Sound-based Sleep Staging at Home Using Smartphone via Deep Learning

May 29, 2023
Sleep 2023

Abstract

Introduction:
Daily sleep tracking at home is growing in demand as more and more people are aware of the significance of sleep. The objective of this study is to propose a sound- based sleep staging model based on deep learning that works well in home environments with recorded audio data from gen- eral smartphones.


Methods:
Three different audio datasets were used. A labeled hospital dataset (PSG and audio, N=812) and an unlabeled home dataset (audio only, N=829) were used for training. A lim- ited number of labeled sound data from home (PSG and audio, N=45) were used for testing. Our proposed HomeSleepNet has three components: (1) supervised learning using the labeled hospital data that trains the model to make correct predictions in hospital environments; (2) unsupervised domain adapta- tion (UDA), which used both the labeled hospital data and unlabeled home data, and transferred the sleep staging power from hospital domain to home domain by adversarial training; (3) unsupervised data augmentation for consistency training (UDC), which augmented hospital data by adding home noise and trained the model to make consistent predictions on orig- inal and augmented data. After all training, HomeSleepNet is expected to make robust sleep staging despite the home noise presence.

Results:
HomeSleepNet achieved 76.2% accuracy on the sleep staging task in home environments for the 3-stage classification case (Wake, NREM, REM). Specifically, it correctly predicted 63.4% of wake, 83.6% of NREM sleep, and 64.9% of REM sleep. The contributions of UDA and UDC were demonstrated by the following results. The accuracy of the model trained with- out both was 69.2%. Either addition of UDA or UDC training to the model improved the performance, with increased accuracy of 69.3% for UDA and 73.5% for UDC. As expected, using both UDA and UDC (i.e., HomeSleepNet) achieved the best perfor- mance, with a 7% increase in accuracy compared to the model trained without both components.


Conclusion:
To the best of our knowledge, this is the first sound- based sleep staging study conducted in home environments. Moreover, the sounds were recorded by commercial smart- phones and not through professional devices. Our proposed model introduced a reliable and convenient method for daily sleep tracking at home.

Authors

Hai Tran
Jung Kyung Hong
Hyeryung Jang
Jinhwan Jung
Jongmok Kim
Joonki Hong
Minji Lee
Jeong-Whun Kim
Clete Kushida
Dongheon Lee

Acknowledgments