Motion classification of EMG signals based on wavelet packet transform and LS-SVMs ensemble

Abstract

This paper presents an effective method for motion classification using the surface electromyographic (sEMG) signal collected from the forearm. Given the nonlinear and time-varying nature of EMG signal, the wavelet packet transform (WPT) is introduced to extract time-frequency joint information. Then the multi-class classifier based on the least squares support vector machine (LS-SVM) is constructed and verified in the various motion classification tasks. The results of contrastive experiments show that different motions can be identified with high accuracy by the presented method. Furthermore, compared with other classifiers with different features, the performance indicates the potential of the SVM techniques combined with WPT in motion classification.

Keywords

pattern recognition / wavelet packet transform / least squares support vector machine / surface electromyographic signal / neural network / separability

References

[1] Fukuda O, Tsuji T, Otsuka A et al. An EMG-based rehabilitation aid for prosthesis control[C]. In: Proceedings of 1998 IEEE International Workshop on Robot and Human Communication. Takamatsu, Japan, 1998. 214–219.

[2] Han J S, Bien Z Z, Bang W C. New EMG pattern recognition based on soft computing techniques and its application to control of a rehabilitation robotic arm[C]. In: Proc of 6th Int Conf on Soft Computing, Lizuka 2000. Lizuka, Japan, 2000. 890–897.

[3] Soares A., Andrade A., Lamounier E., et al. The development of a virtual myoelectric prosthesis controlled by an EMG pattern recognition system based on neural networks[J]. Journal of Intelligent Information Systems, 2003, 21(2): 127-141.

[4] Englehart K., Hudgins B., Parker P. A. Time-frequency representation for classification of the transient myoelectric signal[C] Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1998, 5 2627-2630.

[5] Hudgins B., Parker P. A., Scott R. N. A new strategy for multifunction myoelectric control[J]. IEEE Transactions on Biomedical Engineering, 1993, 40(1): 82-94.

[6] Englehart K., Hudgins B., Parker P. A., et al. Classification of the myoelectric signal using time-frequency based representations[J]. Medical Engineering and Physics, 1999, 21(6/7): 431-438.

[7] Bang W.-C., Han J.-S., Zenn B. Z. Feature set extraction algorithm based on soft computing techniques and its application to EMG pattern classification[J]. Fuzzy Optimization and Decision Making, 2002, 1 269-286.

[8] Nishikawa D., Yu W., Yokoi H., et al. EMG prosthetic hand controller discriminating ten motions using real-time learning method[C] Proceedings of the 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems, 1999, 3 1592-1597.

[9] Chan F. H. Y., Yang Y. S., Lam F. K., et al. Fuzzy EMG classification for prosthesis control[J]. IEEE Transactions on Rehabilitation Engineering, 2000, 8(3): 305-311.

[10] Yang Y. S., Lam F. K., Chan F. H. Y., et al. A new fuzzy approach for pattern recognition with application to EMG classification[C] Proceedings of IEEE International Conference on Neural Networks, 1996, 2 1109-1114.

[11] Hu X., Wang Z. Classification of surface EMG signal using relative wavelet packet energy[J]. Computer Methods and Programs in Biomedicine, 2005, 79 189-195.

[12] Saevarsson Gdmundur, Sveinsson Johannes R, Benediktsson Jon Atli. Wavelet-package transformation as a preprocessor of EEG waveforms for classification[C]. In: Proc of 19th Int Conf IEEE/EMBS. Chicago, USA, 1997. 1305–1308.

[13] Tikkanen P. E. Nonlinear wavelet and wavelet packet denoising of electrocardiogram signal[J]. Biological Cybernetics, 1999, 30(4): 259-267.

[14] Weston J, Watkins C. Multi-Class Support Vector Machines [EB]. http://www.kyb.tuebingen.mpg.de/bs/people/ weston/ESSAN. PS, 1998.

[15] Kalatzis I., Piliouras N., Ventouras E., et al. Design and implementation of an SVM-based computer classification system for discriminating depressive patients from healthy controls using the P600 component of ERP signals[J]. Computer Methods and Programs in Biomedicine, 2004, 75(1): 11-22.

[16] Wu Q., Shen X., Li Y. Classifying the multiplicity of the EEG source models using sphere-shaped support vector machines[J]. IEEE Transactions on Magnetics, 2005, 41(5): 1912-1915.

[17] Hubert Dietl, Stephan Weiss. Detection of cochlear hearing loss applying wavelet packets and support vector machines [C]. In: Proceedings of the 38th Asilomar Conference on Signals, Systems, and Computers. Pacific Grove, USA, 2004. 1575–1579.

[18] Suykens J. A. K., Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3): 293-300.

[19] Weston J, Watkins C. Support Vector Machines for Multi-Class Pattern Recognition[DB]. http://www.kyb.tuebingen.mpg. de/bs/people/weston/ESSAN. PS, 1998.

[20] Friedhelm Schwenker. Hierarchical support vector machines for multi-class pattern recognition[C]. In: Proceedings of the Fourth International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies. Brighton, UK, 2000. 561–565.

[21] Suykens J A K, Vandewalle J. Multi-class least squares support vector machines[C]. In: Proc of the Int Joint Conf on Neural Networks (IJCNN’99). Washington DC, USA, 1999. 900–903.

[22] Yan Z., Wang Z., Xie H. The application of mutual information based feature selection and fuzzy LS-SVM based classifier in motion classification[J]. Computer Methods and Programs in Biomedicine, 2008, 90(3): 275-284.

[23] Lamounier E, Soares Ab, Andrade Ao et al. Power spectrum estimation of EMG signals via chirp-Z transform[C]. In: Proceedings of XIVth Congress of the International Society of Electrophysiology and Kinesiology. Vienna, Austria, 2002. 164–165.

[24] Alcimar Barbosa S., Antonio Clandio Paschoarelli V., Adriano De Oliveria A., et al. Functional languages in signal processing applied to prosthetic limb[J]. Systems Analysis Modelling Simulation, 2002, 42(9): 1377-1389.

[25] Englehart K., Hudgins B., Parker P. A. A wavelet-based continuous classification scheme for multifunction myoelectric control[J]. IEEE Transactions on Biomedical Engineering, 2001, 48(3): 302-311.

[26] Matsumura Y., Fukumi M., Akamatsu N., et al. Wrist EMG pattern recognition system by neural networks and multiple principal component analysis[C] Proceedings of the 8th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, 2004, 3213 891-897.

[27] Suykens J. A. K., van Gestel T., Vandewalle J., et al. A support vector machine formulation to PCA analysis and its kernel version[J]. IEEE Transactions on Neural Networks, 2003, 14(2): 447-450.

[28] Aapo H. Fast and robust fixed-point algorithms for independent component analysis[J]. IEEE Transactions on Neural Networks, 1999, 10(3): 626-634.