Order and structural dependence selection of LPV-ARX models revisited

Abstract

Accurate parametric identification of Linear Parameter-Varying (LPV) systems requires an optimal prior selection of model order and a set of functional dependencies for the parameterization of the model coefficients. In order to address this problem for linear regression models, a regressor shrinkage method, the Non-Negative Garrote (NNG) approach, has been… (More)
DOI: 10.1109/CDC.2012.6426552

1 Figure or Table

Topics

  • Presentations referencing similar topics