Modeling, Estimation and Optimal Filtration in Signal ProcessingThe purpose of this book is to provide graduate students and practitioners with traditional methods and more recent results for model-based approaches in signal processing. Firstly, discrete-time linear models such as AR, MA and ARMA models, their properties and their limitations are introduced. In addition, sinusoidal models are addressed. Secondly, estimation approaches based on least squares methods and instrumental variable techniques are presented. Finally, the book deals with optimal filters, i.e. Wiener and Kalman filtering, and adaptive filters such as the RLS, the LMS and their variants. |
Contents
Parametric Models | 1 |
Least Squares Estimation of Parameters of Linear Models | 49 |
Matched and Wiener Filters | 105 |
Copyright | |
11 other sections not shown
Common terms and phrases
045 05 Normalized 05 Normalized frequency a₁ adaptive filter additive noise algorithm Alm(z analysis approach ARMA model autocorrelation function autocorrelation matrix Automatic Control autoregressive calculation cepstrum Chapter coefficients colored noise consider convergence covariance matrix defined as follows denoted driving process eigenvalues error extended Kalman filter Figure Hankel matrix hopt Identification IEEE IEEE Trans IEEE-ICASSP impulse response input Instrumental Variable introduced iteration Kailath Kalman gain least squares estimation least squares method linear measurement noise modified Moreover Najim noise b(k noisy observations noisy signal nonlinear Normalized frequency observation noise obtain optimal filter parameter estimation particle filtering prediction process u(k proposed Re(z s₁ satisfies the following sequence Signal Processing signal s(k solution space representation Speech Enhancement speech signal subspace techniques transfer function updated variance vector x(k white noise Wiener filter z-plane z-transform zero