Classification of Gesture based on sEMG Decomposition: A Preliminary Study

Multi-channel surface electromyography (sEMG) recognition has been investigated extensively by researchers over the past several decades. However, due to the nature of sEMG sensors, the more sensors are used, the greater chance for the sEMG to be influenced by environment noise. Furthermore, it is not feasible to use multi-sensors in some cases because of the bulky size of the sensors and the limited area of muscles. This paper proposes a novel sEMG recognition method based on the decomposition of single-channel sEMG. At first, sEMG is acquired while the participant does 5 predetermined hand gestures. Then, this signal is decomposed into its component motor unit potential trains (MUAPTs), which includes 4 steps: 2-order differential filtering, spikes detection, dimension reduction and clustering with Gaussian Mixture Model (GMM). Finally, 5 MUAPTs are obtained and used for hand gestures classification: four features, integral of absolute value (IAV), maximum value (MAX), median value of non-zero value (NonZeroMed) and index of NonZeroMed (Ind) are extracted to form feature matrix, which is then classified with the algorithm of Linear Discriminate Analysis (LDA). The classification results indicate this method can achieve an accuracy of 74.7% while the accuracy of traditional classification method for single-channel sEMG is about 52.6%.

[1]  M. Ferrarin,et al.  EMG signals detection and processing for on-line control of functional electrical stimulation. , 2000, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[2]  I. Cosic,et al.  Strategies to identify changes in SEMG due to muscle fatigue during cycling , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[3]  L. Scheker,et al.  Functional anatomy of the hand. , 1993, Emergency medicine clinics of North America.

[4]  M. Bilodeau,et al.  EMG frequency content changes with increasing force and during fatigue in the quadriceps femoris muscle of men and women. , 2003, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[5]  Li Wenguo,et al.  Wavelet transform and independent component analysis application to multi-channel SEMG processing , 2008, 2008 International Conference on Information and Automation.

[6]  Kevin Englehart,et al.  Continuous classification of myoelectric signals for powered prostheses using gaussian mixture models , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[7]  R. Enoka,et al.  Variability of motor unit discharge and force fluctuations across a range of muscle forces in older adults , 2005, Muscle & nerve.

[8]  D W Stashuk,et al.  Decomposition and quantitative analysis of clinical electromyographic signals. , 1999, Medical engineering & physics.

[9]  Ganesh R. Naik,et al.  Twin SVM for Gesture Classification Using the Surface Electromyogram , 2010, IEEE Transactions on Information Technology in Biomedicine.

[10]  Jianda Han,et al.  Feasibility of EMG-based ANN controller for a real-time virtual reality simulation , 2012, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society.

[11]  Hossein Parsaei,et al.  SVM-Based Validation of Motor Unit Potential Trains Extracted by EMG Signal Decomposition , 2012, IEEE Transactions on Biomedical Engineering.

[12]  Joshua C. Kline,et al.  Decomposition of surface EMG signals. , 2006, Journal of neurophysiology.

[13]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[14]  Hyung-Soon Park,et al.  A Practical Strategy for sEMG-Based Knee Joint Moment Estimation During Gait and Its Validation in Individuals With Cerebral Palsy , 2012, IEEE Transactions on Biomedical Engineering.

[15]  Kang-Ming Chang,et al.  Exercise muscle fatigue detection system implementation via wireless surface electromyography and empirical mode decomposition , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[16]  K C McGill,et al.  Rigorous a Posteriori Assessment of Accuracy in EMG Decomposition , 2011, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[17]  Kevin C. McGill,et al.  Automatic Decomposition of the Clinical Electromyogram , 1985, IEEE Transactions on Biomedical Engineering.

[18]  Aiguo Song,et al.  A Backstepping Control Strategy for Prosthetic Hand Based on Fuzzy Observation of Stiffness , 2013 .

[19]  H. Akaike.  A new look at the statistical model identification , 1974 .

[20]  C. D. De Luca,et al.  High-yield decomposition of surface EMG signals , 2010, Clinical Neurophysiology.

[21]  Andreas Daffertshofer,et al.  Improving EMG-based muscle force estimation by using a high-density EMG grid and principal component analysis , 2006, IEEE Transactions on Biomedical Engineering.

[22]  M. Ferrarin,et al.  Unilateral and Bilateral Subthalamic Nucleus Stimulation in Parkinson's Disease: Effects on EMG Signals of Lower Limb Muscles During Walking , 2007, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[23]  Backhouse Km,et al.  Functional anatomy of the hand. , 1968 .

[24]  David G. Stork,et al.  Pattern Classification , 1973 .

[25]  Guido Bugmann,et al.  Classification of Finger Movements for the Dexterous Hand Prosthesis Control With Surface Electromyography , 2013, IEEE Journal of Biomedical and Health Informatics.

[26]  K C McGill,et al.  Automatic decomposition of multichannel intramuscular EMG signals. , 2009, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[27]  Erik J. Scheme,et al.  Selective Classification for Improved Robustness of Myoelectric Control Under Nonideal Conditions , 2011, IEEE Transactions on Biomedical Engineering.

[28]  Guangjun Liu,et al.  A novel HCI based on EMG and IMU , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.