Title
Efficient Implementations Of Complex Block Conjugate Gradient Lms With Individual Adaptation
Abstract
Recent advances in signal processing hardware has made possible the implementation of sophisticated algorithms. The Complex Block Conjugate Least Mean Square algorithm with Individual adaptation (CBCI-LMS) has recently been proposed and applied in adaptive filtering applications. This technique involves matrix inversion, which is computationally intensive. To improve the feasibility of the algorithm in practice, especially for high-order adaptive systems, this paper proposes two efficient implementations of the CBCI-LMS algorithm. The first efficient implementation applies an iterative matrix inversion lemma without any sacrifice in convergence speed and accuracy. The second method further simplifies the algorithm by using a diagonal matrix for approximation at the first iteration, at the expense of a few additional iterations to achieve convergence. Both of the simplified approaches effectively reduce the computational complexities of the CBCI-LMS algorithm. © 2013 IEEE.
Publication Date
12-1-2013
Publication Title
Midwest Symposium on Circuits and Systems
Number of Pages
1403-1406
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/MWSCAS.2013.6674919
Copyright Status
Unknown
Socpus ID
84893194100 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84893194100
STARS Citation
Liu, Ying and Mikhael, Wasfy B., "Efficient Implementations Of Complex Block Conjugate Gradient Lms With Individual Adaptation" (2013). Scopus Export 2010-2014. 5842.
https://stars.library.ucf.edu/scopus2010/5842