Skip to main content
SpringerLink
Log in

Oxygen Uptake Estimation in Humans During Exercise Using a Hammerstein Model

  • Published:
Annals of Biomedical Engineering Aims and scope Submit manuscript

Abstract

This paper aims to establish a block-structured model to predict oxygen uptake in humans during moderate treadmill exercises. To model the steady state relationship between oxygen uptake (oxygen consumption) and walking speed, six healthy male subjects walked on a motor driven treadmill with constant speed from 2 to 7 km/h. The averaged oxygen uptake at steady state (VO 2) was measured by a mixing chamber based gas analysis and ventilation measurement system (AEI Moxus Metabolic Cart). Based on these reliable date, a nonlinear steady state relationship was successfully established using Support Vector Regression methods. In order to capture the dynamics of oxygen uptake, the treadmill velocity was modulated using a Pseudo Random Binary Signal (PRBS) input. Breath by breath analysis of all subjects was performed. An ARX model was developed to accurately reproduce the measured oxygen uptake dynamics within the aerobic range. Finally, a Hammerstein model was developed, which may be useful for implementing a control system for the regulation of oxygen uptake during treadmill exercises.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8

Similar content being viewed by others

References

  1. Allin J., Inbar G. (1986) FNS parameter selection and upper limb characterization. IEEE Trans. Biomed. Eng. 33:809–817

    Article  PubMed  CAS  Google Scholar 

  2. Bai E. W. (1998) An optimal two-stage identification algorithm for Hammerstein–Wiener nonlinear systems. Automatica 34(3):333–338

    Article  Google Scholar 

  3. Bai E. W. (2002) A blind approach to the Hammerstein model identification. IEEE Trans. Signal Proce. 50(7):1610–1619

    Article  Google Scholar 

  4. Bai E. W. (2002) Identification of linear systems with hard input nonlinearities of known structure. Automatica 38:853–860

    Article  Google Scholar 

  5. Bai E. W. (2004) Decoupling the linear and nonlinear parts in Hammerstein model identification. Automatica 40:671–676

    Article  Google Scholar 

  6. Bernotas L., Crago P., Chizeck H. (1986) A discrete-time model of electrically stimulated muscle. IEEE Trans. Biomed. Eng. 33:829–838

    Article  PubMed  CAS  Google Scholar 

  7. Bilings S. A., Fakhouri S. Y. (1978) Identification of a class of nonlinear systems using correlation analysis. Proc. Inst. Elect. Eng. 125(7):691–697

    Google Scholar 

  8. Bussgang, J. J. Crosscorrelation functions of amplitude distorted Gaussian signals. Tech. Rept. 216, MIT Res. Lab. of Electronics, 1952.

  9. Chang F., Luus R. (1971) A noniterative method for identification using Hammerstein model. IEEE Trans. Automat. Contr. 16:464–468

    Article  Google Scholar 

  10. Cristianini N., Shawe-Taylor J. (2000) An Introduction to Support Vector Machines and other Kernel-based Learning Methods. Cambridge University Press, UK

    Google Scholar 

  11. Dempsey E. J., Westwick D. T. (2004) Identification of Hammerstein models with cubic spline nonlinearities. IEEE Trans. Biomed. Eng. 51:237–245

    Article  PubMed  Google Scholar 

  12. Dill D. B. (1965) Oxygen used in horizontal and grade walking and running on the treadmill. J. Appl. Physiol. 20:19–22

    PubMed  CAS  Google Scholar 

  13. Drucker, H., C. Burges, L. Kaufman, A. Smola, and V. Vapnik. Support vector regression machines. In: Advances in Neural Information Procession Systems, edited by M. Mozer, M. Jordan, and T. Petsche. Cambridge MA, 1997, pp. 155–161.

