Table 1 Description of sleep EEG datasets.
From: A robust deep learning detector for sleep spindles and K-complexes: towards population norms
Labeled datasets | Unlabeled datasets | |||||
|---|---|---|---|---|---|---|
MASS2-SS-E1 | MASS2-SS-E2 | MASS2-KC | MODA | CAP | NSRR6 | |
Subjects | 15 | 15 | 15 | 180 | 80 | 11,224 |
Age (mean ± SD) | 23.6 ± 3.7 | 23.6 ± 3.7 | 23.6 ± 3.7 | 40.6 ± 19.4 | 39.5 ± 16.9 | 58.6 ± 23.5 |
Sampling rate (Hz) | 256 | 256 | 256 | 256 | 100–512 | 125–512 |
Annotated event | SS | SS | KC | SS | N.A | N.A |
Annotated or selected segments | Stage N2 | Stage N2 | Stage N2 | 115 s segments* | Stage N2 | Stage N2 |
Annotated or selected size (h) | 60.01 | 60.01 | 60.01 | 24.97 | 251.64 | 36,548.1 |
Annotation source | One expert | One expert | One expert | Consensus of 31–42 exp | N.A | N.A |
Total events | 9,990 | 21,846 | 8,781 | 5,272 | N.A | N.A |
Density (epm) | 2.72 | 6.02 | 2.49 | 3.52 | N.A | N.A |
Mean duration (s) | 0.83 | 1.20 | 0.73 | 0.84 | N.A | N.A |
