Journal of Biomedical Physics and Engineering

Current Issue

By Issue

By Author

By Subject

Author Index

Keyword Index

About Journal

Aims and Scope

Staff Members

Editorial Board

Publication Ethics

Indexing and Abstracting

Related Links

FAQ

Peer Review Process

News

Comparative Analysis of Wavelet-based Feature Extraction for Intramuscular EMG Signal Decomposition

Document Type : Original Research

Authors

Department of Medical Physics and Engineering, Shiraz University of Medical Sciences, Shiraz, Iran

Abstract

Background: Electromyographic (EMG) signal decomposition is the process by which an EMG signal is decomposed into its constituent motor unit potential trains (MUPTs). A major step in EMG decomposition is feature extraction in which each detected motor unit potential (MUP) is represented by a feature vector. As with any other pattern recognition system, feature extraction has a significant impact on the performance of a decomposition system. EMG decomposition has been studied well and several systems were proposed, but feature extraction step has not been investigated in detail.Objective: Several EMG signals were generated using a physiologically-based EMG signal simulation algorithm. For each signal, the firing patterns of motor units (MUs) provided by the simulator were used to extract MUPs of each MU. For feature extraction, different wavelet families including Daubechies (db), Symlets, Coiflets, bi-orthogonal, reverse bi-orthogonal and discrete Meyer were investigated. Moreover, the possibility of reducing the dimensionality of MUP feature vector is explored in this work. The MUPs represented using wavelet-domain features are transformed into a new coordinate system using Principal Component Analysis (PCA). The features were evaluated regarding their capability in discriminating MUPs of individual MUs. Results: Extensive studies on different mother wavelet functions revealed that db2, coif1, sym5, bior2.2, bior4.4, and rbior2.2 are the best ones in differentiating MUPs of different MUs. The best results were achieved at the 4th detail coefficient. Overall, rbior2.2 outperformed all wavelet functions studied; nevertheless for EMG signals composed of more than 12 MUPTs, syms5 wavelet function is the best function. Applying PCA slightly enhanced the results.

Keywords

References
  1. Parsaei H, Stashuk DW, Rasheed S, Farkas C, Hamilton-Wright A. Intramuscular EMG signal decomposition. Crit Rev Biomed Eng. 2010;38:435-65. doi.org/10.1615/CritRevBiomedEng.v38.i5.20. PubMed PMID: 21175408.
  2. McGill KC, Cummins KL, Dorfman LJ. Automatic decomposition of the clinical electromyogram. Biomedical Engineering, IEEE Transactions on. 1985;(7):470-7.
  3. McGill KC, Lateva ZC, Marateb HR. EMGLAB: an interactive EMG decomposition program. J Neurosci Methods. 2005;149:121-33. doi.org/10.1016/j.jneumeth.2005.05.015. PubMed PMID: 16026846.
  4. Katsis CD, Goletsis Y, Likas A, Fotiadis DI, Sarmas I. A novel method for automated EMG decomposition and MUAP classification. Artif Intell Med. 2006;37:55-64. doi.org/10.1016/j.artmed.2005.09.002. PubMed PMID: 16377160.
  5. Nikolic M, Krarup C. EMGTools, an adaptive and versatile tool for detailed EMG analysis. IEEE Trans Biomed Eng. 2011;58:2707-18. doi.org/10.1109/TBME.2010.2064773. PubMed PMID: 20699205.
  6. Christodoulou CI, Pattichis CS. Unsupervided pattern recognition for the classification of EMG signals. IEEE Trans Biomed Eng. 1999;46:169-78. doi.org/10.1109/10.740879. PubMed PMID: 9932338.
  7. Gut R, Moschytz GS. High-precision EMG signal decomposition using communication techniques. Signal Processing, IEEE Transactions on. 2000;48:2487-94. doi.org/10.1109/78.863051.
  8. Nandedkar SD, Barkhaus PE, Charles A. Multi-motor unit action potential analysis (MMA). Muscle Nerve. 1995;18:1155-66. doi.org/10.1002/mus.880181012. PubMed PMID: 7659110.
  9. Parsaei H. EMG signal decomposition using motor unit potential train validity .[Thesis]. University of Waterloo: Waterloo, Ontario, Canada; 2011.
  10. Stashuk D. EMG signal decomposition: how can it be accomplished and used? J Electromyogr Kinesiol. 2001;11:151-73. doi.org/10.1016/S1050-6411(00)00050-X. PubMed PMID: 11335147.
  11. Stashuk DW. Decomposition and quantitative analysis of clinical electromyographic signals. Med Eng Phys. 1999;21:389-404. doi.org/10.1016/S1350-4533(99)00064-8 . PubMed PMID: 10624736.
  12. Hassoun MH, Wang C, Spitzer AR. NNERVE: neural network extraction of repetitive vectors for electromyography--Part I: Algorithm. IEEE Trans Biomed Eng. 1994;41:1039-52. doi.org/10.1109/10.335842. PubMed PMID: 8001993.
  13. Nikolic M, Sorensen J, Dahl K, Krarup C, editors. Detailed analysis of motor unit activity. Engineering in Medicine and Biology Society, 1997. Proceedings of the 19th Annual International Conference of the IEEE; 1997: IEEE. doi.org/10.1109/iembs.1997.756600.
  14. Christodoulou CI, Pattichis CS, editors. A new technique for the classification and decomposition of EMG signals. Neural Networks, 1995. Proceedings., IEEE International Conference on; 1995: IEEE. doi.org/10.1109/icnn.1995.487720.
  15. Haas W, Meyer M. An automatic EMG decomposition system for routine clinical examination and clinical research-ARTMUP. Amsterdam, the Netherlands: Elsevier Science; 1989. p. 67-81.
  16. Koch V, Loeliger H-A, editors. EMG signal decomposition by loopy belief propagation. Acoustics, Speech, and Signal Processing, 2005 Proceedings(ICASSP’05) IEEE International Conference on; 2005. doi: 10.1109/icassp.2005.1416324*.
  17. Nawab SH, Wotiz RP, De Luca CJ. Multi-receiver precision decomposition of intramuscular EMG signals. Conf Proc IEEE Eng Med Biol Soc. 2006;1:1252-5. doi.org/10.1109/iembs.2006.260320. PubMed PMID: 17945629.
  18. Nawab SH, Wotiz RP, De Luca CJ. Decomposition of indwelling EMG signals. J Appl Physiol (1985). 2008;105:700-10. doi.org/10.1152/japplphysiol.00170.2007. PubMed PMID: 18483170. PubMed PMCID: 2519944.
  19. Erim Z, Lin W. Decomposition of intramuscular EMG signals using a heuristic fuzzy expert system. IEEE Trans Biomed Eng. 2008;55:2180-9. doi.org/10.1109/TBME.2008.923915. PubMed PMID: 18713687.
  20. Parsaei H, Stashuk DW. EMG signal decomposition using motor unit potential train validity. IEEE Trans Neural Syst Rehabil Eng. 2013;21:265-74. doi.org/10.1109/TNSRE.2012.2218287. PubMed PMID: 23033332.
  21. Katsis CD, Exarchos TP, Papaloukas C, Goletsis Y, Fotiadis DI, Sarmas I. A two-stage method for MUAP classification based on EMG decomposition. Comput Biol Med. 2007;37:1232-40. doi.org/10.1016/j.compbiomed.2006.11.010. PubMed PMID: 17208215.
  22. Gerber A, Studer RM, de Figueiredo RJ, Moschytz GS. A new framework and computer program for quantitative EMG signal analysis. IEEE Trans Biomed Eng. 1984;31:857-63. doi.org/10.1109/TBME.1984.325248. PubMed PMID: 6549305.
  23. Loudon GH, Jones NB, Sehmi AS. New signal processing techniques for the decomposition of EMG signals. Med Biol Eng Comput. 1992;30:591-9. doi.org/10.1007/BF02446790. PubMed PMID: 1297013.
