# Sleep Stage Classification on Sleep-EDF SC 20 Source: [Sleep Stage Classification on Sleep-EDF SC 20]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:51:24.192Z Evaluation of sleep stage classification performance on the Sleep-EDF SC 20 dataset, reporting Macro F1 (MF1), Accuracy (ACC), and Cohen's Kappa (κ). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Sleep Stage Classification | | Dataset (including any stated split) | Sleep-EDF SC 20 | | Metric | Macro F1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Macro F1](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. - [Kappa](): Higher is better; unit: SCALAR. ## Recorded results | Method | Macro F1 | Result date | Report paper | | --- | --- | --- | --- | | XSleepnet2 | 81.7 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | Classical ML Pipeline | 81 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | Classical ML Pipeline | 80.9 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | Classical ML Pipeline | 80.9 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | Classical ML Pipeline | 80.5 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | TinySleepNet | 80.5 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | SimpleSleepNet | 80.5 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | Classical ML Pipeline | 80.3 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | Classical ML Pipeline | 80.2 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | XSleepnet1 | 79.8 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | Classical ML Pipeline | 79.7 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | SleepEEGNet | 79.7 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | SeqSleepNet+ | 79.6 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | RobustSleepNet | 79.1 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | RobustSleepNet | 79.1 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | DeepSleepNet+ | 79 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | DeepSleepNet-Lite | 78 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | IITNet | 77.6 | Not recorded | 68fa6e2a1e209131cea3e3e6 | | DeepSleepNet | 76.9 | Not recorded | 68fa6e2a1e209131cea3e3e6 | ### XSleepnet2 Macro F1: 81.7. Result ID: 699007573a6c314849fd953e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2021","Technique":"RNN","LP":"FT","Signals":"EEG + EOG"}. This record does not assert independent reproduction. ### Classical ML Pipeline Macro F1: 81. Result ID: 699007573a6c314849fd953f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2022","Technique":"Catboost","LP":"DT","Signals":"EEG + EOG + EMG"}. This record does not assert independent reproduction. ### Classical ML Pipeline Macro F1: 80.9. Result ID: 699007573a6c314849fd9540. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2022","Technique":"CNN & RNN","LP":"LFS","Signals":"EEG + EOG"}. This record does not assert independent reproduction. ### Classical ML Pipeline Macro F1: 80.9. Result ID: 699007573a6c314849fd9541. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2022","Technique":"Logistic regr.","LP":"LFS","Signals":"EEG + EOG + EMG"}. This record does not assert independent reproduction. ### Classical ML Pipeline Macro F1: 80.5. Result ID: 699007573a6c314849fd9542. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2022","Technique":"Logistic regr.","LP":"DT","Signals":"EEG + EOG + EMG"}. This record does not assert independent reproduction. ### TinySleepNet Macro F1: 80.5. Result ID: 699007573a6c314849fd9543. [Reporting paper]() Recorded evaluation configuration: {"Year":"2020","Technique":"CNN & RNN","LP":"LFS","Signals":"EEG"}. This record does not assert independent reproduction. ### SimpleSleepNet Macro F1: 80.5. Result ID: 699007573a6c314849fd9544. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2020","Technique":"RNN","LP":"LFS","Signals":"EEG + EOG"}. This record does not assert independent reproduction. ### Classical ML Pipeline Macro F1: 80.3. Result ID: 699007573a6c314849fd9545. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2022","Technique":"Logistic regr.","LP":"LFS","Signals":"EEG + EOG"}. This record does not assert independent reproduction. ### Classical ML Pipeline Macro F1: 80.2. Result ID: 699007573a6c314849fd9546. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2022","Technique":"Catboost","LP":"LFS","Signals":"EEG + EOG + EMG"}. This record does not assert independent reproduction. ### XSleepnet1 Macro F1: 79.8. Result ID: 699007573a6c314849fd9547. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2020","Technique":"CNN & RNN","LP":"LFS","Signals":"EEG + EOG"}. This record does not assert independent reproduction. ### Classical ML Pipeline Macro F1: 79.7. Result ID: 699007573a6c314849fd9548. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2022","Technique":"Catboost","LP":"LFS","Signals":"EEG + EOG"}. This record does not assert independent reproduction. ### SleepEEGNet Macro F1: 79.7. Result ID: 699007573a6c314849fd9549. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2019","Technique":"CNN & RNN","LP":"LFS","Signals":"EEG"}. This record does not assert independent reproduction. ### SeqSleepNet+ Macro F1: 79.6. Result ID: 699007573a6c314849fd954a. [Reporting paper]() Recorded evaluation configuration: {"Year":"2020","Technique":"RNN","LP":"FT","Signals":"EEG"}. This record does not assert independent reproduction. ### RobustSleepNet Macro F1: 79.1. Result ID: 699007573a6c314849fd954b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2021","Technique":"RNN","LP":"LFS","Signals":"EEG + EOG"}. This record does not assert independent reproduction. ### RobustSleepNet Macro F1: 79.1. Result ID: 699007573a6c314849fd954c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2021","Technique":"RNN","LP":"DT","Signals":"EEG + EOG"}. This record does not assert independent reproduction. ### DeepSleepNet+ Macro F1: 79. Result ID: 699007573a6c314849fd954d. [Reporting paper]() Recorded evaluation configuration: {"Year":"2020","Technique":"CNN","LP":"FT","Signals":"EEG + EOG"}. This record does not assert independent reproduction. ### DeepSleepNet-Lite Macro F1: 78. Result ID: 699007573a6c314849fd954e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2021","Technique":"CNN","LP":"LFS","Signals":"EEG"}. This record does not assert independent reproduction. ### IITNet Macro F1: 77.6. Result ID: 699007573a6c314849fd954f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2019","Technique":"CNN & RNN","LP":"LFS","Signals":"EEG"}. This record does not assert independent reproduction. ### DeepSleepNet Macro F1: 76.9. Result ID: 699007573a6c314849fd9550. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2017","Technique":"CNN & RNN","LP":"FT","Signals":"EEG"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.