DOI QR코드

DOI QR Code

A Study on Feature Projection Methods for a Real-Time EMG Pattern Recognition

실시간 근전도 패턴인식을 위한 특징투영 기법에 관한 연구

  • Published : 2006.08.01

Abstract

EMG pattern recognition is essential for the control of a multifunction myoelectric hand. The main goal of this study is to develop an efficient feature projection method for EMC pattern recognition. To this end, we propose a linear supervised feature projection that utilizes linear discriminant analysis (LDA). We first perform wavelet packet transform (WPT) to extract the feature vector from four channel EMC signals. For dimensionality reduction and clustering of the WPT features, the LDA incorporates class information into the learning procedure, and finds a linear matrix to maximize the class separability for the projected features. Finally, the multilayer perceptron classifies the LDA-reduced features into nine hand motions. To evaluate the performance of LDA for the WPT features, we compare LDA with three other feature projection methods. From a visualization and quantitative comparison, we show that LDA has better performance for the class separability, and the LDA-projected features improve the classification accuracy with a short processing time. We implemented a real-time pattern recognition system for a multifunction myoelectric hand. In experiment, we show that the proposed method achieves 97.2% recognition accuracy, and that all processes, including the generation of control commands for myoelectric hand, are completed within 97 msec. These results confirm that our method is applicable to real-time EMG pattern recognition far myoelectric hand control.

