Two-directional two-dimensional principal component analysis based on wavelet decomposition for high-dimensional biomedical signals classification

Here, we present a multi-scale two-directional two-dimensional principal component analysis (MS2D2PCA) method for the efficient and effective extraction of essential feature information from signals. Time-invariant multi-scale matrices are constructed in the first step. The two-directional two-dimensional principal component analysis then operates on the multi-scale matrices to reduce the dimension, rather than vectors in conventional PCA. Results are presented from an experiment to classify twenty hand motions using 89-channel EMG signals recorded in stroke survivors, which illustrates the efficiency and effectiveness of the proposed method for biomedical signal analysis. With this multi-scale two-directional two-dimensional principal component analysis for high-dimensional signal classification, spatial-time-frequency discriminant information from high-dimensional EMG electrode array can be effectively extracted and reduced using the proposed method. Compared with the time domain feature extraction in conjunction with PCA, MS2D2PCA performed better with higher classification accuracy and less PCs in EMG classification. The efficiency and effectiveness of the method can be further validated by using high-dimensional EEG, MEG, fMRI signals. Although the present study focuses on high-dimensional signal pattern classification, based on the PCs obtained at multiple scales, it is relatively straightforward to expand MS2D2PCA for high-dimensional signal compression, denoising, component extraction, and other related tasks.

[1]  Daoqiang Zhang,et al.  (2D)2PCA: Two-directional two-dimensional PCA for efficient face representation and recognition , 2005, Neurocomputing.

[2]  U. Rajendra Acharya,et al.  Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform , 2013, Knowl. Based Syst..

[3]  Roisin Delaney,et al.  A method for quantifying dynamic muscle dysfunction in children and young adults with cerebral palsy. , 2007, Gait & posture.

[4]  Alejandro F. Frangi,et al.  Two-dimensional PCA: a new approach to appearance-based face representation and recognition , 2004 .

[5]  Ahmad Taher Azar,et al.  Classification of EEG-Based Brain-Computer Interfaces , 2014, Advanced Intelligent Computational Technologies and Decision Support Systems.

[6]  Mehmet Korürek,et al.  Clustering MIT-BIH arrhythmias with Ant Colony Optimization using time domain and PCA compressed wavelet coefficients , 2010, Digit. Signal Process..

[7]  K. Englehart,et al.  Classification of the myoelectric signal using time-frequency based representations. , 1999, Medical engineering & physics.

[8]  V. von Tscharner,et al.  Estimation of the interplay between groups of fast and slow muscle fibers of the tibialis anterior and gastrocnemius muscle while running. , 2006, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[9]  Mehran Jahed,et al.  Real-time intelligent pattern recognition algorithm for surface EMG signals , 2007, Biomedical engineering online.

[10]  H A Weiderpass,et al.  Time-frequency analysis methods for detecting effects of diabetic neuropathy. , 2013, International journal for numerical methods in biomedical engineering.

[11]  Mansoor Zolghadri Jahromi,et al.  Block-wise two-directional 2DPCA with ensemble learning for face recognition , 2013, Neurocomputing.

[12]  Alan Wee-Chung Liew,et al.  Symplectic geometry spectrum analysis of nonlinear time series , 2014, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[13]  M. Wacker,et al.  Time-frequency Techniques in Biomedical Signal Analysis , 2013, Methods of Information in Medicine.

[14]  Paul S Addison,et al.  Wavelet transforms and the ECG: a review , 2005, Physiological measurement.

[15]  F. D. Silva,et al.  EEG and MEG: Relevance to Neuroscience , 2013, Neuron.

[16]  J. Wakeling,et al.  Muscle fibre recruitment can respond to the mechanics of the muscle contraction , 2006, Journal of The Royal Society Interface.

[17]  S. Dokos,et al.  A hybrid symplectic principal component analysis and central tendency measure method for detection of determinism in noisy time series with application to mechanomyography. , 2013, Chaos.

[18]  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.

[19]  James M Wakeling,et al.  Spectral properties of electromyographic and mechanomyographic signals during isometric ramp and step contractions in biceps brachii. , 2011, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[20]  Heidelberg,et al.  Representing complex data using localized principal components with application to astronomical data , 2007, 0709.1538.

[21]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[22]  Wei Guo,et al.  Noise Smoothing for Nonlinear Time Series Using Wavelet Soft Threshold , 2007, IEEE Signal Processing Letters.

[23]  Socrates Dokos,et al.  A symplectic geometry-based method for nonlinear time series decomposition and prediction , 2013 .

[24]  Zhizhong Wang,et al.  Mean frequency derived via Hilbert-Huang transform with application to fatigue EMG signal analysis , 2006, Comput. Methods Programs Biomed..

[25]  Harun Uguz,et al.  A hybrid system based on information gain and principal component analysis for the classification of transcranial Doppler signals , 2012, Comput. Methods Programs Biomed..

[26]  D. F. Lovely,et al.  Myo-electric signals to augment speech recognition , 2001, Medical and Biological Engineering and Computing.

[27]  Paul D. Gader,et al.  2009 Special Issue: RKF-PCA: Robust kernel fuzzy PCA , 2009 .

[28]  Nils Östlund,et al.  Signal processing of the surface electromyogram to gain insight into neuromuscular physiology , 2009, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[29]  Ali Jalali,et al.  An improved procedure for detection of heart arrhythmias with novel pre-processing techniques , 2012, Expert Syst. J. Knowl. Eng..

[30]  Hong-Bo Xie,et al.  Estimation of wrist angle from sonomyography using support vector machine and artificial neural network models. , 2009, Medical engineering & physics.

[31]  U. Rajendra Acharya,et al.  Use of principal component analysis for automatic classification of epileptic EEG activities in wavelet framework , 2012, Expert Syst. Appl..

[32]  Nitin Afzulpurkar,et al.  Use of supervised discretization with PCA in wavelet packet transformation-based surface electromyogram classification , 2009, Biomed. Signal Process. Control..

[33]  Hong-Bo Xie,et al.  Classification of the mechanomyogram signal using a wavelet packet transform and singular value decomposition for multifunction prosthesis control , 2009, Physiological measurement.

[34]  Ping Zhou,et al.  High-Density Myoelectric Pattern Recognition Toward Improved Stroke Rehabilitation , 2012, IEEE Transactions on Biomedical Engineering.

[35]  Chandan Chakraborty,et al.  Automated Screening of Arrhythmia Using Wavelet Based Machine Learning Techniques , 2012, Journal of Medical Systems.