Hybrid Feature Selection for Myoelectric Signal Classification Using MICA

Hybrid Feature Selection for Myoelectric Signal Classification Using MICA This paper presents a novel method to enhance the performance of Independent Component Analysis (ICA) of myoelectric signal by decomposing the signal into components originating from different muscles. First, we use Multi run ICA (MICA) algorithm to separate the muscle activities. Pattern classification of the separated signal is performed in the second step with a back propagation neural network. The focus of this work is to establish a simple, yet robust system that can be used to identify subtle complex hand actions and gestures for control of prosthesis and other computer assisted devices. Testing was conducted using several single shot experiments conducted with five subjects. The results indicate that the system is able to classify four different wrist actions with near 100% accuracy.

[1]  Bruce C. Wheeler,et al.  EMG feature evaluation for movement control of upper extremity prostheses , 1995 .

[2]  G. Hefftner,et al.  The electromyogram (EMG) as a control signal for functional neuromuscular stimulation. I. Autoregressive modeling as a means of EMG signature discrimination , 1988, IEEE Transactions on Biomedical Engineering.

[3]  E. Kaplan.  Muscles Alive. Their Functions Revealed by Electromyography. J. V. Basmajian. Baltimore, The Williams and Wilkins Co., 1962. $8.50 , 1962 .

[4]  J. Hair.  Multivariate data analysis , 1972 .

[5]  T S Kuo,et al.  Real-time implementation of electromyogram pattern recognition as a control command of man-machine interface. , 1996, Medical engineering & physics.

[6]  A. Willsky,et al.  Upper Extremity Limb Function Discrimination Using EMG Signal Analysis , 1983, IEEE Transactions on Biomedical Engineering.

[7]  Edward Hunter,et al.  Vision based hand gesture interpretation using recursive estimation , 1994, Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers.

[8]  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.

[9]  E. Oja,et al.  Independent Component Analysis , 2013 .

[10]  Andrzej Cichocki,et al.  Adaptive blind signal and image processing , 2002 .

[11]  C Fantuzzi,et al.  Automatic tuning of myoelectric prostheses. , 1998, Journal of rehabilitation research and development.

[12]  R.N. Scott,et al.  A new strategy for multifunction myoelectric control , 1993, IEEE Transactions on Biomedical Engineering.

[13]  J. Basmajian.  Muscles Alive—their functions revealed by electromyography , 1963 .

[14]  Takeo Kanade,et al.  DigitEyes: vision-based hand tracking for human-computer interaction , 1994, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.

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

[16]  Andrzej Cichocki,et al.  Adaptive Blind Signal and Image Processing - Learning Algorithms and Applications , 2002 .

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

[18]  Kevin B. Englehart,et al.  A robust, real-time control scheme for multifunction myoelectric control , 2003, IEEE Transactions on Biomedical Engineering.

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

[20]  H. Devries.  MUSCLES ALIVE-THEIR FUNCTIONS REVEALED BY ELECTROMYOGRAPHY , 1976 .