Linear Parameter Estimation with Singular Value Decomposition


ao/linlsqsvd Linear least squares with singular value deconposition - single experiment.
matrix/linlsqsvd Linear least squares with singular value deconposition - multiple experiments.
matrix/linfitsvd Iterative linear parameter estimation for multichannel systems - symbolic system model in frequency domain.
matrix/linfitsvd Iterative linear parameter estimation for multichannel systems - ssm system model in time domain.
References

The following sections gives an introduction to the linear parameters estimation methods based on singular value decomposition.

Linear least squares with singular value deconposition - single experiment.

We report an example of the application of ao/linlsqsvd. The example shows how to perform a linear parameters estimation for a single data series which is representing the output of an experiment on a given physical system.

Linear least squares with singular value deconposition - multiple experiments.

We report an example of the application of matrix/linlsqsvd. The example shows how to perform a linear parameters estimation for multiple data series which are representing the output of multiple experiments on a given physical system.

Iterative linear parameter estimation for multichannel systems - symbolic system model in frequency domain.

We report an example of the application of matrix/linfitsvd. The example shows how to perform an iterative linear parameters estimation for a multichannel system. System model is analystic and frequency domain. Fit is performed in time domain. Further details can be found in ref. [1].

Iterative linear parameter estimation for multichannel systems - ssm system model in time domain.

We report an example of the application of matrix/linfitsvd. The example shows how to perform an iterative linear parameters estimation for a multichannel system. System model is ssm and time domain. Fit is performed in time domain.

References

  1. M Nofrarias, L Ferraioli, G Congedo, Comparison of parameter estimates results in STOC Exercise 6, S2-AEI-TN-3070.



©LTP Team