.png){kind=icon}
返回
Efficient synchronization estimation for complex time series using refined cross-sample entropy measure
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cnsns.2020.105556.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Efficient and robust synchronization estimation, namely refined cross-sample entropy (RCSE) measure, is presented in this study to analyze complex time series. Unlike the original cross-sample entropy (CSE) that relies on a fixed tolerance r , the proposed RCSE is based on a concept called the cumulative histogram method (CHM) to gain a range of entropy values with different r selections in a certain range. Moreover, the dissimilarity measure in RCSE is redefined, rather than the distance function used in the CSE. Trials are conducted over both simulated and real-world data for providing a comparative study. The original CSE is introduced as a comparison to testify that the proposed RCSE is capable of drawing more specific relationships from time series, and it is also a superior method to describe the synchronization between them. The results show that the new method is capable of distinguishing different kinds of time series and possesses robustness in the noise test. It is suggest that the proposed RCSE may potentially become a new reliable method for synchronization estimation of complex time series. (C) 2020 Elsevier B.V. All rights reserved.
Keyword:
Synchronization
Refined cross-sample entropy (RCSE)
Financial time series
Heartbeat signals
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.8
论文数:
9.3K
被引数:
1.8W
机构
引用论文
.png){kind=icon}
Analysis of financial stock markets through multidimensional scaling based on information measures
PREAI
分享收藏分享收藏
查看更多内容