  14. Efeld D., Hoffmann U., Stegemann J. (1987) VO 2 kinetics in subjects differing in aerobic capacity: investigation by spectral analysis. Eur. J. Appl. Physiol. 56(5):508–515

    Article  Google Scholar 

  15. Eskinat E., Johnson S. H., Luyben W. L. (1991) Use of Hammerstein models in identification of nonlinear systems. AIChE J. 37:255–268

    Article  CAS  Google Scholar 

  16. Espinoza, M., K. Pelckmans, L. Hoegaerts, J. Suykens, J. De Brabanter, B. De Moor. A comparative study of LS-SVMs applied to the silver box identification problem. Symposium on nonlinear control systems NOLCOS, 2004, pp. 513–518.

  17. Falugi P., Giarre L., Zappa G. (2005) Approximation of the feasible parameter set in worst-case identification of Hammerstein models. Automatica 41:1017–1024

    Article  Google Scholar 

  18. Franklin B. A. (2000) ACSM’s Guidelines for Exercise Testing and Prescription. Lippincott Williams & Wilkins, New York

    Google Scholar 

  19. Goethals I., Pelckmans K., Suykens J. A. K., De Moor B. (2005) Identification of MIMO Hammerstein models using least squares support vector machines. Automatica 41:1263–1272

    Article  Google Scholar 

  20. Guo Y., Bartlett P. L., Shawe-Taylor J., Williamson R. C. (2002) Covering numbers for support vector machines. IEEE Trans. Inform. Theory 48(1):239–250

    Article  Google Scholar 

  21. Hagberg J. M., Hickson R. C., Ehsani A. A., Holloszy J. O. (1980) Faster adjustment to and recovery from submaximal exercise in the trained state. J. Appl. Physiol. 48:218–224

    PubMed  CAS  Google Scholar 

  22. Hill A. V., Lupton H. (1923) Muscular exercise, lactic acid and the supply and utilization of oxygen. Q. J. Med. 16:l35–171

    Google Scholar 

  23. Hoffmann U., Efeld D., Wunderlich H.-G., Stegemann J. (1992) Dynamic linearity of VO 2 responses during aerobic exercise. Eur. J. Appl. Physiol. 64(2):l39–144

    Article  Google Scholar 

  24. Hunt K. J., Munih M., Donaldson N. de. N., Barr F. M. D. (1998) Investigation of the Hammerstein hypothesis in the modeling of electrically stimulated muscle. IEEE Trans. Biomed. Eng. 45(8):998–1009

    Article  PubMed  CAS  Google Scholar 

  25. Hunter I. W., Korenberg M. J. (1986) The identification of nonlinear biological systems: Wiener and Hammerstein cascade models. Biol. Cybern. 55:135–144

    PubMed  CAS  Google Scholar 

  26. Korenberg M. J. (1973) Identification of biological cascades of linear and nonlinear systems. Proc. Midwest Symp. Circuit Theory 18(2):1–9

    Google Scholar 

  27. Korenberg M. J. (1991) Recent advances in the identification of nonlinear systems: minimumvariance approximation by Hammerstein models. Proc. IEEE EMBS 13:2258–2259

    Google Scholar 

  28. Maksym G. N., Kearney R. E., Bates J. H. (1998) Nonparametric block-structured modeling of lung tissue strip mechanics. Ann. Biomed. Eng. 26(2):242–252

    Article  PubMed  CAS  Google Scholar 

  29. Narendra K. S., Gallman P. G. (1966) An iterative method for the identification of nonlinear systems using Hammerstein model. IEEE Trans. Automat. Contr. 11:546–550

    Article  Google Scholar 

  30. Ninness B., Gibson S. (2002) Quantifying the accuracy of Hammerstein model estimation. Automatica 38:2037–2051

    Article  Google Scholar 

  31. Pawlak M. (1991) On the series expansion approach to the identification of Hammerstein systems. IEEE Trans. Automat. Contr. 36:763–767

    Article  Google Scholar 

  32. Pearce D. H., Milhorn H. T. Jr (1977) Dynamic and steady-state respiratory responses to bicycle exercise. J. Appl. Physiol. 42(6):959–967

