The Blind Source Separation Method Based on Self-organizing Map Neural Network and Convolution Kernel Compensation for Multi-channel sEMG Signals_Journal of Biomedical Engineering

Authors：

NINGYong ¹ ,  ZHUShan ¹ , ZHAOYuming ²

1. College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China;
2. Tiandi Science & Technology Co., Ltd, Beijing 100013, China;

Corresponding author：

ZHUShan, Email: zsa@zju.edu.cn

Keywords：

blind source separation; convolution kernel compensation; self-organizing map neural network

DOI：

10.7507/1001-5515.20150001

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

A new method based on convolution kernel compensation (CKC) for decomposing multi-channel surface electromyogram (sEMG)signals is proposed in this paper. Unsupervised learning and clustering function of self-organizing map (SOM) neural network are employed in this method. An initial innervations pulse train (IPT) is firstly estimated, some time instants corresponding to the highest peaks from the initial IPT are clustered by SOM neural network. Then the final IPT can be obtained from the observations corresponding to these time instants. In this paper, the proposed method was tested on the simulated signal, the influence of signal to noise ratio (SNR), the number of groups clustered by SOM and the number of highest peaks selected from the initial pulse train on the number of reconstructed sources and the pulse accuracy were studied, and the results show that the proposed approach is effective in decomposing multi-channel sEMG signals.

Citation： NINGYong, ZHUShan, ZHAOYuming. The Blind Source Separation Method Based on Self-organizing Map Neural Network and Convolution Kernel Compensation for Multi-channel sEMG Signals. Journal of Biomedical Engineering, 2015, 32(1): 1-7. doi: 10.7507/1001-5515.20150001 Copy

1.	GRAUPE D, CLINE W K. Functional separation of EMG signals via ARMA identification methods for prosthesis control purposes[J]. IEEE Trans Syst Man Cybern, 1975, SMC-5(2): 252-259.
2.	HA K H, VAROL H A, GOLDFARB M. Volitional control of a prosthetic knee using surface electromyography[J]. IEEE Trans Biomed Eng, 2011, 58(1): 144-151.
3.	KOSMIDOU V E, HADJILEONTIADIS L J. Sign language recognition using intrinsic-mode sample entropy on sEMG and accelerometer data[J]. IEEE Trans Biomed Eng, 2009, 56(12): 2879-2890.
4.	KLEINE B U, VAN DIJK J P, LAPATKI B G, et al. Using two-dimensional spatial information in decomposition of surface EMG signals[J]. J Electromyogr Kinesiol, 2007, 17(5): 535-548.
5.	GAZZONI M, FARINA D, MERLETTI R. A new method for the extraction and classification of single motor unit action potentials from surface EMG signals[J]. J Neurosci Methods, 2004, 136(2): 165-177.
6.	WOOD S M, JARRATT J A, BARKER A T, et al. Surface electromyography using electrode arrays: a study of motor neuron disease[J]. Muscle Nerve, 2001, 24(2): 223-230.
7.	GARCÍA G A, OKUNO R, AKAZAWA K. A decomposition algorithm for surface electrode-array electromyogram. A noninvasive, three-step approach to analyze surface EMG signals[J]. IEEE Eng Med Biol Mag, 2005, 24(4): 63-72.
8.	GLIGORIJEVI AĆU I, VAN DIJK J P, MIJOVI AĆU B, et al. A new and fast approach towards sEMG decomposition[J]. Med Biol Eng Comput, 2013, 51(5): 593-605.
9.	HOLOBAR A, ZAZULA D. Multichannel blind source separation using convolution kernel compensation[J]. IEEE Trans Signal Processing, 2007, 55(9): 4487-4496.
10.	HOLOBAR A, ZAZULA D. Gradient convolution kernel compensation applied to surface electromyograms[C]//7th International Conference, ICA. London, UK: 2007: 617-624.
11.	HOLOBAR A, MINETTO M A, BOTTER A, et al. Experimental analysis of accuracy in the identification of motor unit spike trains from high-density surface EMG[J]. IEEE Trans Neural Syst Rehabil Eng, 2010, 18(3): 221-229.
12.	HOLOBAR A, GLASER V, GALLEGO J A, et al. Non-invasive characterization of motor unit behaviour in pathological tremor[J]. J Neural Eng, 2012, 9(5): 056011.
13.	HOLOBAR A, FARINA D, GAZZONI M, et al. Estimating motor unit discharge patterns from high-density surface electromyogram[J]. Clin Neurophysiol, 2009, 120(3): 551-562.
14.	KOHONEN T. Self-organized formation of topologically correct feature maps[J]. Biol Cybern, 1982, 43(1): 59-69.
15.	KOHONEN T. The self-organizing map[J]. Proceedings of the IEEE, 1990, 78(9): 1464-1480.
16.	许力.智能控制与智能系统[M].北京:机械工业出版社, 2007:246-253.

