Annals of Biomedical Engineering

, Volume 47, Issue 1, pp 223–230 | Cite as

sEMG Based Gait Phase Recognition for Children with Spastic Cerebral Palsy

  • Peng-na Wei
  • Rongfu Xie
  • Rongnian TangEmail author
  • Chuang Li
  • Janis Kim
  • Ming Wu


The goal of this study was to examine the optimal strategies for the recognition of gait phase based on surface electromyogram (sEMG) of leg muscles while children with cerebral palsy (CP) walked on a treadmill. Ten children with CP were recruited to participate in this study. sEMG from eight leg muscles and leg position signals were recorded while subjects walked on a treadmill. The position signals of left and right legs were used to develop a five gait sub-phases classifier, i.e., mid stance, terminal stance, pre-swing, mid swing, and terminal swing. Seven feature sets of sEMG signals were tested in recognizing the five gait sub-phases of children with CP. Results from this study indicated that the recognition performance of mean absolute value and zero crossing was better than that with other feature sets when using support vector machine (average classification accuracy was 89.40%). Further, we found that the performance of gait phase recognition is relatively better in pre-swing than other sub-phases, and the performance of gait phase recognition is relatively poorer in mid-swing than other sub-phases. Results from this study may be used to develop an intention-driven robotic gait training system/paradigm for assisting walking in children with CP through robotic training.


sEMG Gait phase recognition Cerebral palsy Feature set Locomotion 



This study was funded by NIDRR/RERC: H133E100007 and Postgraduate Scientific Research and Innovation Projects in Hainan Province [Grant Number Hys2017-128].


