Estimation of mutual information using kernel density estimators

Young-Il Moon, Balaji Rajagopalan, and Upmanu Lall
Phys. Rev. E 52, 2318 – Published 1 September 1995
PDFExport Citation

Abstract

Mutual information is useful for investigating the dependence between two experimental time series. It is often used to establish an appropriate time delay in phase-portrait reconstruction from time-series data. A histogram based approach has been used so far to estimate the probabilities. It is shown here that kernel density estimation of the probability density functions needed in estimating the average mutual information across two coordinates can be more effective than the histogram method of Fraser and Swinney [Phys. Rev. A 33, 1134 (1986)].

  • Received 8 May 1995

DOI:https://doi.org/10.1103/PhysRevE.52.2318

©1995 American Physical Society

Authors & Affiliations

Young-Il Moon, Balaji Rajagopalan, and Upmanu Lall

  • Utah Water Research Laboratory, Utah State University, Logan, Utah 84322-8200

References (Subscription Required)

Click to Expand
Issue

Vol. 52, Iss. 3 — September 1995

Reuse & Permissions
Access Options
Author publication services for translation and copyediting assistance advertisement

Authorization Required


×
×

Images

×

Sign up to receive regular email alerts from Physical Review E

Log In

Cancel
×

Search


Article Lookup

Paste a citation or DOI

Enter a citation
×