1. GRAUPE D, CLINE W K. Functional separation of EMG signals via ARMA identification methods for prosthesis control purposes[J]. IEEE Trans Syst Man Cybern, 1975, SMC-5(2): 252-259.
2. HA K H, VAROL H A, GOLDFARB M. Volitional control of a prosthetic knee using surface electromyography[J]. IEEE Trans Biomed Eng, 2011, 58(1): 144-151.
3. KOSMIDOU V E, HADJILEONTIADIS L J. Sign language recognition using intrinsic-mode sample entropy on sEMG and accelerometer data[J]. IEEE Trans Biomed Eng, 2009, 56(12): 2879-2890.
4. KLEINE B U, VAN DIJK J P, LAPATKI B G, et al. Using two-dimensional spatial information in decomposition of surface EMG signals[J]. J Electromyogr Kinesiol, 2007, 17(5): 535-548.
5. GAZZONI M, FARINA D, MERLETTI R. A new method for the extraction and classification of single motor unit action potentials from surface EMG signals[J]. J Neurosci Methods, 2004, 136(2): 165-177.
6. WOOD S M, JARRATT J A, BARKER A T, et al. Surface electromyography using electrode arrays: a study of motor neuron disease[J]. Muscle Nerve, 2001, 24(2): 223-230.
7. GARCÍA G A, OKUNO R, AKAZAWA K. A decomposition algorithm for surface electrode-array electromyogram. A noninvasive, three-step approach to analyze surface EMG signals[J]. IEEE Eng Med Biol Mag, 2005, 24(4): 63-72.
8. GLIGORIJEVI AĆU I, VAN DIJK J P, MIJOVI AĆU B, et al. A new and fast approach towards sEMG decomposition[J]. Med Biol Eng Comput, 2013, 51(5): 593-605.
9. HOLOBAR A, ZAZULA D. Multichannel blind source separation using convolution kernel compensation[J]. IEEE Trans Signal Processing, 2007, 55(9): 4487-4496.
10. HOLOBAR A, ZAZULA D. Gradient convolution kernel compensation applied to surface electromyograms[C]//7th International Conference, ICA. London, UK: 2007: 617-624.
11. HOLOBAR A, MINETTO M A, BOTTER A, et al. Experimental analysis of accuracy in the identification of motor unit spike trains from high-density surface EMG[J]. IEEE Trans Neural Syst Rehabil Eng, 2010, 18(3): 221-229.
12. HOLOBAR A, GLASER V, GALLEGO J A, et al. Non-invasive characterization of motor unit behaviour in pathological tremor[J]. J Neural Eng, 2012, 9(5): 056011.
13. HOLOBAR A, FARINA D, GAZZONI M, et al. Estimating motor unit discharge patterns from high-density surface electromyogram[J]. Clin Neurophysiol, 2009, 120(3): 551-562.
14. KOHONEN T. Self-organized formation of topologically correct feature maps[J]. Biol Cybern, 1982, 43(1): 59-69.
15. KOHONEN T. The self-organizing map[J]. Proceedings of the IEEE, 1990, 78(9): 1464-1480.
16. 许力.智能控制与智能系统[M].北京:机械工业出版社, 2007:246-253.

Next Article
Effect of Fluid Shear Stress on the Cellular Morphology and Tight Junction of Laryngeal Squamous Carcinoma Hep2 Cells

Journal of Biomedical Engineering

The Blind Source Separation Method Based on Self-organizing Map Neural Network and Convolution Kernel Compensation for Multi-channel sEMG Signals

Abstract Full text Figures/Tables Video References Cited by

Next Article

Format

Content