Mercurial > hg > ltpda
view m-toolbox/html_help/help/ug/sigproc_timedomainfit_content.html @ 42:f90d4f666cc7 database-connection-manager
Cleanup
author | Daniele Nicolodi <nicolodi@science.unitn.it> |
---|---|
date | Mon, 05 Dec 2011 18:04:34 +0100 |
parents | f0afece42f48 |
children |
line wrap: on
line source
<p> <a href="m/sigproc/time_domain/ltpda_timedomainfit.html">ltpda_timedomainfit.m</a> uses the MATLAB function <tt>lscov.m</tt> to fit a set of time-series AOs to a target time-series AO. It gives back a set of fitting coefficients. </p> <p> One can now subtract the fitted time series from the original one - the target- and produce a new time series by calling <a href="m/math/ltpda_lincom.html">ltpda_lincom.m</a> with the calculated coefficients. This function does a linear combination of the inputted coefficients and analysis objects and subtracts the result from the target analysis object, which has to be the first input parameter. </p> <h2><a name="example">An example:</a></h2> <div class="fragment"><pre> coeffsAO = ltpda_timedomainfit(target, ts1, ts2, ts3, ts4); %% Make linear combination x12ns = ltpda_lincom(target, ts1, ts2, ts3, ts4, coeffsAO); </pre></div> <p> <tt>x12ns</tt> represents the noise subtracted target analysis object. With noise here the fitted time series is meant. That is the linear combination of the coefficients <tt>coeffsAO</tt> and the time series objects ts1 to ts4. </p> The number of time or frequency series analysis objects is variable. </br> The first is always taken as target object.