Abstract
This paper presents an effective classification scheme consisting of the rough set theory (RST)-based feature selection and the fuzzy least squares support vector machine (LS-SVM) classifier for the surface electromyographic (sEMG)-based motion classification. The wavelet packet transform (WPT) is exploited to decompose the four-class motion EMG signals to the non-overlapped sub-bands and the energy characteristic of each sub-band is adopted to form the original feature set. In order to reduce the computation complexity, the RST is utilized to get the reduction feature set without compromising classification accuracy. In the feature reduction phase, cluster separation index (CSI) is introduced to evaluate the performance of the proposed algorithm. In the sequel, the Fuzzy LS-SVM is constructed for the multi-class classification task. The RST-based feature selection is independent of the classifier design. Consequently the classification performance will vary with different classifiers. We make the comparison between the proposed classification scheme and the commonly used classification scheme, such as the combination of the principal component analysis (PCA)-based feature selection and the neural network (NN) classifier. The results of comparative experiments show that the diverse motions can be identified with high accuracy by the proposed scheme. Compared with other feature extraction and selection algorithms and classifiers, superior performance of the proposed classification scheme illustrates the potential of the SVM techniques combined with WPT and RST in EMG motion classification.
Similar content being viewed by others
References
Acir N (2006) A support vector machine classifier algorithm based on a perturbation method and its application to ECG beat recognition systems. Exp Syst Appl 31:150–158
Allison GT, Fujiwara T (2002) The relationship between EMG median frequency and low frequency band amplitude changes at different levels of muscle capacity. Clin Biomech 17(6):464–469
Chan FHY, Yang YS, Lam FK et al (2000) Fuzzy EMG classification for prosthesis control. IEEE Trans Rehabil Eng 8(3):305–311
Cheron G, Draye J-P, Bourgeios M et al (1996) A dynamic neural network identification of electromyography and arm trajectory relationship during complex movements. IEEE Trans Biomed Eng 43(5):552–558
Christodoulou CI, Pattichis CS (1995) A new technique for the classification and decomposition of EMG signals. IEEE Int Conf Neural Netw Proc (5):2303–2308
Dash M, Choi K, Scheuermann P et al (2002) Feature selection for clustering—a filter solution, in second IEEE international conference on data mining, pp 115–122
Englehart K, Hudgins B, Parker PA et al (1999) Classification of the myoelectric signal using time-frequency based representations. Med Eng Phys 21(6–7):431–438
Englehart K, Hudgins B, Parker PA (2001) A wavelet-based continuous classification scheme for multifunction myoelectric control. IEEE Trans Biomed Eng 48(3):302–311
Fukuda O, Tsuji T, Otsuka A et al (1998) An EMG-based rehabilitation aid for prosthesis control, in IEEE Int 7 Workshop on robot and human communication 214–219
Gestel TV, Suykens JAK., Baesens B et al (2004) Benchmarking least squares support vector machine classifiers. Mach Learn 54:5–32
Grzymala-Busse JW (2003) A comparison of three strategies to rule induction from data with numerical attributes. Electron Notes Theor Comput Sci 82(4):1–9
Han JS, Bang WC, Bien ZZ (2002) Feature set extraction algorithm based on soft computing techniques and its application to EMG pattern classification. Fuzzy Optim Decis Mak 1:269–286
Han JS, Bien Z, Bang WC (2000) New EMG pattern recognition based on soft computing techniques and its application to control of a rehabilitation robotic arm. in proceedings of 6th IIZUKA2000. Lizuka, Japan
Huang K and Aviyente S (2006) Information-theoretic wavelet packet subband selection for texture classification. Signal Processing, pp 1410–1420
Inan ZH, Kuntalp M (2007) A study on fuzzy C-means clustering-based systems in automatic spike detection. Comput Biol Med 37(8):1160–1166
Kang W-J, Shiu J-R, Cheng C-K et al (1995) The application of cepstral coefficients and maximum likelihood method in EMG pattern recognition. IEEE Trans Biomed Eng 42(8):777–785
Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97(1–2):273–324
