Title :
The ε-normalized sign regressor least mean square (NSRLMS) adaptive algorithm
Author :
Faiz, Mohammed Mujahid Ulla ; Zerguine, Azzedine
Author_Institution :
Electr. Eng. Dept., King Fahd Univ. of Pet. & Miner., Dhahran, Saudi Arabia
Abstract :
In this paper, expressions are derived for the steady-state and tracking excess-mean-square error (EMSE) of the ε-normalized sign regressor least mean square (NSRLMS) adaptive algorithm. Finally, it is shown that simulations performed for both the cases of white and correlated Gaussian regressors substantiate very well the theory developed.
Keywords :
Gaussian processes; correlation theory; least mean squares methods; regression analysis; ε-normalized sign regressor least mean square adaptive algorithm; NSRLMS; correlated Gaussian regressors; excess-mean-square error; white Gaussian regressors; Algorithm design and analysis; Least squares approximation; Random variables; Signal processing algorithms; Simulation; Steady-state; Vectors;
Conference_Titel :
Signal and Image Processing Applications (ICSIPA), 2011 IEEE International Conference on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4577-0243-3
DOI :
10.1109/ICSIPA.2011.6144114
