Soft Computing Techniques for Evaluation and Control of Human Performance

  • Ron Jacobs
  • Carole A. Tucker
  • Rajko Tomovic
Chapter

Abstract

The mystical beauty of our nervous system’s ability to explore and learn new motor behavior is nicely demonstrated by how newborns and toddlers develop new motor skills. Through extensive periods of “oops” and “wow” learning, the nervous system has learned to control the sensitivities of how different muscles work together in affecting movement at various joints. This learning process starts before birth and continues throughout life. Unfortunately, impairment of the neuromuscular system, whether from injury or disease, may result in a disability of motor performance. Therefore, studying neuromuscular control is eminently important, not only from a scientific point of view to gain better insight into the mysteries of how the nervous system learns and controls movements, but also in studying restoration of movement after injury or disease.

Keywords

Neural Network Artificial Neural Network Fuzzy Logic Fuzzy Rule Soft Computing 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Altrock, von C. (1995). Fuzzy logic and neuro-fuzzy applications explained. Prentice Hall, Englewoods Cliffs, New Jersey.Google Scholar
  2. Barto, AG (1991). Connectionist learning for control. In Neural Networks for Control. Miller, W.T., Sutton, R.S., and Werbos, P.J. (eds.), pp. 5–58. The MIT Press, Cambridge, Massachusetts.Google Scholar
  3. Barto, A.G. (1994). Reinforcement learning control. Curr. Opin. Neurobiol., 4:888–893.PubMedCrossRefGoogle Scholar
  4. Barto, A.G., Bradtke, S.J., and Singh, S.P. (1995). Learning to act using real-time dynamic programming. Artif. Intell., 72:81–138.CrossRefGoogle Scholar
  5. Berenji, H.R. and Khedkar, P. (1992). Learning and tuning fuzzy logic controllers through reinforcements. IEEE Trans. Neural Networks.Google Scholar
  6. Bezdek, J.C. (1993). A review of probabilistic, fuzzy, and neural models for pattern recognition. J. Intell. Fuzzy Sys., 1:1–25.Google Scholar
  7. Bezdek, J.C. and Pal, S.K. (1992). Fuzzy models for pattern recognition. IEEE Press, New York, New York.Google Scholar
  8. Chen, J.J.J., Shiavi, R., and Zhang, L.Q. (1992). A quantitative and qualitative description of electromyographic linear envelopes for synergy analysis. IEEE Trans. Biomed. Eng., 39(19):1–18.Google Scholar
  9. Gioftsos, G. and Grieve, D.W. (1995). The use of neural networks to recognize patterns of human movement. Clin. Biomechan., 10(4):179–183.CrossRefGoogle Scholar
  10. Graupe, D. (1995). Artificial neural network control of FES in paraplegics for patient responsive ambulation. IEEE Trans. Biomed. Eng., 42(7):699–707.PubMedCrossRefGoogle Scholar
  11. Hecht-Nielsen, R. (1991). Neurocomputing. Addison-Wesley, Reading Massachusetts.Google Scholar
  12. Holzreiter, S.H. and Kohle, M.E. (1993). Assessment of gait patterns using neural networks. J. Biomech., 26(6):645–651.PubMedCrossRefGoogle Scholar
  13. Jacobs, R., Koopman, B., Veltink, P., Huijing, P.A., Nene, A., van der Kooij, H., and Grootenboer, H. (1996). A simplified control strategy for postural coordination in human stance. Engineering Foundation Biomechanics and Neural Control of Movement IX. Mt. Sterling, Ohio.Google Scholar
  14. Jang, J.S.R. (1992). Self-learning fuzzy controllers based on temporal back propagation. IEEE Trans. Neural Networks, 3:714–723.CrossRefGoogle Scholar
  15. Jang, J.S.R. and Sun, C.T. (1995). Neuro-fuzzy modeling and control. Proceedings of the IEEE, 83:378–406.CrossRefGoogle Scholar
  16. Kawato, M. (1990). Computational schemes and neural network models for formation and control of multijoint trajectory. In Neural Networks for Control, Miller, T., Sutten, R.S., and Werbos, P.J. (eds.), pp. 197–228. The MIT Press, Cambridge, Massachusetts.Google Scholar
