Title :
A modified adaptive sign algorithm used on the hybrid norm error criterion
Author :
Cho, Sung Ho ; Kim, Sang Duck ; Kim, Seong Su
Author_Institution :
Dept. of Electron. Eng., Hanyang Univ., Ansan, South Korea
Abstract :
In this paper a modified adaptive sign (MSA) algorithm based on the hybrid norm error criterion is described. The hybrid norm error criterion to be minimized is built as a combined convex function of the mean-absolute error and the mean-absolute error to the third power. Under a set of mild assumptions, the nonlinear evolution equations that characterize the statistical mean and mean-squared behavior of the algorithm are derived. Computer simulations are carried out to verify the validity of our derivations.
Keywords :
adaptive estimation; adaptive filters; filtering theory; adaptive filters; combined convex function; hybrid norm error criterion; mean-absolute error; mean-squared behavior; modified adaptive sign algorithm; nonlinear evolution equations; statistical mean; Adaptive algorithm; Application software; Computer errors; Computer simulation; Convergence; Filtering algorithms; Least squares approximation; Nonlinear equations; Robustness; Stability;
Conference_Titel :
Circuits and Systems, 1997. Proceedings of the 40th Midwest Symposium on
Print_ISBN :
0-7803-3694-1
DOI :
10.1109/MWSCAS.1997.662331
