Published In
Kybernetes
Document Type
Post-Print
Publication Date
2004
Subjects
Cybernetics, Fourier transformations, Information theory, Data mining
Abstract
Fourier methods used in two‐ and three‐dimensional image reconstruction can be used also in reconstructability analysis (RA). These methods maximize a variance‐type measure instead of information‐theoretic uncertainty, but the two measures are roughly collinear and the Fourier approach yields results close to that of standard RA. The Fourier method, however, does not require iterative calculations for models with loops. Moreover, the error in Fourier RA models can be assessed without actually generating the full probability distributions of the models; calculations scale with the size of the data rather than the state space. State‐based modeling using the Fourier approach is also readily implemented. Fourier methods may thus enhance the power of RA for data analysis and data mining.
DOI
10.1108/03684920410534083
Persistent Identifier
http://archives.pdx.edu/ds/psu/16493
Citation Details
Martin Zwick, (2004) "Reconstructability analysis with Fourier transforms", Kybernetes, Vol. 33, No.: 5/6, pp. 1026 - 1040
Included in
Databases and Information Systems Commons, Probability Commons, Theory and Algorithms Commons
Description
Author's version of an article that subsequently appeared in Kybernetes, published by Emerald Group Publishing Limited. The version of record may be found at http://dx.doi.org/10.1108/03684920410534083.