Monitoring Sleep with WISP Tags

Monitoring Sleep with WISP Tags

Enamul Hoque (University of Virginia, USA), Robert F. Dickerson (University of Virginia, USA) and John A. Stankovic (University of Virginia, USA)
DOI: 10.4018/978-1-4666-1990-6.ch007


This chapter presents a sleep monitoring system based on WISP tags. The authors show that their system accurately infers fine-grained body positions from accelerometer data collected from the WISP tags attached to the sides of a bed. Movements, duration, and bed entrances and exits are also detected by the system. The chapter presents the results of an empirical study from 10 subjects on three different mattresses in controlled experiments to show the accuracy of the inference algorithms. The authors also evaluate the accuracy of the movement detection and body position inference for six nights on one subject, and compare these results with two baseline systems. Preliminary data investigating the correlation between sleep stages from the Zeo and movement is also presented.
Chapter Preview


To date, while there are many sleep monitoring systems there are very few low-cost, unobtrusive (comfortable) solutions. In this section we outline the major categories of solutions and describe their characteristics and limitations.

Physiological signals are regarded as the most accurate means to differentiate between awake and sleep phases such as light, REM, and deep sleep. The electroencephalogram (EEG) measures the frequency of brain waves to discern sleep and wake stages (Carskadon 1989). The electrooculogram (EOG) and electromyogram (EMG) are also standard technologies for sleep monitoring. The electrocardiogram (ECG) can be used to measure the heart rate, which is well known to decrease upon sleep onset. Some studies show that heart rate varies over different sleep stages (Redmond 2006, Shinar 2006) by use respiratory-derived features together with ECG-derived features for classifying different sleep stages automatically. These techniques have major limitations- they are costly since they require trained professionals in clinical environments to administer them and invasive since these techniques require equipment to be attached to patients, limiting their movement and causing discomfort. These physiological signals do not support monitoring body positions during sleep.

Temperature regulation in a body can also be used to monitor sleep quality. Skin temperature increases during sleep onset and decreases during wakeup (Krauchi 2004). But these temperature variations can only be measured under controlled laboratory conditions. (Yang 2006) uses an infrared triangulation distance sensor to detect movements of different body parts without attaching any device to the body. But it does not provide any information about body position.

To overcome the limitations of the above techniques, there are many systems that enable sleep monitoring in home environments. Actigraphy (Sadeh 2002) is a commonly used technique for sleep monitoring that uses a watch-like accelerometer based device attached typically to the wrist. The device monitors activities and later labels periods of low activity as sleep. There are many commercial products like the Philips Actiwatch that are designed based on actigraphy. The Zeo is another commercial product for sleep monitoring in home environments. It is a headband that users need to wear each night so that it can detect sleep patterns through the electrical signals naturally produced by the brain. There is also an associated display that shows a person’s sleep pattern for the previous night. These products are expensive and users need to wear the device.

Complete Chapter List

Search this Book: