Abstract
In the study, an efficient method to perform supervised classification of surface electromyogram (EMG) signals is proposed. The method is based on the choice of a relevant representation space and its optimisation with respect to a training set. As EMG signals are the summation of compact-support waveforms (the motor unit action potentials), a natural tool for their representation is the discrete dyadic wavelet transform. The feature space was thus built from the marginals of a discrete wavelet decomposition. The mother wavelet was designed to minimise the probability of classification error estimated on the learning set (supervised classification). As a representative example, the method was applied to simulate surface EMG signals generated by motor units with different degrees of short-term synchronisation. The proposed approach was able to distinguish surface EMG signals with degrees of synchronisation that differed by 10%, with a misclassification rate of 8%. The performance of a spectral-based classification (error rate approximately 33%) and of the classification with Daubechies wavelet (21%) was significantly poorer than with the proposed wavelet optimisation. The method can be used for a number of different application fields of surface EMG classification, as the feature space is adapted to the characteristics of the signal that discriminate between classes.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Andreassen, S., andArendt-Nielsen, L. (1987): ‘Muscle fibre conduction velocity in motor units of the human anterior tibial muscle: a new size principle parameter’,J. Physiol.,391, pp. 561–571
Boostani, R., andMoradi, M.H. (2003): ‘Evaluation of the forearm EMG signal features for the control of a prosthetic hand’,Physiol. Meas.,24, pp. 309–319
Burrus, C.S., Gopinath, R.A. andGuo, H. (1997): ‘Introduction to wavelets and wavelet transforms’ (Prentice Hall, 1997), pp. 53–66
Chan, A., Englehart, K., andHudgins, B. (2004): ‘Automatic speech recognition using myoelectric signals’. Proc. XV ISEK Congress, Boston, USA.
Davy, M., Doncarli, C., andBoudreaux, F. (2001): ‘Improved optimisation of time-frequency based classifiers’,IEEE Signal Proc. Lett.,8, pp. 52–57
Duchene, J., andLamotte, T. (2001): ‘Surface electromyography analysis in long-term recordings: application to head rest comfort in cars’,Ergonomics,44, pp. 313–327
Duda, R., Hart, P., andStork, D. (2001): ‘Pattern classification’ (Wiley Interscience, 2001).
Englehart, K., Hudgins, B., andParker, P.A. (2001): ‘A wavelet-based continuous classification scheme for multifunction myoelectric control’,IEEE Trans. Biomed. Eng.,48, pp. 302–311
Fang, J., Agarwal, G.C., andShahani, B.T. (1999): ‘Decomposition of multiunit electromyographic signals’,IEEE Trans. Biomed. Eng.,46, pp. 685–697.
Farina, D., Fortunato, E., andMerletti, R. (2000): ‘Non-invasive estimation of motor unit conduction velocity distribution using linear electrode arrays’,IEEE Trans. Biomed. Eng.,47, pp. 380–388
Farina, D., andMerletti, R. (2001): ‘A novel approach for precise simulation of the EMG signal detected by surface electrodes’,IEEE Trans. Biomed. Eng.,48, pp. 637–646
Farina, D., Fosci, M., andMerletti, R. (2002): ‘Motor unit recruitment strategies investigated by surface EMG variables’,J. Appl. Physiol. 92, pp. 235–247
Farina, D., Merletti, R., andEnoka, R.M. (2004): ‘The extraction of neural strategies from the surface EMG’,J. Appl. Physiol.,96, pp. 486–495
Farmer, S.F., Halliday, D.M., Conway, B.A., Stephens, J.A., andRosenberg, J.R. (1997): ‘A review of recent applications of cross-correlation methodologies to human motor unit recording’,J. Neurosci. Methods,74, pp. 175–187
Fuglevand, A.J., Winter, D.A., andPatla, A.E. (1993): ‘Models of recruitment and rate coding organization in motor-unit pools’,J. Neurophysiol. 70, pp. 2470–2488
