Using Smartwatch Sensors to Support the Acquisition of Sleep Quality Data for Supervised Machine Learning

  • Cinzia Bernardeschi
  • Mario G. C. A. Cimino
  • Andrea Domenici
  • Gigliola Vaglini
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 192)


It is a common practice in supervised learning techniques to use human judgment to label training data. For this process, data reliability is fundamental. Research on sleep quality found that human sleep stage misperception may occur. In this paper we propose that human judgment be supported by software-driven evaluation based on physiological parameters, selecting as training data only data sets for which human judgment and software evaluation are aligned. A prototype system to provide a broad-spectrum perception of sleep quality data comparable with human judgment is presented. The system requires users to wear a smartwatch recording heartbeat rate and wrist acceleration. It estimates an overall percentage of the sleep stages, to achieve an effective approximation of conventional sleep measures, and to provide a three-class sleep quality evaluation. The training data are composed of the heartbeat rate, the wrist acceleration and the three-class sleep quality. As a proof of concept, we experimented the approach on three subjects, each one over 20 nights.


Sleep monitoring Smartwatch Sleep quality estimation 



This work was partially supported by the PRA 2016 project “Analysis of Sensory Data: from Traditional Sensors to Social Sensors” funded by the University of Pisa. The authors thank Giovanni Pollina, Silvio Bacci and Silvia Volpe for their work on the subject during their thesis.


  1. 1.
    Redmond, S.J., Lee, Q.Y., Xie, Y., Lovell, N.H.: Applications of supervised learning to biological signals: ECG signal quality and systemic vascular resistance. In: 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 57–60, August 2012Google Scholar
  2. 2.
    Aztiria, A., Farhadi, G., Aghajan, H.: User behavior shift detection in ambient assisted living environments. JMIR Mhealth Uhealth 1(1), e6 (2013)CrossRefGoogle Scholar
  3. 3.
    Barsocchi, P., Cimino, M.G.C.A., Ferro, E., Lazzeri, A., Palumbo, F., Vaglini, G.: Monitoring elderly behavior via indoor position-based stigmergy. Pervasive Mob. Comput. 23, 26–42 (2015)CrossRefGoogle Scholar
  4. 4.
    Cimino, M.G.C.A., Lazzeri, A., Vaglini, G.: Improving the analysis of context-aware information via marker-based stigmergy and differential evolution. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2015. LNCS, vol. 9120, pp. 341–352. Springer, Cham (2015). doi: 10.1007/978-3-319-19369-4_31 CrossRefGoogle Scholar
  5. 5.
    Weigand, D., Michael, L., Schulz, H.: When sleep is perceived as wakefulness: an experimental study on state perception during physiological sleep. J. Sleep Res. 16(4), 346–353 (2007)CrossRefGoogle Scholar
  6. 6.
    Nam, Y., Kim, Y., Lee, J.: Sleep monitoring based on a tri-axial accelerometer and a pressure sensor. Sensors 16(5), 750 (2016)CrossRefGoogle Scholar
  7. 7.
    Suzuki, T., Ouchi, K., Kameyama, K.-I., Takahashi, M.: Development of a sleep monitoring system with wearable vital sensor for home use. In: BIODEVICES 2009 International Conference on Biomedical Electronics and Devices, pp. 326–331 (2009)Google Scholar
  8. 8.
    Guiry, J.J., van de Ven, P., Nelson, J.: Multi-sensor fusion for enhanced contextual awareness of everyday activities with ubiquitous devices. Sensors 14(3), 5687–5701 (2014)CrossRefGoogle Scholar
  9. 9.
    Hobson, J.A.: Sleep and dreaming. J. Neurosci. 10(2), 371–382 (1990)Google Scholar
  10. 10.
    Versace, F., Mozzato, M., De Min, G., Tona, C.C., Stegagno, L.: Heart rate variability during sleep as a function of sleep cycle. Biol Psychol. 63(2), 149–162 (2003)CrossRefGoogle Scholar
  11. 11.
    Stein, P.K., Yachuan, P.: Heart rate variability, sleep and sleep disorders. Sleep Med. Rev. 16(1), 47–66 (2012)CrossRefGoogle Scholar
  12. 12.
    Mendez, M.O., Matteucci, M., Castronovo, V., Ferini-Strambi, L., Cerutti, S., Bianchi, A.M.: Sleep staging from heart rate variability: time-varying spectral features and hidden markov models. Int. J. Biomed. Eng. Technol. 3(3/4), 246–263 (2010)CrossRefGoogle Scholar
  13. 13.
    Shinar, Z., Akselrod, S., Daga, Y., Baharav, A.: Autonomic changes during wake-sleep transition: a heart rate variability based approach. Auton. Neurosci. 130(12), 17–27 (2006)CrossRefGoogle Scholar
  14. 14.
    Imtiaz, S.A., Rodriguez-Villegas, E.: Automatic sleep staging using state machine-controlled decision trees. In: Proceedings of the IEEE Engineering in Medicine and Biology Society, pp. 378–381. IEEE (2015)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2017

Authors and Affiliations

  • Cinzia Bernardeschi
    • 1
  • Mario G. C. A. Cimino
    • 1
  • Andrea Domenici
    • 1
  • Gigliola Vaglini
    • 1
  1. 1.Department of Information EngineeringUniversity of PisaPisaItaly

Personalised recommendations