Advertisement

Neural Networks Based System for the Supervision of Therapeutic Exercises

  • Sven Nõmm
  • Alar Kuusik
  • Sergei Ovsjanski
  • Ines Malmberg
  • Marko Parve
  • L. Orunurm
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7666)

Abstract

Present contribution describes application of the neural networks based models to detect incorrectly performed therapeutic exercises within the frameworks of wearable supervision system. Electronic accelerometers and gyroscopes attached to the human upper and lower limbs gather information about performed exercise in real time. Trained, on the data describing correctly done exercises, neural network based dynamic model of the limb is used to find the difference between the actual and ”ideal” performances and judge if exercises are performed in a correct way or not.

Keywords

Neural networks dynamic model NN-ANARX model medical system rehabilitation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Friedrich, M., Cermak, T., Maderbacher, P.: The effect of brochure use versus therapist teaching on patients performing therapeutic exercise and on changes in impairment status. Physical Therapy (Journal of the American Physical Therapy Association) 76, 1082–1088 (1996)Google Scholar
  2. 2.
    Kotta, Ü., Chowdhury, F., Nõmm, S.: On realizability of neural networks-based input-output models in the classical state space form. Automatica 42(6), 1211–1216 (2006)zbMATHCrossRefGoogle Scholar
  3. 3.
    Nõmm, S., Petlenkov, E., Vain, J., Yoshimitsu, K., Ohnuma, K., Sadahiro, T., Miyawaki, F.: Nn-based anarx model of the surgeon’s hand for the motion recognition. In: Proceedings of the 4th COE Workshop on Human Adaptive Mechatronics (HAM), pp. 19–24. Tokyo Denki University, Tokyo (2007)Google Scholar
  4. 4.
    Zhou, H., Hu, H.: A Survey - Human Movement Tracking and Stroke Rehabilitation. Technical report, CSM-420, University of Essex (2004) ISSN 1744 - 8050Google Scholar
  5. 5.
    Lorincz, K., Chen, B., Welsh, M.: Mercury: a wearable sensor network platform for high-fidelity motion analysis. In: Proc of the 7th ACM Conference on Embedded Networked Sensor Systems, SenSys 2009, Bercley, pp. 183–196 (2009)Google Scholar
  6. 6.
    Kisner, C., Colby, L.: Therapeutic Exercise, Foundations and Techniques, 5th edn. F.A.Davis Company, Philadelfia (2007)Google Scholar
  7. 7.
    Nomm, S., Belikov, J.: Online identification of unknown plant by nn-based anarx model. In: 2011 International Conference on Adaptive and Intelligent Systems, Klagenfurt, Austria, pp. 5–15 (2011)Google Scholar
  8. 8.
    Nomm, S., Vassilejva, K., Beliokv, J., Petlenkov, E.: Structure identification of nn-anarx model by genetic algorithm with combined cross-correlation-test based evaluation function. In: 2011 9th IEEE International Conference on Control and Automation (ICCA), Santiago,Chile, pp. 65–70 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Sven Nõmm
    • 1
  • Alar Kuusik
    • 3
  • Sergei Ovsjanski
    • 2
  • Ines Malmberg
    • 4
  • Marko Parve
    • 4
  • L. Orunurm
    • 4
  1. 1.Institute of Cybernetics at Tallinn University of TechnologyTallinnEstonia
  2. 2.T.J. Seebeck Institute of ElectronicsTallinn University of TechnologyTallinnEstonia
  3. 3.Competence Center ELIKOTallinnEstonia
  4. 4.East-Tallinn Central HospitalTallinnEstonia

Personalised recommendations