References

  1. OttoBock, MYOBOCK Arm Components 2005, 2005
  2. S. C. Jacobson, D. F. Knutti, R. T. Johnson, and H. H. Shears, 'Development of the Utah artificial ann,' IEEE Trans. Biomed. Eng, vol. 29, pp. 249-269, Apr. 1982 https://doi.org/10.1109/TBME.1982.325033
  3. P. J. Kyberd, O. E. Holland, P. H. Chappel, S. Smith, R. Tregidgoi, P. J. Bagwell, and M. Snaith, 'MARCUS: A two degree of freedim hand prosthesis with hierarchical grip control,' IEEE Trans. Rehab. Eng, vol. 3, no. 1, pp. 70-76, 1995 https://doi.org/10.1109/86.372895
  4. C. M. Light and P. H. Chappell, 'Development of a lightweight and adaptable multiple-axis hand prosthesis,' Medical Engineering and Physics, vol. 22, pp. 679-684, 2000 https://doi.org/10.1016/S1350-4533(01)00017-0
  5. J. Butterfab, M. Grebenstein, H. Uu, and G Hirzinger, 'DLR-hand II: Next generation of a dexterous robot hand,' Proc. of IEEE Int'I. Conf. Robotics and Automation, pp. 109-114, 2001 https://doi.org/10.1109/ROBOT.2001.932538
  6. B. Hudgins, P. A. Parker, and R. N. Scott, 'A new strategy for multifunction myoelectric control,' IEEE Trans. Biomed. Eng, vol. 40, no. 1, pp. 82-94, Jan. 1993 https://doi.org/10.1109/10.204774
  7. F. H. Y. Chan, Y. S. Yang, F. K. Lam, Y. T. Zhang, and P. A. Parker, 'Fuzzy EMG classification for prosthesis control,' IEEE Trans. Rehab. Eng, vol. 8, no. 3, pp. 305-311, Sept. 2000 https://doi.org/10.1109/86.867872
  8. H. P. Huang, Y. H. Liu, L. W. Liu, and C. S. Wong, 'EMG classification for prehensile posture using cascaded architecture of neural networks with self-organizing maps,' Proc. IEEE Int'l. Conf. Robotics and Automation, pp. 1497-1502, Sept. 2003 https://doi.org/10.1109/ROBOT.2003.1241803
  9. K. Englehart and B. Hudgins, 'A robust, real-time control scheme for multifunction myoelectric control,' IEEE Trans. Biomed. Eng, vol. 50, no. 7, pp. 848-854, July 2003 https://doi.org/10.1109/TBME.2003.813539
  10. Y. Huang, K. B. Englehart, B. Hudgins, and A. D. C. Chan, 'Optimized Gaussian mixture models for upper limb motion classification,' Proc. IEEE Int'l. Conf. EMBS, pp. 72-75, Sept. 2004 https://doi.org/10.1109/IEMBS.2004.1403093
  11. A. D. C. Chan and K. B. Engelehart, 'Continuous myoelectric control for powered prostheses using hidden Markov models,' IEEE Trans. Biomed. Eng, vol. 52, no. 1, pp. 121-124, Jan https://doi.org/10.1109/TBME.2004.836492
  12. B. Karlik, M. O. Tokhi, and M. Alci, 'A fuzzy clustering neural network architecture for multifimction upper-limb prosthesis,' IEEE Trans. Biomed. Eng, vol. 50, no. 11, pp. 1255-1261, Nov. 2003 https://doi.org/10.1109/TBME.2003.818469
  13. A. Hiraiwa, N. Uchida, N. Sonehara, and K. Shimohara, 'EMG pattern recognition by neural networks for prosthetic fingers control - Cyber finger,' Proc. Int'l. Symp. Measurement and control in Robotics, pp. 535-542, Nov. 1992
  14. S. H. Park and S. P. Lee, 'EMG pattem recognition based on artificial intelligence techniques,' IEEE Trans. Rehab. Eng., vol. 6, no. 4, pp. 400-405, Dec. 1998 https://doi.org/10.1109/86.736154
  15. K. Englehart, B. Hudgins, P. A. Parker, and M. Stevenson, 'Classification of the myoelectric signal using time-frequency based representations,' Medical Engineering and Physics, vol. 21, pp. 431-438, 1999 https://doi.org/10.1016/S1350-4533(99)00066-1
  16. K. Englehart, B. Hudgins, and P. A. Parker, 'A wavelet-based continuous classification scheme for multifunction myoelectric control,' IEEE Trans. Biomed Eng., vol. 48, no. 3, pp. 302-311, Mar. 2001 https://doi.org/10.1109/10.914793
  17. D. Nishikawa, W. Yu, H. Yokoi, and Y. Kakazu, 'EMG prosthetic hand controller discriminating ten motions using realtime learning method,' Proc. IEEE/RSJ Int'l. Conf. Intelligent Robots and Systems, pp. 1592-1597, 1999
  18. O. Fukuda, T. Tsuji, M. Kaneko, and A. Otuka, ' A human-assisting manipulator teleoperated by EMG signals and arm motions,' IEEE Trans. Robot. Automat., vol. 19, no. 2, pp. 210-222, Apr. 2003 https://doi.org/10.1109/TRA.2003.808873
  19. Surface Electromyography: Detection and Recording, Delsys Incorporated, 2002
  20. http://www.delsys.com
  21. http://www.ni.com
  22. N. Saito and R. R. Coifinan, 'Local discriminant bases and their applications,' Journal of Mathematical Imaging and Vision, vol. 5, no. 4, pp. 337-358, 1995 https://doi.org/10.1007/BF01250288
  23. S. G Mallat, 'A theory for multiresolution signal decomposition: The wavelet representation,' IEEE Trans. Pattern Anal. and Machine Intell., vol. 11, no. 7, pp. 674-693, July 1989 https://doi.org/10.1109/34.192463
  24. C. Chatterjee and V. P. Roychowdhury, 'On self-organizing algorithms and networks for class-separability features,' IEEE Trans. Neural Networks, vol. 8, no. 3, May 1997 https://doi.org/10.1109/72.572105
  25. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern classification. New York: Wiley, 2001
  26. D. Lowe and R. Webb, 'Optimized feature extraction and bayes decision in feed-forward classifier networks,' IEEE Trans. Pattern Anal. and Machine Intell., vol. 13, no. 4, pp. 355-364, Apr. 1991 https://doi.org/10.1109/34.88570
  27. T. Kohonen, 'The self-organizing map,' Proc. IEEE, vol. 78, no. 9, pp. 1464-1480, 1990 https://doi.org/10.1109/5.58325
  28. J. W. Sammon, 'A nonlinear mapping for data structure analysis,' IEEE Trans. Comput., vol. C-18, pp. 401-409, 1969 https://doi.org/10.1109/T-C.1969.222678

Cited by

  1. Development of the Myoelectric Hand with a 2 DOF Auto Wrist Module vol.17, pp.8, 2011, https://doi.org/10.5302/J.ICROS.2011.17.8.824