Sign in

username:

password:



Not a member?

Search matlab



Search tips

Subscribe to matlab



matlab by Keywords

Atanh | Autocorrelation | Bandpass Filter | C++ | Conv | Database | Deconv | Excel | FFT | Filter | Filtering | FIR | Fourier Transfrom | FSK | Gaussian Noise | Haykin | IFFT | Image | Java | LFSR | LMS | LPC | MEX | OFDM | QPSK | Radix | Random | Sampling | Segmentation | Simulink | Visual Basic | Waveform | Wavelet

Ads

Discussion Groups

Discussion Groups | Matlab DSP | Adaptive filtering

Technical discussion about Matlab and issues related to Digital Signal Processing.

  

Post a new Thread

Adaptive filtering - narokel - Oct 20 17:16:00 2002



Hello,

I am beginning to learn dsp and would very much appreciate some help
regarding adaptive filtering.

I have an input signal and an output signal. I would like to design a
filter such that when convolved with the input signal, the output
signal will be produced.

I have been reading up on the LMS technique for calculating the
filter coefficients. The book that I have been using describes a
method of calculating the filter coefficients for one input/output
signal.

Suppose I have many input signals, and their corresponding output
signals. Can the LMS technique be used to produce a 'general' filter,
based on all the input/output signals.

I am using MATLAB and would very much appreciate any help or pointers
as to where I can find help.

Thanks






(You need to be a member of matlab -- send a blank email to matlab-subscribe@yahoogroups.com )

Re: Adaptive filtering - Author Unknown - Oct 21 14:24:00 2002

i have a few questions b4 suggesting an answer
r u particular about LMS or an online technique or any other method is fine?
what are the requirements & constraints on implementation?
is the input signal stationary?

if ur objective is to simulate in matlab, i would suggest that u try wiener
solution first.. its easy to implement in matlab and for stationary signals,
thats the best u can do. since u dont have theoretical background in LMS i
wouldnt suggest implementing it unless u r sure where & how to tweak

anyways... now the answers...
if u r using wiener filter method, find out the filter coefficients for each
one of the i/o combo and then average them
if u r using LMS or any online method, make a longer input signal by appending
the individual ones and longer desired signal by correspondingly appending
their desired signals
say if u have i/o pairs (x1,y1), (x2,y2),...
then make ([x1,x2,...],[y1,y2,...])
now run through ur LMS...
try to change the order in which x1, x2 appear and simulate again... find out
whether the result remains the same

mail me if u need more details
hope this helps ----- Original Message -----
From: narokel
To:
Sent: Sunday, October 20, 2002 1:16 PM
Subject: [matlab] Adaptive filtering Hello,

I am beginning to learn dsp and would very much appreciate some help
regarding adaptive filtering.

I have an input signal and an output signal. I would like to design a
filter such that when convolved with the input signal, the output
signal will be produced.

I have been reading up on the LMS technique for calculating the
filter coefficients. The book that I have been using describes a
method of calculating the filter coefficients for one input/output
signal.

Suppose I have many input signals, and their corresponding output
signals. Can the LMS technique be used to produce a 'general' filter,
based on all the input/output signals.

I am using MATLAB and would very much appreciate any help or pointers
as to where I can find help.

Thanks

Yahoo! Groups Sponsor
ADVERTISEMENT _____________________________________
/groups.php3

Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.




(You need to be a member of matlab -- send a blank email to matlab-subscribe@yahoogroups.com )