A4 Article in conference proceedings
A Deep Learning Model for Automatic Sleep Scoring using Multimodality Time Series (2020)

Yan, R., Li, F., Zhou, D., Ristaniemi, T., & Cong, F. (2020). A Deep Learning Model for Automatic Sleep Scoring using Multimodality Time Series. In EUSIPCO 2020 : 28th European Signal Processing Conference (pp. 1090-1094). IEEE. European Signal Processing Conference. https://doi.org/10.23919/Eusipco47968.2020.9287518

JYU authors or editors

Publication details

All authors or editors: Yan, Rui; Li, Fan; Zhou, DongDong; Ristaniemi, Tapani; Cong, Fengyu

Parent publication: EUSIPCO 2020 : 28th European Signal Processing Conference

Place and date of conference: Amsterdam, Netherlands, 18.-21.1.2021

ISBN: 978-1-7281-5001-7

eISBN: 978-9-0827-9705-3

Journal or series: European Signal Processing Conference

ISSN: 2219-5491

eISSN: 2076-1465

Publication year: 2020

Pages range: 1090-1094

Publisher: IEEE

Publication country: United States

Publication language: English

DOI: https://doi.org/10.23919/Eusipco47968.2020.9287518

Publication open access: Not open

Publication channel open access:

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/73485

Abstract

Sleep scoring is a fundamental but time-consuming process in any sleep laboratory. Automatic sleep scoring is crucial and urgent to help address the increasing unmet need for sleep research. Therefore, this paper aims to develop an end-to-end deep learning architecture using raw polysomnographic recordings to automate sleep scoring. The proposed model adopts two-dimensional convolutional neural networks (2D-CNN) to automatically learn features from multi-modality signals, together with a "squeeze and excitation" block for recalibrating channel-wise feature responses. The learnt representations are finally fed to a softmax classifier to generate predictions for each sleep stage. The model performance is evaluated on two public sleep datasets (SHHS and Sleep-EDF) with different available channels. The results have shown that our model achieves an overall accuracy of 85.2% on the SHHS dataset and an accuracy of 85% on the Sleep-EDF dataset. We have also demonstrated that the proposed architecture not only is able to handle various numbers of input channels and several signal modalities from different datasets but also exhibits short runtimes and low computational cost.

Keywords: brain research; sleep research; sleep; signal analysis; signal processing; time series; machine learning

Free keywords: polysomnography; automatic sleep scoring; multimodality analysis; deep learning; transfer learning

Contributing organizations

Ministry reporting: Yes

Reporting Year: 2020

JUFO rating: 1