Computer and Information Engineering | Conference paper | Published 2020

DEFINING THE FEATURES OF EMG SIGNALS ON THE FOREARM OF THE HAND USING SVM, RF,K-NN CLASSIFICATION ALGORITHMS

Authors:

Kudratjon Zohirov

Alisher Ganiyev

Barno Sharopova

Keywords: rehabilitation, electromyograms, filtering, invasive, features, classification, knn, random forest, support vector machine.

Abstract

EMG (electromyogram) signal-based control systems that provide important information on muscle activity are now in development. In this article, through some of the features of the EMG signal, three hand movements are classified. Experiments show that by using with the combination of Simple Square Integral (SSI), Average Amplitude Change (ACC), Integrated EMG (IEMG), Waveform Length (WL), Root Mean Square (RMS), Mean Absolute Value (MAV), Zero Crossing (ZC), Wilson Amplitude (WAMP) and Log-Detect (log-D) of EMG signal, 99% result of the process of signal recognition used in the classifier algorithms in k-NN (K -nearest neighbor) and RF (Random Forest), 96% result in SVM (Support vector machine) is achieved.

References

  1. [1] https://www.sralab.org/facts-about-limb-loss
  2. [2] http://www.who.int/medical_devices/publications/guide_prosthe_ortho_
  3. train/en/
  4. [3] http://www.amputeecoalition.org/inmotion/nov_dec_07/history_prosthet
  5. ics.pdf
  6. [4] R. N. Khushaba, S. Kodagoda, D. Liu, and G. Dissanayake, "Muscle
  7. computer interfaces for driver distraction reduction", Computer
  8. Methods and Programs in Biomedicine, vol. 110, no. 2, pp. 137-149,
  9. 2012.
  10. [5] H. Huang, J. Y. Guo, and H. J. Chen,"Ant colony optimization-based
  11. feature selection method for surface electromyography signals
  12. classification", Computers in Biology and Medicine, vol. 42, no. 1, pp.
  13. 30-38, 2012.
  14. [6] J. Kilby, H. Gholam, "Wavelet analysis of surface electromyography
  15. signals," In: Annual International Conference of the IEEE Engineering
  16. in Medicne and Biology Society, San Francisco-USA, 2004.
  17. [7] Fraiwan, L., Awwad, M., Mahdawi, M., and Jamous, S., "Real time
  18. virtual prosthetic hand controlled using EMG signals", pp. 225-227
  19. (2011).
  20. [8] Francesca Cordella, Anna Lisa Ciancio, Rinaldo Sacchetti, Angelo
  21. Davalli., et al. “Literature Review on Needs of Upper Limb Prosthesis”,
  22. Frontiers in Neuroscience journal, May 2016
  23. [9] H. Lippert, Lehrbuch Anatomie: 184 Tabellen. Elsevier,
  24. Urban&FischerVerlag, 2006)
  25. [10] M. A. Oskoei, and H. Hu. "A survey-Myoelectric control systems",
  26. Biomedical Signal Processing and Control, vol. 2, pp. 275-294, 2012.
  27. [11] A. Phinyomark, P. Phukpattaranont, and C. Limsakul, "Feature
  28. reduction and selection for EMG signal classification," Expert Systems
  29. with Applications, vol. 39, no. 8, pp. 7420-7431, 2012.
  30. [12] K. S. Kim, H. H. Moon, and C. S. Mun, "Comparison of k-nearest
  31. neighbor, quadratic discriminant and linear discriminant analysis in
  32. classification of electromyogram signals based on the wrist-motion
  33. directions", Current Applied Physics, vol. 11, no. 3, pp. 740-745, 2011.
  34. [13] Gonzalez-Abril L, Velasco F, Angulo C, Ortega JA. A study on output
  35. normalization in multiclass SVMs. Pattern Recogn Lett 2013; 34: 344-
  36. 348.
  37. [14] BreimanLeo Random Forests inMachine Learning, 45, 5–32, 2001,
  38. Statistics Department, University of California, Berkeley, CA 94720
  39. Kluwer Academic Publishers. 2001.
Loading...
0

Views

0

Reads

0

Comments

0

Reviews

0

Liked

0

Shared

0

Bibliography

0

Citations

Like and share on

Cite this publication

Copy text below and use in your article