Clustering and Data Augmentation to Improve Accuracy of Sleep Assessment and Sleep Individuality Analysis

TL;DR

This study aims to construct a machine learning-based sleep assessment model providing evidence-based assessments, such as poor sleep due to frequent movement during sleep onset, by extracting sleep sound events, deriving latent representations using VAE, clustering with GMM, and training LSTM for subjective sleep assessment.

Abstract

Recently, growing health awareness, novel methods allow individuals to monitor sleep at home. Utilizing sleep sounds offers advantages over conventional methods like smartwatches, being non-intrusive, and capable of detecting various physiological activities. This study aims to construct a machine learning-based sleep assessment model providing evidence-based assessments, such as poor sleep due to frequent movement during sleep onset. Extracting sleep sound events, deriving latent representations using VAE, clustering with GMM, and training LSTM for subjective sleep assessment achieved a high accuracy of 94.8% in distinguishing sleep satisfaction. Moreover, TimeSHAP revealed differences in impactful sound event types and timings for different individuals.

Figures (14)

• Figure 1: Overview of the proposed sleep satisfaction classification introducing clustering of sound events
• Figure 2: Random sampling of sound events for data augmentation
• Figure 3: Sleep sound events within important clusters on the latent representation plot by t-SNE (Subject 1)
• Figure 4: SHAP values for different satisfactions (Subject 1)
• Figure 5: SHAP values on divided into three equal parts on satisfied days (Subject 1)