    PubMed  CAS  Google Scholar 

  33. Prampero D. I., Davies P., Cerretelli P., Margria R. (1970) An analysis of O 2 debt contracted in submaximal exercise. J. Appl. Physiol. 29:547–551

    PubMed  Google Scholar 

  34. Schlkopf B., Smola A. (2002) Learning with Kernels. MIT Press, Cambridge, MA

    Google Scholar 

  35. Smola A., Schlkopf B. (2004) A tutorial on support vector regression. Stat. Comput. 14:199–222

    Article  Google Scholar 

  36. Su S. W., Bao J., Lee P. L. (2005) Control of multivariable Hammerstein systems by using feedforward passivation. Ind. Eng. Chem. Res. 44(4):891–899

    Article  CAS  Google Scholar 

  37. Su, S. W., L. Wang, B. Celler, A. Savkin, and Y. Guo. Identification and control for heart rate regulation during treadmill exercise. IEEE Trans. Biomed. Eng. 54(7):1238–1246, 2007.

    Article  PubMed  Google Scholar 

  38. Suykens J. A. K., Van Gestel T., de Brabanter J., de Moor B., Vandewalle J. (2002) Least Squares Support Vector Machines. WorldScientific, Singapore

    Google Scholar 

  39. Suykens J. A. K., Van Gestel, de Brabanter J., de Moor B., Vandewalle J. (2002) Least Squares Support Vector Machines. Neurocomputing 48:85–105

    Article  Google Scholar 

  40. Vapnik V. (1995) The Nature of Statistical Learning Theory. Springer, New York

    Google Scholar 

  41. Vapnik V. (1998) Statistical Learning Theory. John Wiley, New York

    Google Scholar 

  42. Vapnik, V., and A. Lerner. Pattern recognition using generalized portrait method. Automat. Rem. Contr. 14:774–780, 1963.

    Google Scholar 

  43. Voros J. (1999) Iterative algorithm for parameter identification of Hammerstein systems with two-segment nonlinearities. IEEE Trans. Automat. Contr. 44:2145–2149

    Article  Google Scholar 

  44. van der Walt W. H., Wyndham C. H. (1973) An equation for prediction of energy expenditure of walking and running. J. Appl. Physiol. 34:559–563

    PubMed  Google Scholar 

  45. Wang, L., S. W. Su, B. Celler, and A. Savkin. Modeling of a gas concentration measurement system. Proc. IEEE EMBS. Shanghai, China, September, 2005, pp. 6695–6698.

  46. Whipp B. J., Ward S. A., Lamarra N., Davis J. A., Wasserman K. (1982) Parameters of ventilatory and gas exchange dynamics during exercise. J. Appl. Physiol. 52(6):1506–1513

    PubMed  CAS  Google Scholar 

  47. Yanagawa K., Abe D., Niihata S. (2004) Effects of load carriage, load position, and walking speed on energy cost of walking. Appl. Ergon. 35:329–335

    Article  PubMed  Google Scholar 

Download references

Acknowledgment

The authors gratefully acknowledge the financial support of the Australian Research Council (Grant DP0452186).

Author information

Authors and Affiliations

  1. Human Performance Group, Biomedical Systems Lab, School of Electrical Engineering & Telecommunications, University of New South Wales, Sydney, NSW, 2052, Australia

    Steven W. Su, Lu Wang, Branko G. Celler & Andrey V. Savkin

  2. Faculty of Engineering, University of Technology, Sydney, Australia

    Steven W. Su

Authors
  1. Steven W. Su
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lu Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Branko G. Celler
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Andrey V. Savkin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Steven W. Su.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Su, S.W., Wang, L., Celler, B.G. et al. Oxygen Uptake Estimation in Humans During Exercise Using a Hammerstein Model. Ann Biomed Eng 35, 1898–1906 (2007). https://doi.org/10.1007/s10439-007-9362-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10439-007-9362-2

Keywords

Search

Navigation