Robust EMG Pattern Recognition to Muscular Fatigue Effect for Human-Machine Interaction

  • Jae-Hoon Song
  • Jin-Woo Jung
  • Zeungnam Bien
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4293)


The main goal of this paper is to design an electromyogram (EMG) pattern classifier which is robust to muscular fatigue effects for human-machine interaction. When a user operates some machines such as a PC or a powered wheelchair using EMG-based interface, muscular fatigue is generated by sustained duration time of muscle contraction. Therefore, recognition rates are degraded by the muscular fatigue. In this paper, an important observation is addressed: the variations of feature values due to muscular fatigue effects are consistent for sustained duration time. From this observation, a robust pattern classifier was designed through the adaptation process of hyperboxes of Fuzzy Min-Max Neural Network. As a result, significantly improved performance is confirmed.


Contraction Time Central Fatigue Muscular Fatigue Prosthetic Hand Peripheral Fatigue 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Collins COBUILD Advanced Learner’s English Dictionary, 4th edn. (2003)Google Scholar
  2. 2.
    Bigland-Ritchie, B., Jones, D.A., Hosking, G.P., Edwards, R.H.: Central and peripheral fatigue in sustained maximum voluntary contractions of human quadriceps muscle. Journal of Clinical Science and Molecular Medicine 54(6), 609–614 (1978)Google Scholar
  3. 3.
    Kiryu, T., Morishiata, M., Yamada, H., Okada, M.: A muscular fatigue index based on the relationships between superimposed M wave and preceding background activity. IEEE Transactions on Biomedical Engineering 45(10), 1194–1204 (1998)CrossRefGoogle Scholar
  4. 4.
    Bonato, P., Roy, S.H., Knaflitz, M., de Luca, C.J.: Time-frequency parameters of the surface myoelectric signal for assessing muscle fatigue during cyclic dynamic contractions. IEEE Transactions on Biomedical Engineering 48(7), 745–753 (2001)CrossRefGoogle Scholar
  5. 5.
    Park, E., Meek, S.G.: Fatigue compensation of the electromyographic signal for prosthetic control and force estimation. IEEE Transactions on Biomedical Engineering 40(10), 1019–1023 (1993)CrossRefGoogle Scholar
  6. 6.
    Winslow, J., Jacobs, P.L., Tepavac, D.: Fatigue compensation during FES using surface EMG. Journal of Electromyography and Kinesilogy 13(6), 555–568 (2003)CrossRefGoogle Scholar
  7. 7.
    Chen, J.-J.J., Yu, N.-Y.: The validity of stimulus-evoked EMG for studying muscle fatigue characteristics of paraplegic subjects during dynamic cycling movement. IEEE Transactions on Rehabilitation Engineering 5(2), 170–178 (1997)CrossRefGoogle Scholar
  8. 8.
    Knox, R.R., Brooks, D.H., Manolakos, E., Markogiannakis, S.: Time-series based features for EMG pattern recognition: Preliminary results. In: Bioengineering Conference, Proceedings of the IEEE Nineteenth Annual Northeast, March 18-19 (1993)Google Scholar
  9. 9.
    Boostani, R., Moradi, M.H.: Evaluation of the forearm EMG signal features for the control of a prosthetic hand. Journal of Physiological Measurement 24, 309–319 (2003)CrossRefGoogle Scholar
  10. 10.
    Simpson, P.: Fuzzy min-max neural networks - Part 1: Classification. IEEE Transactions on Neural Networks 3, 776–786 (1992)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jae-Hoon Song
    • 1
  • Jin-Woo Jung
    • 2
  • Zeungnam Bien
    • 3
  1. 1.Air Navigation and Traffic System DepartmentKorea Aerospace Research InstituteDaejeonKorea
  2. 2.Department of Computer EngineeringDongguk UniversitySeoulKorea
  3. 3.Department of Electrical Engineering and Computer ScienceKorea Advanced Institute of Science and TechnologyDaejeonKorea

Personalised recommendations