Classification of EMG signals using wavelet neural network

An accurate and computationally efficient means of classifying electromyographic (EMG) signal patterns has been the subject of considerable research effort in recent years. Quantitative analysis of EMG signals provides an important source of information for the diagnosis of neuromuscular disorders. Following the recent development of computer-aided EMG equipment, different methodologies in the time domain and frequency domain have been followed for quantitative analysis. In this study, feedforward error backpropagation artificial neural networks (FEBANN) and wavelet neural networks (WNN) based classifiers were developed and compared in relation to their accuracy in classification of EMG signals. In these methods, we used an autoregressive (AR) model of EMG signals as an input to classification system. A total of 1200 MUPs obtained from 7 normal subjects, 7 subjects suffering from myopathy and 13 subjects suffering from neurogenic disease were analyzed. The success rate for the WNN technique was 90.7% and for the FEBANN technique 88%. The comparisons between the developed classifiers were primarily based on a number of scalar performance measures pertaining to the classification. The WNN-based classifier outperformed the FEBANN counterpart. The proposed WNN classification may support expert decisions and add weight to EMG differential diagnosis.

[1]  Kwok-Wo Wong,et al.  On-line Successive Synthesis of Wavelet Networks , 1998, Neural Processing Letters.

[2]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[3]  Abdulhamit Subasi,et al.  Wavelet neural network classification of EEG signals by using AR model with MLE preprocessing , 2005, Neural Networks.

[4]  N. Thakor,et al.  Spectral analysis methods for neurological signals , 1998, Journal of Neuroscience Methods.

[5]  Abdulhamit Subasi,et al.  Comparison of subspace-based methods with AR parametric methods in epileptic seizure detection , 2006, Comput. Biol. Medicine.

[6]  J Pardey,et al.  A review of parametric modelling techniques for EEG analysis. , 1996, Medical engineering & physics.

[7]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[8]  N. Malmurugan,et al.  Neural classification of lung sounds using wavelet coefficients , 2004, Comput. Biol. Medicine.

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

[10]  K Kunze,et al.  Frequency analysis and duration of motor unit potentials: reliability and diagnostic usefulness. , 1993, Electroencephalography and clinical neurophysiology.

[11]  C S Pattichis,et al.  Learning systems in biosignal analysis. , 1997, Bio Systems.

[12]  Roberto Kawakami Harrop Galvão,et al.  Linear-wavelet networks , 2004 .

[13]  M.H. Hassoun,et al.  NNERVE: Neural Network Extraction of Repetitive Vectors for Electromyography. I. Algorithm , 1994, IEEE Transactions on Biomedical Engineering.

[14]  Abdulhamit Subasi,et al.  Classification of EEG signals using neural network and logistic regression , 2005, Comput. Methods Programs Biomed..

[15]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[16]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[17]  Constantinos S. Pattichis,et al.  Neural network models in EMG diagnosis , 1995 .

[18]  Abdulhamit Subasi,et al.  Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients , 2005, Expert Syst. Appl..

[19]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[20]  Gérard Dreyfus,et al.  Initialization by selection for wavelet network training , 2000, Neurocomputing.

[21]  Daniel W. C. Ho,et al.  A basis selection algorithm for wavelet neural networks , 2002, Neurocomputing.

[22]  M.H. Hassoun,et al.  NNERVE: Neural Network Extraction of Repetitive Vectors for Electromyography. II. Performance analysis , 1994, IEEE Transactions on Biomedical Engineering.

[23]  Yagyensh C. Pati,et al.  Analysis and synthesis of feedforward neural networks using discrete affine wavelet transformations , 1993, IEEE Trans. Neural Networks.

[24]  S. Tseng,et al.  Evaluation of parametric methods in EEG signal analysis. , 1995, Medical engineering & physics.

[25]  Jay A. Farrell,et al.  Wavelet-based system identification for nonlinear control , 1999, IEEE Trans. Autom. Control..

[26]  Ahmet Alkan,et al.  Automatic seizure detection in EEG using logistic regression and artificial neural network , 2005, Journal of Neuroscience Methods.

[27]  C.S. Pattichis,et al.  Time-scale analysis of motor unit action potentials , 1999, IEEE Transactions on Biomedical Engineering.

[28]  John G. Proakis,et al.  Digital Signal Processing: Principles, Algorithms, and Applications , 1992 .

[29]  S. Andreassen,et al.  Quantitative Analysis of Individual Motor Unit Potentials: A Proposition for Standardized Terminology and Criteria for Measurement , 1986, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[30]  John G. Proakis,et al.  Digital signal processing (3rd ed.): principles, algorithms, and applications , 1996 .

[31]  Qinghua Zhang,et al.  Using wavelet network in nonparametric estimation , 1997, IEEE Trans. Neural Networks.

[32]  Jun Zhang,et al.  Wavelet neural networks for function learning , 1995, IEEE Trans. Signal Process..

[33]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[34]  G Pfurtscheller,et al.  Using time-dependent neural networks for EEG classification. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[35]  A. Wennberg,et al.  Computer analysis of EEG signals with parametric models , 1981, Proceedings of the IEEE.

[36]  C.I. Christodoulou,et al.  Unsupervised pattern recognition for the classification of EMG signals , 1999, IEEE Transactions on Biomedical Engineering.

[37]  Elif Derya Übeyli,et al.  Application of classical and model-based spectral methods to ophthalmic arterial Doppler signals with uveitis disease , 2003, Comput. Biol. Medicine.

[38]  C. Pattichis,et al.  Autoregressive and cepstral analyses of motor unit action potentials. , 1999, Medical engineering & physics.

[39]  S.M. Kay,et al.  Spectrum analysis—A modern perspective , 1981, Proceedings of the IEEE.

[40]  Inan Güler,et al.  AR spectral analysis of EEG signals by using maximum likelihood estimation , 2001, Comput. Biol. Medicine.

[41]  Gérard Dreyfus,et al.  Training wavelet networks for nonlinear dynamic input-output modeling , 1998, Neurocomputing.

[42]  G. H. Loudon,et al.  New signal processing techniques for the decomposition of EMG signals , 1992, Medical and Biological Engineering and Computing.

[43]  Stefano Sello,et al.  Cross-correlation time-frequency analysis for multiple EMG signals in Parkinson's disease: a wavelet approach. , 2003, Medical engineering & physics.