SynthSleepNet (EEG1+EOG1+EMG1)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical4 results

Sleep QualityonSHHS
Cohen's Kappa· 2025-02-18
0.85
best: 0.86 (SynthSleepNet (EEG2+EOG2+EMG1))
Toward Foundational Model for Sleep Analysis Using a Multimodal Hybrid Self-Supervised Learning Framework arXiv:2502.17481
Sleep QualityonSHHS
Macro-F1· 2025-02-18
0.835
best: 0.845 (SynthSleepNet (EEG2+EOG2+EMG1))
Toward Foundational Model for Sleep Analysis Using a Multimodal Hybrid Self-Supervised Learning Framework arXiv:2502.17481
Sleep Stage DetectiononSHHS
Cohen's Kappa· 2025-02-18
0.85
best: 0.86 (SynthSleepNet (EEG2+EOG2+EMG1))
Toward Foundational Model for Sleep Analysis Using a Multimodal Hybrid Self-Supervised Learning Framework arXiv:2502.17481
Sleep Stage DetectiononSHHS
Macro-F1· 2025-02-18
0.835
best: 0.845 (SynthSleepNet (EEG2+EOG2+EMG1))
Toward Foundational Model for Sleep Analysis Using a Multimodal Hybrid Self-Supervised Learning Framework arXiv:2502.17481