Advertisement

Estimating the Physical Activity with Smartphones: Analysis of the Device Position and Comparison with GT3X+ Actigraph

  • Victor H. Rodriguez
  • Carlos Medrano
  • Inmaculada Plaza
  • Cristina Corella
  • Alberto Abarca
  • Jose A. Julian
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 476)

Abstract

Nowadays there are commercial devices such as the GT3X+ that can analyze the performance of those who practice some kind of sport, but these devices tend to be rather expensive and complex to use. The objectives of this research are: i) to study the correlation between the measurements of the physical activity with the smartphone and a dedicated accelerometer GT3X+ through the calculation of the counts, ii) to analyze the influence of the position of the smartphone and iii) compare several methods to calculate the energy expenditure trough the counts. Nine volunteers participated in an experiment. They performed different physical activities carrying a smartphone in the right pocket and another one in the hip, together with the GT3X+. The results obtained show a high correlation between the GT3X+ and smartphones for the different types of training (hip and pocket). However the result of the ANOVA indicates that there is no significant difference between the positions of the smartphone.

Keywords

Physical Activity Smartphones Accelerometer eHealth 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Liu, S., Gao, R.X., John, D., Staudenmayer, J., Freedson, P.: SVM-Based Multi-Sensor Fusion for Free-Living Physical Activity Assessment. IEEE in Medicine and Biology Society, pp. 3188–3191 (2011)Google Scholar
  2. 2.
    http://apps.who.int/iris/bitstream/10665/44441/1/9789243599977_spa.pdf, recommendations of the World Health Organization (WHO) (accessed January 24, 2016)
  3. 3.
    Liu, S., Gao, R.X., Freedson, P.: Design of a wearable multi-sensor system for physical activity assessment. In: IEEE/ASME Int. Conf. on Advanced Intelligent Mechatronics, pp. 254–259 (2010)Google Scholar
  4. 4.
    Mo, L., Liu, S., Gao, R.X., Freedson, P.: Energy-efficient and data synchronized body sensor network for physical activity measurement. In: Instrumentation and Measurement Technology Conference, pp. 1120–1124 (2013)Google Scholar
  5. 5.
    Gyllensten, I.C., Bonomi, A.G.: Identifying Types of Physical Activity With a Single Accelerometer: Evaluating Laboratory-trained Algorithms in Daily Life. IEEE Transactions on Biomedical Engineering 58(9) (2011)Google Scholar
  6. 6.
    Hekler, E.H., Buman, P.M., Grieco, L., Rosenberger, M., Winter, J.S., Haskell, W., King, C.A.: Validation of Physical Activity Tracking via Android Smartphones Compared to Actigraph Accelerometer: Laboratory-Based and Free-Living Validation Studies. JMIR mHealth uHealth 3(2), e36 (2015)CrossRefGoogle Scholar
  7. 7.
    http://www.actigraph.nl/downloads/getDownload/id/24, ActiLife 6 User’s Manual (accessed January 24, 2016)
  8. 8.
    https://help.theactigraph.com/entries/20723176-What-are-counts-, What are counts (accessed January 24, 2016)
  9. 9.
  10. 10.
    Peach, D., Van Hoomissen, J., Callender, H.L.: Exploring the ActiLife® filtration algorithm: converting raw acceleration data to counts. Physiol. Meas. 35, 2359–2367 (2014). IOP PublishingCrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Victor H. Rodriguez
    • 1
  • Carlos Medrano
    • 1
  • Inmaculada Plaza
    • 1
  • Cristina Corella
    • 2
  • Alberto Abarca
    • 2
  • Jose A. Julian
    • 2
  1. 1.EduQTech, E.U. PolitecnicaTeruelSpain
  2. 2.EFYPAF, Facultad de Ciencias Sociales y HumanasTeruelSpain

Personalised recommendations