Picture of a black hole

Strathclyde Open Access research that creates ripples...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of research papers by University of Strathclyde researchers, including by Strathclyde physicists involved in observing gravitational waves and black hole mergers as part of the Laser Interferometer Gravitational-Wave Observatory (LIGO) - but also other internationally significant research from the Department of Physics. Discover why Strathclyde's physics research is making ripples...

Strathprints also exposes world leading research from the Faculties of Science, Engineering, Humanities & Social Sciences, and from the Strathclyde Business School.

Discover more...

Direct identification of nonlinear structure using Gaussian process prior models

Leithead, W.E. and Solak, E. and Leith, D.J. (2003) Direct identification of nonlinear structure using Gaussian process prior models. In: European Control Conference ECC 2003, 2003-09-01 - 2003-09-04.

Full text not available in this repository. (Request a copy from the Strathclyde author)

Abstract

When inferring nonlinear dependence from measured data,the nonlinear nature of the relationship may be characterisedin terms of all the explanatory variables. However, this israrely the most parsimonious, or insightful, approach.Instead, it is usually much more useful to be able to exploitthe inherent nonlinear structure to characterise the nonlineardependence in terms of the least possible number of variables.In this paper a new way of inferring nonlinear structure frommeasured data is investigated. The measured data isinterpreted as providing information on a nonlinear map. Thespace containing the domain of the map is sub-divided intounique linear and nonlinear sub-spaces that are structuralinvariants. The most parsimonious representation of the mapis obtained by the restriction of the map to the nonlinear sub-space. A direct constructive algorithm based on Gaussianprocess prior models, defined using a novel covariancefunction, is proposed. The algorithm infers the linear andnonlinear sub-spaces from noisy data and provides a non-parametric model of the parsimonious map. Use of thealgorithm is illustrated by application to a Wiener-Hammerstein system.