Unsupervised discriminator-guided fine-tuning of a pretrained u-sleep model improves Cohen's kappa by 0.03-0.29 on artificially degraded sleep signals but falls short of supervised optima and yields insignificant gains on real domain mismatches.
Resting-state EEG recorded with gel-based vs. consumer dry electrodes: spectral characteristics and across-device correlations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Gradient- and perturbation-based XAI methods show substantial agreement on frontal, temporal, and posterior EEG regions for an InceptionTime MDD classifier, while DeepSHAP differs, with overall partial convergence and method-dependent variability.
citing papers explorer
-
Unsupervised domain transfer: Overcoming signal degradation in sleep monitoring by increasing scoring realism
Unsupervised discriminator-guided fine-tuning of a pretrained u-sleep model improves Cohen's kappa by 0.03-0.29 on artificially degraded sleep signals but falls short of supervised optima and yields insignificant gains on real domain mismatches.
-
Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection
Gradient- and perturbation-based XAI methods show substantial agreement on frontal, temporal, and posterior EEG regions for an InceptionTime MDD classifier, while DeepSHAP differs, with overall partial convergence and method-dependent variability.