Empirical data modelling algorithms: additive spline models and support vector machines

• Published in: IEE conference publication pp. 709 - 714
• Main Authors: Brown, M, Gunn, S.R
• Format: Conference Proceeding
• Language: English
• Published: London IEE 1998
• Subjects: Algebra; Applied sciences; Computer science; control theory; systems; Control theory. Systems; Exact sciences and technology; Interpolation and function approximation (numerical analysis); Modelling and identification; Neural computing techniques; Neural nets; Other topics in statistics; Simulation, modelling and identification; splines (mathematics); support vector machines; time series; modelling; ANOVA representation; empirical data modelling algorithms; additive spline models; transparency; Hessian matrices; neural nets; verification; validation; nonlinear multivariate data; Non linear system; Multivariate process; Modeling
• ISBN: 085296708X; 9780852967089
• ISSN: 0537-9989
• DOI: 10.1049/cp:19980316

Empirical data modelling techniques are widely used in the control field, from simple white-box, linear parameter identification schemes to black-box nonlinear models. Non-linear, semi-parametric model building algorithms have been extensively studied over the past ten years, and despite their success in many applications where prior information is lacking or incorrect, verification and validation is notoriously difficult. One of the key aspects of verification and validation is transparency, where the network's generalisation abilities are explicitly represented. The paper describes two approaches for building an ANOVA representation of non-linear, multivariate data: one based on forwards selection and backwards elimination spline models and the other using a support vector machine with an ANOVA-kernel decomposition.