Abstract
Motor unit (MU) firing pattern information can be used clinically or for physiological investigation. It can also be used to enhance and validate electromyographic (EMG) signal decomposition. However, in all instances the validity of the extracted MU firing patterns must first be determined. Two supervised classifiers that can be used to validate extracted MU firing patterns are proposed. The first classifier, the single/merged classifier (SMC), determines whether a motor unit potential train (MUPT) represents the firings of a single MU or the merged activity of more than one MU. The second classifier, the single/contaminated classifier (SCC), determines whether the estimated number of false-classification errors in a MUPT is acceptable or not. Each classifier was trained using simulated data and tested using simulated and real data. The accuracy of the SMC in categorizing a train correctly is 99% and 96% for simulated and real data, respectively. The accuracy of the SCC is 84% and 81% for simulated and real data, respectively. The composition of these classifiers, their objectives, how they were trained, and the evaluation of their performances using both simulated and real data are presented in detail.
Similar content being viewed by others
Notes
These signals and more information about them are available from: http://emglab.net/emglab/Signals/N2001/index.html.
Abbreviations
- CasC:
-
Contaminated trains classified as a contaminated train
- CV:
-
Coefficient of variation
- CVL :
-
Lower CV
- CVU :
-
Upper CV
- EFE:
-
Error-filtering estimation
- EMG:
-
Electromyographic
- FCE:
-
False-classification error
- FLDA:
-
Fisher linear discriminate analysis
- FR-MCD:
-
Firing rate mean consecutive difference
- IDI:
-
Inter-discharge interval
- ID rate:
-
Identification rate
- IDI-MCD:
-
IDI mean consecutive difference
- LIDIR :
-
Lower IDI ratio
- MasM:
-
Merged trains classified as a merged train
- MCE:
-
Missed classification error
- MVC:
-
Maximum voluntary contraction
- MU:
-
Motor unit
- MUP:
-
Motor unit potential
- MUPT:
-
Motor unit potential train
- PD:
-
Pattern discovery
- PI:
-
Percentage of inconsistent IDIs
- SasS:
-
Single trains classified as a single train
- SCC:
-
Single/contaminated classifier
- SMC:
-
Single/merged classifier
- SVMs :
-
Support vector machines
- r 1 :
-
First coefficient of serial correlation
- μ:
-
The mean of IDIs of a MUPT
- μLoc :
-
Local mean of IDIs of a MUPT
- σ:
-
The standard deviation of the IDIs of a MUPT
References
Basmajian J, DeLuca CJ (1985) Muscle alive their function revealed by electromyography. Williams and Wilkins, Baltimore, MD
Chen Y, Laszlo CA, Hershle C (1993) Estimation of the firing rate of an incomplete MUAP train. IEEE CCECE/CCGEI, pp 970–972
Christodoulou CI, Pattichis CS (1999) Unsupervised pattern recognition for the classification of EMG signals. IEEE Trans Biomed Eng 46(2):169–178
Clamann H (1969) Statistical analysis of motor unit firing patterns in a human skeletal muscle. Biophys J 9:1233–1251
De Luca CJ, LeFever RS, McCue MP, Xenakis AP (1982) Behaviour of human motor units in different muscles during linear varying contractions. J Physiol 329:113–128
De Luca CJ, LeFever RS, McCue MP, Xenakis AP (1982) Control scheme governing concurrently active human motor units during voluntary contractions. J Physiol 329:129–142
Ekstedt J, Nilsson G, Stålberg E (1974) Calculation of the electromyographic jitter. J Neurol Neurosurg Psychiatry 37:526–539
Erim Z, Lin W (2008) Decomposition of intramuscular EMG signals using a heuristic fuzzy expert system. IEEE Trans Biomed Eng 55(9):2180–2189
Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugen 7(2):179–188
Freund H, Dietz V, Wita C, Kapp H (1973) Discharge characteristics of single motor units in normal subjects and patients with supraspinal motor disturbances. In: Desmedt JE (ed) New developments in electromyography and clinical neurophysiology, vol 3. Karger, Basel, pp 242–250
Fuglsang-Frederiksen A (2006) The role of different EMG methods in evaluating myopathy. Clin Neurophysiol 117:1173–1189
Halonen JP, Falck B, Kalino H (1981) The firing rate of motor units in neuromuscular disorders. J Neurophysiol 225:269–276
Hamilton-Wright A, Stashuk D, Tizhoosh H (2007) Fuzzy classification using pattern discovery. IEEE Trans Fuzzy Syst 15(5):772–783
Hassoun M, Wang C, Spitzer A (1994) NNERVE: neural network extraction of repetitive vectors for electromyography part I: algorithm. IEEE Trans Biomed Eng 41(11):1039–1052
Kukulka CG, Clamann HP (1981) Comparison of the recruitment and discharge properties of motor units in human brachial biceps and abductor pollicis during isometric contractions. Exp Brain Res 219:45–55
LeFever RS, DeLuca CJ (1982) A procedure for decomposing the myoelectric signal into its constituent action potentials. IEEE Trans Biomed Eng 29(3):149–162
Loudon GH, Jones NB, Sehmi AS (1992) New signal processing techniques for the decomposition of EMG signals. Med Biol Eng Comput 30(6):591
McGill K, Cummins K, Dorfman L (1985) Automatic decomposition of the clinical electromyogram. IEEE Trans Biomed Eng 32(7):470–477
Nikolic M (2001) Detailed analysis of clinical electromyography signals EMG decomposition, findings and firing pattern analysis in controls and patients with myopathy and amytrophic lateral sclerosis. PhD Thesis, Faculty of Health Science, University of Copenhagen. The data are available as dataset N2001 at http://www.emglab.net
Pudil P, Novovičová J, Kittler J (1994) Floating search methods in feature selection. Pattern Recogn Lett 15:1119–1125
Rasheed S, Stashuk D W, Kamel M (2004) Multi-classification techniques applied to EMG signal decomposition. In: Proceedings of the 2004 IEEE international conference on systems, man and cybernetics, SMC 04, vol 2, pp 1226–1231
Rasheed S, Stashuk DW, Kamel M (2006) Adaptive certainty-based classification for decomposition of EMG signals. Med Biol Eng Comput 44(4):298–310
Rasheed S, Stashuk DW, Kamel M (2006) Adaptive Fuzzy K-NN classifier EMG decomposition. Med Eng Phys 28(7):694–709
Rasheed S, Stashuk DW, Kamel M (2008) A software package for interactive motor unit potential classification using fuzzy k-NN classifier. Comput Methods Programs Biomed 8(9):56–71
Reiners K, Herdmann J, Freund H (1989) Altered mechanisms of muscular force generation in lower motor neuron disease. Muscle Nerve 12:647–659
Rosenfalck A, Andreassen S (1980) Impaired regulation of force and firing pattern of single motor units in patients with spasticity. J Neurol Neurosurg Psychiatry 43:907–916
Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, Cambridge
Stålberg E, Falck B (1997) The role of electromyography in neurology. Electroencephalogr Clin Neurophysiol 97:145–154
Stålberg E, Flack B, Sonoo M, Stålberg S, Åström M (1995) Multi-MUP EMG analysis—a two year experience in daily clinical work. Electroencephalogr Clin Neurophysiol 97:145–154
Stashuk DW (1999) Decomposition and quantitative analysis of clinical electromyographic signals. Med Eng Phys 21:389–404
Stashuk DW (2001) EMG signal decomposition: how can it be accomplished and used? J Electromyogr Kinesiol 11(3):151–173
Stashuk DW, Paoli G (1998) Robust supervised classification of motor units action potentials. Med Biol Eng Comput 36(1):50–57
Stashuk DW, Qu Y (1996) Adaptive motor unit action potential clustering using shape and temporal information. Med Biol Eng Comput 34(1):41–49
Stashuk DW, Qu Y (1996) Robust method for estimating motor unit firing pattern statistics. Med Biol Eng Comput 34(1):50–57
Sun TY, Chen JJ, Lin TS (2000) Analysis of motor unit firing patterns for patients with central or peripheral lesions using singular value decomposition. Muscle Nerve 23(7):1057–1068
Vapnik VN (2000) The nature of statistical learning theory, 2nd ed. Springer, New York
Wang Y, Wong AKC (2003) From association to classification: inference using weight of evidence. IEEE Trans Knowl Data Eng 15(3):764–767
Yue S, Wang CY (2002) The null distribution of sample serial correlation coefficient. Stoc Envor Research Risk Asses 16:77–100
Acknowledgments
The authors gratefully acknowledge financial support from the Natural Sciences and Engineering Research Council of Canada (NSERC).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Parsaei, H., Nezhad, F.J., Stashuk, D.W. et al. Validating motor unit firing patterns extracted by EMG signal decomposition. Med Biol Eng Comput 49, 649–658 (2011). https://doi.org/10.1007/s11517-010-0703-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-010-0703-1