Abstract
We propose a Bayesian model for extracting sleep patterns from smartphone events. Our method is able to identify individuals’ daily sleep periods and their evolution over time, and provides an estimation of the probability of sleep and wake transitions. The model is fitted to more than 400 participants from two different datasets, and we verify the results against ground truth from dedicated armband sleep trackers. We show that the model is able to produce reliable sleep estimates with an accuracy of 0.89, both at the individual and at the collective level. Moreover the Bayesian model is able to quantify uncertainty and encode prior knowledge about sleep patterns. Compared with existing smartphone-based systems, our method requires only screen on/off events, and is therefore much less intrusive in terms of privacy and more battery-efficient.
Highlights
Sleep is an important part of life, and quality of sleep has a significant impact on individual well-being and performance. This calls for methods to analyze sleep patterns in large populations, preferably without laborious or invasive consequences, as people typically disapprove of the use of intrusive technologies [1]
For dataset A we verify the fit by comparing with the sleep patterns from sleep trackers, while for dataset B we evaluate the fit by inspecting the inferred sleep patterns
We provide a qualitative analysis of some key examples of individual sleep patterns, and a description of the aggregated sleep patterns for both datasets
Summary
Sleep is an important part of life, and quality of sleep has a significant impact on individual well-being and performance. This calls for methods to analyze sleep patterns in large populations, preferably without laborious or invasive consequences, as people typically disapprove of the use of intrusive technologies [1]. Large scale studies of human sleep patterns are typically carried out using questionnaires, a method that is known to be unreliable. It is possible to perform more accurate studies, but these are currently carried out within small controlled environments, such as sleep labs. In order to perform accurate measurements of sleep in large populations—consisting of thousands of individuals—without dramatically increasing costs, alternative methods are needed. Smartphones have become excellent proxies for studies of human behavior [2, 3], as they are able to automatically log data from built-in sensors (GPS, Bluetooth, WiFi) and on usage patterns (phone calls, SMS and screen interaction), from which underlying user behavioral patterns can be derived
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
