Title :
A new class of gradient adaptive step-size LMS algorithms
Author :
Ang, Wee-Peng ; Farhang-Boroujeny, B.
Author_Institution :
Dept. of Wireless Technol. Centre, Nanyang Polytech., Singapore
fDate :
4/1/2001 12:00:00 AM
Abstract :
The gradient adaptive step-size least-mean-square (LMS) algorithms [an important family of variable step-size LMS (VSLMS) algorithms] are revisited. We propose a simplification to a class of the studied algorithms and show that this leads to a new class of VSLMS algorithms with reduced complexity but with no observable loss in performance
Keywords :
adaptive filters; adaptive signal processing; computational complexity; filtering theory; least mean squares methods; VSLMS algorithms; adaptive filters; adaptive signal processing; gradient adaptive step-size LMS algorithms; multipath channels; reduced complexity algorithms; variable step-size LMS algorithms; Adaptive filters; Adaptive signal processing; Channel estimation; Communication channels; Degradation; Least squares approximation; Noise measurement; Performance loss; Signal processing algorithms; Working environment noise;
Journal_Title :
Signal Processing, IEEE Transactions on
