A randomised approach for NARX model identification based on a multivariate Bernoulli distribution

DOI10.1080/00207721.2016.1244309zbMath1362.93159OpenAlexW2540760014MaRDI QIDQ5347338

Maria Prandini, Federico Bianchi, Alessandro Falsone, Luigi Piroddi

Publication date: 23 May 2017

Published in: International Journal of Systems Science (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/11311/1009157

zbMATH Keywords

model structure selectionrandomised algorithmsmultivariate Bernoulli distributionpolynomial NARX modelsnonlinear model identificationprediction error minimisation methods

Mathematics Subject Classification ID

Related Items (6)

Stability orthogonal regression for system identification ⋮ Active preference-based optimization for human-in-the-loop feature selection ⋮ Enhanced algorithm for randomised model structure selection ⋮ Model structure selection for switched NARX system identification: a randomized approach ⋮ A randomized method for the identification of switched NARX systems ⋮ Fault identification in nonlinear hybrid systems

Cites Work

• A randomized algorithm for nonlinear model structure selection
• Dynamical effects of overparametrization in nonlinear models
• Some simple methods for generating correlated categorical variates
• Nonlinear black-box modeling in system identification: A unified overview
• Computational system identification for Bayesian NARMAX modelling
• Structure identification of nonlinear dynamic systems - A survey on input/output approaches
• Modelling and generating correlated binary variables
• Nonlinear System Identification
• Model selection approaches for non-linear system identification: a review
• Input-output parametric models for non-linear systems Part I: deterministic non-linear systems
• Input-output parametric models for non-linear systems Part II: stochastic non-linear systems
• Miscellanea. A note on generating correlated binary variables
• Matrices, Vector Spaces, and Information Retrieval
• An identification algorithm for polynomial NARX models based on simulation error minimization
• A family of multivariate binary distributions for simulating correlated binary variables with specified marginal means and correlations
• An iterative orthogonal forward regression algorithm
• Sparse kernel regression modeling using combined locally regularized orthogonal least squares and d-optimality experimental design
• A fast nonlinear model identification method

This page was built for publication: A randomised approach for NARX model identification based on a multivariate Bernoulli distribution