-
Home
- Adaptive filters
- Adaptive filters
- Summary of adaptive filtering
-
Lms
remains the simplest and best algorithm when
slow convergence is not a serious issue (typically used)
-
Nlms
simple extension of the LMS with much faster
convergence in many cases (very commonly used)
-
Frequency-domain methods
offer computational savings
(
) for long filters and usually offer faster
convergence, too (sometimes used; very commonly used whenthere are already FFTs in the system)
-
Lattice methods
are stable and converge quickly,
but cost substantially more than LMS and have higher residualEMSE than many methods (very occasionally used)
-
Rls
algorithms that converge quickly and are
stable exist. However, they are considerably more expensivethan LMS. (almost never used)
-
Block rls
(least squares) methods exist and can
be pretty efficient in some cases. (occasionally used)
,
,
-
Iir
methods are difficult to implement
successfully and pose certain difficulties, but are sometimesused in some applications, for example noise cancellation of
low frequency noise (very occasionally used)
-
Cma
very useful when applicable (blind
equalization); CMA is
the method for
blind equalizer initialization (commonly used in a few specific equalization applications)
In general, getting adaptive filters to work well in an
application is much more challenging than, say, FFTs or IIRfilters; they generally require lots of tweaking!
Source:
OpenStax, Adaptive filters. OpenStax CNX. May 12, 2005 Download for free at http://cnx.org/content/col10280/1.1
Google Play and the Google Play logo are trademarks of Google Inc.
