Bayesian complete-pooling models slightly improve calibration and prediction uncertainty for cross-subject motor-imagery EEG, but the effects are practically negligible.
Chapman and Hall/CRC, 1st edition, 2019
1 Pith paper cite this work, alongside 467 external citations. Polarity classification is still indexing.
1
Pith paper citing it
467
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bayesian Complete-Pooling in Cross-Subject Classification for Motor Imagery Electroencephalogram
Bayesian complete-pooling models slightly improve calibration and prediction uncertainty for cross-subject motor-imagery EEG, but the effects are practically negligible.