List your company
ResearchFormerly WizWand

Sleep Stage Classification on Sleep-EDF

94.4Accuracyk-NN
21.100840.130459.1678.1896May 16, 2018Jul 29, 2019Oct 11, 2020Dec 25, 2021Mar 10, 2023May 23, 2024Aug 6, 2025
Updated 6mo ago

Evaluation results

MethodLinks
k-NNInput channel=Fpz-Cz, Feature type=hand-crafted, Subjects=20 SC, Independent testing=yes, In-bed data only=no2018.0594.4
Decision treesInput channel=Fpz-Cz + Pz-Oz, Feature type=hand-crafted, Subjects=20 SC, Independent testing=no, In-bed data only=no2018.0593.1
Ensemble SVMInput channel=Pz-Oz, Feature type=hand-crafted, Subjects=10 SC + 10 ST, Independent testing=yes, In-bed data only=no2018.0591.1
LITEAvg Params=16.84K, Avg GFlops=0.27G2025.0885.3
PRISMAvg Params=13.59K, Avg GFlops=0.04G2025.0885.02
Deep CNNInput channel=Fpz-Cz + hor. EOG, Feature type=learned, Subjects=20 SC, Independent testing=no, In-bed data only=yes2018.0584
MambaAvg Params=235.81K, Avg GFlops=5.11G2025.0883.75
TSLANetAvg Params=762.32K, Avg GFlops=2.12G2025.0883.67
Multitask 1-max CNNInput channel=Fpz-Cz + hor. EOG, Feature type=learned, Subjects=20 SC, Independent testing=yes, In-bed data only=yes2018.0582.3
Deep CNN + RNNInput channel=Fpz-Cz, Feature type=learned, Subjects=20 SC, Independent testing=yes, In-bed data only=no2018.0582
Multitask 1-max CNNInput channel=Fpz-Cz, Feature type=learned, Subjects=20 SC, Independent testing=yes, In-bed data only=yes2018.0581.9
MiniROCKETAvg Params=72.55K, Avg GFlops=0.55G2025.0880.55
k-NNInput channel=Fpz-Cz + Pz-Oz, Feature type=hand-crafted, Subjects=20 SC, Independent testing=no, In-bed data only=no2018.0580
1-max CNNInput channel=Fpz-Cz, Feature type=learned, Subjects=20 SC, Independent testing=yes, In-bed data only=yes2018.0579.8
Attentional RNNInput channel=Fpz-Cz, Feature type=learned, Subjects=20 SC, Independent testing=yes, In-bed data only=yes2018.0579.1
Deep auto-encoderInput channel=Fpz-Cz, Feature type=hand-crafted, Subjects=20 SC, Independent testing=yes, In-bed data only=yes2018.0578.9
Ensemble SVMInput channel=Fpz-Cz + Pz-Oz, Feature type=hand-crafted, Subjects=20 SC + 22 ST, Independent testing=no, In-bed data only=yes2018.0578.9
PatchTSTAvg Params=485.79K, Avg GFlops=1.63G2025.0877.66
ResNetInput channel=Fpz-Cz + hor. EOG, Feature type=learned, Subjects=20 SC, Independent testing=yes, In-bed data only=yes2018.0576.8
Decision treesInput channel=Fpz-Cz, Feature type=hand-crafted, Subjects=10 ST, Independent testing=yes, In-bed data only=no2018.0575
Deep CNNInput channel=Fpz-Cz, Feature type=learned, Subjects=20 SC, Independent testing=yes, In-bed data only=yes2018.0574.8
GMMInput channel=Pz-Oz, Feature type=hand-crafted, Subjects=19 SC, Independent testing=no, In-bed data only=no2018.0573.2
TimesNetAvg Params=56.69M, Avg GFlops=4.07T2025.0860.18
LightTSAvg Params=1.85M, Avg GFlops=0.07G2025.0857.6
FiLMAvg Params=12.59M, Avg GFlops=0.58G2025.0849.66
iTransformerAvg Params=491.73K, Avg GFlops=0.05G2025.0839.21
DLinearAvg Params=3.64M, Avg GFlops=0.12G2025.0823.92