# Detection of Sleep Posture via Humidity Fluctuation Analysis in a Sensor-Embedded Pillow

## TL;DR

A new non-invasive sleep monitoring method uses humidity sensors in a pillow to detect sleep posture changes with high accuracy.

## Contribution

A novel sleep posture detection system using humidity fluctuations in a sensor-embedded pillow, achieving 96% accuracy via transfer learning.

## Key findings

- Humidity data showed more significant fluctuations than temperature data during sleep movements.
- A transfer learning model using Vision Transformer achieved 96% accuracy in classifying sleep postures.
- Humidity-based monitoring proved feasible for non-intrusive sleep analysis.

## Abstract

This study presents a novel method for detecting sleep posture changes—specifically tossing and turning—by monitoring variations in humidity using an array of humidity sensors embedded at regular intervals within a memory-foam pillow. Unlike previous approaches that rely primarily on temperature or pressure sensors, our method leverages the observation that humidity fluctuations are more pronounced during movement, enabling the more sensitive detection of posture changes. We demonstrate that dynamic patterns in humidity data correlate strongly with physical motion during sleep. To identify these transitions, we applied the Pruned Exact Linear Time (PELT) algorithm, which effectively segmented the time series based on abrupt changes in humidity. Furthermore, we converted humidity fluctuation curves into image representations and employed a transfer-learning-based model to classify sleep postures, achieving accurate recognition performance. Our findings highlight the potential of humidity sensing as a reliable modality for non-invasive sleep monitoring. In this study, we propose a novel method for detecting tossing and turning during sleep by analyzing changes in humidity captured by a linear array of sensors embedded in a memory foam pillow. Compared to temperature data, humidity data exhibited more significant fluctuations, which were leveraged to track head movement and infer sleep posture. We applied a rolling smoothing technique and quantified the cumulative deviation across sensors to identify posture transitions. Furthermore, the PELT algorithm was utilized for precise change-point detection. To classify sleep posture, we converted the humidity time series into images and implemented a transfer learning model using a Vision Transformer, achieving a classification accuracy of approximately 96%. Our results demonstrate the feasibility of a sleep posture analysis using only humidity data, offering a non-intrusive and effective approach for sleep monitoring.