Comparison Study of Muscular-Contraction Classification Between Independent Component Analysis and Artificial Neural Network

We developed a multi-channel electromyogram acquisition system using PSOC microcontroller to acquire multi-channel EMG signals. An array of 4 times 4 surface electrodes was used to record the EMG signal. The obtained signals were classified by a back-propagation-type artificial neural network. B-spline interpolation technique has been utilized to map the EMG signal on the muscle surface. The topological mapping of the EMG is then analyzed to classify the pattern of muscle contraction using independent component analysis. The proposed system was successfully demonstrated to record EMG data and its surface mapping. The comparison study of muscular contraction classification using independent component analysis and artificial neural network demonstrates shows that performance of ANN classification is as comparable as that of the ICA. The computational time of ANN is also less than that of the ICA.

[1]  R Plonsey,et al.  The active fiber in a volume conductor. , 1974, IEEE transactions on bio-medical engineering.

[2]  JoAnne K. Gronley,et al.  Timing and relative intensity of hip extensor and abductor muscle action during level and stair ambulation. An EMG study. , 1983, Physical therapy.

[3]  Morrenhof Jw,et al.  Cross-correlation and cross-talk in surface electromyography. , 1985 .

[4]  Michael I. Jordan,et al.  Local linear perceptrons for classification , 1996, IEEE Trans. Neural Networks.

[5]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[6]  T. S. Miles,et al.  Cross-talk from other muscles can contaminate EMG signals in reflex studies of the human leg , 1990, Neuroscience Letters.

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

[8]  Y. L. Yu,et al.  Face recognition with eigenfaces , 1994, Proceedings of 1994 IEEE International Conference on Industrial Technology - ICIT '94.

[9]  J. Cardoso.  Infomax and maximum likelihood for blind source separation , 1997, IEEE Signal Processing Letters.

[10]  Marian Stewart Bartlett,et al.  Independent component representations for face recognition , 1998, Electronic Imaging.

[11]  Aapo Hyvärinen,et al.  The Fixed-Point Algorithm and Maximum Likelihood Estimation for Independent Component Analysis , 1999, Neural Processing Letters.

[12]  J. Perry,et al.  Pattern recognition of multiple EMG signals applied to the description of human gait , 1977, Proceedings of the IEEE.

[13]  J. Cartinhour.  A Bayes classifier when the class distributions come from a common multivariate normal distribution , 1992 .

[14]  J W Morrenhof,et al.  Cross-correlation and cross-talk in surface electromyography. , 1985, Electromyography and clinical neurophysiology.

[15]  Carlo J. De Luca.  Use of the surface EMG signal for performance evaluation of back muscles , 1993 .

[16]  Nicolaos B. Karayiannis,et al.  Soft learning vector quantization and clustering algorithms based on non-Euclidean norms: single-norm algorithms , 2005, IEEE Transactions on Neural Networks.

[17]  Winter Da,et al.  Pathologic gait diagnosis with computer-averaged electromyographic profiles. , 1984 .

[18]  D A Winter,et al.  Pathologic gait diagnosis with computer-averaged electromyographic profiles. , 1984, Archives of physical medicine and rehabilitation.

[19]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[20]  Pierre Comon.  Independent component analysis - a new concept? signal processing , 1994 .