{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sleepyco-automatic-sleep-scoring-with-feature","title":"SleePyCo: Automatic Sleep Scoring with Feature Pyramid and Contrastive Learning","arxiv_id":"2209.09452","date":"2022-09-20","proceeding":null,"authors":["Seongju Lee","Yeonguk Yu","Seunghyeok Back","Hogeon Seo","Kyoobin Lee"],"abstract":"Automatic sleep scoring is essential for the diagnosis and treatment of sleep disorders and enables longitudinal sleep tracking in home environments. Conventionally, learning-based automatic sleep scoring on single-channel electroencephalogram (EEG) is actively studied because obtaining multi-channel signals during sleep is difficult. However, learning representation from raw EEG signals is challenging owing to the following issues: 1) sleep-related EEG patterns occur on different temporal and frequency scales and 2) sleep stages share similar EEG patterns. To address these issues, we propose a deep learning framework named SleePyCo that incorporates 1) a feature pyramid and 2) supervised contrastive learning for automatic sleep scoring. For the feature pyramid, we propose a backbone network named SleePyCo-backbone to consider multiple feature sequences on different temporal and frequency scales. Supervised contrastive learning allows the network to extract class discriminative features by minimizing the distance between intra-class features and simultaneously maximizing that between inter-class features. Comparative analyses on four public datasets demonstrate that SleePyCo consistently outperforms existing frameworks based on single-channel EEG. Extensive ablation experiments show that SleePyCo exhibits enhanced overall performance, with significant improvements in discrimination between the N1 and rapid eye movement (REM) stages.","url_abs":"https://arxiv.org/abs/2209.09452v1","url_pdf":"https://arxiv.org/pdf/2209.09452v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sleepyco-automatic-sleep-scoring-with-feature","repo_url":"https://github.com/gist-ailab/sleepyco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg","task_name":"Electroencephalogram (EEG)"},{"task_slug":"sleep-stage-detection","task_name":"Sleep Stage Detection"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sleep-stage-detection-on-mass-single-channel","task":"Sleep Stage Detection","dataset":"MASS (single-channel)","model":"SleePyCo (C4-A1 only)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"86.8%","Cohen's Kappa":"0.811","Macro-F1":"0.825"},"uses_additional_data":false},{"leaderboard":"/sota/sleep-stage-detection-on-montreal-archive-of","task":"Sleep Stage Detection","dataset":"Montreal Archive of Sleep Studies","model":"SleePyCo (C4-A1 only)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"86.8%","Cohen's kappa":"0.811","Macro-F1":"0.825"},"uses_additional_data":false},{"leaderboard":"/sota/sleep-stage-detection-on-physionet-challenge-1","task":"Sleep Stage Detection","dataset":"PhysioNet Challenge 2018","model":"SleePyCo (C3-A2 only)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"80.9%","Cohen's Kappa":"0.737","Macro-F1":"0.789"},"uses_additional_data":false},{"leaderboard":"/sota/sleep-stage-detection-on-physionet-challenge","task":"Sleep Stage Detection","dataset":"PhysioNet Challenge 2018 (single-channel)","model":"SleePyCo (C3-A2 only)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"80.9%","Cohen's Kappa":"0.737","Macro-F1":"0.789"},"uses_additional_data":false},{"leaderboard":"/sota/sleep-stage-detection-on-shhs-single-channel","task":"Sleep Stage Detection","dataset":"SHHS (single-channel)","model":"SleePyCo (C4-A1 only)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"87.9%","Cohen's Kappa":"0.830","Macro-F1":"0.807"},"uses_additional_data":false},{"leaderboard":"/sota/sleep-stage-detection-on-sleep-edf","task":"Sleep Stage Detection","dataset":"Sleep-EDF","model":"SleePyCo (Fpz-Cz only)","rank_in_archive_order":1,"of":8,"metrics":{"Accuracy":"86.8%","Cohen's kappa":"0.820","Macro-F1":"0.812"},"uses_additional_data":false},{"leaderboard":"/sota/sleep-stage-detection-on-sleep-edf-single","task":"Sleep Stage Detection","dataset":"Sleep-EDF (single-channel)","model":"SleePyCo (Fpz-Cz only)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"86.8%"},"uses_additional_data":false},{"leaderboard":"/sota/sleep-stage-detection-on-sleep-edfx","task":"Sleep Stage Detection","dataset":"Sleep-EDFx","model":"SleePyCo (Fpz-Cz only)","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"84.6%","Cohen's Kappa":"0.787","Macro-F1":"0.790"},"uses_additional_data":false},{"leaderboard":"/sota/sleep-stage-detection-on-sleep-edfx-single","task":"Sleep Stage Detection","dataset":"Sleep-EDFx (single-channel)","model":"SleePyCo (Fpz-Cz only)","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"84.6%","Cohen's Kappa":"0.787","Macro-F1":"0.790"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}