Using LMS & NLMS algorithm, the system identification is implemented in MATLAB.
A method for system identification is proposed that is based on the error-correcting training procedure in learning machines and is referred to as ‘learning identification’. The algorithm is the procedure used to adjust the adaptive filter coefficients to minimize a prescribed criterion i.e., error signal. Most reported developments and applications use the FIR filter with the LMS algorithm because it relatively simple to design and implement. Many adaptive algorithms can be viewed as approximations of the wiener filter. A new framework for designing robust adaptive filters is introduced. It is based on the optimization of a certain cost function subject to a time-dependent constraint on the norm of the filter update. Particularly, we present a robust variable step-size LMS & NLMS algorithm which optimizes the square of the a posteriori error. This report also shows the link between the proposed algorithm and another one derived using a robust statistics approach. In addition, a theoretical model for predicting the transient and steady-state behaviour and a proof of almost sure filter convergence is provided. The algorithm is then tested in different environments for system identification.
MUST need MATLAB 2015a or greater version with DSP-Communication Toolbox and Visualization Toolbox Also, one can use the online MATLAB available.
Note= To use MATLAB, one might have to use institutional login or might have to work with free trial.
I advise to use the book of the Monson H. Hayes for the reference with the codes and the explaination. See Statistical Digital Signal Processing and Modeling for the more information.
Distributed under the GNU License. See LICENSE for more information.