Clustering and Data Augmentation to Improve Accuracy of Sleep Assessment and Sleep Individuality Analysis
This work addresses sleep monitoring for individuals at home, offering a non-intrusive alternative to smartwatches, but it is incremental as it combines existing methods like VAE, GMM, and LSTM for a specific application.
The study tackled the problem of sleep assessment by constructing a machine learning model using sleep sounds to provide evidence-based evaluations, achieving a high accuracy of 94.8% in distinguishing sleep satisfaction.
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.