Cluster Computing

, Volume 20, Issue 4, pp 3051–3059 | Cite as

Extreme learning machine classification method for lower limb movement recognition

  • Yuxiang KuangEmail author
  • Qun Wu
  • Junkai Shao
  • Jianfeng Wu
  • Xuehua Wu


In order to identify the lower limb movements accurately and quickly, a recognition method based on extreme learning machine (ELM) is proposed. The recognizing target set is constructed by decomposing the daily actions into different segments. To get the recognition accuracy of seven movements based on the surface electromyography, the recognition feature vector space is established by integrating short-time statistical characteristics under time domain, and locally linear embedding algorithm is used to reduce the computational complexity and improve robustness of algorithm. Compared with BP, the overall recognition accuracy for each subject in the best dimension with ELM is above 95%.


Movement recognition Surface EMG ELM-LLE Multi-classification 



The authors would like to gratefully acknowledge the reviewers’ comments. This work is supported by Jiangxi Science and Technology Plan (20161BBE50058), Science and Technology Major Project of Zhejiang province (2013C03017-1), Taizhou Science and Technology Plan (13ZJU007).


  1. 1.
    Yong, H., Foody, J., Linong, J., Dong, Z., Wang, Y.J., Ma, L., Meng, H.J., Shiff, S., Dayi, H.: A systematic literature review of risk factors for stroke in China. Cardiol. Rev. 21(2), 77–93 (2013)CrossRefGoogle Scholar
  2. 2.
    Chen, Y., Yang, C.J.: The human-machine intelligent system. Zhejiang University Press Inc., Hangzhou (2006)Google Scholar
  3. 3.
    Bulea, T.C., Prasad, S., Kilicarslan, A., Contrerasvidal, J.L.: International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 6341–6344. doi: 10.1109/EMBC.2013.6611004
  4. 4.
    Wagner, J., Solis-Escalante, T., Grieshofer, P., Neuper, C., Müller-Putz, G., Scherer, R.: Level of participation in robotic-assisted treadmill walking modulates midline sensorimotor EEG rhythms in able-bodied subjects. Neuroimage 63(3), 1203–1211 (2012)CrossRefGoogle Scholar
  5. 5.
    Zhou, H.Y., Hu, H.S., Harris, N.D., Hammerton, J.: Applications of wearable inertial sensors in estimation of upper limb movements. Biomed. Signal Process. Control. 1(1), 22–32 (2006)CrossRefGoogle Scholar
  6. 6.
    De, N.M., Bussmann, J.B., Ribbers, G.M., Stam, H.J.: The stroke upper-limb activity monitor: its sensitivity to measure hemiplegic upper-limb activity during daily life. Arch. Phys. Med. Rehabil. 88(9), 1121–1126 (2007)CrossRefGoogle Scholar
  7. 7.
    Bataineh, M., Marler, T., Abdel-Malek, K., Arora, J.: Neural network for dynamic human motion prediction. Expert Syst. Appl. 48, 26–34 (2015)CrossRefGoogle Scholar
  8. 8.
    Khezri, M., Hezri, M., Jahed, M.: An exploratory study to design a novel hand movement identification system. Comput. Biol. Med. 39, 433–442 (2009)CrossRefGoogle Scholar
  9. 9.
    Phinyomark, A., Quaine, F., Charbonnier, S., Serviere, C., Tarpin-Bernard, F., Laurillau, Y.: Emg feature evaluation for improving myoelectric pattern recognition robustness. Expert Syst. Appl. 40(12), 4832–4840 (2013)CrossRefGoogle Scholar
  10. 10.
    Khushaba, R., Kodagoda, S., Takruri, M., Dissanayake, G.: Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals. Expert Syst. Appl. 39(12), 10731–10738 (2012)CrossRefGoogle Scholar
  11. 11.
    Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011)CrossRefGoogle Scholar
  12. 12.
    Chen, Y.Z., Zhou, Y.Q., Cheng, X.L., Mi, Y.Z.: Upper limb motion recognition based on two-step SVM classification method of surface EMG. Int. J. Control. Autom. 6(3), 249–265 (2013)Google Scholar
  13. 13.
    Young, A.J., Smith, L.H., Rouse, E.J., Hargrove, L.J.: Classification of simultaneous movements using surface EMG pattern recognition. IEEE Trans. Bio-med. Eng. 60(5), 1250–1258 (2013)CrossRefGoogle Scholar
