Symbolic Information Flow Measurement (SIFM): A software for measurement of information flow using symbolic analysis

Abstract

Symbolic Information Flow Measurement software is used to compute the information flow between different components of a dynamical system or different dynamical systems using symbolic transfer entropy. The time series represents the time evolution trajectory of a dynamical system. We introduce a method to perform a symbolic analysis of the time series based on the coarse-graining using a machine learning approach and computation of the embedding parameters. Information flow is measured in terms of the local and average symbolic transfer entropies. We also introduce a new measure of mutual information based on the symbolic analysis.

Keywords

• Embedded Parameters
• Symbolic transfer entropy
• Symbolic local transfer entropy
• Symbolic Mutual Information