Delgado-Bonal Alfonso, Marshak Alexander
NASA Goddard Space Flight Center, Greenbelt, MD 20771, USA.
Universities Space Research Association, Columbia, MD 21046, USA.
Entropy (Basel). 2019 May 28;21(6):541. doi: 10.3390/e21060541.
Approximate Entropy and Sample Entropy are two algorithms for determining the regularity of series of data based on the existence of patterns. Despite their similarities, the theoretical ideas behind those techniques are different but usually ignored. This paper aims to be a complete guideline of the theory and application of the algorithms, intended to explain their characteristics in detail to researchers from different fields. While initially developed for physiological applications, both algorithms have been used in other fields such as medicine, telecommunications, economics or Earth sciences. In this paper, we explain the theoretical aspects involving Information Theory and Chaos Theory, provide simple source codes for their computation, and illustrate the techniques with a step by step example of how to use the algorithms properly. This paper is not intended to be an exhaustive review of all previous applications of the algorithms but rather a comprehensive tutorial where no previous knowledge is required to understand the methodology.
近似熵和样本熵是基于模式存在来确定数据序列规律性的两种算法。尽管它们有相似之处，但这些技术背后的理论思想不同，却常被忽视。本文旨在成为这些算法理论与应用的完整指南，旨在向不同领域的研究人员详细解释它们的特性。虽然这两种算法最初是为生理应用而开发的，但它们已被应用于其他领域，如医学、电信、经济学或地球科学。在本文中，我们解释了涉及信息论和混沌理论的理论方面，提供了用于计算的简单源代码，并通过一个如何正确使用这些算法的逐步示例来说明这些技术。本文并非旨在对这些算法以前的所有应用进行详尽回顾，而是一个全面的教程，理解该方法无需任何先前的知识。
