Convergence Analysis of Adaptive Filters Using Normalized Sign-Sign Algorithm

Shin'ichi KOIKE  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E88-A   No.11   pp.3218-3224
Publication Date: 2005/11/01
Online ISSN: 
DOI: 10.1093/ietfec/e88-a.11.3218
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Digital Signal Processing
Keyword: 
convergence analysis,  adaptive filter,  normalized sign-sign algorithm,  

Full Text: PDF>>
Buy this Article




Summary: 
This letter develops convergence analysis of normalized sign-sign algorithm (NSSA) for FIR-type adaptive filters, based on an assumption that filter tap weights are Gaussian distributed. We derive a set of difference equations for theoretically calculating transient behavior of filter convergence, when the filter input is a White & Gaussian process. For a colored Gaussian input and a large number of tap weights, approximate difference equations are also proposed. Experiment with simulations and theoretical calculations of filter convergence demonstrates good agreement between simulations and theory, proving the validity of the analysis.