Discrimination of Sleep Posture Using CNN in Smart Bed

Authors

  • Tae-Hwan Kim
  • Ki-Young Lee
  • Youn-Sik Hong

Abstract

Sleep posture is one of the important indicators to measure the health status of a person. The purpose of this paper is to know which posture a sleeping person took while sleeping and to know which body part of the sleep posture produced the strongest pressure. To do this, we have implemented a smart bed with a set of FSR sensors arranged in a grid structure. The pressure intensity of each FSR sensor is converted into the corresponding gray image. Then the convolutional neural network composed of eight layers was applied to the 50 samples to discriminate one of the three lying postures. The results showed 94.42% accuracy, which is more than 7% higher than the typical method based on the distribution of pressure intensity.

Keywords: CNN, FSR sensor, Lying posture, Smart bed, WiFi

Downloads

Published

2019-12-12

Issue

Section

Articles