Correlation coefficient based featue selection for actuating myoelectric prosthetic arm

Human hand is one of the most intricate organs of the human body next to brain. Replicating human hand motions are necessary to perform routine activities. Surface Electromyography (sEMG) signals are used clinically as diagnostic tool for neurological disorders. These signals have been widely employed in applications such as prosthesis, control signal in rehabilitation and a means of diagnosis in health care. In this work, a single channel surface EMG amplifier is designed to acquire sEMG signal non-invasively. The correlation coefficient is calculated to identify the effective features of sEMG signal. These effective features could be given as input to the controller which will further help the movement of prosthetic arm. The signals are recorded from controlled subjects for three different hand movements namely closed fist, spherical grasp and point from left and right arm. Pre-processing of acquired signals is performed using Empirical Mode Decomposition (EMD) method which reduces noise. Time and frequency domain features are extracted from sEMG signal. Time-frequency domain features are extracted by analysing sEMG signals using wavelet transform. The correlation between features of sEMG signals of left and right arm is obtained. Three effective features, viz., time domain RMS, frequency domain SM2 and wavelet domain RMS are identified from regression analysis. Calculated values of correlation coefficient show strong dependence of sEMG signals of both arms. This interdependence can be exploited to harness the signals for either arm interchangeably.

[1]  A. Fuglsang-Frederiksen.  The utility of interference pattern analysis , 2000, Muscle & nerve.

[2]  Carlo Menon,et al.  A preliminary investigation assessing the viability of classifying hand postures in seniors , 2011, Biomedical engineering online.

[3]  Alan C. Bovik,et al.  Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures , 2009, IEEE Signal Processing Magazine.

[4]  Volkan Y. Senyurek,et al.  Performance Comparison of Artificial Neural Network and Gaussian Mixture Model in Classifying Hand Motions by Using sEMG Signals , 2013 .

[5]  K V Vidya,et al.  Frailty Analysis of SEMG Signals for Different Hand Movements Based on Temporal and Spectral Approach. , 2015, Biomedical sciences instrumentation.

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

[7]  T. Fukuda,et al.  Root Mean Square Value of the Electromyographic Signal in the Isometric Torque of the Quadriceps, Hamstrings and Brachial Biceps Muscles in Female Subjects , 2010 .

[8]  Manuel Duarte Ortigueira,et al.  On the HHT, its problems, and some solutions , 2008 .

[9]  M. Mitra,et al.  Detection of ECG characteristic points using Multiresolution Wavelet Analysis based Selective Coefficient Method , 2010 .

[10]  Ta-Te Lin,et al.  A comparison of upper-limb motion pattern recognition using EMG signals during dynamic and isometric muscle contractions , 2014, Biomed. Signal Process. Control..

[11]  Ping Zhou,et al.  Filtering of surface EMG using ensemble empirical mode decomposition. , 2013, Medical engineering & physics.

[12]  Mamun Bin Ibne Reaz,et al.  Surface Electromyography Signal Processing and Classification Techniques , 2013, Sensors.

[13]  M Solomonow,et al.  Force generation performance and motor unit recruitment strategy in muscles of contralateral limbs. , 1999, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[14]  F. Mohd-Yasin,et al.  EMG analysis using wavelet functions to determine muscle contraction , 2006, HEALTHCOM 2006 8th International Conference on e-Health Networking, Applications and Services.

[15]  H. Christensen,et al.  Power spectrum and turns analysis of EMG at different voluntary efforts in normal subjects. , 1986, Electroencephalography and clinical neurophysiology.

[16]  Yang Guang-ying,et al.  Surface electromyography disposal based on the method of wavelet de-noising and power spectrum , 2004, 2004 International Conference on Intelligent Mechatronics and Automation, 2004. Proceedings..

[17]  Huosheng Hu,et al.  ' s personal copy Review Myoelectric control systems — A survey , 2007 .

[18]  H B Boom,et al.  The median frequency of the surface EMG power spectrum in relation to motor unit firing and action potential properties. , 1992, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[19]  Noel B. Linsangan,et al.  Surface Electromyography Signal for Control of Myoelectric Prosthesis of the Upper-Limb Using Independent Component Analysis , 2014 .

[20]  A. Lazakidou,et al.  Concepts and Trends in Healthcare Information Systems , 2014 .

[21]  U. Rajendra Acharya,et al.  ECG beat classification using PCA, LDA, ICA and Discrete Wavelet Transform , 2013, Biomed. Signal Process. Control..

[22]  Gang Wang,et al.  The Analysis of Surface EMG Signals with the Wavelet-Based Correlation Dimension Method , 2014, Comput. Math. Methods Medicine.

[23]  C. J. Luca,et al.  SURFACE ELECTROMYOGRAPHY : DETECTION AND RECORDING , 2022 .

[24]  Igor Meglinski,et al.  Application of wavelet analysis in optical coherence tomography for obscured pattern recognition , 2009 .

[25]  Sabri Koçer,et al.  Classification of EMG Signals Using PCA and FFT , 2005, Journal of Medical Systems.

[26]  Pamela F. Jones,et al.  Computational and Mathematical Methods in Medicine , 2011, Comput. Math. Methods Medicine.

[27]  Nianfeng Wang,et al.  Realtime recognition of multi-finger prehensile gestures , 2014, Biomed. Signal Process. Control..

[28]  Blair A. Lock,et al.  Determining the Optimal Window Length for Pattern Recognition-Based Myoelectric Control: Balancing the Competing Effects of Classification Error and Controller Delay , 2011, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[29]  Pornchai Phukpattaranont,et al.  EMG feature extraction for tolerance of white Gaussian noise , 2008 .

[30]  J. Rafiee,et al.  Feature extraction of forearm EMG signals for prosthetics , 2011, Expert Syst. Appl..

[31]  K. Ishioka,et al.  Investigation on parametric analysis of dynamic EMG signals by a muscle-structured simulation model , 1992, IEEE Transactions on Biomedical Engineering.