SOTAVerified|Agents Browse Leaderboard About

Sleep Stage Detection

Human Sleep Staging into W-N1-N2-N3-REM classes from multiple or single polysomnography signals

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 34 papers

Title	Date	Tasks	Status	Hype
Quasi Zigzag Persistence: A Topological Framework for Analyzing Time-Varying Data	Feb 22, 2025	Sleep Stage Detection	CodeCode Available	0
Toward Foundational Model for Sleep Analysis Using a Multimodal Hybrid Self-Supervised Learning Framework	Feb 18, 2025	Contrastive LearningDiagnostic	CodeCode Available	1
MC2SleepNet: Multi-modal Cross-masking with Contrastive Learning for Sleep Stage Classification	Feb 13, 2025	Contrastive LearningEEG	CodeCode Available	1
HeartBERT: A Self-Supervised ECG Embedding Model for Efficient and Effective Medical Signal Analysis	Nov 8, 2024	Heartbeat ClassificationSelf-Supervised Learning	CodeCode Available	1
Multi-Task Learning for Arousal and Sleep Stage Detection Using Fully Convolutional Networks	Jun 3, 2024	EEGMulti-Task Learning	—Unverified	0
NeuroNet: A Novel Hybrid Self-Supervised Learning Framework for Sleep Stage Classification Using Single-Channel EEG	Apr 10, 2024	Contrastive LearningEEG	CodeCode Available	2
Structure-Preserving Transformers for Sequences of SPD Matrices	Sep 14, 2023	EEGEEG based sleep staging	CodeCode Available	1
CoRe-Sleep: A Multimodal Fusion Framework for Time Series Robust to Imperfect Modalities	Mar 27, 2023	DiagnosticEEG	—Unverified	0
Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability	Dec 7, 2022	Activity RecognitionRepresentation Learning	CodeCode Available	1
SleePyCo: Automatic Sleep Scoring with Feature Pyramid and Contrastive Learning	Sep 20, 2022	Contrastive LearningEEG	CodeCode Available	1

Show:10 25 50

← PrevPage 1 of 4Next →

All datasets SHHS Sleep-EDF MASS SS3 SHHS (single-channel)DODO Sleep-EDFx Sleep-EDFx (single-channel)DODH ISRUC-Sleep MASS (single-channel)MASS SS2 Montreal Archive of Sleep Studies

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	SynthSleepNet (EEG2+EOG2+EMG1)	Accuracy	89.89	—	Unverified
2	CoRe-Sleep (EEG-EOG)	Accuracy	89.5	—	Unverified
3	SynthSleepNet (EEG1+EOG1+EMG1)	Accuracy	89.28	—	Unverified
4	XSleepNet2 (EEG, EOG, EMG)	Accuracy	89.1	—	Unverified
5	MC2SleepNet 50% Masking (C4-A1 only)	Accuracy	88.6	—	Unverified
6	MC2SleepNet 15% Masking (C4-A1 only)	Accuracy	88.5	—	Unverified
7	SynthSleepNet (EEG1+EOG1)	Accuracy	88.31	—	Unverified
8	CoRe-Sleep (EEG)	Accuracy	88.2	—	Unverified
9	SleePyCo (C4-A1 only)	Accuracy	87.9	—	Unverified
10	NeuroNet (C4-A1 only)	Accuracy	86.88	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SleePyCo (Fpz-Cz only)	Accuracy	86.8	—	Unverified
2	CatBoost	Accuracy	86.6	—	Unverified
3	XSleepNet (EEG, EOG)	Accuracy	86.4	—	Unverified
4	Linear model	Accuracy	86.3	—	Unverified
5	IITNet CRNN (Fpz-Cz only)	Accuracy	84	—	Unverified
6	DeepSleepNet	Accuracy	82	—	Unverified
7	Multitask 1-max CNN	Accuracy	81.9	—	Unverified
8	Deep CNN with transfer-learning	Accuracy	81.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Deep Sleep Net	Accuracy	89.1	—	Unverified
2	Simple Sleep Net	Accuracy	88.8	—	Unverified
3	CatBoost	Accuracy	86.7	—	Unverified
4	DeepSleepNet	Accuracy	86.2	—	Unverified
5	Linear model	Accuracy	85.3	—	Unverified
6	SPDTransNet	Macro-F1	0.81	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MC2SleepNet 50% Masking (C4-A1 only)	Accuracy	88.6	—	Unverified
2	MC2SleepNet 15% Masking (C4-A1 only)	Accuracy	88.5	—	Unverified
3	SleePyCo (C4-A1 only)	Accuracy	87.9	—	Unverified
4	XSleepNet (C4-A1 only)	Accuracy	87.7	—	Unverified
5	NeuroNet (C4-A1 only)	Accuracy	86.88	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SimpleSleepNet	Accuracy	88.7	—	Unverified
2	DeepSleepNet	Accuracy	87.5	—	Unverified
3	SeqSleepNet	Accuracy	85.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	NeuroNet (Fpz-Cz only)	Accuracy	85.24	—	Unverified
2	SleePyCo (Fpz-Cz only)	Accuracy	84.6	—	Unverified
3	XSleepNet (EEG, EOG)	Accuracy	84	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	NeuroNet (Fpz-Cz only)	Accuracy	85.24	—	Unverified
2	SleePyCo (Fpz-Cz only)	Accuracy	84.6	—	Unverified
3	XSleepNet (Fpz-Cz only)	Accuracy	84	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SimpleSleepNet	Accuracy	89.9	—	Unverified
2	DeepSleepNet	Accuracy	89.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SLEEPER-DT	Accuracy	78.5	—	Unverified
2	NeuroNet (C4-A1 only)	Accuracy	77.05	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SleePyCo (C4-A1 only)	Accuracy	86.8	—	Unverified
2	XSleepNet (C4-A1 only)	Accuracy	85.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	IITNet (F4-EOG [Left] only)	Accuracy	84.5	—	Unverified
2	Multitask 1-max CNN	Accuracy	78.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SleePyCo (C4-A1 only)	Accuracy	86.8	—	Unverified
2	U-time EEG only (4 classes)	Accuracy	85	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	XSleepNet (EEG, EOG, EMG)	Accuracy	81.1	—	Unverified
2	SleePyCo (C3-A2 only)	Accuracy	80.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SleePyCo (C3-A2 only)	Accuracy	80.9	—	Unverified
2	XSleepNet (C3-A2 only)	Accuracy	80.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SleePyCo (Fpz-Cz only)	Accuracy	86.8	—	Unverified
2	IITNet (Fpz-Cz only)	Accuracy	83.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	NeuroNet (C4-A1 only)	Accuracy	77.05	—	Unverified