Forearm EMG Signal Classification Based on Singular Value Decomposition and Wavelet Packet Transform Features

Abstract:

The myoelectric signal (MES) with broad applications in various areas especially in prosthetics and myoelectric control, is one of the biosignals utilized in helping humans to control equipments. In this paper, a technique for feature extraction of forearm electromyographic (EMG) signals using wavelet packet transform (WPT) and singular value decomposition (SVD) is proposed. In the first step, the WPT is employed to generate a wavelet decomposition tree from which features are extracted. In the second step, an algorithm based on singular value decomposition (SVD) method is introduced to compute the feature vectors for every hand motion. This technique can successfully identify eight hand motions including forearm pronation, forearm supination, wrist flexion, wrist abduction, wrist adduction, chuck grip, spread fingers and rest state. These motions can be obtained by measuring the surface EMG signal through sixteen electrodes mounted on the pronator and supinator teres, flexor digitorum, sublimas, extensor digitorum communis, and flexor and extensor carpi ulnaris. Moreover, through quantitative comparison with other feature extraction methods like entropy concept in this paper, SVD method has a better performance. The results showed that proposed technique can achieve a classification recognition accuracy of over 96% for the eight hand motions.

• Periodical: Advanced Materials Research (Volumes 433-440)
• Pages: 912-916
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.433-440.912
• Online since: January 2012
• Authors: Mohammad Karimi
• Keywords: Electromyographic (EMG) Signals, Entropy Concept, Feature Extraction, Pattern Recognition, Singular Value Decomposition (SVD), Wavelet Packet Transform (WPT)

References

[1] M. Yoshikawa, M. Mikawa, and K. Tanaka, Real-timehand motion estimation using EMG signals with supportvector machines, SICE ICASE International JointConference, Bexco, Busan, Korea, pp.593-598‏, Oct. (2006).

DOI: 10.1109/sice.2006.315553

[2] J. Chu, I. Moon, Y. Lee, S. Kim, M. Mun, A supervised feature projection based real-time EMG pattern recognition for multifunction myoelectric hand control, IEEE/ASME Transactions onMechatronics, vol. 12, no. 3, pp.282-290, ‏ (2007).

DOI: 10.1109/tmech.2007.897262

[3] J. Zhao, L. Jiang, H. Cai, H. Liu, and G. Hirzinger, A novel EMG motion pattern classifier based on wavelet transform and nonlinear analysis method, Robotics and Biomimetics, pp.1494-1499‏, (2006).

DOI: 10.1109/robio.2006.340150

[4] J. Chu, I. Moon, and M. Mun, A real-time EMG pattern recognition system based on linear-nonlinear feature projection for a multifunction myoelectric hand, IEEE Transactions on Biomedical Engineer, vol. 53, no. 11, pp.2232-2239, (2006).

DOI: 10.1109/tbme.2006.883695

[5] R. N. Khushaba, A. Al-Jumaily, and A. Al Ani, Novel feature extraction method based on fuzzy entropy and wavelet packet transform for myoelectric control, Communication and Information Technologies, pp.352-357, (2007).

DOI: 10.1109/iscit.2007.4392044

[6] Park, S.H. and Lee, S.P., EMG pattern recognition based on artificial intelligence techniques, IEEE Transactions on Rehabilitation Engineering, VOL. 6, NO. 4 (1998).

[7] Englehart, K., Hudgins, B., Parker, P.A., Stevenson, M., Classification of the myoelectricn signal using time–frequency based representations, Med. Eng. Phys., VOL. 21, p.431–438, (1999).

DOI: 10.1016/s1350-4533(99)00066-1

[8] Englehart, K., Hudgins, B., and Parker, P.A., A wavelet-based continuous classification scheme for multifunction myoelectric control, IEEE Transactions on Biomedical Engineering, VOL. 48, NO. 3, p.302–311, (2001).

DOI: 10.1109/10.914793

[9] K. Englehart, and B. Hudgins, A robust, real time control scheme for multifunction myoelectric control, IEEE Transactions on Biomedical Engineering, VOL. 50, NO. 7, (2003).

DOI: 10.1109/tbme.2003.813539