Gazzoni, M., Farina, D., andMerletti, R. (2004): ‘A new method for the extraction and classification of single motor unit action potentials from surface EMG signals’,J. Neurosci. Methods,136, pp. 165–177
Hu, X., andNenov, V. (2004): ‘Multivariate AR modeling of electromyography for the classification of upper arm movements’,Clin. Neurophysiol.,115, pp. 1276–1287
Hudgins, B., Parker, P., andScott, R.N. (1993): ‘A new strategy for multifunction myoelectric control’,IEEE Trans. Biomed. Eng.,40, pp. 82–94
Huppertz, H.J., Disselhorst-Klug, C., Silny, J., Rau, G., andHeimann, G. (1997): ‘Diagnostic yield of noninvasive high spatial resolution electromyography in neuromuscular diseases’,Muscle Nerve,20, pp. 1360–1370
Khalil, M., andDuchene, J. (2000): ‘Uterine EMG analysis: a dynamic approach for change detection and classification’,IEEE Trans. Biomed. Eng.,47, pp. 748–756
Kleine, B.U., Stegeman, D.F., Mund, D. andAnders, C. (2001): ‘Influence of motoneuron firing synchronization on SEMG characteristics in dependence of electrode position’,J. Appl. Physiol.,91, pp. 1588–1599
Korosec, D. (1999): ‘Analysis of one-dimensional signals by processing of their time-frequency representations’. PhD thesis, Université de Maribor and Université de Nantes
Lawton, W. (1990): ‘Tight frames of compactly supported affine wavelets’,J. Math. Phys.,31, pp. 1898–1901
Lawton, W. (1991): ‘Necessary and sufficient conditions for constructing orthonormal wavelet base’,J. Math. Phys.,32, pp. 1440–1443
Lindstrom, L. andMagnusson, R. (1977): ‘Interpretation of myoelectric power spectra: a model and its applications’.Proc. IEEE,65, pp. 653–662
Lucas, M.F., Doncarli, C., Hitti, E., andDechamps, N. (2002): Wavelet optimization for olassification’. Proc. ICASSP'02, pp. 1249–1251
Mallat, S. (1989): ‘A theory for multiresolution signal decomposition: the wavelet representation’,IEEE Trans. Pattern Anal. Mach. Intell.,7, pp. 674–693
Mallat, S. (1998): ‘A wavelet tour of signal processing’, (Academic Press, 1998).
Merletti, R., andParker, P. (2004): ‘Electromyography: physiology, engineering and non-invasive applications’, (Wiley-IEEE Press, 2004).
Parker, P.A., andScott, R.N. (1986): ‘Myoelectric control of prostheses’,Crit. Rev. Biomed. Eng.,13, pp. 283–310
Selesnick, I.W. (1997): ‘Maple and the parameterization of orthogonal wavelet bases’. http://taco.poly.edu/selesi/theta2h/
Semmler, J.G., andNordstrom, M.A. (1998): ‘Motor unit discharge and force tremor in skill- and strength-trained individuals’Exp. Brain Res.,119, pp. 27–38
Semmler, J.G. (2002): ‘Motor unit synchronization and neuromuscular performance’,Exerc. Sport Sci. Rev.,30, pp. 8–14
Semmler, J.G., Sale, M.V., Meyer, F.G., andNordstrom, M.A. (2004): ‘Motor-unit coherence and its relation with synchrony are influenced by training’,J. Neurophysiol.,92, pp. 3320–3331
Ungureanu, M., Strungaru, R., andLazarescu, V. (1998): ‘Myoelectric signal classification using neural networks’,Biomed. Tech. (Berl.).43, pp. 87–90
Vaidyanathan, P.P. (1996): ‘Multirate systems and filter banks’ (Wellesley-Cambridge Press, 1996).
Weytjens, J.L. andVan Steenberghe, D. (1984): ‘The effects of motor unit synchronization on the power spectrum of the electromyogram’,Biol. Cybern.,51, pp. 71–77
Yao, W., Fuglevand, R.J., andEnoka, R.M. (2000): ‘Motor-unit synchronization increases EMG amplitude and decreases force steadiness of simulated contractions’,J. Neurophysiol.,83, pp. 441–452
Author information
Authors and Affiliations
Corresponding author
Additional information
An erratum to this article is available at http://dx.doi.org/10.1007/s11517-007-0208-8.
Rights and permissions
About this article
Cite this article
Maitrot, A., Lucas, M.F., Doncarli, C. et al. Signal-dependent wavelets for electromyogram classification. Med. Biol. Eng. Comput. 43, 487–492 (2005). https://doi.org/10.1007/BF02344730
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02344730