2014 • Computer and Information Sciences
A System For Gathering Data on Sleep Behavior and Context in the Home Setting
Lead Presenter: Aida Ehyaei
Additional Presenters: Stephen Intille
Faculty Advisor / PI: Aida Ehyaei
We spend almost one third of our lives sleeping. Quality and quantity of sleep affect health and how people feel and behave during the day, but better tools are needed to study sleep behaviors unobtrusively, outside of the laboratory. Polysomnography, the gold standard laboratory sleep monitoring method, is expensive and burdensome for the person wearing the system; typically the electrodes required must be attached by an expert. Actigraphy, where accelerometers measure user movement, is an inexpensive method of measuring sleep but does not provide information about a person’s sleep environment that may impact sleep quality, such as noise.
We have developed a system for sleep monitoring in home settings that gathers data on not only sleep quality, but also sleep environment and possible sleep disruptors. A user’s motion data are gathered using a wireless wrist worn accelerometer sensor and a mobile phone device. Ambient noise levels are also monitored. Data are processed in real time to detect sleep vs. wake states, wake periods and noise disturbances during the night. Data processing is used to trigger context-aware and time-dependent self-report surveys on the mobile phone to collect more precise information from users about their sleep and events that may impact sleep quality. The mobile system also simplifies research study administration by sending data to a research webserver regularly for incremental data cleaning and compliance checking. The system is currently being deployed in a pilot study to assess sleep disturbances and peer and family effects on urban African-American children’s sleep.