TOWARDS A HAND GESTURES RECOGNITION USING WEAK AND A SINGLE-CHANNEL SURFACE EMG SIGNALS

This article presents a method to obtain a myoelectric control system for hand prosthesis with individual fingers, wrist flexion/extension and grasp movements, based on weak surface electromyogram (sEMG) recorded from the forearm, both able-bodied and amputees. This study aims to a reduced-channel scheme (a single sEMG channel) for hand patterns discrimination. A combination of commonly used features in the Frequency Domain (FD) and Time Domain (TD) with the analysis fractal was studied to obtain the best set of features. The results were validated with different classifiers showing the high performance of the method, above 90%.

[1]  Junuk Chu,et al.  A Real-Time EMG Pattern Recognition System Based on Linear-Nonlinear Feature Projection for a Multifunction Myoelectric Hand , 2006, IEEE Transactions on Biomedical Engineering.

[2]  R. Merletti,et al.  Modeling of surface myoelectric signals. I. Model implementation , 1999, IEEE Transactions on Biomedical Engineering.

[3]  Christian Cipriani,et al.  The SmartHand transradial prosthesis , 2011, Journal of NeuroEngineering and Rehabilitation.

[4]  Sridhar P. Arjunan,et al.  Pattern classification of Myo-Electrical signal during different Maximum Voluntary Contractions: A study using BSS techniques , 2010 .

[5]  Nitish V. Thakor,et al.  Decoding of Individuated Finger Movements Using Surface Electromyography , 2009, IEEE Transactions on Biomedical Engineering.

[6]  Anselmo Frizera,et al.  Identification of low level sEMG signals for individual finger prosthesis , 2014, 5th ISSNIP-IEEE Biosignals and Biorobotics Conference (2014): Biosignals and Robotics for Better and Safer Living (BRC).

[7]  Pornchai Phukpattaranont,et al.  Fractal analysis features for weak and single-channel upper-limb EMG signals , 2012, Expert Syst. Appl..

[8]  Huosheng Hu,et al.  Myoelectric control systems - A survey , 2007, Biomed. Signal Process. Control..

[9]  R. Merletti,et al.  Modeling of surface myoelectric signals--Part I: Model implementation. , 1999, IEEE transactions on bio-medical engineering.