Multiscale reconstruction of time series

A new method is proposed which allows a reconstruction of time series based on higher order multiscale statistics given by a hierarchical process. This method is able to model the time series not only on a specific scale but for a range of scales. It is possible to generate complete new time series, or to model the next steps for a given sequence of data. The method itself is based on the joint probability density which can be extracted directly from given data, thus no estimation of parameters is necessary. The results of this approach are shown for a real world dataset, namely for turbulence. The unconditional and conditional probability densities of the original and reconstructed time series are compared and the ability to reproduce both is demonstrated. Therefore in the case of Markov properties the method proposed here is able to generate artificial time series with correct n-point statistics.     

An electronic technique for measuring phase space dimension from chaotic time series

An instrument for determining the number of independent variables involved in chaotic dynamical systems is described. The elaborated technique allows to obtain this measure in real time from a single observable. It has been used for the quantitative characterization of strange attractors underlying chaotic oscillations in anumber of nonlinear electronic circuits. This technique is found to be fairly insensitive to stochastic noise inherent in real experimental systems.     

基于径向基函数神经网络的混沌时间序列相空间重构双参数联合估计

鉴于径向基函数(RBF)神经网络模型在非线性预测方面的优良性能, 提出了利用该预测模型对混沌时间序列相空间重构的两个关键参数——延迟时间和嵌入维数进行联合估计的方法, 并以客观的评价指标为依据给出其最优估计值. 以Lorenz系统为例进行数值分析, 得到RBF单步及多步预测模型中嵌入维数和延迟时间的最佳参数估计值, 并在原模型中对估计值进行校验. 结果表明, 该方法可以有效地估计出嵌入维数和延迟时间, 从而显著提高预测精度.     

Multiscale entropy analysis of complex physiologic time series

There has been considerable interest in quantifying the complexity of physiologic time series, such as heart rate. However, traditional algorithms indicate higher complexity for certain pathologic processes associated with random outputs than for healthy dynamics exhibiting long-range correlations. This paradox may be due to the fact that conventional algorithms fail to account for the multiple time scales inherent in healthy physiologic dynamics. We introduce a method to calculate multiscale entropy (MSE) for complex time series. We find that MSE robustly separates healthy and pathologic groups and consistently yields higher values for simulated long-range correlated noise compared to uncorrelated noise.     

Inferring phase equations from multivariate time series

An approach is presented for extracting phase equations from multivariate time series data recorded from a network of weakly coupled limit cycle oscillators. Our aim is to estimate important properties of the phase equations including natural frequencies and interaction functions between the oscillators. Our approach requires the measurement of an experimental observable of the oscillators; in contrast with previous methods it does not require measurements in isolated single or two-oscillator setups. This noninvasive technique can be advantageous in biological systems, where extraction of few oscillators may be a difficult task. The method is most efficient when data are taken from the nonsynchronized regime. Applicability to experimental systems is demonstrated by using a network of electrochemical oscillators; the obtained phase model is utilized to predict the synchronization diagram of the system.     

Detecting anomalous phase synchronization from time series

Modeling approaches are presented for detecting an anomalous route to phase synchronization from time series of two interacting nonlinear oscillators. The anomalous transition is characterized by an enlargement of the mean frequency difference between the oscillators with an initial increase in the coupling strength. Although such a structure is common in a large class of coupled nonisochronous oscillators, prediction of the anomalous transition is nontrivial for experimental systems, whose dynamical properties are unknown. Two approaches are examined; one is a phase equational modeling of coupled limit cycle oscillators and the other is a nonlinear predictive modeling of coupled chaotic oscillators. Application to prototypical models such as two interacting predator-prey systems in both limit cycle and chaotic regimes demonstrates the capability of detecting the anomalous structure from only a few sets of time series. Experimental data from two coupled Chua circuits shows its applicability to real experimental system.     

基于相空间邻域的混沌时间序列自适应预测滤波器(Ⅱ)非线性自适应滤波

根据相空间重构理论、最小均方误差准则和最陡下降原理，提出了一种基于相空间邻域的非线性自适应滤波算法.实验结果表明：这种非线性自适应预测滤波器能够有效预测一些混沌序列，在某种程度上具有抗噪声的能力. 关键词： 混沌时间序列 重构矢量 最小均方误差准则 非线性自适应预测     

基于相空间邻域的混沌时间序列自适应预测滤波器(Ⅰ)线性自适应滤波

提出了一种基于相空间邻域的线性自适应滤波算法，将时间域变换到高维重构矢量空间，使 得不可能实现的线性预测变成了可能.实验结果表明：这种基于相空间邻域的线性自适应预 测滤波器能够有效预测一些混沌序列，能够检测到一些混沌载波中的信号，具有去混沌噪声 的能力. 关键词： 混沌时间序列 重构矢量 自适应预测     

Multiscale entropy based study of the pathological time series

This paper studies the multiscale entropy （MSE） of electrocardiogram＇s ST segment and compares the MSE results of ST segment with that of electrocardiogram in the first time. Electrocardiogram complexity changing characteristics has important clinical significance for early diagnosis. Study shows that the average MSE values and the varying scope fluctuation could be more effective to reveal the heart health status. Particularly the multiscale values varying scope fluctuation is a more sensitive parameter for early heart disease detection and has a clinical diagnostic significance.     

基于信息熵优化相空间重构参数的混沌时间序列预测

提出一种混沌时间序列相空间重构参数的信息熵优化方法(IEOP),该方法首先使用条件熵表示信息量,建立时间延迟和嵌入维数在相空间中的信息熵优化模型,然后利用遗传算法同时求解两个重构参数,使重构坐标间既保持了良好的独立性又保留了原系统的动力学特征.通过在Lorenz和Mackey-Glass系统上的数值实验,该方法不仅能够确定合适的嵌入维数和时间延迟,而且能在优化的相空间中获得更多的信息,提高了混沌时间序列的预测精度.     

