Nonlinear multiscale Maximal Lyapunov Exponent for accurate myoelectric signal classification

We use nonlinear and non-stationary features of sEMG to identify various gestures.In order to reduce the complexity of EMD nonlinear MLE method is used.In order to improve characteristic stability we use a method based on nonlinear MLE.The proposed method classifies six different hand gestures up to 97.6% accuracy.The method can be used for prosthetics and other rehabilitation applications. Surface Electromyography (sEMG) is a non-invasive, easy to record signal of superficial muscles from the skin surface. The sEMG is widely used in evaluating the functional status of the hand to assist in hand gesture recognition, prosthetics and rehabilitation applications. Considering the nonlinear and non-stationary characteristics of sEMG, hand gesture recognition using sEMG signals necessitate designers to use Maximal Lyapunov Exponent (MLE) or ensemble Empirical Mode Decomposition (EMD) based MLEs. In this research, we propose a hand gesture recognition method of sEMG based on nonlinear multiscale MLE. The aim is to increase the classification accuracy of sEMG features while reducing the complexity of EMD. The nonlinear MLE features are classified using Flexible Neural Tree (FNT), which can solve highly structured dependent problems of the Artificial Neural Network (ANN). The testing has been conducted using several experiments with five participants. The classification performance of nonlinear multiscale MLE method is compared with MLE and EMD-based MLE through simulations. Experimental results demonstrate that the former algorithm outperforms the two latter algorithms and can classify six different hand gestures up to 97.6% accuracy.

[1]  I. Jolliffe.  Principal Component Analysis , 2002 .

[2]  Walmir M. Caminhas,et al.  Fuzzy evolving linear regression trees , 2011, Evol. Syst..

[3]  Yongtang Li,et al.  Single-Mixture Source Separation Using Dimensionality Reduction of Ensemble Empirical Mode Decomposition and Independent Component Analysis , 2012, Circuits, Systems, and Signal Processing.

[4]  Guang Meng,et al.  Analysis of surface EMG signal based on empirical mode decomposition , 2009, 2009 IEEE International Conference on Rehabilitation Robotics.

[5]  E. M. Sadler,et al.  Local dynamic stability of trunk movements during the repetitive lifting of loads. , 2012, Human movement science.

[6]  H. Abdi,et al.  Principal component analysis , 2010 .

[7]  Yuan Yu,et al.  Fault diagnosis and classification for bearing based on EMD-ICA , 2011, EMEIT.

[8]  Ramazan Gençay,et al.  Testing chaotic dynamics via Lyapunov exponents , 1998 .

[9]  A. Wolf,et al.  Determining Lyapunov exponents from a time series , 1985 .

[10]  Li Yang,et al.  Feature extraction and classification of sEMG based on ICA and EMD decomposition of AR model , 2011, 2011 International Conference on Electronics, Communications and Control (ICECC).

[11]  Zhizhong Wang,et al.  Detecting nonlinearity of action surface EMG signal , 2001 .

[12]  Wangxin Yu,et al.  Characterization of Surface EMG Signal Based on Fuzzy Entropy , 2007, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[13]  Walmir M. Caminhas,et al.  A fast learning algorithm for evolving neo-fuzzy neuron , 2014, Appl. Soft Comput..

[14]  Qingsong Ai,et al.  Gestures recognition based on wavelet and LLE , 2013, Australasian physical & engineering sciences in medicine.

[15]  S. Puthusserypady,et al.  Nonlinear analysis of EMG signals - a chaotic approach , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  L. Cao.  Practical method for determining the minimum embedding dimension of a scalar time series , 1997 .

[17]  Sabine Van Huffel,et al.  Source Separation From Single-Channel Recordings by Combining Empirical-Mode Decomposition and Independent Component Analysis , 2010, IEEE Transactions on Biomedical Engineering.

[18]  Yanli Meng,et al.  Test nonlinear determinacy of Electromyogram , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[19]  Philippe Terrier,et al.  Kinematic variability, fractal dynamics and local dynamic stability of treadmill walking , 2011, Journal of NeuroEngineering and Rehabilitation.

[20]  Yasuji Sawada,et al.  Practical Methods of Measuring the Generalized Dimension and the Largest Lyapunov Exponent in High Dimensional Chaotic Systems , 1987 .

[21]  Bo Yang,et al.  Feature selection and classification using flexible neural tree , 2006, Neurocomputing.

[22]  Ajith Abraham,et al.  Swarm Intelligence: Foundations, Perspectives and Applications , 2006, Swarm Intelligent Systems.

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

[24]  S. S. Shen,et al.  Applications of Hilbert–Huang transform to non‐stationary financial time series analysis , 2003 .

[25]  Kevin P Granata,et al.  Stability of Dynamic Trunk Movement , 2006, Spine.