• DocumentCode
    3706431
  • Title

    Biowatch: Estimation of heart and breathing rates from wrist motions

  • Author

    Javier Hernandez;Daniel McDuff;Rosalind W. Picard

  • Author_Institution
    Media Lab, Massachusetts Institute of Technology, Cambridge, USA
  • fYear
    2015
  • fDate
    5/1/2015 12:00:00 AM
  • Firstpage
    169
  • Lastpage
    176
  • Abstract
    Continued developments of sensor technology including hardware miniaturization and increased sensitivity have enabled the development of less intrusive methods to monitor physiological parameters during daily life. In this work, we present methods to recover cardiac and respiratory parameters using accelerometer and gyroscope sensors on the wrist. We demonstrate accurate measurements in a controlled laboratory study where participants (n = 12) held three different positions (standing up, sitting down and lying down) under relaxed and aroused conditions. In particular, we show it is possible to achieve a mean absolute error of 1.27 beats per minute (STD: 3.37) for heart rate and 0.38 breaths per minute (STD: 1.19) for breathing rate when comparing performance with FDA-cleared sensors. Furthermore, we show comparable performance with a state-of-the-art wrist-worn heart rate monitor, and when monitoring heart rate of three individuals during two consecutive nights of in-situ sleep measurements.
  • Keywords
    "Heart rate","Wrist","Accelerometers","Gyroscopes","Biomedical monitoring","Estimation","Monitoring"
  • Publisher
    ieee
  • Conference_Titel
    Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2015 9th International Conference on
  • Print_ISBN
    978-1-63190-045-7
  • Electronic_ISBN
    2153-1641
  • Type

    conf

  • DOI
    10.4108/icst.pervasivehealth.2015.259064
  • Filename
    7349394