Journal of Electrical Engineering and Automation
IRO Journals
Volume 4 — Issue 4 — December 2022

sEMG based Real-Time Motion Classification using Virtual Reality and Artificial Neural Networks

https://doi.org/10.36548/jeea.2022.4.003
Asib Mahmud
Measurement and Control Engineering Research Center, Idaho State University, Pocatello ID, USA
Omid Heidari
Measurement and Control Engineering Research Center, Idaho State University, Pocatello, USA
Marco P. Schoen
Department of Mechanical Engineering, Idaho State University, Pocatello ID, USA
PDF
PDF

How to Cite

Mahmud, Asib, Omid Heidari, and Marco P. Schoen. 2022. “SEMG Based Real-Time Motion Classification Using Virtual Reality and Artificial Neural Networks”. Journal of Electrical Engineering and Automation 4 (4): 241-56. https://doi.org/10.36548/jeea.2022.4.003.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Artificial neural network
— motion identification
— rehabilitation
— prosthesis hand
— real – time model
— surface electromyography classification
— virtual reality
Published: 29-11-2022

Abstract

The work presented in this paper addresses the enhancement of upper body rehabilitation and training methods for stroke victims and upper body amputees. One of the primary aims is to develop a tool that utilizes augmented reality to facilitate the rehabilitation of impaired human hand and forearm movements by employing mirror neurons and virtual reality. The second objective of the proposed tool is to allow for evaluation and specification of prostheses prior to acquisition and fitting of such devices to upper limb amputees. The proposed system involves the development of real–time surface Electromyography (sEMG) signal classification methods, Artificial Neural Network training, and implementation and the development of identification algorithms for inferring motion intend. The results of the proposed approach indicate preferences of specific classifiers used in the processing of sEMG data. The proposed methods are implemented in a virtual reality environment allowing for potential selection and training of prosthetic device usage as well as for physical therapy rehabilitation sessions of stroke victims.

References

  1. Atzori, Manfredo, and Henning Müller. "Control capabilities of myoelectric robotic prostheses by hand amputees: a scientific research and market overview." Frontiers in systems neuroscience 9 (2015): 162.
  2. Sturma, Agnes, Roche, Aidan D., Göbel, Peter, Herceg, Malvina, Ge, Nan, Fialka-Moser, Veronika and Aszmann, Oskar. "A surface EMG test tool to measure proportional prosthetic control" Biomedical Engineering / Biomedizinische Technik 60, no. 3 (2015): 207-213.
  3. Roche, Aidan Dominic, Ivan Vujaklija, Sebastian Amsüss, Agnes Sturma, Peter Göbel, Dario Farina, and Oskar C. Aszmann. "A structured rehabilitation protocol for improved multifunctional prosthetic control: a case study." JoVE (Journal of Visualized Experiments) 105 (2015): e52968.
  4. Prahm, Cosima, Fares Kayali, Ivan Vujaklija, Agnes Sturma, and Oskar Aszmann. "Increasing motivation, effort and performance through game-based rehabilitation for upper limb myoelectric prosthesis control." In 2017 International Conference on Virtual Rehabilitation (ICVR), pp. 1-6. IEEE, 2017.
  5. Saridis, George N. and Thomas P. Gootee. “EMG Pattern Analysis and Classification for a Prosthetic Arm.” IEEE Transactions on Biomedical Engineering BME-29 (1982): 403-412.
  6. Hudgins, Bernard, Philip Parker, and Robert N. Scott. "A new strategy for multifunction myoelectric control." IEEE transactions on biomedical engineering 40, no. 1 (1993): 82-94.
  7. Guo, Weichao, Xinjun Sheng, Honghai Liu, and Xiangyang Zhu. "Toward an enhanced human–machine interface for upper-limb prosthesis control with combined EMG and NIRS signals." IEEE Transactions on Human-Machine Systems 47, no. 4 (2017): 564-575.
  8. Phinyomark, Angkoon, Chusak Limsakul, and Pornchai Phukpattaranont. "A novel feature extraction for robust EMG pattern recognition." arXiv preprint arXiv:0912.3973 (2009).
  9. Beebe, Justin A., and Catherine E. Lang. "Active range of motion predicts upper extremity function 3 months after stroke." Stroke 40, no. 5 (2009): 1772-1779.
  10. Fogassi, Leonardo, Pier Francesco Ferrari, Benno Gesierich, Stefano Rozzi, Fabian Chersi, and Giacomo Rizzolatti. "Parietal lobe: from action organization to intention understanding." Science 308, no. 5722 (2005): 662-667.
  11. Calvo-Merino, Beatriz, Daniel E. Glaser, Julie Grèzes, Richard E. Passingham, and Patrick Haggard. "Action observation and acquired motor skills: an FMRI study with expert dancers." Cerebral cortex 15, no. 8 (2005): 1243-1249.
  12. Buccino, Giovanni, Ana Solodkin, and Steven L. Small. "Functions of the mirror neuron system: implications for neurorehabilitation." Cognitive and behavioral neurology 19, no. 1 (2006): 55-63.
  13. Instruments T. Universal Active Filter UAF42. www.ti.com/product/UAF2/description, accessed 18-Dec-2018
  14. Yarlagadda PK. "Real-time SEMG-based Finger Joint Angle Control for a Smart Prosthetic Hand. " Department of Mechanical Engineering, Idaho State University (2013).
  15. MATHWORKS, "Simulink on/off switch” by Gleen Gomes,2012[Online]Available: https://www.mathworks.com/matlabcentral/fileexchange/39348-simulink-on-off-switch,accessed 30-Mar-2018
  16. Gavin, Henri P. "The Levenberg-Marquardt algorithm for nonlinear least squares curve-fitting problems." Department of Civil and Environmental Engineering, Duke University 19 (2019).