Point Information Gain and Multidimensional Data Analysis

Renata Rychtáriková; Jan Korbel; Petr Macháček; Petr Císař; Jan Urban; Dalibor Štys

doi:10.3390/e18100372

Entropy (Oct 2016)

Point Information Gain and Multidimensional Data Analysis

Renata Rychtáriková,
Jan Korbel,
Petr Macháček,
Petr Císař,
Jan Urban,
Dalibor Štys

Affiliations

Renata Rychtáriková: Institute of Complex Systems, South Bohemian Research Center of Aquaculture and Biodiversity of Hydrocenoses, Faculty of Fisheries and Protection of Waters (FFWP), University of South Bohemia in České Budějovice, Zámek 136, Nové Hrady 373 33, Czech Republic
Jan Korbel: Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague, Břehová 7, Prague 155 19, Czech Republic
Petr Macháček: Institute of Complex Systems, South Bohemian Research Center of Aquaculture and Biodiversity of Hydrocenoses, Faculty of Fisheries and Protection of Waters (FFWP), University of South Bohemia in České Budějovice, Zámek 136, Nové Hrady 373 33, Czech Republic
Petr Císař: Institute of Complex Systems, South Bohemian Research Center of Aquaculture and Biodiversity of Hydrocenoses, Faculty of Fisheries and Protection of Waters (FFWP), University of South Bohemia in České Budějovice, Zámek 136, Nové Hrady 373 33, Czech Republic
Jan Urban: Institute of Complex Systems, South Bohemian Research Center of Aquaculture and Biodiversity of Hydrocenoses, Faculty of Fisheries and Protection of Waters (FFWP), University of South Bohemia in České Budějovice, Zámek 136, Nové Hrady 373 33, Czech Republic
Dalibor Štys: Institute of Complex Systems, South Bohemian Research Center of Aquaculture and Biodiversity of Hydrocenoses, Faculty of Fisheries and Protection of Waters (FFWP), University of South Bohemia in České Budějovice, Zámek 136, Nové Hrady 373 33, Czech Republic

DOI: https://doi.org/10.3390/e18100372
Journal volume & issue: Vol. 18, no. 10
p. 372

Abstract

Read online

We generalize the point information gain (PIG) and derived quantities, i.e., point information gain entropy (PIE) and point information gain entropy density (PIED), for the case of the Rényi entropy and simulate the behavior of PIG for typical distributions. We also use these methods for the analysis of multidimensional datasets. We demonstrate the main properties of PIE/PIED spectra for the real data with the examples of several images and discuss further possible utilizations in other fields of data processing.

Published in Entropy

ISSN: 1099-4300 (Online)
Publisher: MDPI AG
Country of publisher: Switzerland
LCC subjects: Science: Astronomy: Astrophysics; Science: Physics
Website: http://www.mdpi.com/journal/entropy

About the journal

Abstract

Keywords