Design of an Above Knee Low-Cost Powered Prosthetic Leg Using Electromyography and Machine Learning

  • Cyril Joe Baby
  • Ketan Jitendra Das
  • P. VenugopalEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1057)


Electronic knee prosthesis provides a wide range of mobility when compared to mechanical prosthesis. Powered prosthetics are quite expensive and hence are not widely used. In this paper, we have proposed a low-cost above knee powered prosthetic leg which is reliable and the complexity of the model is less. Theprosthesis works by taking inputs from sensor placed in the model and an EMG sensor that records muscle activity of the thigh of the amputee. In order to calculate joint motion and knee angle a variety of methods can be used which include goniometer, inertial measurement units and magnetic encoders. Based on these sensor values, the actuation of the joint is determined. In this paper, we are discussing about an approach that uses sensor data along with muscle activity for actuation. The model classifies the current phase of walking based on the EMG sensor and angle values obtained from the leg. Once the gait phase is determined, the next gait phase is initiated. This enables the prosthesis to be reliable and efficient at the same time being cost effective.


Prosthesis EMG IMUs Piezo Random forest classifier SVM 


  1. 1.
    Sup, F., Bohara, A., Goldfarb, M.: Design and control of a powered transfemoral prosthesis. Int. J. Robot. Res. 27(2), 263–273 (2008)CrossRefGoogle Scholar
  2. 2.
    Hargrove, L.J., Young, A.J., Simon, A.M., Fey, N.P., Lipschutz, R.D., Finucane, S.B., Kuiken, T.A.: Intuitive control of a powered prosthetic leg during ambulation: a randomized clinical trial. JAMA 313(22), 2244–2252 (2015)CrossRefGoogle Scholar
  3. 3.
    Scheme, E.P., Englehart, K.: Electromyogram pattern recognition for control of powered upper-limb prostheses: State of the art and challenges for clinical use. J. Rehabil. Res. Dev. 48(6), 643 (2011)CrossRefGoogle Scholar
  4. 4.
    Chan, A.D., Englehart, K.B.: Continuous myoelectric control for powered prostheses using hidden Markov models. IEEE Trans. Biomed. Eng. 52(1), 121–124 (2005)CrossRefGoogle Scholar
  5. 5.
    Englehart, K., Hudgins, B.: A robust, real-time control scheme for multifunction myoelectric control. IEEE Trans. Biomed. Eng. 50(7), 848–854 (2003)CrossRefGoogle Scholar
  6. 6.
    Seel, T., Raisch, J., Schauer, T.: IMU-based joint angle measurement for gait analysis. Sensors 14(4), 6891–6909 (2014)CrossRefGoogle Scholar
  7. 7.
    El-Sheimy, N., Nassar, S., Noureldin, A.: Wavelet de-noising for IMU alignment. IEEE Aerosp. Electron. Syst. Mag. 19(10), 32–39 (2004)CrossRefGoogle Scholar
  8. 8.
    Saridis, G.N., Gootee, T.P.: EMG pattern analysis and classification for a prosthetic arm. IEEE Trans. Biomed. Eng. 6, 403–412 (1982)CrossRefGoogle Scholar
  9. 9.
    Ajiboye, A.B., Weir, R.F.: A heuristic fuzzy logic approach to EMG pattern recognition for multifunctional prosthesis control. IEEE Trans. Neural Syst. Rehabil. Eng. 13(3), 280–291 (2005)CrossRefGoogle Scholar
  10. 10.
    Parker, P., Englehart, K., Hudgins, B.: Myoelectric signal processing for control of powered limb prostheses. J. Electromyogr. Kinesiol. 16(6), 541–548 (2006)CrossRefGoogle Scholar
  11. 11.
    Breiman, L., Cutler, A.: Random forests manual (version 4.0). Technical Report of the University of California, Berkeley, Department of Statistics (2003)Google Scholar
  12. 12.
    Han, H., Guo, X., Yu, H.: Variable selection using mean decrease accuracy and mean decrease Gini based on random forest. In: 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS), pp. 219–224 (2016)Google Scholar
  13. 13.
    Kumar, A., Shahnawazuddin, S., Pradhan, G.: Exploring different acoustic modeling techniques for the detection of vowels in speech signal. In: 2016 Twenty Second National Conference on Communication (NCC), pp. 1–5 (2016)Google Scholar
  14. 14.
    Ljumović, M., Klar, M.: Estimating expected error rates of random forest classifiers: a comparison of cross-validation and bootstrap. In: 2015 4th Mediterranean Conference on Embedded Computing (MECO), pp. 212–215 (2015)Google Scholar
  15. 15.
    Ehlers, A., Rosenhahn, B., Liu, W., Baumann, F.: Sequential boosting for learning a random forest classifier. In: 2015 IEEE Winter Conference on Applications of Computer Vision, pp. 442–447 (2015)Google Scholar
  16. 16.
    Itagi, A., Baby, C.J., Rout, S., Bharath, K.P., Karthik, R., Kumar, M.R.: Lisp detection and correction based on feature extraction and random forest classifier. In: Microelectronics, Electromagnetics and Telecommunications (pp. 55–64). Springer, Singapore (2019)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Cyril Joe Baby
    • 1
  • Ketan Jitendra Das
    • 1
  • P. Venugopal
    • 1
    Email author
  1. 1.School of Electronics and Communications EngineeringVIT UniversityVelloreIndia

Personalised recommendations