A comprehensive comparison and overview of R packages for calculating sample entropy

Chang Chen, Shixue Sun, Zhixin Cao, Yan Shi, Baoqing Sun, Xiaohua Douglas Zhang

Research output: Contribution to journalArticlepeer-review

16 Scopus citations

Abstract

Sample entropy is a powerful tool for analyzing the complexity and irregularity of physiology signals which may be associated with human health. Nevertheless, the sophistication of its calculation hinders its universal application. As of today, the R language provides multiple open-source packages for calculating sample entropy. All of which, however, are designed for different scenarios. Therefore, when searching for a proper package, the investigators would be confused on the parameter setting and selection of algorithms. To ease their selection, we have explored the functions of five existing R packages for calculating sample entropy and have compared their computing capability in several dimensions. We used four published datasets on respiratory and heart rate to study their input parameters, types of entropy, and program running time. In summary, NonlinearTseries and CGManalyzer can provide the analysis of sample entropy with different embedding dimensions and similarity thresholds. CGManalyzer is a good choice for calculating multiscale sample entropy of physiological signal because it not only shows sample entropy of all scales simultaneously but also provides various visualization plots. MSMVSampEn is the only package that can calculate multivariate multiscale entropies. In terms of computing time, NonlinearTseries, CGManalyzer, and MSMVSampEn run significantly faster than the other two packages. Moreover, we identify the issues in MVMSampEn package. This article provides guidelines for researchers to find a suitable R package for their analysis and applications using sample entropy.

Original languageEnglish
Article numberbpz016
JournalBiology Methods and Protocols
Volume4
Issue number1
DOIs
StatePublished - Dec 27 2019

Bibliographical note

Publisher Copyright:
© 2019 The Author(s) 2019. Published by Oxford University Press.

Keywords

  • R package
  • comparison
  • nonlinear dynamics
  • sample entropy
  • time series

ASJC Scopus subject areas

  • General Biochemistry, Genetics and Molecular Biology
  • General Agricultural and Biological Sciences

Fingerprint

Dive into the research topics of 'A comprehensive comparison and overview of R packages for calculating sample entropy'. Together they form a unique fingerprint.

Cite this