Advertisement

Statistical Machine Learning for Automatic Assessment of Physical Activity Intensity Using Multi-axial Accelerometry and Heart Rate

  • Fernando García-García
  • Gema García-Sáez
  • Paloma Chausa
  • Iñaki Martínez-Sarriegui
  • Pedro José Benito
  • Enrique J. Gómez
  • M. Elena Hernando
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6747)

Abstract

This work explores the automatic recognition of physical activity intensity patterns from multi-axial accelerometry and heart rate signals. Data collection was carried out in free-living conditions and in three controlled gymnasium circuits, for a total amount of 179.80 h of data divided into: sedentary situations (65.5%), light-to-moderate activity (17.6%) and vigorous exercise (16.9%). The proposed machine learning algorithms comprise the following steps: time-domain feature definition, standardization and PCA projection, unsupervised clustering (by k-means and GMM) and a HMM to account for long-term temporal trends. Performance was evaluated by 30 runs of a 10-fold cross-validation. Both k-means and GMM-based approaches yielded high overall accuracy (86.97% and 85.03%, respectively) and, given the imbalance of the dataset, meritorious F-measures (up to 77.88%) for non-sedentary cases. Classification errors tended to be concentrated around transients, what constrains their practical impact. Hence, we consider our proposal to be suitable for 24 h-based monitoring of physical activity in ambulatory scenarios and a first step towards intensity-specific energy expenditure estimators.

