March 7, 2018IEEE Transactions on Neural Systems and Rehabilitation EngineeringOpen Access

A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series

View Full Paper

Ask AI

Bookmark

Population

61 publicly available polysomnography (PSG) records from 61 subjects (MASS dataset - session 3)

Comparison

Deep learning architecture for temporal sleep… vs Alternative automatic approaches based on…

Design

Other

Authors

SCStanislas Chambon MGMathieu Galtier PAPierrick J. Arnal

Discussion

Member takes

Overview

Hypothesis-generating for automated PSG staging; requires prospective clinical validation before adoption.

Structured PICO

Population

61 publicly available polysomnography (PSG) records from 61 subjects (MASS dataset - session 3)

Intervention

Deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series (EEG, EOG, EMG) without hand-crafted features

Comparator

Alternative automatic approaches based on convolutional networks or decisions trees (gradient boosting on hand-crafted features)

Outcome

Sleep stage classification performance measured with balanced accuracy

A novel end-to-end deep learning architecture using multivariate and multimodal PSG signals achieves state-of-the-art sleep stage classification performance.

Cite This Study

Chambon et al. (2018) studied this question.

synapsesocial.com/papers/6a833742f71f34e1aae8f2ca https://doi.org/10.1109/tnsre.2018.2813138

View Full Paper

Ask AI

Bookmark

March 7, 2018IEEE Transactions on Neural Systems and Rehabilitation EngineeringOpen Access

A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series

View Full Paper

Ask AI

Bookmark

Population

61 publicly available polysomnography (PSG) records from 61 subjects (MASS dataset - session 3)

Comparison

Deep learning architecture for temporal sleep… vs Alternative automatic approaches based on…

Design

Other

Authors

SCStanislas Chambon MGMathieu Galtier PAPierrick J. Arnal

Discussion

Member takes

Overview

Hypothesis-generating for automated PSG staging; requires prospective clinical validation before adoption.

Structured PICO

Population

61 publicly available polysomnography (PSG) records from 61 subjects (MASS dataset - session 3)

Intervention

Deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series (EEG, EOG, EMG) without hand-crafted features

Comparator

Alternative automatic approaches based on convolutional networks or decisions trees (gradient boosting on hand-crafted features)

Outcome

Sleep stage classification performance measured with balanced accuracy

A novel end-to-end deep learning architecture using multivariate and multimodal PSG signals achieves state-of-the-art sleep stage classification performance.

Cite This Study

Chambon et al. (2018) studied this question.

synapsesocial.com/papers/6a833742f71f34e1aae8f2ca https://doi.org/10.1109/tnsre.2018.2813138

View Full Paper

Ask AI

Bookmark