Li K and Liu Y (2002) Rough set based attribute reduction approach in data mining. Proceedings of the first international conference on machine learning and cybernetics
Liu J, Yu D, Hu Q et al (2004) Granular entropy based hybrid knowledge reduction using uniform rough approximations. Proceedings of the third international conference on machine learning and cybernetics
Matsumura Y, Fukumi M, Akamatsu N et al (2004) Wrist EMG pattern recognition system by neural networks and multiple principal component analysis. Knowledge-Based Intelligent Information and Engineering Systems, Pt 1, Proceedings 3213:891–897
Nishikawa D, Yu W, Yokoi H et al (1999) EMG prosthetic hand controller discriminating ten motions using real-time learning method. In proceedings of the 1999 IEEE/RSJ international conference on intelligent robots and systems
Patrick J. Sparto MP, Enrique A. Barria, Jogikal M (2000) Jagadeesh wavelet and short-time fourier transform analysis of electromyography for detection of back muscle fatigue. IEEE Trans Rehabil Eng 8(3):433–436
Pawlak Z (1982) Rough set. Int J Comp Inf Sci 341–356
Rahime C, Yuksel O (2007) Comparison of FCM, PCA and WT techniques for classification ECG arrhythmias using artificial neural network. Expert Syst Appl 33:286–295
Roy A, Pal SK (2003) Fuzzy discretization of feature space for a rough set classifier. Pattern Recognit Lett 24(6):895–902
Schwenker F (2000) Hierarchical support vector machines for multi-class pattern recognition, in fourth international conference on knowledge-based intelligent engineering systems and allied technologies. Brighton, pp. 561–565
Shao Y, Chang C-H (2005) Wavelet transform to hybrid support vector machine and hidden Markov model for speech recognition. Circuits and systems, 2005. ISCAS 2005. IEEE International Symposium on, 2005 4:3833–3836
Soares A, Andrade A, Lamounier E et al (2003) The development of a virtual myoelectric prosthesis controlled by an EMG pattern recognition system based on neural networks. J Intell Inf Sys 21(2):127–141
Soares AB, Berzin F and Andrade A (2002a) Power spectrum estimation of EMG signals via Chirp-Z transform, in XIV congress of the International Society of Electrophysiology and Kinesiology, Vienna, pp 164–165
Soares AB, Veiga ACP, Andrade AdO et al (2002) Functional languages in signal processing applied to prosthetic limb. Syst Anal Model Simul 9(42):1377–1389
Suykens JAK. and Vandewalle J (1999) Multiclass least squares support vector machines, in Proceedings of the international joint conference on neural networks (IJCNN’99). Washington, pp 900–903
Tsujinishi D, Abe S (2003) Fuzzy least squares support vector machines for multiclass problems. Neural Netw 16(5–6):785–92
Vapnik V (1998) The support vector method of function estimation, in international workshop on advanced black-box techniques for nonlinear modeling: theory and applications with time-series prediction competition. Kluwer, Boston, pp 55–85
Wang X and Wu C (2004) Using membership functions to improve multiclass SVM. ICSP’04 Proceeding
Wickerhauser MV (1994) Adapted wavelet analysis from theory to software wellesley. AK Peters Ltd, MA
Wu C, Li M, Han Z et al (2004) Discretization algorithms of rough sets using clustering, in proceedings of the 2004 IEEE international conference on robotics and biomimetics. Shenyang
Wu M, Qie J, Gu Q (2003) Wavelet package-neural network based on rough set diesel engine vibration signal identification model. IEEE Int Conf Neural Netw Signal Process 1:185–190
Xu Z and Xiao S (1999) Digital filter design for peak detection of surface EMG. J Electromyogra Kinesiol
Yu D, Hu Q and Bao W (2003) Combining multiple neural networks for classification based on rough set reduction. IEEE international conference on neural networks and signal processing, pp 543–548
Yu W, Yamaguchi H, Yokov H et al (2002) EMG automatic switch for FES control for hemiplegics using artificial neural network. Rob Auton Syst 40:213–224
Ziarko W (1993) The discovery, analysis and representation of data dependencies in databases. Knowl discov databases pp 213–228
Acknowledgments
This work is supported by the grants from 973 Project (2005CB724303).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yan, Z., Wang, Z. & Xie, H. Joint application of rough set-based feature reduction and Fuzzy LS-SVM classifier in motion classification. Med Biol Eng Comput 46, 519–527 (2008). https://doi.org/10.1007/s11517-007-0291-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-007-0291-x