Point Divergence Gain and Multidimensional Data Sequences Analysis

TL;DR

This paper introduces new information-entropic variables based on Rényi entropy to analyze and characterize changes in multidimensional data sequences, applicable to both simulated and real image datasets.

Contribution

It presents novel point divergence gain variables derived from Rényi entropy for analyzing spatio-temporal changes in multidimensional data.

Findings

Behavior of Point Divergence Gain simulated for typical distributions

Applied to analyze series of multidimensional datasets of images

Effective in characterizing changes in data sequences

Abstract

We introduce novel information-entropic variables -- a Point Divergence Gain (${\Omega}^{(l \rightarrow m)}_\alpha$), a Point Divergence Gain Entropy ($I_\alpha$), and a Point Divergence Gain Entropy Density ($P_\alpha$) -- which are derived from the R\'{e}nyi entropy and describe spatio-temporal changes between two consecutive discrete multidimensional distributions. The behavior of ${\Omega}^{(l \rightarrow m)}_\alpha$ is simulated for typical distributions and, together with $I_\alpha$ and $P_\alpha$, applied in analysis and characterization of series of multidimensional datasets of computer-based and real images.