Baldacchino, T., Worden, K. orcid.org/0000-0002-1035-238X and Rowson, J. orcid.org/0000-0002-5226-680X (2017) Robust nonlinear system identification: Bayesian mixture of experts using the t-distribution. Mechanical Systems and Signal Processing, 85. pp. 977-992. ISSN 0888-3270
Abstract
A novel variational Bayesian mixture of experts model for robust regression of bifurcating and piece-wise continuous processes is introduced. The mixture of experts model is a powerful model which probabilistically splits the input space allowing different models to operate in the separate regions. However, current methods have no fail-safe against outliers. In this paper, a robust mixture of experts model is proposed which consists of Student-t mixture models at the gates and Student-t distributed experts, trained via Bayesian inference. The Student-t distribution has heavier tails than the Gaussian distribution, and so it is more robust to outliers, noise and nonnormality in the data. Using both simulated data and real data obtained from the Z24 bridge this robust mixture of experts performs better than its Gaussian counterpart when outliers are present. In particular, it provides robustness to outliers in two forms: unbiased parameter regression models, and robustness to overfitting/complex models.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2016 Elsevier. This is an author produced version of a paper subsequently published in Mechanical Systems and Signal Processing. Uploaded in accordance with the publisher's self-archiving policy. Article available under the terms of the CC-BY-NC-ND licence (https://creativecommons.org/licenses/by-nc-nd/4.0/) . |
Keywords: | Outliers; Robust estimation; Student-t distribution; Variational; Bayes; Mixture of experts; Bifurcating mechanical structures |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Mechanical Engineering (Sheffield) |
Funding Information: | Funder Grant number LEVERHULME TRUST (THE) RPG-2012-816 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 19 Jan 2017 11:28 |
Last Modified: | 03 Nov 2017 01:38 |
Published Version: | https://doi.org/10.1016/j.ymssp.2016.08.045 |
Status: | Published |
Publisher: | Elsevier |
Identification Number: | 10.1016/j.ymssp.2016.08.045 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:110703 |