Sustained logging and discrimination of sleep postures with low-level, wrist-worn sensors

Abstract

We present a study which evaluates the use of simple lowpower sensors for a long-term, coarse-grained detection of sleep postures. In contrast to the information-rich but complex recording methods used in sleep studies, we follow a paradigm closer to that of actigraphy by using a wrist-worn device that continuously logs and processes data from the user. Experiments show that it is feasible to detect nightly sleep periods with a combination of light and simple motion and posture sensors, and to detect within these segments what basic sleeping postures the user assumes. These findings can be of value in several domains, such as monitoring of sleep apnea disorders, and support the feasibility of a continuous home-monitoring of sleeping trends where users wear the sensor device uninterruptedly for weeks to months in a row.

Combining wearable and environmental sensing into an unobtrusive tool for long-term sleep studies

“…Several studies are dedicated to the detection of body posture and movements during the sleep, motivated by especially sleep apnea [23] and as a tool to measure for sleep quality [14]. This paper addresses the long-term challenges in particular by integrating methods for night segmentation, posture clustering, and myoclonic twitch detection, in order that these can be applied in behavioral monitoring.…”

Wearable accelerometer based extended sleep position recognition

“…A 100% accuracy is achieved for recognizing three of the five positions and 85% for the other two. Van Laerhoven et al [21] uses tilt switches on the dominant wrist to be able to detect eight postures during the sleep. These postures include the four main positions plus four intermediate positions based on angle, e.g., left-prone.…”

“…Furthermore, this is an immobile system as it requires sensors to be installed in or on the bed. The second category uses wearable devices [2], [14], [15], [21], which provide a mobile solution and are able to monitor different people in the same bed. A disadvantage is that the sensors have to be worn on the body, which can possibly lead to discomfort.…”

Healthcare algorithms by wearable inertial sensors: a survey

“…By detecting wrist movement: Koristof [53] uses a energy-efficient wrist-worn device Porcupine [52] that exploits tilt switches and light sensors to detect sleep postures, amount of motion and night segment. Sleep postures include left lateral, supine and right lateral in basic scenario to detect.…”