Robust least mean mixed norm adaptive filtering for α-stable random processes
Date
1997Source Title
Proceedings of the 1997 IEEE International Symposium on Circuits and Systems
Print ISSN
0271-4310
Publisher
IEEE
Pages
2296 - 2299
Language
English
Type
Conference PaperItem Usage Stats
125
views
views
96
downloads
downloads
Metadata
Show full item recordAbstract
Based on the concept of Fractional Lower Order Statistics (FLOS), we present the Robust Least Mean Mixed Norm (RLMMN) adaptive algorithm for applications in impulsive environments modeled by α-stable distributions. A sufficient condition for finite variance of the update term is obtained for the underlying α-stable process. Simulation results are provided regarding the identification of the parameters of an AR system.
Keywords
Adaptive algorithmsMathematical models
Probability
Random processes
Spurious signal noise
Robust least mean mixed norm adaptive algorithm
Robust least mean mixed norm adaptive filtering
Adaptive filtering
Permalink
http://hdl.handle.net/11693/27713Published Version (Please cite this version)
https://www.doi.org/10.1109/ISCAS.1997.612781Collections
Related items
Showing items related by title, author, creator and subject.
-
Boosted LMS-based piecewise linear adaptive filters
(IEEE, 2016)We introduce the boosting notion extensively used in different machine learning applications to adaptive signal processing literature and implement several different adaptive filtering algorithms. In this framework, we ... -
Adaptive control design for nonlinear systems via successive approximations
(ASME, 2017)The paper presents an approach to the Model Reference Adaptive Control (MRAC) design for nonlinear dynamical systems. A nonlinear reference system is considered such that its response is designed to be stable via Successive ... -
Improved convergence performance of adaptive algorithms through logarithmic cost
(IEEE, 2014-05)We present a novel family of adaptive filtering algorithms based on a relative logarithmic cost. The new family intrinsically combines the higher and lower order measures of the error into a single continuous update based ...
