A Study of Bed-Leaving Prediction by Using a Pressure-Sensitive Sensor

摘要

Currently in care facilities, a bed-leaving sensor is often used in preventing falls of care receivers during the night. However, these current sensors are usually designed to detect the motion of care receivers getting out of bed and therefore, there are cases in which the care receiver has already fallen from the bed, by the time the sensor had reacted to the movement. It is common knowledge that a person frequently changes position while sleeping. In this research, we focus on the frequency of changes in sleep positions and aim to realize a method for precise prediction of care receivers' attempt in getting out of bed sufficiently before the actual action occurs. We employed the automatic classification method of sleeping positions in the pressure-sensitive sensor, with consideration to privacy of the research subjects, and identified nine types of sleeping positions that are common, with 80.9% accuracy. These results are reported in this paper.