Movement Identification Based on Transient sEMG for Control of Prosthesis

Abstract:

Researches on surface electromyography (sEMG) for upper-limb prosthesis control have been going on for several years. Most published studies on prosthesis usually use the steady-state sEMG or the transient sEMG for identification. However, the transient sEMG is less stable than steady-state sEMG. The nonstationarity in transient sEMG greatly affects the performance of myoelectric control. In this paper, we propose a method based on sparse representation to capture the characteristics of transient sEMG to identify movements. Experiment results show the proposed method extracts the variations in transient sEMG activity from different movements effectively. The proposed feature achieves a satisfactory classification rate, which outperforms the other features.

• Periodical: Advanced Materials Research (Volumes 971-973)
• Pages: 1651-1654
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.971-973.1651
• Online since: June 2014
• Authors: Shuai Ding*, Liang Wang, Zhan Peng Sun, Wei Jin Gao, Shou Long Fang
• Keywords: Feature Extraction, Sparse Representation, Temporal MMV Sparse Bayesian Learning (T-MSBL), Transient Surface Electromyography (sEMG)

References

[1] R. Merletti, M. Aventaggiato, A. Botter, A. Holobar, H. Marateb and T. M. Vieira. Advances in surface EMG: recent progress in detection and processing techniques. Critical Reviews™ in Biomedical Engineering, Vol. 38 (2010), pp.305-311.

DOI: 10.1615/critrevbiomedeng.v38.i4.10

[2] L. J. Hargrove, K. Englehart and B. Hudgins. A Comparison of Surface and Intramuscular Myoelectric Signal Classification. IEEE Trans. Biomed. Eng., Vol. 54 (2007), pp.847-853.

DOI: 10.1109/tbme.2006.889192

[3] B. Hudgins, P. Parker and R. N. Scott. A new strategy for multifunction myoelectric control. IEEE Trans. Biomed. Eng., Vol. 40 (1993), pp.82-94.

DOI: 10.1109/10.204774

[4] X. Chen, X. Zhu and D. Zhang. A discriminant bispectrum feature for surface electromyogram signal classification. Med. Eng. Phys., Vol. 32 (2010), pp.126-135.

DOI: 10.1016/j.medengphy.2009.10.016

[5] M. A. Oskoei and H. Hu. Support vector machine­based classification scheme for myoelectric control applied to upper limb. IEEE Trans. Biomed. Eng., Vol. 55 (2008), p.1956-(1965).

DOI: 10.1109/tbme.2008.919734

[6] S. Bitzer and P. van der Smagt. Learning EMG control of a robotic hand: towards active prostheses, in IEEE International Conference on Robotics and Automation (ICRA) (IEEE Press, Orlando, FL, 2006), pp.2819-2823.

DOI: 10.1109/robot.2006.1642128

[7] T. Lorrain, N. Jiang and D. Farina. Influence of the training set on the accuracy of surface EMG classification in dynamic contractions for the control of multifunction prostheses. J. NeuroEng. Rehabil., Vol. 8 (2011).

DOI: 10.1186/1743-0003-8-25

[8] D. L. Donoho and M. Elad. Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ1 minimization. Proceedings Nat. Acad. Sci., Vol. 100 (2003), pp.2197-2202.

DOI: 10.1073/pnas.0437847100

[9] D. Yang, J. Zhao, L. Jiang and H. Liu. Dynamic hand motion recognition based on transient and steady-state EMG signals. International Journal of Humanoid Robotics, Vol. 9 (2012).

DOI: 10.1142/s0219843612500077

[10] Z. Zhang and B. Rao. Sparse signal recovery with temporally correlated source vectors using sparse Bayesian learning. IEEE J. Sel. Topics Signal Process., Vol. 5 (2011), pp.912-926.

DOI: 10.1109/jstsp.2011.2159773

[11] M. E. Tipping. Sparse Bayesian learning and the relevance vector machine. J. Mach. Learn. Res., Vol. 1 (2001), pp.211-244.

[12] D. L. Donoho. Compressed sensing. IEEE Trans. Inf. Theory, Vol. 52 (2006), pp.1289-1306.