  14. 14.
    Naeem, U.J., Xiong, C.H., Abdullah, A.A.: EMG-muscle force estimation model based on back-propagation neural network. In: IEEE International Conference on Virtual Environments Human-Computer Interfaces and Measurement Systems, pp. 222–227 (2012). doi: 10.1109/VECIMS.2012.6273225
  15. 15.
    Wang, N.F., Chen, Y.L., Zhang, X.M.: Realtime recognition of multi-finger prehensile gestures. Biomed. Signal Process. Control. 13(1), 262–269 (2014)CrossRefGoogle Scholar
  16. 16.
    Kiguchi, K.: A study on EMG-based human motion prediction for power assist exoskeletons. In: International Symposium on Computational Intelligence in Robotics and Automation, pp. 190–195 (2007). doi: 10.1109/CIRA.2007.382917
  17. 17.
    Zhang, K., Luo, M.X.: Outlier-robust extreme learning machine for regression problems. Neurocomputing 151, 1519–1527 (2015)CrossRefGoogle Scholar
  18. 18.
    Xin, J.C., Wang, Z.Q., Qu, L.X., Wang, G.R.: Elastic extreme learning machine for big data classification. Neurocomputing 149(149), 464–471 (2015)CrossRefGoogle Scholar
  19. 19.
    Cao, J.W., Xiong, L.L.: Protein sequence classification with improved extreme learning machine algorithms. Biomed Res. Int. 2014(1), 660–677 (2014)Google Scholar
  20. 20.
    Deo, R.C., Şahinb, M.: Application of the extreme learning machine algorithm for the prediction of monthly effective drought index in eastern Australia. Atmos. Res. 153, 512–525 (2015)CrossRefGoogle Scholar
  21. 21.
    Huang, G.B., Ding, X.J., Zhou, H.M.: Optimization method based extreme learning machine for classification. Neurocomputing 74(1–3), 155–163 (2010)CrossRefGoogle Scholar
  22. 22.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by local linear embedding. Science 290(5), 2323–2326 (2012)Google Scholar
  23. 23.
    Donoho, D.L., Carrie, G.: Hessian eigenmaps: new locally linear embedding techniques for high dimensional data. Proc. Natl. Acad. Sci. 100(100), 5591–5596 (2003)CrossRefzbMATHMathSciNetGoogle Scholar
  24. 24.
    Wu, J.F.: Research on Information Acquisition Technology for Human Lower Limb Movement Based on EMG Signals. Zhejiang University, Hangzhou (2008)Google Scholar
  25. 25.
    Hudgins, B., Parker, P., Scott, R.: A new strategy for multifunction myoelectric control. IEEE Trans. Biomed. Eng. 40(1), 82–94 (1993)CrossRefGoogle Scholar
  26. 26.
    Wang, N., Chen, Y., Zhang, X.: The recognition of multi-finger prehensile postures using lda. Biomed. Signal Process. Control. 8(6), 706–712 (2013)CrossRefGoogle Scholar
  27. 27.
    Lawrence, K.S., Sam, T.R.: Nonlinear dimensionality reduction by locally linear embedding. Science. 290(12), 2323–2326 (2000)Google Scholar
  28. 28.
    Matrone, G., Cipriani, C., Secco, E., Magenes, G., Carrozza, M.: Principal components analysis based control of a multi-DoF underactuated prosthetic hand. J. Neuroeng. Rehabil. 7(1), 16–28 (2010)CrossRefGoogle Scholar
  29. 29.
    Huang, G.B., Babri, H.A.: Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions. IEEE Trans. Neural Netw. 9(1), 224–229 (1998)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  • Yuxiang Kuang
    • 1
    • 2
    Email author
  • Qun Wu
    • 3
    • 4
  • Junkai Shao
    • 5
  • Jianfeng Wu
    • 6
  • Xuehua Wu
    • 3
  1. 1.College of Computer Science and TechnologyZhejiang UniversityHangzhouChina
  2. 2.School of ArtJiangxi University of Finance & EconomicsNanchangChina
  3. 3.Universal Design InstituteZhejiang Sci-Tech UniversityHangzhouChina
  4. 4.Taizhou Research InstituteZhejiang UniversityHangzhouChina
  5. 5.Product Design and Reliability Engineering InstituteSoutheast UniversityNanjingChina
  6. 6.School of ArtZhejiang University of TechnologyHangzhouChina

Personalised recommendations