Optimizing Support Vector Machine with Genetic Algorithm for Capacitive Sensing-Based Locomotion Mode Recognition

  • Yi Song
  • Yating Zhu
  • Enhao Zheng
  • Fei Tao
  • Qining Wang
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 302)


Capacitive sensing has been proven valid for locomotion mode recognition as an alternative of popular electromyography-based methods in the control of powered prostheses. In order to obtain higher recognition accuracy, in this paper, we try to improve the support vector machine (SVM)-based classifier by selecting suitable kernel function and optimizing the parameters with genetic algorithm (GA). According to different phases of the gait, the phase-dependant GA-SVM models are built and the recognition accuracy increase from 94.0 to \(99.1\,\%\), which is satisfactory for practical applications.


Capacitive sensing Support vector machine Genetic algorithm Locomotion mode recognition Lower-limb prostheses 



This work was supported by the National Natural Science Foundation of China (No. 61005082, 61020106005), the Beijing Nova Program (No. Z141101001814001) and the 985 Project of Peking University (No. 3J0865600).


  1. 1.
    M. Goldfarb, B. E. Lawson, and A. H. Shultz, Realizing the promise of robotic leg prostheses, Sci. Tranl. Med., vol. 5, no. 210, pp. 210ps15, 2013.Google Scholar
  2. 2.
    S. K. Au, J. Weber, and H. Herr, Powered ankle-foot prosthesis improves walking metabolic economy, IEEE Trans. Robot., vol. 25, no. 1, pp. 51–66, 2009.Google Scholar
  3. 3.
    J. Hitt, T. Sugar, M. Holgate, R. Bellman, and K. Hollander, Robotic transtibial prosthesis with biomechanical energy regeneration, Ind. Robot., vol. 36, no. 5, pp. 441–447, 2009.Google Scholar
  4. 4.
    F. Sup, H.A. Varol, J. Mitchell, T. Withrow, and M. Goldfarb, Preliminary evaluations of a self-contained anthropomorphic transfemoral prosthesis, IEEE/ASME Trans. Mechatronics, vol. 14, no. 6, pp. 667–676, 2009.Google Scholar
  5. 5.
    J. Zhu, Q. Wang, and L. Wang, On the design of a powered transtibial prosthesis with stiffness adaptable ankle and toe joints, IEEE Trans. Ind. Electron., vol. 61, no. 9, pp. 4797–4807, 2014.Google Scholar
  6. 6.
    P. Cherelle, V. Grosu, A. Matthys, B. Vanderborght, and D. Lefeber, Design and validation of the ankle mimicking prosthetic (AMP-) foot 2.0, IEEE Trans. Neural. Syst. Rehabil. Eng., vol. 22, no. 1, pp. 138–148, 2014.Google Scholar
  7. 7.
    R. Jim\(\acute{e}\)nez-Fabi\(\acute{a}\)n and O. Verlinden, Review of control algorithms for robotic ankle systems in lower-limb orthoses, prostheses, and exoskeletons, Med. Eng. Phys., vol. 34, pp. 397–408, 2012.Google Scholar
  8. 8.
    H. Huang, T. A. Kuiken, and R. D. Lipschutz, A strategy for identifying locomotion modes using surface electromyography, IEEE Trans. Biomed. Eng., vol. 56, no. 1, pp. 65–72, 2009.Google Scholar
  9. 9.
    H. A. Varol, F. Sup, and M. Goldfarb, Multiclass real-time intent recognition of a powered lower limb prosthesis, IEEE Trans Biomed. Eng., pp. 542–551, 2010.Google Scholar
  10. 10.
    X. Wang, Q. Wang, E. Zheng, K. Wei, and L. Wang, A wearable plantar pressure measurement system: design specifications and first experiments with an amputee, Proc. of the 12th Int. Conf. Intelligent Autonomous Systems, 2012, pp. 273–281.Google Scholar
  11. 11.
    B. Chen, E. Zheng, X. Fan, T. Liang, Q. Wang, K. Wei, and L. Wang, Locomotion mode classification using a wearable capacitive sensing system, IEEE Trans. Neur. Sys. Reh. Eng., vol. 21, no. 5, pp. 744–755, 2013.Google Scholar
  12. 12.
    E. Zheng, L. Wang, Y. Luo, K. Wei, and Q. Wang, Non-contact capacitance sensing for continuous locomotion mode recognition: Design specifications and experiments with an amputee, Proc. of the Int. Conf. Rehabilitation Robotics, 2013.Google Scholar
  13. 13.
    K. Yuan, S. Sun, Z. Wang, Q. Wang, and L. Wang, A fuzzy logic based terrain identification approach to prosthesis control using multi-sensor fusion, Proc. of the IEEE Int. Conf. Robotics and Automation, 2013, pp. 3361–3366.Google Scholar
  14. 14.
    N. E. Bunderson and T. A. Kuiken, Quantification of feature space changes with experience during electromyogram pattern recognition control, IEEE Trans. Neur. Sys. Reh. Eng., vol. 20, pp. 239–246, 2012.Google Scholar
  15. 15.
    J. Cheng, O. Amft, and P. Lukowicz, Active capacitive sensing: exploring a new wearable sensing modality for activity recognition, Proc. of 8th Int. Conf. Pervasive Computing, 2010, pp. 319–336.Google Scholar
  16. 16.
    E. Zheng, B. Chen, K. Wei, and Q. Wang, Lower limb wearable capacitive sensing and its applications to recognizing human gaits, Sensors, vol. 13, no. 10, pp. 13334–13355, 2013.Google Scholar
  17. 17.
    D. H. Wolpert and W. G. Macready, No free lunch theorems for optimization, IEEE Trans. Evolutionary Computation, vol. 1, pp. 67–82, Apr. 1997.Google Scholar
  18. 18.
    Y. Song, Y., Zhu, E. Zheng, F. Tao, and Q. Wang, Classifier selection for locomotion mode recognition using wearable capacitive sensing systems, Proc. of the Int. Conf. Robot Intelligence Technology and Applications, Denver, USA, 2013, pp. 763–774.Google Scholar
  19. 19.
    V. Vapnik, Statistical Learning Theory, John Wiley & Sons Ltd, 1998.Google Scholar
  20. 20.
    C.-C. Chang and C.-J. Lin, LIBSVM: A library for support vector machines,
  21. 21.
    D. E. Goldberg, Genetic algorithms in search, optimization, and machine learning, Addison Wesley, 1989.Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Yi Song
    • 1
    • 3
  • Yating Zhu
    • 2
  • Enhao Zheng
    • 1
    • 3
  • Fei Tao
    • 2
  • Qining Wang
    • 1
    • 3
  1. 1.Intelligent Control Laboratory, College of EngineeringPeking UniversityBeijingChina
  2. 2.School of Automation Science and Electrical EngineeringBeihang UniversityBeijingChina
  3. 3.Beijing Engineering Research Center of Intelligent Rehabilitation EngineeringBeijingChina

Personalised recommendations