sEMG Based Joint Angle Estimation of Lower Limbs Using LS-SVM

  • Qingling Li
  • Yu Song
  • Zengguang Hou
  • Bin Zhu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8226)


In this paper, a new estimation model based on least squares support vector machine (LS-SVM) is proposed to build up the relationship between Surface electromyogram (sEMG) signal and joint angle of the lower limb. The input of the model is 2 channels of preprocessed sEMG signal. The outputs of the model are joint angles of the hip and the knee. sEMG signal is acquired from 7 motion muscles in treadmill exercise. And two channels of them are selected for dynamic angle estimation for their strong correlation with angle data. Angle estimation model is constructed by 2 independent LS-SVM based regression model with radial basis function (RBF). It is trained using part of the sample sets acquired in 10s exercise duration and test by all data. Experimental result shows proposed method has good performance on joint angles estimation based sEMG. Root mean square error (RMSE) of prediction knee and hip joint angles is 3.02° and 2.09° respectively. It provide new human-machine interface for active rehabilitation training of SCI, stroke or neurological injury patients.


sEMG LS-SVM Angle estimation Rehabilitation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Mayr, A., Kofler, M., Quirbach, E., et al.: Prospective, blinded, randomized crossover study of gait rehabilitation in stroke patients using the Lokomat gait orthosis. Neurorehabilitation and Neural Repair 21(4), 307–314 (2007)CrossRefGoogle Scholar
  2. 2.
    Krebs, H.I., Volpe, B.T., Aisen, M.L., et al.: Increasing productivity and quality of care:Robot-aided neuro-rehabilitation. Journal of Rehabilitation Research and Development 37(6), 639–652 (2000)Google Scholar
  3. 3.
    Lum, P.S., Burgar, C.G., Van der Loos, H.F.M., et al.: The MIME robotic system for upper-limb neuro-rehabilitation: results from a clinical trial in subacute stroke. In: Proceeding of the 9th IEEE International Conference on Rehabilitation Robotics, pp. 511–514 (2005)Google Scholar
  4. 4.
    Ando, T., Okamoto, J., Fujie, M.G.: Optimal Design of a Micro Macro Neural Network to Recognize Rollover Movement. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (2009 IEEE IROS), pp. 1615–1620 (2009)Google Scholar
  5. 5.
    Kim, J., Mastnik, S., André, E.: EMG-based hand gesture recognition for real-time biosignal interfacing. In: The 13th International Conference on IUI, pp. 30–39 (2008)Google Scholar
  6. 6.
    Hashemi, J., Morin, E., Mousavi, P., Hashtrudi-Zaad, K.: Joint Angle-based EMG Amplitude Calibration. In: The 33rd Annual International Conference of the IEEE EMBS, pp. 4439–4442 (2011)Google Scholar
  7. 7.
    Ngeo, J., Tamei, T., Shibata, T.: Continuous Estimation of Finger Joint Angles using Muscle Activation Inputs from Surface EMG Signals. In: The 34th Annual International Conference of the IEEE EMBS, pp. 2756–2759 (2012)Google Scholar
  8. 8.
    Wang, S., Gao, Y., Zhao, J., Yang, T., Zhu, Y.: Prediction of sEMG-Based Tremor Joint Angle Using the RBF Neural Network. In: Proceeding of 2012 IEEE International Conference on Mechatronics and Automation, pp. 2103–2108 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Qingling Li
    • 1
  • Yu Song
    • 2
  • Zengguang Hou
    • 3
  • Bin Zhu
    • 1
  1. 1.Department of Mechanical EngineeringChina University of Mining & TechnologyBeijingChina
  2. 2.School of Electronic & Information EngineeringBeijing Jiaotong UniversityBeijingChina
  3. 3.State Key Laboratory of Management and Control for Complex SystemsInstitute of Automation, Chinese Academy of ScienceBeijingChina

Personalised recommendations