Unconstrained measurement of lying posture, respiration and heartbeat using a tactile sensor on a bed

Sleep monitoring provides useful information for keeping a good health condition and detecting diseases. The monitoring system should not interfere with natural sleep, and be an existence that is almost unnoticed by the person being measured, to be used in daily life. We propose a method for unconstrained measurement of the lying posture, respiration and heartbeat of a person on a rubber-based tactile sensor sheet. The tactile sensor is soft, flexible, and thin, and is not uncomfortable for the person lying on it. To extract faint heartbeat signals from pressure detected by the tactile sensor, improvement of the S/N ratio by averaging oversampled data is needed. This process takes some time, and can be conducted at only a limited number of locations on the tactile sensor. The suitable locations for the heartbeat detection depend on not only the location but also the lying posture of the person on the sensor. In the proposed method, the lying location and posture are detected using a pattern recognition technique applied on pressure pattern obtained by the tactile sensor. The parameters in the pattern recognition are adjusted by using machine learning based on pressure pattern samples. In this paper, we describe the method for unconstrained measurement and report the experimental results.