Share Email Print
cover

Proceedings Paper

Avoiding the inverse fractal problem for compressive sampling of 1/f data sets
Author(s): Holger Jaenisch
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present a novel fractal Iterated Function System (IFS based) data interpolation algorithm enabling compressive sampling of 1/f data sets. We avoid the classical inverse IFS parameter estimation problem by using a novel analytical function driven variant of the random Iterated Function System (IFS) algorithm. We attempt to optimize the parameters of the analytical driver equation to optimize the data reconstruction by minimizing errors using various state-of-the-art genetic algorithms. We demonstrate our encouraging results and detail our methods and findings.

Paper Details

Date Published: 10 May 2012
PDF: 17 pages
Proc. SPIE 8401, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X, 84010N (10 May 2012); doi: 10.1117/12.914805
Show Author Affiliations
Holger Jaenisch, Johns Hopkins Univ. (United States)
Licht Strahl Engineering Inc. (United States)


Published in SPIE Proceedings Vol. 8401:
Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X
Harold Szu, Editor(s)

© SPIE. Terms of Use
Back to Top