GSFAP Adaptive Filtering Using Log Arithmetic for Resource-Constrained Embedded Systems

0341115 - ÚTIA 2011 RIV US eng J - Journal Article
Tichý, Milan - Schier, Jan - Gregg, D.
GSFAP Adaptive Filtering Using Log Arithmetic for Resource-Constrained Embedded Systems.
ACM Transactions on Embedded Computing Systems. Roč. 9, č. 3 (2010), s. 1-31. ISSN 1539-9087. E-ISSN 1558-3465
R&D Projects: GA MŠMT 7H09005
Institutional research plan: CEZ:AV0Z10750506
Keywords : FPGA * DSP * logarithmic arithmetic * affine projection
Subject RIV: BD - Theory of Information
Impact factor: 1.057, year: 2010
http://library.utia.cas.cz/separaty/2010/ZS/tichy-0341115.pdf

This article shows that FPGA devices are a highly suitable platform for more computationally intensive adaptive algorithms. We present an optimized core which implements GSFAP. GSFAP is an algorithm with far superior adaptation properties than NLMS, and with only slightly higher computational complexity. To further optimize resource requirements we use logarithmic arithmetic, rather than conventional floating point, within the custom core.
Permanent Link: http://hdl.handle.net/11104/0184199