Title :
The leaky least mean mixed norm algorithm
Author :
Nasar, Mohammed Abdul ; Zerguine, Azzedine
Author_Institution :
Dept. of Electr. Eng., King Fahd Univ. of Pet. & Miner., Dhahran, Saudi Arabia
Abstract :
In this work, a leakage-based variant of the Least Mean Mixed Norm (LMMN) algorithm, the leaky Least Mean Mixed Norm (LLMMN) algorithm, is derived. The proposed algorithm will help mitigate the weight drift problem experienced in the conventional Least Mean Square (LMS) and Least Mean Fourth (LMF) algorithms. The main aim of this work is to derive the LLMMN adaptive algorithm and conduct transient analysis using the energy conservation relation framework. Finally, a number of simulation results are carried out to corroborate the theoretical findings, and show improved performance obtained through the use of LLMMN over the conventional LMMN algorithm in a weight drift environment.
Keywords :
adaptive filters; least mean squares methods; transient analysis; LLMMN adaptive algorithm; LMF algorithms; LMS algorithms; energy conservation relation framework; leakage-based variant; leaky least mean mixed norm algorithm; least mean fourth algorithms; least mean square algorithms; transient analysis; weight drift problem; Algorithm design and analysis; Convergence; Least squares approximations; Noise; Stability analysis; Transient analysis; Vectors; Adaptive filters; leaky least mean mixed norm; weight drift;
Conference_Titel :
Signals, Systems and Computers, 2013 Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
978-1-4799-2388-5
DOI :
10.1109/ACSSC.2013.6810550
