7th International Conference on Pervasive Computing Technologies for Healthcare

Research Article

Unobtrusive Sleep Monitoring using Smartphones

Download2401 downloads
  • @INPROCEEDINGS{10.4108/icst.pervasivehealth.2013.252148,
        author={Zhenyu Chen and Mu Lin and Fanglin Chen and Nicholas Lane and Giuseppe Cardone and Rui Wang and Tianxing Li and Yiqiang Chen and Tanzeem Choudhury and Andrew Cambell},
        title={Unobtrusive Sleep Monitoring using Smartphones},
        proceedings={7th International Conference on Pervasive Computing Technologies for Healthcare},
        keywords={mhealth activity recognition sleep monitoring smartphone sensing},
  • Zhenyu Chen
    Mu Lin
    Fanglin Chen
    Nicholas Lane
    Giuseppe Cardone
    Rui Wang
    Tianxing Li
    Yiqiang Chen
    Tanzeem Choudhury
    Andrew Cambell
    Year: 2013
    Unobtrusive Sleep Monitoring using Smartphones
    DOI: 10.4108/icst.pervasivehealth.2013.252148
Zhenyu Chen1,*, Mu Lin1, Fanglin Chen1, Nicholas Lane2, Giuseppe Cardone3, Rui Wang1, Tianxing Li1, Yiqiang Chen4, Tanzeem Choudhury5, Andrew Cambell1
  • 1: Dartmouth College
  • 2: Microsoft Research Asia
  • 3: University of Bologna
  • 4: Chinese Academy of Sciences
  • 5: Cornell University
*Contact email: Zhenyu.Chen@Dartmouth.edu


How we feel is greatly influenced by how well we sleep. Emerging quantified-self apps and wearable devices allow people to measure and keep track of sleep duration, patterns and quality. However, these approaches are intrusive, placing a burden on the users to modify their daily sleep related habits in order to gain sleep data; for example, users have to wear cumbersome devices (e.g., a headband) or inform the app when they go to sleep and wake up. In this paper, we present a radically different approach for measuring sleep duration based on a novel best effort sleep (BES) model. BES infers sleep using smartphones in a completely unobtrusive way – that is, the user is removed from the monitoring process and does not interact with the phone beyond normal user behavior. A sensor-based inference algorithm predicts sleep duration by exploiting a collection of soft hints that tie sleep duration to various smartphone usage patterns (e.g., the time and length of recharge events) and environmental observations (e.g., prolonged silence and darkness). We perform detailed comparisons between two smartphone only approaches that we developed (i.e., BES model and a sleep-with-the-phone approach) and two commercial wearable systems (i.e., the Zeo headband and Jawbone wristband). Results from our one-week 8-person study show that BES can accurately infer sleep duration using a completely “hands off” approach that can cope with the natural variation in users’ sleep routines and environments.