Special Issue on Biosignal Sensing and Intelligent Information ProcessingNo Access

LIMITATIONS AND APPLICATIONS OF ICA FOR SURFACE ELECTROMYOGRAM FOR IDENTIFYING HAND GESTURES

Department of Electrical Engineering, Faculty of Engineering, Universitas Surabaya, J1. Raya Kalirungkut, TB.2.3 Building Surabaya 60293, Indonesia

Search for more papers by this author

DINESH K. KUMAR

School of Electrical and Computer Engineering, RMIT University, GPO Box 2476V, Melbourne, Victoria 3001, Australia

Search for more papers by this author

SRIDHAR P. ARJUNAN

School of Electrical and Computer Engineering, RMIT University, GPO Box 2476V, Melbourne, Victoria 3001, Australia

Search for more papers by this author

, and

GANESH R. NAIK

School of Electrical and Computer Engineering, RMIT University, GPO Box 2476V, Melbourne, Victoria 3001, Australia

Search for more papers by this author

https://doi.org/10.1142/S1469026808002272Cited by:2 (Source: Crossref)

Abstract

Surface electromyogram (SEMG) has numerous applications, but the presence of artifacts and cross talk especially at low level of muscle activity makes the recordings unreliable. Spectral and temporal overlap can make the removal of artifacts and noise, or separation of relevant signals from other bioelectric signals extremely difficult. Identification of hand gestures using low level of SEMG is one application that has a number of applications but the presence of high level of cross talk makes such an application highly unreliable. Individual muscles may be considered as independent at the local level and this makes an argument for separating the signals using independent component analysis (ICA). In the recent past, due to the easy availability of ICA tools, a number of researchers have attempted to use ICA for this application. This paper reports research conducted to evaluate the use of ICA for the separation of muscle activity and removal of the artifacts 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 a number of sources. This paper also identifies the lack of suitable measure of quality of separation for bioelectric signals and it recommends and tests a more robust measure of separation. This paper also proposes semi-blind ICA approach with the combination of prior knowledge of SEMG sources with ICA to identify hand gestures using low level of SEMG recordings. The theoretical analysis and experimental results demonstrate that ICA is suitable for SEMG signals. The results demonstrate the limitations of such applications due to the inability of the system to identify the correct order and magnitude of the signals. This paper determines the suitability of the use of error between estimated and actual mixing matrix as a mean for identifying the quality of separation of the output. This work also demonstrates that semi-blind ICA can accurately identify complex hand gestures from the low-level SEMG recordings.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

M. Alemu, D. Kumar and A. Bradley, IEEE Trans. Neural Syst. Rehabil. 11(2), 431 (2003). Google Scholar
J. S. Barlow, IEEE Trans. Biomed. Eng. 26, 377 (1979). Google Scholar
A. Bartolo and E. Goldman, Am. J. Physiol. (1999). Google Scholar
A. Bell and T. Sejnowski, Neural Comput. 7, 1129 (1995), DOI: 10.1162/neco.1995.7.6.1129. Crossref, Google Scholar
G. Cheronet al., IEEE Trans. Biomed. Eng. 43, 552 (1996), DOI: 10.1109/10.488803. Crossref, Google Scholar
D. Djuwari et al. , Multi-step independent component analysis for removing cardiac artifacts from back SEMG signals , Proc. 8th Austral. New Zealand Intell. Inform. Syst. Conf. ( 2003 ) . Google Scholar
A. Grecoet al., Neural Networks 1, 166 (2003). Google Scholar
V. Gupta and N. P. Reddy, Student Health Technol. Inform. 29, 482 (1996). Google Scholar
T. He, G. Clifford and L. Tarassenko, Neural Comput. Appll. (2002). Google Scholar
S. Hilyard and R. Galambos, Electroen. Clin. Neurol. 28, 173 (1970), DOI: 10.1016/0013-4694(70)90185-9. Crossref, Google Scholar
A. Hyvarinen and E. Oja, Neural Comput. 9(7), 1483 (1997), DOI: 10.1162/neco.1997.9.7.1483. Crossref, Google Scholar
A. Hyvarinen and E. Oja, The Fast ICA MATLAB Package (1997), http://www.cis.hut.fi/projects/ica/fastica/index.shtml. Google Scholar
A. Hyvarinen , J. Karhunen and E. Oja , Independent Component Analysis ( John Wiley , New York , 2001 ) . Crossref, Google Scholar
Y. Koike and M. Kawato, Electronics and Communications 1996 79, eds. F. Godlee and T. Jefferson (BMJ Books, 1999) pp. 15–22. Google Scholar
D. K. Kumar, M. Alemu and A. Bradley, Electromyo. Clin. Neurol. 41, 401 (2001). Google Scholar
T. Moritani and M. Muro, Eur. J. Appl. Physiol. Occup. Physiol. 56, 260 (1987), DOI: 10.1007/BF00690890. Crossref, Google Scholar
H. Nakamuraet al., J. Electromyogr. Kines. 14(4), 423 (2004), DOI: 10.1016/j.jelekin.2004.01.004. Crossref, Google Scholar
P. Oster and J. Stern, Measurement of Eye Movement Electroocculography (Wiley, Chichester, UK, 1980) pp. 275–390. Google Scholar
V. I. Pavlovic, R. Sharma and T. S. Huang, IEEE Trans. Pattern Anal. 19(9), 677 (1997), DOI: 10.1109/34.598226. Crossref, Google Scholar
J. Peters, J. Electroen. Tech. 7, 1129 (1967). Google Scholar
J. M. Rehg and T. Kanade, Vision-based hand tracking for human-computer interaction, Proc. IEEE Workshop on Motion of Non-Rigid and Articulated Objects (1994) pp. 16–22. Google Scholar
J. Schlenzig, E. Hunter and R. Jain, Vision based hand gesture interpretation using recursive estimation, Proc. Twenty-Eighth Asilomar Conf. Signals, Systems and Computers (1994) pp. 14–31. Google Scholar
R. Vergler, T. Gasser and J. Mocks, Psychophysiology 19, 472 (1982). Google Scholar
R. Verleger, Electroen. Clin. Neurol. 87, 354 (1993), DOI: 10.1016/0013-4694(93)90148-O. Crossref, Google Scholar
T. Weerts and P. Lang, Biol. Psychol. 1, 1 (1983), DOI: 10.1016/0301-0511(73)90010-0. Crossref, Google Scholar
J. Whitton, F. Lue and H. Moldofsky, Electroen. Clin. Neurol. 44, 735 (1978), DOI: 10.1016/0013-4694(78)90208-0. Crossref, Google Scholar
J. O. Wisbeck, A. K. Barros and R. G. Ojeda, Neural Comput. Appl. (2000). Google Scholar
J. Woestenburg, M. Verbaten and J. Slangen, Biol. Psychol. 16, 127 (1983), DOI: 10.1016/0301-0511(83)90059-5. Crossref, Google Scholar
Y. Hu et al. , ECG cancellation of surface electromyography measurements using independent component analysis , Proc. World Congress on Medical Physics and Bio-Medical Engineering ( 2003 ) . Google Scholar