  1. 1.
    Asghari Oskoei, M., and H. Hu. Myoelectric control systems—a survey. Biomed. Signal Process. Control 2:275–294, 2007.CrossRefGoogle Scholar
  2. 2.
    Borggraefe, I., J. S. Schaefer, M. Klaiber, E. Dabrowski, C. Ammann-Reiffer, B. Knecht, S. Berweck, F. Heinen, and A. Meyer-Heim. Robotic-assisted treadmill therapy improves walking and standing performance in children and adolescents with cerebral palsy. Eur. J. Paediatr. Neurol. 14:496–502, 2010.CrossRefGoogle Scholar
  3. 3.
    Druzbicki, M., W. Rusek, S. Snela, J. Dudek, M. Szczepanik, E. Zak, J. Durmala, A. Czernuszenko, M. Bonikowski, and G. Sobota. Functional effects of robotic-assisted locomotor treadmill thearapy in children with cerebral palsy. J. Rehabil. Med. 45:358–363, 2013.CrossRefGoogle Scholar
  4. 4.
    Englehart, K., B. Hudgins, and P. A. Parker. A wavelet-based continuous classification scheme for multifunction myoelectric control. IEEE Trans. Bio-med. Eng. 48:302–311, 2001.CrossRefGoogle Scholar
  5. 5.
    Gordon, K. E., and D. P. Ferris. Learning to walk with a robotic ankle exoskeleton. J. Biomech. 40:2636–2644, 2007.CrossRefGoogle Scholar
  6. 6.
    Li, Y., F. Gao, H. Chen, and M. Xu. Gait recognition based on EMG with different individuals and sample sizes. In: Control Conference (CCC), 2016 35th Chinese IEEE, pp. 4068–4072, 2016.Google Scholar
  7. 7.
    Neumann, D. A. Kinesiology of the musculoskeletal system: foundations for rehabilitation. Amsterdam: Elsevier Health Sciences, 2013.Google Scholar
  8. 8.
    Palisano, R., P. Rosenbaum, S. Walter, D. Russell, E. Wood, and B. Galuppi. Development and reliability of a system to classify gross motor function in children with cerebral palsy. Dev. Med. Child Neurol. 39:214–223, 1997.CrossRefGoogle Scholar
  9. 9.
    Phinyomark, A., P. Phukpattaranont, and C. Limsakul. Feature reduction and selection for EMG signal classification. Expert. Syst. Appl. 39:7420–7431, 2012.CrossRefGoogle Scholar
  10. 10.
    Phinyomark, A., F. Quaine, S. Charbonnier, C. Serviere, F. Tarpin-Bernard, and Y. Laurillau. EMG feature evaluation for improving myoelectric pattern recognition robustness. Expert. Syst. Appl. 40:4832–4840, 2013.CrossRefGoogle Scholar
  11. 11.
    Ryu, J.-H. and D.-H. Kim. Multiple gait phase recognition using boosted classifiers based on sEMG signal and classification matrix. In: Proceedings of the 8th International Conference on Ubiquitous Information Management and Communication. Siem Reap, Cambodia: ACM, pp. 1–4, 2014.Google Scholar
  12. 12.
    Tkach, D., H. Huang, and T. A. Kuiken. Study of stability of time-domain features for electromyographic pattern recognition. J. Neuroeng. Rehabil. 7:21, 2010.CrossRefGoogle Scholar
  13. 13.
    Van Eck, M., A. J. Dallmeijer, I. S. van Lith, J. M. Voorman, and J. G. Becher. Manual ability and its relationship with daily activities in adolescents with cerebral palsy. J. Rehabil. Med. 42:493–498, 2010.CrossRefGoogle Scholar
  14. 14.
    Vos, R. C., J. G. Becher, M. Ketelaar, D.-W. Smits, J. M. Voorman, S. S. Tan, H. A. Reinders-Messelink, and A. J. Dallmeijer. Developmental trajectories of daily activities in children and adolescents with cerebral palsy. Pediatrics 132:e915–e923, 2013.CrossRefGoogle Scholar
  15. 15.
    Willerslev-Olsen, M., T. H. Petersen, S. F. Farmer, and J. B. Nielsen. Gait training facilitates central drive to ankle dorsiflexors in children with cerebral palsy. Brain 138:589–603, 2015.CrossRefGoogle Scholar
  16. 16.
    Wu, M., J. Kim, D. J. Gaebler-Spira, B. D. Schmit, and P. Arora. Robotic resistance treadmill training improves locomotor function in children with cerebral palsy: a randomized controlled pilot study. Arch. Phys. Med. Rehabil. 98:2126–2133, 2017.CrossRefGoogle Scholar
  17. 17.
    Xin, L., Z. Rui, Y. Licai, and L. Guanglin. Performance of various EMG features in identifying ARM movements for control of multifunctional prostheses. In: YC-ICT’09. IEEE Youth Conference on Information, Computing and Telecommunication, pp. 287–290, 2009.Google Scholar
  18. 18.
    Yen, S. C., B. D. Schmit, J. M. Landry, H. Roth, and M. Wu. Locomotor adaptation to resistance during treadmill training transfers to overground walking in human SCI. Exp. Brain Res. 216:473–482, 2012.CrossRefGoogle Scholar
  19. 19.
    Zecca, M., S. Micera, M. C. Carrozza, and P. Dario. Control of multifunctional prosthetic hands by processing the electromyographic signal. Crit. Rev. Biomed. Eng. 30:459–485, 2002.CrossRefGoogle Scholar
  20. 20.
    Zeni, Jr, J. A., J. G. Richards, and J. S. Higginson. Two simple methods for determining gait events during treadmill and overground walking using kinematic data. Gait & Posture 27:710–714, 2008.CrossRefGoogle Scholar

Copyright information

© Biomedical Engineering Society 2018

Authors and Affiliations

  • Peng-na Wei
    • 1
    • 2
  • Rongfu Xie
    • 1
  • Rongnian Tang
    • 1
    • 3
    • 4
    Email author
  • Chuang Li
    • 1
  • Janis Kim
    • 3
    • 5
  • Ming Wu
    • 3
    • 4
    • 5
  1. 1.School of Mechanical and Electrical EngineeringThe Hainan UniversityHaikouPeople’s Republic of China
  2. 2.Key Laboratory of Education Ministry for Modern Design & Rotor-Bearing SystemXi’an Jiaotong UniversityXi’anPeople’s Republic of China
  3. 3.Sensory Motor Performance ProgramRehabilitation Institute of ChicagoChicagoUSA
  4. 4.Department of PM&RNorthwestern University Medical SchoolChicagoUSA
  5. 5.Legs and Walking LabShirley Ryan AbilitylabChicagoUSA

Personalised recommendations