基于条件熵扩维的多变量混沌时间序列相空间重构

提出一种多变量混沌时间序列相空间重构的条件熵扩维方法.首先使用互信息法求解每个变量的时间延迟,其次按条件熵最大原则逐步扩展相空间的嵌入维数,使得重构坐标从低维到高维的转换保持较强的独立性,最终的重构相空间具有较低的冗余度,为多变量时间序列的预测构造了有效的模型输入向量.通过对几个经典多变量混沌时间序列进行数值实验,结果表明该方法比单变量预测和已有多变量预测方法具有更好的预测效果,说明了该重构方法的有效性. 关键词： 多变量混沌时间序列 相空间重构 条件熵 神经网络预测     

混沌时序相空间重构参数确定的信息论方法

根据信息论基本原理，研究了混沌时间序列相空间重构参数延迟时间和嵌入维数的选取.提出了用符号分析的方法计算互信息函数，确定出延迟时间，在此基础上，提出了一种估计嵌入维数的信息论方法，即根据重构向量条件熵随向量维数的变化关系来确定嵌入维数，通过对几种典型混沌动力学系统的数值验证，结果表明该方法能够确定出合适的相空间重构嵌入维数. 关键词： 混沌 相空间重构 互信息 条件熵 符号分析     

Inner composition alignment for inferring directed networks from short time series

Identifying causal links (couplings) is a fundamental problem that facilitates the understanding of emerging structures in complex networks. We propose and analyze inner composition alignment-a novel, permutation-based asymmetric association measure to detect regulatory links from very short time series, currently applied to gene expression. The measure can be used to infer the direction of couplings, detect indirect (superfluous) links, and account for autoregulation. Applications to the gene regulatory network of E. coli are presented.     

Relaxation and phase space singularities in time series of human magnetoencephalograms as indicator of photosensitive epilepsy

To analyze the crucial role of fluctuation and relaxation effects for the function of the human brain we studied some statistical quantifiers that support the information characteristics of neuromagnetic brain responses (magnetoencephalogram, MEG). The signals to a flickering stimulus of different color combinations have been obtained from a group of control subjects which is then contrasted with those of a patient suffering photosensitive epilepsy (PSE). We found that the existence of the specific stratification of the phase clouds and the concomitant relaxation singularities of the corresponding nonequilibrium dynamics of the chaotic behavior of the signals in separate areas in a patient provide likely indicators for the zones which are responsible for the appearance of PSE.     

Complex networks constructed from irrational number sequences

In this paper, we construct (d,r) networks from sequences of different irrational numbers. In detail, segment an irrational number sequence of length M into groups of d digits which represent the nodes while two consecutive groups overlap by r digits (r=0,1,…,d−1), and the undirected edges indicate the adjacency between two consecutive groups. (3,r) and (4,r) networks are respectively constructed from 14 different irrational numbers and their topological properties are examined. By observation, we find that network topologies change with different values of d, r and even sequence length M instead of the types of irrational numbers, although they share some similar features with traditional random graphs. We make a further investigation to explain these interesting phenomena and propose the identical-degree random graph model. The results presented in this paper provide some insight into distributions of irrational number digits that may help better understanding of the nature of irrational numbers.     

变参数混沌时间序列的神经网络预测研究

研究一类复杂变参数混沌系统时间序列的预测问题.首先构造一个变参数Logistic映射,分析变参数混沌系统的特点,指出动力学特征不断变化的这类系统不存在恒定形状的吸引子;结合Takens嵌入定理和神经网络理论,阐述神经网络方法预测具有恒定吸引子形状的混沌系统可行的原因,分析研究其用于预测变参数混沌系统的潜在问题.变参数Ikeda系统的神经网络预测试验验证了理论分析结果,试验还表明,简单增大预测训练样本数可能降低泛化预测精度,训练集的选择对这类系统的泛化预测效果影响极大,指出混沌时间序列预测实用化必须研究解决这类变参数混沌系统的预测. 关键词： 混沌 预测 神经网络 变参数系统     

混沌时间序列的模糊神经网络预测

设计一种新型混合模糊神经推理系统，该系统仅从期望输入输出数据集即可达到获取知识、确定模糊初始规则基的目的.再利用神经网络学习能力便不难修改规则库中的模糊规则以及隶属函数和网络权值等参数，这样大大减少了规则匹配过程，加快了推理速度，从而极大程度地提高了系统的自适应能力.用它对Mackey-Glass混沌时间序列进行预测试验,结果表明利用该网络模型无论离线还是在线学习均能对Mackey-Glass混沌时间序列进行准确的预测，证明了该系统的有效性. 关键词： 神经网络模型 模糊逻辑 混合推理系统 混沌时间序列     

Detection of determinism and randomness in time series: A method based on phase space overlap of attractors

The space overlap of an attractor reconstructed from a time series with a similarly reconstructed attractor from a random series is shown to be a sensitive measure of determinism. Results for the time series for Henon, Lorenz and Rössler systems as well as a linear stochastic signal and an experimental ECG signal are reported. The overlap increases with increasing levels of added noise, as shown in the case of Henon attractor. Further, the overlap is shown to decrease as noise is reduced in the case of the ECG signal when subjected to singular value decomposition. The scaling behaviour of the overlap with bin size affords a reliable estimate of the fractal dimension of the attractor even with limited data.