  24. Stalberg E, Andreassen S, Falck B, Lang H, Rosenfalck A, Trojaborg W. Quantitative analysis of individual motor unit potentials: a proposition for standardized terminology and criteria for measurement. J Clin Neurophysiol. 1986;3:313-48. doi.org/10.1097/00004691-198610000-00003. PubMed PMID: 3332279.
  25. Florestal JR, Mathieu PA, Malanda A. Automated decomposition of intramuscular electromyographic signals. IEEE Trans Biomed Eng. 2006;53:832-9. doi.org/10.1109/TBME.2005.863893. PubMed PMID: 16686405.
  26. Stashuk D, de Bruin H. Automatic decomposition of selective needle-detected myoelectric signals. IEEE Trans Biomed Eng. 1988;35:1-10. doi.org/10.1109/10.1330. PubMed PMID: 3338806.
  27. Florestal JR, Mathieu PA, McGill KC. Automatic decomposition of multichannel intramuscular EMG signals. J Electromyogr Kinesiol. 2009;19:1-9. doi.org/10.1016/j.jelekin.2007.04.001. PubMed PMID: 17513128.
  28. Zennaro D, Läubli T, Wellig P, Krebs D, Schnoz M, Klipstein A, et al. A method to test reliability and accuracy of the decomposition of multi-channel long-term intramuscular EMG signal recordings. International journal of industrial ergonomics. 2002;30:211-24. doi.org/10.1016/S0169-8141(02)00126-9.
  29. Zennaro D, Wellig P, Koch VM, Moschytz GS, Laubli T. A software package for the decomposition of long-term multichannel EMG signals using wavelet coefficients. IEEE Trans Biomed Eng. 2003;50:58-69. doi.org/10.1109/TBME.2002.807321. PubMed PMID: 12617525.
  30. Wellig P, Moschytz GS, editors. Analysis of wavelet features for myoelectric signal classification. Electronics, Circuits and Systems, 1998 IEEE International Conference on; 1998: IEEE. doi.org/10.1109/icecs.1998.813946.
  31. Yamada R, Ushiba J, Tomita Y, Masakado Y, editors. Decomposition of electromyographic signal by principal component analysis of wavelet coefficients. Biomedical Engineering, 2003. IEEE EMBS Asian-Pacific Conference on; 2003: IEEE. doi.org/10.1109/apbme.2003.1302612.
  32. Ren X, Huang H, Deng L, editors. MUAP Classification Based on Wavelet Packet and Fuzzy Clustering Technique. Bioinformatics and Biomedical Engineering, 2009. ICBBE 2009. 3rd International Conference on; 2009: IEEE. doi.org/10.1109/icbbe.2009.5163091.
  33. Rasheed S, Stashuk DW, Kamel MS. A hybrid classifier fusion approach for motor unit potential classification during EMG signal decomposition. IEEE Trans Biomed Eng. 2007;54:1715-21. doi.org/10.1109/TBME.2007.892922. PubMed PMID: 17867366.
  34. Li D, Pedrycz W, Pizzi NJ. Fuzzy wavelet packet based feature extraction method and its application to biomedical signal classification. IEEE Trans Biomed Eng. 2005;52:1132-9. doi.org/10.1109/TBME.2005.848377. PubMed PMID: 15977743.
  35. LeFever RS, De Luca CJ. A procedure for decomposing the myoelectric signal into its constituent action potentials--Part I: Technique, theory, and implementation. IEEE Trans Biomed Eng. 1982;29:149-57. doi.org/10.1109/TBME.1982.324881. PubMed PMID: 7084948.
  36. Etawil H, Stashuk D. Resolving superimposed motor unit action potentials. Med Biol Eng Comput. 1996;34:33-40. doi.org/10.1007/BF02637020. PubMed PMID: 8857310.
  37. De Figueiredo R, Gerber A. Separation of superimposed signals by a cross-correlation method. Acoustics, Speech and Signal Processing, IEEE Transactions on. 1983;31:1084-9. doi.org/10.1109/TASSP.1983.1164215.
  38. Hamid Nawab S, Wotiz R, De Luca CJ. Improved resolution of pulse superpositions in a knowledge-based system EMG decomposition. Conf Proc IEEE Eng Med Biol Soc. 2004;1:69-71. doi.org/10.1109/iembs.2004.1403092. PubMed PMID: 17271605.
  39. Marateb HR, McGill KC. Resolving superimposed MUAPs using particle swarm optimization. IEEE Trans Biomed Eng. 2009;56:916-9. doi.org/10.1109/TBME.2008.2005953. PubMed PMID: 19272923. PubMed PMCID: 2673334.
  40. Florestal JR, Mathieu PA, Plamondon R. A genetic algorithm for the resolution of superimposed motor unit action potentials. IEEE Trans Biomed Eng. 2007;54:2163-71. doi.org/10.1109/TBME.2007.894977. PubMed PMID: 18075032.
  41. Hamilton-Wright A, Stashuk DW. Physiologically based simulation of clinical EMG signals. IEEE Trans Biomed Eng. 2005;52:171-83. doi.org/10.1109/TBME.2004.840501. PubMed PMID: 15709654.
  42. Person K. On Lines and Planes of Closest Fit to System of Points in Space. Philiosophical Magazine, 2; 1901. p. 559-572..
  43. Abdi H, Williams LJ. Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics. 2010;2:433-59. doi.org/10.1002/wics.101.
Journal of Biomedical Physics and Engineering
Volume 7, Issue 4 - Serial Number 4
26
November and December 2017
Pages 365-378
Files
Share
How to cite
Statistics