Using Manifold Learning for Nonlinear System Identification
2007 (English)Report (Other academic)
A high-dimensional regression space usually causes problems in nonlinear system identiﬁcation.However, if the regression data are contained in (or spread tightly around) some manifold, thedimensionality can be reduced. This paper presents a use of dimension reduction techniques tocompose a two-step identiﬁcation scheme suitable for high-dimensional identiﬁcation problems withmanifold-valued regression data. Illustrating examples are also given.
Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2007. , 9 p.706-711 p.
LiTH-ISY-R, ISSN 1400-3902 ; 2795
Nonlinear system identification; Dimension reduction techniques; Manifold learning
IdentifiersURN: urn:nbn:se:liu:diva-56048ISRN: LiTH-ISY-R-2795OAI: oai:DiVA.org:liu-56048DiVA: diva2:316892