A Dynamic Programming Approach for Ambient Intelligence Platforms in Running Sports Based on Markov Decision Processes

  • J. Vales-Alonso
  • P. López-Matencio
  • J. J. Alcaraz
  • J. L. Sieiro-Lomba
  • E. Costa-Montenegro
  • F. J. González-Castaño
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 98)

Abstract

Outdoor sport practitioners can improve greatly their performance if they train at the right intensity. Nevertheless, in common training systems, performance is only evaluated at the end of the training session, and sensed data are incomplete because only human biometrics are analyzed. These systems do not consider environmental conditions, which may influence athletes’ performance directly during instruction. In this paper, we introduce a decision making method for a multi-step training scenario based on dynamic program optimization and formulated as a Markov Decision Process, which allow athletes to complete heterogeneous training programs with several levels of exercise intensity. This methodology is applied in a pilot experiment of cross-country running. Environment and athletes are monitored by means of a wireless sensor network deployed over the running circuit, and by mobile elements carried by the users themselves, which monitor their heart rate (HR). The goal is to select, for a given user, a running track that optimizes heart rate according to a predefined training program. Results show that the proposal is of practical interest. It achieves a notable success in heart rate control over non-optimal track selection policies. The importance of environmental data is shown as well, since heart rate control improves when those data are taken into account.

Keywords

Wireless Sensor Network Optimal Policy User Equipment Markov Decision Process Dynamic Program Approach 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Almgren and Tourin 2004]
    Almgren, R., Tourin, A.: Optimal Soaring with Hamilton-Jacobi-Bellman Equations (2004), http://www.cims.nyu.edu/~almgren/optsoar/optsoar.pdf (accessed October 25, 2010)
  2. [Backx et al. 2003]
    Backx, K., Someren, K.V., Nevill, A., et al.: Mathematical prediction of one hour cycle time trial performance under different ambient temperatures. Medicine & Science in Sports & Exercise 35(5), S30 (2003)CrossRefGoogle Scholar
  3. [Bellman 2003]
    Bellman, R.E.: Dynamic programming. Princeton University Press, Princeton (2003) (republished) MATHGoogle Scholar
  4. [Clarke 1988]
    Clarke, S.R.: Dynamic programming in one-day cricket-optimal scoring rates. J. of the Operational Research Society 39(4), 331–337 (1988)Google Scholar
  5. [Ghasemzadeh and Jafari 2009]
    Ghasemzadeh, H., Jafari, R.: Sport training using body sensor networks: A statistical approach to measure wrist rotation for golf swing. In: The 4th Int. Conf. on Body Area Networks, Los Angeles, CA (2009)Google Scholar
  6. [Haskell et al. 2007]
    Haskell, W., Lee, I., et al.: Physical activity and public health: updated recommendation for adults from the American College of Sports Medicine and the American Heart Association. Circulation 116(9), 1081 (2007)CrossRefGoogle Scholar
  7. [López-Matencio et al. 2010]
    López-Matencio, P., Vales-Alonso, J., González-Castaño, F.J., et al.: Ambient intelligence assistant forn running sports based on k-NN classifiers. In: Proc. of 3rd Int. Conf. on Human System Interactions, Rzeszow, Poland, pp. 605–611 (2010)Google Scholar
  8. [Pfisterer et al. 2006]
    Pfisterer, D., Lipphardt, M., Buschmann, C., et al.: Marathonnet: adding value to large scale sport events-a connectivity analysis. In: Proc. of the First Int. Conf. on Integrated Internet Ad Hoc and Sensor Networks, p. 12. ACM, New York (2006)CrossRefGoogle Scholar
  9. [Saponas et al. 2008]
    Saponas, T., Lester, J., Froehlich, J., et al.: Ilearn on the iphone: Real-time human activity classification on commodity mobile phones. University of Washington CSE Tech. Report UW-CSE-08-04-02 (2008)Google Scholar
  10. [Spelmezan and Borchers 2008]
    Spelmezan, D., Borchers, J.: Real-time snowboard training system. In: CHI 2008 Extended Abstracts on Human Factors in Computing Systems. ACM, New York (2008)Google Scholar
  11. [Tanaka et al. 2001]
    Tanaka, H., Monahan, K., Seals, D.: Age-predicted maximal heart rate revisited. J. of the American College of Cardiology 37(1), 153 (2001)CrossRefGoogle Scholar
  12. [Vales-Alonso et al. 2010]
    Vales-Alonso, J., López-Matencio, P., González-Castaño, F.J., et al.: Ambient intelligence systems for personalized sport training. Sensors 10(3), 2359–2385 (2010)CrossRefGoogle Scholar
  13. [Vihma 2009]
    Vihma, T.: Effects of weather on the performance of marathon runners. Int. J. of Biometeorology, 1–10 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • J. Vales-Alonso
    • 1
  • P. López-Matencio
    • 1
  • J. J. Alcaraz
    • 1
  • J. L. Sieiro-Lomba
    • 1
  • E. Costa-Montenegro
    • 2
  • F. J. González-Castaño
    • 2
  1. 1.Department of Information Technology and CommunicationsPolytechnic University of CartagenaSpain
  2. 2.Departament of Telematic EngineeringUniversity of VigoSpain

Personalised recommendations