Keywords

physical activity intensity accelerometry heart rate k-means Gaussian Mixture Models Hidden Markov Models F-measure 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Crouter, S.E., Churilla, J.R., Bassett, D.R.: Estimating energy expenditure using accelerometers. Eur. J. Appl. Physiol. 98(6), 601–612 (2006)CrossRefGoogle Scholar
  2. 2.
    Freedson, P.S., Miller, K.: Objective monitoring of physical activity using motion sensors and heart rate. Res. Q Exercise Sport 71(2 Suppl), S21 (2000)CrossRefGoogle Scholar
  3. 3.
    Gotshalk, L.A., Berger, R.A., Kraemer, W.J.: Cardiovascular responses to a high-volume continuous circuit resistance training protocol. J. Strength Cond. Res. 18(4), 760 (2004)Google Scholar
  4. 4.
    Strath, S.J., Brage, S., Ekelund, U.: Integration of physiological and accelerometer data to improve physical activity assessment. Med. Sci. Sport Exer. 37(11), S563 (2005)CrossRefGoogle Scholar
  5. 5.
    Plasqui, G., Westerterp, K.R.: Accelerometry and heart rate as a measure of physical fitness: Cross-validation. Med. Sci. Sport Exer. 38(8), 1510 (2006)CrossRefGoogle Scholar
  6. 6.
    Bonomi, A.G., Plasqui, G., Goris, A.H.C., Westerterp, K.R.: Improving assessment of daily energy expenditure by identifying types of physical activity with a single accelerometer. J. Appl. Physiol. 107(3), 655 (2009)CrossRefGoogle Scholar
  7. 7.
    Munguia Tapia, E., Intille, S.S., Haskell, W., Larson, K., Wright, J., King, A., Friedman, R.: Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart rate monitor. In: 2007 11th IEEE International Symposium on Wearable Computers, pp. 37–40. IEEE, Los Alamitos (2007)Google Scholar
  8. 8.
    Albinali, F., Intille, S.S., Haskell, W., Rosenberger, M.: Using wearable activity type detection to improve physical activity energy expenditure estimation. In: Proceedings of the 12th ACM International Conference on Ubiquitous Computing, pp. 311–320. ACM, New York (2010)CrossRefGoogle Scholar
  9. 9.
    Bao, L., Intille, S.S.: Activity recognition from user-annotated acceleration data. In: Ferscha, A., Mattern, F. (eds.) PERVASIVE 2004. LNCS, vol. 3001, pp. 1–17. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  10. 10.
    Allen, F.R., Ambikairajah, E., Lovell, N.H., Celler, B.G.: An adapted Gaussian Mixture Model approach to accelerometry-based movement classification using time-domain features. In: 28th Annual International Conference Engineering in Medicine and Biology Society, EMBS 2006, pp. 3600–3603. IEEE, Los Alamitos (2008)Google Scholar
  11. 11.
    Ermes, M., Parkka, J., Mantyjarvi, J., Korhonen, I.: Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. IEEE T. Inf. Technol. B 12(1), 20–26 (2008)CrossRefGoogle Scholar
  12. 12.
    Krause, A., Siewiorek, D.P., Smailagic, A., Farringdon, J.: Unsupervised, dynamic identification of physiological and activity context in wearable computing. In: Proceedings of the 7th IEEE International Symposium on Wearable Computers (ISWC 2003). IEEE Computer Society, Los Alamitos (2003)Google Scholar
  13. 13.
    Lester, J., Choudhury, T., Borriello, G.: A practical approach to recognizing physical activities. In: Fishkin, K.P., Schiele, B., Nixon, P., Quigley, A. (eds.) PERVASIVE 2006. LNCS, vol. 3968, pp. 1–16. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    Duchêne, F., Garbay, C., Rialle, V.: Learning recurrent behaviors from heterogeneous multivariate time-series. Artif. Intell. Med. 39(1), 25–47 (2007)CrossRefGoogle Scholar
  15. 15.
    Freedson, P.S., Melanson, E., Sirard, J.: Calibration of the Computer Science and Applications, Inc. accelerometer. Med. Sci. Sport Exer. 30(5), 777 (1998)CrossRefGoogle Scholar
  16. 16.
    Brage, S., Brage, N., Franks, P.W., Ekelund, U., Wong, M.Y., Andersen, L.B., Froberg, K., Wareham, N.J.: Branched equation modeling of simultaneous accelerometry and heart rate monitoring improves estimate of directly measured physical activity energy expenditure. J. Appl. Physiol. 96(1), 343 (2004)CrossRefGoogle Scholar
  17. 17.
    Ainsworth, B.E., Haskell, W.L., Whitt, M.C., Irwin, M., Swartz, A.M., Strath, S.J., O’Brien, W.L., Bassett Jr., D.R., Schmitz, K.H., Emplaincourt, P.O., et al.: Compendium of physical activities: An update of activity codes and MET intensities. Med. Sci. Sport Exer. 32(9 Suppl), S498 (2000)CrossRefGoogle Scholar
  18. 18.
    Benito Peinado, P.J., Álvarez Sánchez, M., Díaz Molina, V., Peinado Lozano, A.B., Calderón Montero, F.J.: Aerobic Energy Expenditure and Intensity Prediction during a Specific Circuit Weight Training: A Pilot Study. J. Hum. Sport Exerc. 5(2), 134–145 (2010)CrossRefGoogle Scholar
  19. 19.
    Lester, J., Choudhury, T., Kern, N., Borriello, G., Hannaford, B.: A hybrid discriminative/generative approach for modeling human activities. In: Proc. of the International Joint Conference on Artificial Intelligence (IJCAI), Citeseer (2005)Google Scholar
  20. 20.
    He, J., Li, H., Tan, J.: Real-time daily activity classification with wireless sensor networks using Hidden Markov Model. In: 29th Annual International Conference Engineering in Medicine and Biology Society, EMBS 2007, pp. 3192–3195. IEEE, Los Alamitos (2007)CrossRefGoogle Scholar
  21. 21.
    García-García, F., Martínez-Sarriegui, I., Gómez, E.J., Rigla, M., Hernando, M.E.: Automatic assessment of physical activity using multi-axial accelerometry and heart rate. J. Diab. Tech. Therap. 13(2), 182 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Fernando García-García
    • 1
    • 2
  • Gema García-Sáez
    • 1
    • 2
  • Paloma Chausa
    • 1
    • 2
  • Iñaki Martínez-Sarriegui
    • 1
    • 2
  • Pedro José Benito
    • 3
  • Enrique J. Gómez
    • 1
    • 2
  • M. Elena Hernando
    • 1
    • 2
  1. 1.Grupo de Bioingeniería y TelemedicinaUniversidad Politécnica de MadridSpain
  2. 2.Networking Research Center on BioengineeringBiomaterials and Nanomedicine (CIBER-BBN)MadridSpain
  3. 3.Laboratory of Exercise Physiology, Facultad de Ciencias de la Actividad Física y del Deporte (INEF)Universidad Politécnica de MadridSpain

Personalised recommendations