  17. Kawato, M., Furukawa, K., and Suzuki, R. (1987). A hierarchical neural-network model for control and learning of voluntary movement. Biol Cybern., 57:169–185.PubMedCrossRefGoogle Scholar
  18. Kawato, M., Maeda, Y., Uno, Y., and Suzuki, R. (1990). Trajectory formation of arm movement by cascade neural network model based on minimum torquechange criterion. Biol. Cybern., 62:275–288.PubMedCrossRefGoogle Scholar
  19. Kelly, N.E., Parker, P.A., and Scott, R.N. (1990). Myoelectric signal analysis using neural networks. IEEE Trans. Med. Biol., 61–64.Google Scholar
  20. Kosko, B. (1992). Neural networks and fuzzy systems. A dynamical systems approach to machnie intelligence. Prentice Hall, Englewoods Cliffs, New Jersey.Google Scholar
  21. Kosko, B. (1993). Fuzzy thinking. Hyperion, New York.Google Scholar
  22. Kubica, E.G., Wang, D., and Winter, D.A. (1995). Modelling balance and posture control mechanisms of the upper body using conventional and fuzzy techniques. Gait and Posture, 3(2):111.CrossRefGoogle Scholar
  23. Meier, W., Weber, R., and Zimmerman, H.J. (1994). Fuzzy data analysis—Methods and industrial applications In Fuzzy Sets and Systems 61. Negoita, C.V., Zadeh, L.A., and Zimmerman, H.J. (eds.), pp. 19–28. Elsevier, North Holland.Google Scholar
  24. O’Malley, M.J., Abel, M., and Damiano, D. (1995). Fuzzy clustering of temporal-distance and kinematic parameters for cerebral palsy children. Gait and Posture, 3(2):92.CrossRefGoogle Scholar
  25. Schalkoff, R. (1992). Pattern recognition: syntactical, structural, and neural approaches. John Wiley & Sons, New York, New York.Google Scholar
  26. Sepulveda, F., Wells, D.M., and Vaughan, C.L. (1993). A neural network representation of electromyography and joint dynamics in human gait. J. Biomech., 26(2):101–109.PubMedCrossRefGoogle Scholar
  27. Tucker, C.A. (1996). Artificial neural network approaches to synergy analysis of electromyographic data. In Engineering Foundation Conference: Biomechanics and Neural Control of Movement IX. Winters, J. and Crago, P. (eds.), Mt. Sterling, Ohio.Google Scholar
  28. Tucker, C.A., Yack, H.J., and White, S.C. (1994). A neural network approach to synergy analysis of electromyographic data. In Proceedings of the Tenth Congress of the International Society of Electrophysiology and Kinesiology. Charleston, South Carolina.Google Scholar
  29. Wada, Y. and Kawato, M. (1993). A neural network model for arm trajectory formation using forward and inverse dynamics models. Neural Networks, 6:919–932.CrossRefGoogle Scholar
  30. Werbos, P.J. (1991). A menu of designs for reinforcement learning over time. In Neural Networks for Control. Miller, W.T., Sutton, R.S., and Werbos, P.J. (eds.), pp. 67–95. MIT Press, Cambridge, MA.Google Scholar
  31. Zadeh, L. (1965). Fuzzy sets. Infor. Control, 8:338–353.CrossRefGoogle Scholar
  32. Zadeh, L. (1994). Fuzzy logic, neural networks and soft computing. Comm. Assoc. Computing Machinery, 3:77–84.Google Scholar
  33. Zadeh, L. (1996). Fuzzy logic—computing with words. IEEE Trans. Fuzzy Sys., 4:103–111.CrossRefGoogle Scholar
  34. Zhang, L.Q. and Shiavi, R. (1991). Clustering analysis and pattern discrimination of EMG linear envelopes. IEEE-BME, 38(8):777–784.CrossRefGoogle Scholar
  35. Zurada, J.M. (1992). An introduction to artificial neural systems. West Publishing Co., St. Paul, Minnesota.Google Scholar

References

  1. Smith, C.U.M. (1989). Elements of molecular neurobiology. John Wiley and Sons, New York.Google Scholar
  2. Tomovic, R., Popovic, D., and Stein, R.B. (1995). Non-analytical methods for motor control. World Scientific, Singapore.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag New York, Inc. 2000

Authors and Affiliations

  • Ron Jacobs
  • Carole A. Tucker
  • Rajko Tomovic

There are no affiliations available

Personalised recommendations