an independent eyeblink dataset via agreement with regression-based ocular-reference topographies, and in two applications: (i) gating stationary wavelet blink removal on a P3 ERP dataset and (ii) gating the same denoiser on a 55-subject RSVP P300 speller dataset (FP1/FP2). Main results. A dilated temporal convolutional network (TCN) performed best (EOG: MAE ≈ 1.8 dB, R² ≈ 0.82; EMG: MAE ≈ 1.0 dB, R² ≈ 0.94) with low bias across NSR. The EOG head recovered blink topographies (median spatial correlation ≈ 0.91). On the P3 dataset, indiscriminate wavelet denoising reduced significant ERP channels, whereas TCN-guided gating preserved 22-23 of 24 while processing ~9-20% of segments. On the speller dataset, denoising all epochs reduced decoding, while selective denoising improved AUC (θ = 9 dB: ΔAUC = 0.327, p = 0.0040) while denoising 12.45 ± 9.29% of test segments. Significance. Multi-head noise regression provides interpretable, continuous ocular and muscle contamination estimates that can act as control signals for conservative, noise-aware artifact handling under constrained-lead conditions. .
Shaikh et al. (2026) studied this question.