Sage Journals: Discover world-class research

Abstract

Sleep disorders have become a prevalent health concern in today’s society, significantly impacting the daily lives and work efficiency of a vast number of individuals. Traditional sleep aid methods, such as pharmacological treatments and standard sleep aid music, offer some relief but come with inherent limitations, including potential side effects and variations due to individual differences. To address this more effectively, this study introduces a strategy model that integrates self-attention with time-domain features, aiming to produce more personalized sleep aid music. Utilizing deep learning techniques, the model can adjust the audio strategy in real-time based on the physiological responses of the participants, thereby generating sleep aid music tailored to individual needs. Through a series of experimental validations, we found that compared to traditional strategy models, our proposed model demonstrates significant advantages in promoting relaxation and sleep for participants, especially in the scores across various dimensions of the PSQI. This research offers new theoretical insights and practical considerations for the study and application of sleep aid music.

Keywords

sleep disorders personalized sleep aid self-attention time-domain analysis deep learning

Get full access to this article

View all access options for this article.

References

Kaneita

Yokoyama

Harano

, et al. Associations between sleep disturbance and mental health status: a longitudinal study of Japanese junior high school students. Sleep Med 2009; 10(7): 780–786.

Fultz

Bonmassar

Setsompop

, et al. Coupled electrophysiological, hemodynamic, and cerebrospinal fluid oscillations in human sleep. Science 2019; 366(6465): 628–631.

Jespersen

Otto

Kringelbach

, et al. A randomized controlled trial of bedtime music for insomnia disorder. J Sleep Res 2015; 24(5): 574–586.

Vaswani

Shazeer

Parmar

, et al. Attention is all you need. Adv Neural Inf Process Syst 2017; 30.

Smith

Jones

. The role of physiological features in sleep assessment. J Sleep Res 2016; 25(3): 123–130.

Brown

Davis

. Correlation between sleep quality and physiological parameters. Sleep Med Rev 2017; 31: 45–52.

Lee

Park

. Analysis of physiological signals for sleep quality assessment. J Biomed Inf 2018; 40(2): 81–88.

Kim

Choi

. Real-time adjustment of audio stimuli based on physiological features. J Audio Eng Soc 2019; 67(4): 253–260.

Wang

Zhang

. Real-time audio adjustment based on physiological features. J Aud Res 2016; 28(2): 45–53.

10.

Liu

Chen

. A dynamic audio adjustment strategy based on physiological signals. J Biomed Signal Process 2017; 32(4): 81–89.

11.

Zhao

. Self-Attention based feature weight allocation for audio adjustment. J Artif Intell Res 2018; 40(1): 123–130.

12.

Yang

. A comprehensive model for real-time audio adjustment. J Sound Vib 2019; 45(3): 253–260.

13.

Chen

. Real-time audio adjustment using self-attention mechanism. J Audio Eng 2020; 46(2): 112–120.

14.

Smith

Johnson

. Audio strategy optimization using integrated features. J Sound Vib 2018; 38(2): 150–160.

15.

Lee

Kim

. Deep neural networks for audio signal processing. IEEE Trans Audio Speech Lang Process 2019; 27(5): 867–878.

16.

Smith

Doe

. Physiological responses to music stimuli. J Music Ther 2020; 57(3): 234–256.

17.

Wang

Zhang

Liu

. PSQI-based music effect evaluation. Sleep Med Rev. 2019; 45:78–85.

Personalized sleep aid audio strategy model based on self-attention and time-domain analysis

Abstract

Keywords

Get full access to this article

References