Please use this identifier to cite or link to this item:
|Title:||A class of affine projection filters that exploit sparseness under symmetric alpha-Stable noise||Authors:||Pelekanakis, K.
|Issue Date:||2013||Citation:||Pelekanakis, K.,Chitre, M. (2013). A class of affine projection filters that exploit sparseness under symmetric alpha-Stable noise. OCEANS 2013 MTS/IEEE Bergen: The Challenges of the Northern Dimension : -. ScholarBank@NUS Repository. https://doi.org/10.1109/OCEANS-Bergen.2013.6607964||Abstract:||A new algorithmic framework for sparse underwater acoustic channel estimation under the presence of Symmetric α-Stable (SαS) noise is proposed. The framework is inspired by the low-complexity affine projection algorithm (APA) and employs a novel cost function that includes robust methods for impulsive noise suppression and a sparseness constraint. The constraint exploits the non-isotropic (Riemannian) structure of the channel, which leads to natural gradient adaptation. Based on this framework, new algorithms are derived with linear algorithmic complexity. The effectiveness of the new algorithms is confirmed by computer simulations. © 2013 IEEE.||Source Title:||OCEANS 2013 MTS/IEEE Bergen: The Challenges of the Northern Dimension||URI:||http://scholarbank.nus.edu.sg/handle/10635/68728||ISBN:||9781479900015||DOI:||10.1109/OCEANS-Bergen.2013.6607964|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Apr 13, 2019
checked on Apr 19, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.