Limitations and Applications of ICA for Surface Electromyogram

This paper reports research conducted to evaluate the use of sparse ICA for the separation of muscle activity from SEMG. It discusses some of the conditions that could affect the reliability of the separation and evaluates issues related to the properties of the signals and number of sources. The paper reports tests using Zibulevsky's method of temporal plotting to identify number of independent sources in SEMG recordings. The theoretical analysis and experimental results demonstrate that sparse ICA is not suitable for SEMG signals. The results identify that the technique is unable to identify finite number of active muscles. The work demonstrates that even at extremely low level of muscle contraction, and with filtering using wavelets and band pass filters, it is not possible to get the data sparse enough to identify number of independent sources using Zibulevsky's sparse decomposition technique

[1]  S. Hillyard,et al.  Eye movement artifact in the CNV. , 1970, Electroencephalography and clinical neurophysiology.

[2]  P. Lang,et al.  The effects of eye fixation and stimulus and response location on the contingent negative variation (CNV). , 1973, Biological psychology.

[3]  H. Moldofsky,et al.  A spectral method for removing eye movement artifacts from the EEG. , 1978, Electroencephalography and clinical neurophysiology.

[4]  John S. Barlow,et al.  Computerized Clinical Electroencephalography in Perspective , 1979, IEEE Transactions on Biomedical Engineering.

[5]  T. Gasser,et al.  Correction of EOG artifacts in event-related potentials of the EEG: aspects of reliability and validity. , 1982, Psychophysiology.

[6]  J. C. Woestenburg,et al.  The removal of the eye-movement artifact from the EEG by regression analysis in the frequency domain , 1983, Biological Psychology.

[7]  Tzi-Dar Chiueh,et al.  Learning algorithms for neural networks with ternary weights , 1988, Neural Networks.

[8]  R. Verleger.  Valid identification of blink artefacts: are they larger than 50 microV in EEG records? , 1993, Electroencephalography and clinical neurophysiology.

[9]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[10]  G. Cheron,et al.  A dynamic neural network identification of electromyography and arm trajectory relationship during complex movements , 1996, IEEE Transactions on Biomedical Engineering.

[11]  Mitsuo Kawato,et al.  Human interface using surface electromyography signals , 1996 .

[12]  Aapo Hyvärinen,et al.  A Fast Fixed-Point Algorithm for Independent Component Analysis , 1997, Neural Computation.

[13]  Vladimir Pavlovic,et al.  Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Hideo Nakamura,et al.  The application of independent component analysis to the multi-channel surface electromyographic signals for separation of motor unit action potential trains: part I-measuring techniques. , 2004, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[15]  T. Moritani,et al.  Motor unit activity and surface electromyogram power spectrum during increasing force of contraction , 2004, European Journal of Applied Physiology and Occupational Physiology.