S4Sleep: Elucidating the design space of deep-learning-based sleep stage classification models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Tiezhi, Strodthoff, Nils
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917899750342656
author Wang, Tiezhi
Strodthoff, Nils
author_facet Wang, Tiezhi
Strodthoff, Nils
contents Scoring sleep stages in polysomnography recordings is a time-consuming task plagued by significant inter-rater variability. Therefore, it stands to benefit from the application of machine learning algorithms. While many algorithms have been proposed for this purpose, certain critical architectural decisions have not received systematic exploration. In this study, we meticulously investigate these design choices within the broad category of encoder-predictor architectures. We identify robust architectures applicable to both time series and spectrogram input representations. These architectures incorporate structured state space models as integral components and achieve statistically significant performance improvements compared to state-of-the-art approaches on the extensive Sleep Heart Health Study dataset. We anticipate that the architectural insights gained from this study along with the refined methodology for architecture search demonstrated herein will not only prove valuable for future research in sleep staging but also hold relevance for other time series annotation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2310_06715
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle S4Sleep: Elucidating the design space of deep-learning-based sleep stage classification models
Wang, Tiezhi
Strodthoff, Nils
Machine Learning
Signal Processing
Scoring sleep stages in polysomnography recordings is a time-consuming task plagued by significant inter-rater variability. Therefore, it stands to benefit from the application of machine learning algorithms. While many algorithms have been proposed for this purpose, certain critical architectural decisions have not received systematic exploration. In this study, we meticulously investigate these design choices within the broad category of encoder-predictor architectures. We identify robust architectures applicable to both time series and spectrogram input representations. These architectures incorporate structured state space models as integral components and achieve statistically significant performance improvements compared to state-of-the-art approaches on the extensive Sleep Heart Health Study dataset. We anticipate that the architectural insights gained from this study along with the refined methodology for architecture search demonstrated herein will not only prove valuable for future research in sleep staging but also hold relevance for other time series annotation tasks.
title S4Sleep: Elucidating the design space of deep-learning-based sleep stage classification models
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2310.06715