Subspace identification using predictor estimation via Gaussian regression

In this paper we propose a new nonparametric approach to identification of linear time invariant systems using subspace methods. The nonparametric paradigm to prediction of stationary stochastic processes, developed in a companion paper, is integrated into a recently proposed subspace method. Simulation results show that this approach significantly improves over standard subspace methods when using small sample sizes. In particular, the new approach facilitates significantly the order selection step.