Accurate estimator of correlations between asynchronous signals

The estimation of the correlation between time series is often hampered by the asynchronicity of the signals. Cumulating data within a time window suppresses this source of noise but weakens the statistics. We present a method to estimate correlations without applying long time windows. We decompose the correlations of data cumulated over a long window using decay of lagged correlations as calculated from short window data. This increases the accuracy of the estimated correlation significantly and decreases the necessary effort of calculations both in real and computer experiments.     

滑动移除小波分析法在动力学结构突变检验中的应用

标度指数计算的即时性与准确性对相关时间序列的动力学结构突变分析至关重要,然而现有方法在即时性与准确性上一直无法兼顾.将小波分析方法与滑动移除窗口技术相融合,提出一种新的动力学结构突变检测方法——滑动移除小波分析法.通过选取不同的滑动移除窗口,分别对构建的线性、非线性理想时间序列进行动力学结构突变分析,结果表明不论是线性时间序列还是非线性时间序列,滑动移除小波分析能够准确地检测到序列的动力学结构突变点及突变区间,对于滑动移除窗口长度依赖性较小,具有很强的稳定性,而且在计算速度上明显优于滑动移除重标极差和滑动移除方差分析方法,将在大数据处理中具有一定的优势.同时分别对线性、非线性理想时间序列添加高斯白噪声,结果表明滑动移除小波分析具有很强的抗噪能力,能够准确地检测到加噪后序列的突变点.对佛坪站日最高温度实测资料的动力学结构突变的准确检测进一步验证了该方法的有效性.滑动移除小波分析法可为具有相关性的系统动力学结构突变的快速、准确检测提供一种途径.     

Entropy correlation distance method. The Euro introduction effect on the Consumer Price Index

The idea of entropy was introduced in thermodynamics, but it can be used in time series analysis. There are various ways to define and measure the entropy of a system. Here the so called Theil index, which is often used in economy and finance, is applied as it were an entropy measure. In this study the time series are remapped through the Theil index. Then the linear correlation coefficient between the remapped time series is evaluated as a function of time and time window size and the corresponding statistical distance is defined. The results are compared with the the usual correlation distance measure for the time series themselves. As an example this entropy correlation distance method (ECDM) is applied to several series, as those of the Consumer Price Index (CPI) in order to test some so called globalisation processes. Distance matrices are calculated in order to construct two network structures which are next analysed. The role of two different time scales introduced by the Theil index and a correlation coefficient is also discussed. The evolution of the mean distance between the most developed countries is presented and the globalisation periods of the prices discussed. It is finally shown that the evolution of mean distance between the most developed countries on several networks follows the process of introducing the European currency — the Euro. It is contrasted to the GDP based analysis. It is stressed that the entropy correlation distance measure is more suitable in detecting significant changes, like a globalisation process than the usual statistical (correlation based) measure.     

滑动移除重标方差在动力学结构突变检验中的应用

标度指数是一个有效的非线性动力学指数,能够针对相关性时间序列动力学结构突变进行检测;通过滑动窗口技术和滑动移除窗口技术,重标极差对于相关时间序列动力学突变具有很好的检测能力,但由于重标极差方法本身的不完善,在滑动移除窗口较小时其检测结果出现一些虚假的突变点和突变区间.鉴于此,本文提出了一种新的动力学检测方法—–滑动移除重标方差.理想序列数值试验表明,滑动移除重标方差具有很强的稳定性和准确性,在滑动窗口较小时其检测结果没有出现虚假的突变点和区间,实测资料的应用进一步验证了新方法的可靠性.     

Dynamics of episodic transient correlations in currency exchange rate returns and their predictability

We study the dynamics of the linear and non-linear serial dependencies in financial time series in a rolling window framework. In particular, we focus on the detection of episodes of statistically significant two- and three-point correlations in the returns of several leading currency exchange rates that could offer some potential for their predictability. We employ a rolling window approach in order to capture the correlation dynamics for different window lengths and analyze the distributions of periods with statistically significant correlations. We find that for sufficiently large window lengths these distributions fit well to power-law behavior. We also measure the predictability itself by a hit rate, i.e. the rate of consistency between the signs of the actual returns and their predictions, obtained from a simple correlation-based predictor. It is found that during these relatively brief periods the returns are predictable to a certain degree and the predictability depends on the selection of the window length.     

Stimulus-induced transition of clustering firings in neuronal networks with information transmission delay

We propose a conceptually novel method of reconstructing the topology of dynamical networks. By examining the correlation between the variable of one node and the derivative of another node’s variable, we derive a simple matrix equation yielding the network adjacency matrix. Our assumptions are the possession of time series describing the network dynamics, and the precise knowledge of the internal interaction functions. Our method involves a tunable parameter, allowing for the reconstruction precision to be optimized within the constraints of given dynamical data. The method is illustrated on a simple example, and the dependence of the reconstruction precision on the dynamical properties of time series is discussed. Our theory is in principle applicable to any weighted or directed network whose interaction functions are known.     

