生理时间序列的一种符号化分析方法

廖福元; 王珏

您当前的位置：

首页 >

文章列表页 >

生理时间序列的一种符号化分析方法

专题研究 | 更新时间：2025-12-08

- 生理时间序列的一种符号化分析方法
- Symbolic Dynamic Approach for Analyzing Physiological Time Series
- 西安交通大学学报 2007年41卷第12期页码：1479-1482
- 作者机构：
  
  西安交通大学生物医学信息工程教育部重点实验室,西安,710049
- 作者简介：
- 基金信息：
  
  : 2007-05-18. 作者简介: 廖福元(1969～),男,博士生;王珏(联系人),女,教授,博士生导师. 基金项目: 国家自然科学基金资助项目(30670660)
- DOI：
  中图分类号： R318
- 网络首发：2007-12-10，
  
  纸质出版：2007
- 稿件说明：
移动端阅览
廖福元, 王珏. 生理时间序列的一种符号化分析方法[J]. 西安交通大学学报, 2007,41(12):1479-1482.

廖福元, 王珏. Symbolic Dynamic Approach for Analyzing Physiological Time Series[J]. 2007, 41(12): 1479-1482.
廖福元, 王珏. 生理时间序列的一种符号化分析方法[J]. 西安交通大学学报, 2007,41(12):1479-1482. DOI：

廖福元, 王珏. Symbolic Dynamic Approach for Analyzing Physiological Time Series[J]. 2007, 41(12): 1479-1482. DOI：

摘要

提出了一种分析生理时间序列的方法

即对重构的相空间进行符号化分析.因生理时间序列通常是非平稳的

为去除时间序列中的局部趋势、提取时间序列的波形特征

相空间中的向量被归一化

从而具有相同的均值和标准差.然后

引入最大拓扑熵(MTE)原则来寻找相空间的适当划分以实现向量的符号化.采用Logistic 映射和人体运动信号检验的结果表明

用MTE原则比用最大熵原则得到的划分更接近最优划分.原时间序列的波动特征用出现的字模式个数与所有可能的字模式个数之比以及字模式分布概率的Shannon熵来描述.对人体运动信号的分析结果表明

该方法能够有效区分不同生理状态下的时间序列.

Abstract

An approach for investigating the dynamics of physiological time series is presented

namely the symbolic dynamics analyzing the reconstructed phase space. Since physiological time series are usually nonstationary

to remove the time varying local mean and extract the wave characteristics of the time series

all the vectors in the reconstructed phase space are normalized to be endowed with the same mean and standard deviation. The maximum topological entropy(MTE)criterion is then introduced to find a partition for the phase space. The tested results on the logistic map and the signals of postural stability show that the MTE criterion provides a partition closer to the optimal partition than a partition leading to equiprobable symbols. Two measures from symbolic dynamics are used to characterize the dynamics of the time series. The calculated results for the signals of postural stability show that this approach enables to detect the dissimilarity of physiological time series in different physiological states.

关键词

Keywords

references

Goldberger A L, Peng C K, Lipsitz L A. What is physiologic complexity and how does it change with aging and disease? [J]. Neurobiol Aging, 2002, 23(1): 23-26.

Grassberger P, Procaccia I. Characterization of strange attractors [J]. Phys Rev Lett, 1983, 50(5): 346-349.

Ding M, Grebogi C, Ott E,et al. Plateau onset for correlation dimension: when does it occur?[J]. Phys Rev Lett, 1993, 70(25): 3872-3875.

Wolf A, Swift J B, Swinney H L, et al. Determining Lyapunov exponents from a time series [J]. Physica:D, 1985, 16(3):285-317.

Porta A, Guzzetti S, Furlan R,et al. Complexity and non linearity in short-term heart period variability: comparison of methods based on local non linear prediction [J]. IEEE Trans Biomedical Engineering, 2007, 54(1): 94-106.

Richman J S, Moorman J R. Physiological time series analysis using approximate entropy and sample entropy [J]. Am J Physiol Heart Circ Physiol, 2000, 278(6): H2039-H2049.

Voss A, Kurths J, Kleiner H J,et al. The application of methods of nonlinear dynamics for the improved and predictive recognition of patients threatened by sudden cardiac death [J]. Cardiovasc Res, 1996, 31(3): 419-433.

Sauer T, Yorke J A, Casdagli M. Embedology [J]. J of Stat Phys, 1991, 65(3/4):579-616.

Veenman C J, Reinders M J T, Bolt E M,et al. A maximum variance cluster algorithm [J]. IEEE Trans Pattern Anal Mach Intell, 2002, 24(9): 1273-1280.

Chau T, Wong A K C. Pattern discovery by residual analysis and recursive partitioning [J]. IEEE Trans Knowledge Data Eng, 1999, 11(6): 833-852.

Rajagopalan V, Ray A. Symbolic time series analysis via wavelet-based partitioning [J]. Signal Processing, 2006, 86(11): 3309-3320.

Letellier C. Symbolic sequence analysis using approximated partition [J]. Chaos, Solitons Fractals,2008,36(1): 32-41.

Bollt E M, Stanford T, Lai Y C, et al. What symbolic dynamics do we get with a misplaced partition?: on the validity of threshold crossings analysis of chaotic time-series [J]. Physica: D, 2001, 154(3/4):259-286.

Amoud H, Snoussi H, Hewson D,et al. Intrinsic mode entropy for nonlinear discriminant analysis [J]. IEEE Signal Processing Lett, 2007, 14(5): 297-300.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

隧道内燃料电池汽车氢气泄漏扩散特性及影响因素

采用机器学习的大规模并行程序I/O性能建模与预测方法

离子液体改性燃料的电流体动力学效应研究

冷库水平空气幕热湿阻隔性能数值模拟研究

电动车辆间接热系统快速除湿响应迟滞机理及优化控制策略