Skip to main content

Data fusion via intrinsic dynamic variables: An application of data-driven Koopman spectral analysis

Author(s): Williams, Matthew O; Rowley, Clarence W; Mezić, Igor; Kevrekidis, Ioannis G

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr15p53
Abstract: We demonstrate that the Koopman eigenfunctions and eigenvalues define a set of intrinsic coordinates, which serve as a natural framework for fusing measurements obtained from heterogeneous collections of sensors in systems governed by nonlinear evolution laws. These measurements can be nonlinear, but must, in principle, be rich enough to allow the state to be reconstructed. We approximate the associated Koopman operator using extended dynamic mode decomposition, so the method only requires time series of data for each set of measurements, and a single set of "joint" measurements, which are known to correspond to the same underlying state. We apply this procedure to the FitzHugh-Nagumo PDE, and fuse measurements taken at a single point with principal-component measurements.
Publication Date: 1-Feb-2015
Electronic Publication Date: 26-Feb-2015
Citation: Williams, Matthew O, Rowley, Clarence W, Mezić, Igor, Kevrekidis, Ioannis G. "Data fusion via intrinsic dynamic variables: An application of data-driven Koopman spectral analysis" EPL (Europhysics Letters), 109, 4, 40007-1 - 40007-6, doi:10.1209/0295-5075/109/40007
DOI: doi:10.1209/0295-5075/109/40007
ISSN: 0295-5075
EISSN: 1286-4854
Pages: 40007-1 - 40007-6
Type of Material: Journal Article
Journal/Proceeding Title: EPL (Europhysics Letters)
Version: This is the author’s final manuscript. All rights reserved to author(s).



Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.