Ranking Variables in Nonlinear Nonparametric Additive System Identification

Identification of a high dimensional nonlinear nonparametric system is costly. On the other hand for many real-world problems, they are sparse in the sense that not all variables contribute or contribute significantly. If these variables that do not contribute or contribute little can be identified and removed prior to system identification, the identification problem is of lower dimension. In this paper, depending on the identification purposes, importance measures are defined. Based on these measures, ways to calculate these measures and to rank the importance of variables are proposed. This paper addresses such questions. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.