{"url":"/dataset/montreal-archive-of-sleep-studies","name":"Montreal Archive of Sleep Studies","full_name":"Montreal Archive of Sleep Studies","description_markdown":"The Montreal Archive of Sleep Studies (MASS) is an open-access and collaborative database of laboratory-based polysomnography (PSG) recordings O’Reilly, C., et al. (2014) J Seep Res, 23(6):628-635. Its goal is to provide a standard and easily accessible source of data for benchmarking the various systems developed to help the automation of sleep analysis. It also provides a readily available source of data for fast validation of experimental results and for exploratory analyses. Finally, it is a shared resource that can be used to foster large-scale collaborations in sleep studies.\r\n\r\nMASS is composed of cohorts themselves comprising subsets. Recordings within subsets is kept as homogeneous as possible, whereas it is more heterogeneous between subsets. To allow inter-study comparisons, researchers validating their results on MASS are encouraged to specify which portion of the database they used in their assessment (e.g., MASS-C1 for the whole cohort 1, MASS-C1/SS1-SS3 for subsets 1, 2 and 3 of cohort 1).\r\n\r\nCurrently, the first MASS cohort available is described in O’Reilly, C., et al. (2014) J Seep Res, 23(6):628-635. This cohort comprises polysomnograms of 200 complete nights recorded in 97 men and 103 women of age varying between 18 and 76 years (mean: 38.3 years, SD: 18.9 years). It has been split into five different subsets.\r\n\r\nSource: [Montreal Archive of Sleep Studies: an open-access resource for instrument benchmarking and exploratory research](https://onlinelibrary.wiley.com/doi/full/10.1111/jsr.12169)","description_withheld":null,"homepage":"http://ceams-carsm.ca/mass/","introduced_date":"2014-06-09","introduced_date_note":null,"introduced_by":null,"license":{"name":"Open Access","url":"http://ceams-carsm.ca/en/MASS/"},"modalities":[{"name":"EEG","url":"/datasets/modality/eeg"},{"name":"PSG","url":"/datasets/modality/psg"}],"tasks":[{"name":"Sleep Stage Detection","url":"/task/sleep-stage-detection","datasets_with_task":"/datasets/task/sleep-stage-detection"},{"name":"Spindle Detection","url":"/task/spindle-detection","datasets_with_task":"/datasets/task/spindle-detection"},{"name":"Automatic Sleep Stage Classification","url":"/task/automatic-sleep-stage-classification","datasets_with_task":"/datasets/task/automatic-sleep-stage-classification"},{"name":"Sleep Staging","url":"/task/sleep-staging","datasets_with_task":"/datasets/task/sleep-staging"},{"name":"K-complex detection","url":"/task/k-complex-detection","datasets_with_task":"/datasets/task/k-complex-detection"},{"name":"W-R-L-D Sleep Staging","url":"/task/w-r-l-d-sleep-staging","datasets_with_task":"/datasets/task/w-r-l-d-sleep-staging"},{"name":"W-R-N Sleep Staging","url":"/task/w-r-n-sleep-staging","datasets_with_task":"/datasets/task/w-r-n-sleep-staging"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"}],"variants":["MASS SS2","MASS SS3","Montreal Archive of Sleep Studies"],"data_loaders":[{"repo":"https://github.com/PJcheese/data","url":"https://github.com/PJcheese/data","frameworks":[]}],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sleep-stage-detection-on-mass-ss3","task":"Sleep Stage Detection","dataset_variant":"MASS SS3","rows":6,"metrics":["Accuracy","Cohen's kappa","Macro-F1","Macro-averaged Accuracy"],"first_row_in_archive_order":{"model":"Deep Sleep Net","paper":"/paper/dreem-open-datasets-multi-scored-sleep","metrics":{"Accuracy":"89.1%"},"code_links":[{"title":"Dreem-Organization/dreem-learning-open","url":"https://github.com/Dreem-Organization/dreem-learning-open"},{"title":"Dreem-Organization/dreem-learning-evaluation","url":"https://github.com/Dreem-Organization/dreem-learning-evaluation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/sleep-stage-detection-on-montreal-archive-of","task":"Sleep Stage Detection","dataset_variant":"Montreal Archive of Sleep Studies","rows":2,"metrics":["Accuracy","Cohen's kappa","Macro-F1"],"first_row_in_archive_order":{"model":"SleePyCo (C4-A1 only)","paper":"/paper/sleepyco-automatic-sleep-scoring-with-feature","metrics":{"Accuracy":"86.8%","Cohen's kappa":"0.811","Macro-F1":"0.825"},"code_links":[{"title":"gist-ailab/sleepyco","url":"https://github.com/gist-ailab/sleepyco"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/w-r-l-d-sleep-staging-on-montreal-archive-of","task":"W-R-L-D Sleep Staging","dataset_variant":"Montreal Archive of Sleep Studies","rows":2,"metrics":["Weighted F1"],"first_row_in_archive_order":{"model":"EEG 1-ch","paper":"/paper/a-deep-knowledge-distillation-framework-for","metrics":{"Weighted F1":"0.85"},"code_links":[{"title":"acrophase/sleep_staging_kd","url":"https://github.com/acrophase/sleep_staging_kd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/w-r-n-sleep-staging-on-montreal-archive-of","task":"W-R-N Sleep Staging","dataset_variant":"Montreal Archive of Sleep Studies","rows":2,"metrics":["Weighted F1"],"first_row_in_archive_order":{"model":"EEG 1-ch","paper":"/paper/a-deep-knowledge-distillation-framework-for","metrics":{"Weighted F1":"0.90"},"code_links":[{"title":"acrophase/sleep_staging_kd","url":"https://github.com/acrophase/sleep_staging_kd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/structure-preserving-transformers-for","title":"Structure-Preserving Transformers for Sequences of SPD Matrices","date":"2023-09-14","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/sleepyco-automatic-sleep-scoring-with-feature","title":"SleePyCo: Automatic Sleep Scoring with Feature Pyramid and Contrastive Learning","date":"2022-09-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/do-not-sleep-on-linear-models-simple-and","title":"Do Not Sleep on Traditional Machine Learning: Simple and Interpretable Techniques Are Competitive to Deep Learning for Sleep Scoring","date":"2022-07-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-deep-knowledge-distillation-framework-for","title":"A Deep Knowledge Distillation framework for EEG assisted enhancement of single-lead ECG based sleep staging","date":"2021-12-14","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/dreem-open-datasets-multi-scored-sleep","title":"Dreem Open Datasets: Multi-Scored Sleep Datasets to compare Human and Automated sleep staging","date":"2019-10-31","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":22,"samples_ran":3,"samples_unverified":19,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deepsleepnet-a-model-for-automatic-sleep","title":"DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG","date":"2017-03-12","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":33,"samples_ran":0,"samples_unverified":33,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":2,"samples_harvested":55,"samples_ran":3,"samples_unverified":52,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}