A state recognition of system dynamics based on moving sample entropy and their applications

ZHANG Jie, WAN Li, LUO Wen-xiang

PDF(2379 KB)
PDF(2379 KB)
Journal of Guangzhou University(Natural Science Edition) ›› 2018, Vol. 17 ›› Issue (2) : 27-32.

A state recognition of system dynamics based on moving sample entropy and their applications

  • ZHANG Jiea, WAN Lia,b, LUO Wen-xianga
Author information +
History +

Abstract

Sample entropy is a dynamic exponent which can depict the complexity of system effectively. Based on this, we analyze variation of linear and nonlinear sequences under different dynamic system by using sliding technology to generate sample entropy function. The results show that the sample entropy function of linear and nonlinear sequences could be affected by various dynamic system greatly. The jumping points of sample entropy function indicate break point of dynamic state. Furthermore, compared with traditional identification method, moving sample entropy, which can be used to identify the dynamical state of time series effectively, it is more stable and applicable. It can be a new approach for analyzing the dynamic state of time series.

Key words

moving windows / sample entropy / state identification

Cite this article

Download Citations
ZHANG Jie, WAN Li, LUO Wen-xiang. A state recognition of system dynamics based on moving sample entropy and their applications. Journal of Guangzhou University(Natural Science Edition). 2018, 17(2): 27-32

References

[1] KAFFASHI F, FOGLYANO R, WILSON G G, et al. The effect of time delay on Approximate & Sample Entropy calculations [J]. Physica D: Nonlinear Phenomena, 2008, 237(23):3069-3074.
[2] 李立. 基于脑电信号样本熵的情感识别[D]. 太原:太原理工大学, 2014.
[3] KOLMOGOROV N A. Three approaches to the quantitative definition of information[J]. Problems of Information Transmission, 1965, 2(1/4): 157-168.
[4] 沈文昊, 乔坎坤, 卢志明. 金融股指稳定性的样本熵分析[J]. 山东大学学报, 2014, 49(7):50-56.
[5] PINCUS S M. Approximate entropy as a measure of system complexity[J]. Proceedings of the National Academy of Sciences of the United States of America, 1991, 88(6): 2297-2301.
[6] JOSHUA S, RICHMAN, DOUGLAS E L,et al. Sample entropy[J]. Methods in Enzymology, 2004, 384(11): 172-173.
[7] 周鹏, 葛家怡, 曹红宝,等. 基于样本熵的运动想象分类研究[J]. 信息与控制, 2008, 37(2):191-196.
[8] 何文平, 吴琼, 张文,等. 滑动去趋势波动分析与近似熵在动力学结构突变检测中的性能比较[J]. 物理学报, 2009, 58(4): 2863-2864.
[9] 金鸿章, 郭健, 韦琦,等. 基于滑动t检验法的非典型性肺炎疫情的脆性分析[J]. 哈尔滨工程大学学报, 2003,24(6):640-645.
[10]MANN H B. Nonparametric test against trend[J]. Econometrica, 1945, 13(3): 245-259.
[11] KENDALL M G, CHARLES G. Rank correlation methods[M]. Oxford: Oxford University, 1975.
[12]成海英, 何文平, 何涛,等. 基于概率密度分布型变化的突变检测新途径[J]. 物理学报, 2012, 61(3): 540-546.
[13]何文平, 何涛, 成海英, 等. 基于近似熵的突变检验新方法[J]. 物理学报, 2011, 60(4): 813-821.
[14]COSTA M, GOLDBERGER A L, PENG C K. Multiscale entropy analysis of biological signals[J]. Physical Review E Statistical Nonlinear & Soft Matter Physics, 2005, 71(1):1-16.
[15]孙东永, 张洪波, 王义民. 滑动移除小波分析法在动力学结构突变检验中的应用[J]. 物理学报, 2017, 66(7): 1-10.
[16]万丽, 胡序懿, 邓小成. 成矿元素含量序列的近似熵分析及矿化识别[J]. 中国矿业大学学报, 2014, 43(2):345-350.
PDF(2379 KB)

147

Accesses

0

Citation

Detail

Sections
Recommended

/