dsp.BurgAREstimator System object

Package: dsp

Estimate of autoregressive (AR) model parameters using Burg method


The BurgAREstimator object computes the estimate of the autoregressive (AR) model parameters using the Burg method.

To compute the estimate of the AR model parameters:

  1. Define and set up your System object™. See Construction.

  2. Call step to compute the estimate according to the properties of dsp.BurgAREstimator. The behavior of step is specific to each object in the toolbox.


H = dsp.BurgAREstimator returns a Burg BurgAREstimator System object, H, that performs parametric AR estimation using the Burg maximum entropy method.

H = dsp.BurgAREstimator('PropertyName',PropertyValue,...) returns a Burg AR estimator object, H, with each specified property set to the specified value.



Enable output of polynomial coefficients

Set this property to true to output the polynomial coefficients, A, of the AR model the object computes. The default is true. Either the AOutputPort property, the KOutputPort property, or both must be true.


Enable output of reflection coefficients

Set this property to true to output the reflection coefficients, K, for the AR model that the object computes. The default is false. Either the AOutputPort property, the KOutputPort property, or both must be true.


Source of estimation order

Specify how to determine estimator order as Auto or Property. When you set this property to Auto, the object assumes the estimation order is one less than the length of the input vector. When you set this property to Property, the value in EstimationOrder is used. The default is Auto.


Order of AR model

Set the AR model estimation order to a real positive integer. This property applies when you set the EstimationOrderSource to Property. The default is 4.


cloneCreate Burg AR Estimator object with same property values
getNumInputsNumber of expected inputs to step method
getNumOutputsNumber of outputs of step method
isLockedLocked status for input attributes and nontunable properties
releaseAllow property value and input characteristics changes
stepNormalized estimate of AR model parameter


Use the Burg AR Estimator System object to estimate the parameters of an AR model:

 rng default; % Use default random number generator and seed
 noise = randn(100,1); % Normalized white Gaussian noise
 x = filter(1,[1 1/2 1/3 1/4 1/5],noise);
 hburgarest = dsp.BurgAREstimator(...
 'EstimationOrderSource', 'Property', ...
 'EstimationOrder', 4);
 [a, g] = step(hburgarest, x);
 x_est = filter(g, a, x);
 plot(1:100,[x x_est]);
 title('Original and estimated signals');
 legend('Original', 'Estimated');


This object implements the algorithm, inputs, and outputs described on the Burg AR Estimator block reference page. The object properties correspond to the block parameters, except:

Output(s) block parameter corresponds to the AOutputPort and the KOutputPort object properties.
Was this topic helpful?