• DocumentCode
    2115278
  • Title

    Classification of human physical activity and energy expenditure estimation by accelerometry and barometry

  • Author

    Anastasopoulou, P. ; Tansella, M. ; Stumpp, J. ; Shammas, L. ; Hey, S.

  • Author_Institution
    Inst. for Inf. Process. Technol., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany
  • fYear
    2012
  • fDate
    Aug. 28 2012-Sept. 1 2012
  • Firstpage
    6451
  • Lastpage
    6454
  • Abstract
    Regular exercise and physical activity are among the most important factors influencing the quality of life and make a significant contribution to the maintenance of health and well-being. The assessment of physical activity via accelerometry has become a promising technique often used as means to objectively measure physical activity. This work proposes a simple and reliable method to assess human physical activity and calculate the energy expenditure (EE) by using an acceleration and an air pressure sensor. Our proposed algorithm differentiates between 7 activities with an average accuracy of 98.2% and estimates the second by second EE with an average percent error of 1.59 ± 8.20% using a single measurement unit attached to the subject´s hip.
  • Keywords
    acceleration; accelerometers; biomedical equipment; biomedical measurement; estimation theory; medical signal processing; pressure sensors; signal classification; acceleration; accelerometry; air pressure sensor; average percent error; barometry; energy expenditure estimation; health maintenance; human physical activity classification; physical activity measurement; regular exercise; subject hip; Acceleration; Legged locomotion; MATLAB; Mathematical model; Reliability; Sensitivity; Weight measurement; Accelerometry; Algorithms; Energy Metabolism; Female; Humans; Male; Motor Activity; Signal Processing, Computer-Assisted;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE
  • Conference_Location
    San Diego, CA
  • ISSN
    1557-170X
  • Print_ISBN
    978-1-4244-4119-8
  • Electronic_ISBN
    1557-170X
  • Type

    conf

  • DOI
    10.1109/EMBC.2012.6347471
  • Filename
    6347471