B
Brett Ninness
Researcher at University of Newcastle
Publications - 179
Citations - 5724
Brett Ninness is an academic researcher from University of Newcastle. The author has contributed to research in topics: Estimation theory & System identification. The author has an hindex of 36, co-authored 178 publications receiving 5396 citations. Previous affiliations of Brett Ninness include Newcastle University & Australian Research Council.
Papers
More filters
Journal ArticleDOI
System identification of nonlinear state-space models
TL;DR: A Maximum Likelihood (ML) framework is employed and an Expectation Maximisation (EM) algorithm is derived to compute these ML estimates, which lend itself perfectly to the particle smoother, which provides arbitrarily good estimates.
Journal ArticleDOI
A unifying construction of orthonormal bases for system identification
Brett Ninness,Fredrik Gustafsson +1 more
TL;DR: This construction provides a unifying formulation of many previously studied orthonormal bases since the common FIR and recently popular Laguerre and two-parameter Kautz model structures are restrictive special cases of the construction presented here.
Journal ArticleDOI
Quantifying the error in estimated transfer functions with application to model order selection
TL;DR: The paper concludes by showing how the obtained error bounds can be used for intelligent model order selection that takes into account both measurement noise and under-model- ing.
Journal ArticleDOI
Modelling and Identification with Rational Orthogonal Basis Functions
Paul M.J. Van den Hof,Bo Wahlberg,Peter S. C. Heuberger,Brett Ninness,József Bokor,Tomás Oliveira e Silva +5 more
TL;DR: A recently developed general theory for basis construction will be presented, that is a generalization of the classical Laguerre theory, particularly exploiting the property that basis function models are linearly parametrized.
Journal ArticleDOI
Robust maximum-likelihood estimation of multivariable dynamic systems
Stuart Gibson,Brett Ninness +1 more
TL;DR: The theoretical and empirical evidence presented here establishes additional attractive properties such as numerical robustness, avoidance of difficult parametrization choices, the ability to naturally and easily estimate non-zero initial conditions, and moderate computational cost.