Gait Phase Classification from Surface EMG Signals Using Neural Networks

  • Christian MorbidoniEmail author
  • Lorenzo Principi
  • Guido Mascia
  • Annachiara Strazza
  • Federica Verdini
  • Alessandro Cucchiarelli
  • Francesco Di Nardo
Conference paper
Part of the IFMBE Proceedings book series (IFMBE, volume 76)


Identification and classification of different gait phases is an essential requirement to temporally characterize muscular recruitment during human walking. The present study proposes a Deep-learning methodology for the classification of the two main gait phases (stance and swing), based on the interpretation of surface electromyographic (sEMG) signals alone. Three different Multi Layer Perceptron (MLP) models are tested to this aim. The present approach does not require specific features to be extracted from the signal, differently from previous studies. 12 healthy adult subjects are analyzed during walking over-ground at comfortable speed. sEMG signals from eight leg muscles are selected. Performance of classifiers is tested vs. gold standard, represented by basographic signals measured by means of three foot-switches. A 10-fold evaluation is computed to take into account the possible variability of the results. The direct comparison among the performances of the three different MLP models shows an average high accuracy over the population (around 95%) for all the models, independent from the increasing complexity. Moreover, the accuracy in each single subject does not fall below 92.6% (range of accuracy variability = 92.6–97.2%). This present study suggests that artificial neural networks may be a suitable tool for the automatic classification of gait phases from electromyographic signals, in overall walking tasks.


sEMG Deep learning Neural networks Gait phase classification 


  1. 1.
    Perry, J.: Gait Analysis: Normal and Pathological Function. Slack Inc., USA (1992)Google Scholar
  2. 2.
    Mengarelli, A., Maranesi, E., Burattini, L., Fioretti, S., Di Nardo, F.: Co-contraction activity of ankle muscles during walking: a gender comparison. Biomed. Signal Process. Control 33, 1–9 (2017). Scholar
  3. 3.
    Gurney, J., Kersting, U., Rosenbaum, D.: Between-day reliability of repeated plantar pressure distribution measurements in a normal population. Gait Posture 27(4), 706–709 (2008). Scholar
  4. 4.
    Bovi, G., Rabuffetti, M., Mazzoleni, P., Ferrarin, M.: A multiple-task gait analysis approach: kinematic, kinetic and emg reference data for healthy young and adult subjects. Gait Posture 33(1), 6–13 (2011). Scholar
  5. 5.
    Caldas, R., Mundt, M., Potthast, W., de Lima Neto, F.B., Markert, B.: A systematic review of gait analysis methods based on inertial sensors and adaptive algorithms. Gait Posture 57, 204–210 (2017). Scholar
  6. 6.
    Koller, J.R., Jacobs, D.A., Ferris, D.P., Remy, C.D.: Learning to walk with an adaptive gain proportional myoelectric controller for a robotic ankle exoskeleton. J. NeuroEng. Rehabil. 12(1), 97 (2015)CrossRefGoogle Scholar
  7. 7.
    Ziegier, J., Gattringer, H., Mueller, A.: Classification of gait phases based on bilateral EMG data using support vector machines. In: Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, pp. 978–983, August 2018.
  8. 8.
    Nazmi, N., Abdul Rahman, M., Yamamoto, S.-I., Ahmad, S.: Walking gait event detection based on electromyography signals using artificial neural network. Biomed. Signal Process. Control 47, 334–343 (2019). Scholar
  9. 9.
    Kaczmarczyk, K., Wit, A., Krawczyk, M., Zaborski, J., Piłsudskii, J.: Artificial neural networks (ANN) applied for gait classification and physiotherapy monitoring in post stroke patients. In: Artificial Neural Networks, Chap. 16. IntechOpen, Rijeka (2011). Scholar
  10. 10.
    Wang, J., Zielińska, T.: Gait features analysis using artificial neural networks - testing the footwear effect. Acta Bioeng. Biomech. 19(1), 17–32 (2017)Google Scholar
  11. 11.
    Nazmi, N., Yamamoto, S., Rahman, M., Ahmad, S., Adiputra, D., Zamzuri, H., Mazlan, S.: Fuzzy logic for walking patterns based on surface electromyography signals with different membership functions. In: 2016 6th International Workshop on Computer Science and Engineering, WCSE 2016, pp. 636–639 (2016)Google Scholar
  12. 12.
    Nazmi, N., Rahman, M.A.A., Ahmad, S.A.: Generalization of ANN model in classifying stance and swing phases of gait using EMG signals. In: 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES) (2018)Google Scholar
  13. 13.
    Di Nardo, F., Mengarelli, A., Maranesi, E., Burattini, L., Fioretti, S.: Gender differences in the myoelectric activity of lower limb muscles in young healthy subjects during walking. Biomed. Signal Process. Control 19, 14–22 (2015). Scholar
  14. 14.
    Strazza, A., Mengarelli, A., Fioretti, S., Burattini, L., Agostini, V., Knaflitz, M., Di Nardo, F.: Surface-EMG analysis for the quantification of thigh muscle dynamic co-contractions during normal gait. Gait Posture. 51, 228–233 (2017)CrossRefGoogle Scholar
  15. 15.
    Agostini, V., Balestra, G., Knaflitz, M.: Segmentation and classification of gait cycles. IEEE Trans. Neural Syst. Rehabil. Eng. 22(5), 946–952 (2014). Scholar
  16. 16.
    Taborri, J., Palermo, E., Rossi, S., Cappa, P.: Gait partitioning methods: a systematic review. Sens. (Switz.) 16(1), 66 (2016). Scholar
  17. 17.
    Winiarski, S., Rutkowska-Kucharska, A.: Estimated ground reaction force in normal and pathological gait. Acta Bioeng. Biomech. 11(1), 53–60 (2009)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Christian Morbidoni
    • 1
    Email author
  • Lorenzo Principi
    • 1
  • Guido Mascia
    • 1
  • Annachiara Strazza
    • 1
  • Federica Verdini
    • 1
  • Alessandro Cucchiarelli
    • 1
  • Francesco Di Nardo
    • 1
  1. 1.Department of Information EngineeringUniversità Politecnica delle MarcheAnconaItaly

Personalised recommendations