A Multiple Beta Wavelet-Based Locally Regularized Ultraorthogonal Forward Regression Algorithm for Time-Varying System Identification With Applications to EEG

Time-varying (TV) nonlinear systems widely exist in various fields of engineering and science. Effective identification and modeling of TV systems is a challenging problem due to the nonstationarity and nonlinearity of the associated processes. In this paper, a novel parametric modeling algorithm is proposed to deal with this problem based on a TV nonlinear autoregressive with exogenous input (TV-NARX) model. A new class of multiple beta wavelet (MBW) basis functions is introduced to represent the TV coefficients of the TV-NARX model to enable the tracking of both smooth trends and sharp changes of the system behavior. To produce a parsimonious model structure, a locally regularized ultraorthogonal forward regression (LRUOFR) algorithm aided by the adjustable prediction error sum of squares (APRESS) criterion is investigated for sparse model term selection and parameter estimation. Simulation studies and a real application to EEG data show that the proposed MBW-LRUOFR algorithm can effectively capture the global and local features of nonstationary systems and obtain an optimal model, even for signals contaminated with severe colored noise.

[1]  Tingwen Huang,et al.  Time-Varying System Identification Using an Ultra-Orthogonal Forward Regression and Multiwavelet Basis Functions With Applications to EEG , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[2]  S. Billings,et al.  Time-varying model identification for time–frequency feature extraction from EEG data , 2011, Journal of Neuroscience Methods.

[3]  Xia Hong,et al.  Robust neurofuzzy rule base knowledge extraction and estimation using subspace decomposition combined with regularization and D-optimality , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Hua-Liang Wei,et al.  A robust model structure selection method for small sample size and multiple datasets problems , 2018, Inf. Sci..

[5]  Anil Kumar,et al.  Beta wavelet based ECG signal compression using lossless encoding with modified thresholding , 2013, Comput. Electr. Eng..

[6]  Stephen A. Billings,et al.  Ultra-Orthogonal Forward Regression Algorithms for the Identification of Non-Linear Dynamic Systems , 2016, Neurocomputing.

[7]  Ke Li,et al.  A multiwavelet-based time-varying model identification approach for time-frequency analysis of EEG signals , 2016, Neurocomputing.

[8]  Hélio M. de Oliveira,et al.  Compactly Supported One-cyclic Wavelets Derived from Beta Distributions , 2015, Anais do XXII Simpósio Brasileiro de Telecomunicações.

[9]  Sami El-Ferik,et al.  Modeling and Identification of Nonlinear Systems: A Review of the Multimodel Approach—Part 1 , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[10]  Jian Yang,et al.  Multilinear Sparse Principal Component Analysis , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Stephen A. Billings,et al.  A Parametric Method to Measure Time-Varying Linear and Nonlinear Causality With Applications to EEG Data , 2013, IEEE Transactions on Biomedical Engineering.

[12]  Sandeep Raj,et al.  ECG Signal Analysis Using DCT-Based DOST and PSO Optimized SVM , 2017, IEEE Transactions on Instrumentation and Measurement.

[13]  Johan Schoukens,et al.  Structure Detection of Wiener–Hammerstein Systems With Process Noise , 2017, IEEE Transactions on Instrumentation and Measurement.

[14]  Yang Li,et al.  Identification of Time-Varying Systems Using Multi-Wavelet Basis Functions , 2011, IEEE Transactions on Control Systems Technology.

[15]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[16]  C. L. Philip Chen,et al.  I-Ching Divination Evolutionary Algorithm and its Convergence Analysis , 2017, IEEE Transactions on Cybernetics.

[17]  Håkan Hjalmarsson,et al.  A Multi-Time-Scale Generalization of Recursive Identification Algorithm for ARMAX Systems , 2015, IEEE Transactions on Automatic Control.

[18]  Benoît Champagne,et al.  Estimation of Space-Time Varying Parameters Using a Diffusion LMS Algorithm , 2014, IEEE Transactions on Signal Processing.

[19]  Lina Wang,et al.  High-resolution time–frequency representation of EEG data using multi-scale wavelets , 2017, Int. J. Syst. Sci..

[20]  Stephen A. Billings,et al.  Sparse Model Identification Using a Forward Orthogonal Regression Algorithm Aided by Mutual Information , 2007, IEEE Transactions on Neural Networks.

[21]  Ke Li,et al.  Epileptic Seizure Classification of EEGs Using Time–Frequency Analysis Based Multiscale Radial Basis Functions , 2018, IEEE Journal of Biomedical and Health Informatics.

[22]  Sheng Chen,et al.  Nonlinear Identification Using Orthogonal Forward Regression With Nested Optimal Regularization , 2015, IEEE Transactions on Cybernetics.

[23]  Emanuel A. P. Habets,et al.  Online Dereverberation for Dynamic Scenarios Using a Kalman Filter With an Autoregressive Model , 2016, IEEE Signal Processing Letters.

[24]  Chi-Hung Huang,et al.  Application of Cauchy wavelet transformation to identify time-variant modal parameters of structures , 2016 .

[25]  Teodoro Alamo,et al.  Slide Window Bounded-Error Time-Varying Systems Identification , 2016, IEEE Transactions on Automatic Control.

[26]  Tadeusz Uhl,et al.  Identification of modal parameters of non-stationary systems with the use of wavelet based adaptive filtering , 2014 .

[27]  N. Birbaumer,et al.  BCI2000: a general-purpose brain-computer interface (BCI) system , 2004, IEEE Transactions on Biomedical Engineering.

[28]  S. Billings.  Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains , 2013 .

[29]  Yang Li,et al.  Time-varying linear and nonlinear parametric model for Granger causality analysis. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[30]  Tong Zhang,et al.  Design of Highly Nonlinear Substitution Boxes Based on I-Ching Operators , 2018, IEEE Transactions on Cybernetics.

[31]  Stephen A. Billings,et al.  Identification and frequency domain analysis of non-stationary and nonlinear systems using time-varying NARMAX models , 2015, Int. J. Syst. Sci..

[32]  Johan Schoukens,et al.  Nonparametric Time-Domain Identification of Linear Slowly Time-Variant Systems Using B-Splines , 2015, IEEE Transactions on Instrumentation and Measurement.

[33]  Tao Song,et al.  Hybrid Time-Variant Frequency Response Function Estimates Using Multiple Sets of Basis Functions , 2017, IEEE Transactions on Instrumentation and Measurement.

[34]  Kei Hirose,et al.  Readouts for echo-state networks built using locally regularized orthogonal forward regression , 2011 .

[35]  C. L. Philip Chen,et al.  Gradient Radial Basis Function Based Varying-Coefficient Autoregressive Model for Nonlinear and Nonstationary Time Series , 2015, IEEE Signal Processing Letters.

[36]  Aggelos K. Katsaggelos,et al.  Bayesian Simultaneous Sparse Approximation With Smooth Signals , 2013, IEEE Transactions on Signal Processing.

[37]  Chokri Ben Amar,et al.  Beta wavelets. Synthesis and application to lossy image compression , 2005, Adv. Eng. Softw..