Evaluation of the cross correlation method by using PIV standard images

Effects of various parameters for PIV image acquiring and processing on the final velocity field is studied by using PIV standard images (Okamoto et al., 1997) to evaluate the cross correlation method. The studied parameters include the size of interrogation window, the size of search window, the number of tracer particles, the diameter of tracer particles, out-of-plane velocity and average image velocity or the time interval between two images. In order to improve the PIV sub-pixel accuracy, the validity of the “sub-pixel interpolation” process also is discussed in the paper. Some useful conclusions are suggested for the optimal parameter selection for a final PIV result with high accuracy.     

基于反向传播神经网络的拉曼光谱去噪方法

拉曼光谱技术作为一种典型的光学检测方法,因其独特的非侵入性、快速、原位和极高的特异性,在生物分析、疾病诊断及分子识别等众多领域得到广泛应用.拉曼光谱的指纹特性使其成为生物医学分析领域的重要工具,但拉曼散射信号微弱,数据处理分析大量依赖分析人员、自动化处理能力低等因素都会极大影响该技术在实际中的应用.实验设备、环境产生的...     

Nonlinear dynamical analysis of turbulence in a stable cloud layer

An eight mode truncated spectral model based on Burgers' approximation to the one-dimensional Navier-Stokes equations is used to compute the Lyapunov dimension of the dynamical attractor for turbulence in a stable cloud layer. The model results are compared with the correlation dimension obtained earlier from a time series of radar Doppler and reflectivity signals from a turbulent layer in a marine stratus cloud. The analysis supports a weak coupling explanation for the lower correlation dimension found for the reflectivity time series compared with that for the Doppler time series. Turbulent Prandtl number emerges from the analysis as a flow parameter which can enlarge the dimension of the model's dynamical attractor, but the attractor dimension computed for the model remains lower than the radar Doppler correlation dimension. Linear stability analysis of the model's equilibrium states suggests that a nontruncated version of the model will possess an attractor which is also of lower dimension than the radar Doppler correlation dimension. (c) 1995 American Institute of Physics.     

Correlation measure to detect time series distances, whence economy globalization

An instantaneous time series distance is defined through the equal time correlation coefficient. The idea is applied to the Gross Domestic Product (GDP) yearly increments of 21 rich countries between 1950 and 2005 in order to test the process of economic globalisation. Some data discussion is first presented to decide what (EKS, GK, or derived) GDP series should be studied. Distances are then calculated from the correlation coefficient values between pairs of series. The role of time averaging of the distances over finite size windows is discussed. Three network structures are next constructed based on the hierarchy of distances. It is shown that the mean distance between the most developed countries on several networks actually decreases in time, —which we consider as a proof of globalization. An empirical law is found for the evolution after 1990, similar to that found in flux creep. The optimal observation time window size is found ?15 years.     

基于时间序列符号化模式表征的有向加权复杂网络

时间序列复杂网络分析近些年已发展成为非线性信号分析领域的一个国际热点课题.为了能更有效地挖掘时间序列(特别是非线性时间序列)中的结构特征,同时简化时间序列分析的复杂度,提出了一种新的基于时间序列符号化结合滑窗技术模式表征的有向加权复杂网络建网方法.该方法首先按照等概率区段划分的方式将时间序列做符号化处理,结合滑窗技术确定不同时刻的符号化模式作为网络的节点;然后将待分析时间序列符号化模式的转换频次和方向作为网络连边的权重和方向,从而建立时间序列有向加权复杂网络.通过对Logistic系统不同参数设置对应的时间序列复杂网络建网测试结果表明,相比经典的可视图建网方法,本文方法的网络拓扑能更简洁、直观地展示时间序列的结构特征.进而,将本文方法应用于规则排列采集的自然风场信号分析,其网络特性指标能较准确地预测采集信号的排布规律,而可视图建网方法的网络特性指标没有任何规律性的结果.     

Regular and stochastic behavior of Parkinsonian pathological tremor signals

Regular and stochastic behavior in the time series of Parkinsonian pathological tremor velocity is studied on the basis of the statistical theory of discrete non-Markov stochastic processes and flicker-noise spectroscopy. We have developed a new method of analyzing and diagnosing Parkinson's disease (PD) by taking into consideration discreteness, fluctuations, long- and short-range correlations, regular and stochastic behavior, Markov and non-Markov effects and dynamic alternation of relaxation modes in the initial time signals. The spectrum of the statistical non-Markovity parameter reflects Markovity and non-Markovity in the initial time series of tremor. The relaxation and kinetic parameters used in the method allow us to estimate the relaxation scales of diverse scenarios of the time signals produced by the patient in various dynamic states. The local time behavior of the initial time correlation function and the first point of the non-Markovity parameter give detailed information about the variation of pathological tremor in the local regions of the time series. The obtained results can be used to find the most effective method of reducing or suppressing pathological tremor in each individual case of a PD patient. Generally, the method allows one to assess the efficacy of the medical treatment for a group of PD patients.     

混合交通流时间序列的去趋势波动分析

应用去趋势波动分析法研究交通流时间序列的复杂性,探讨了混合交通流时间序列演变行为的标度指数.根据标度指数的变化特征,进而揭示交通流时间序列所具有的长程相关性和短程相关性.通过分析发现,存在一密度ρ,当ρ₁<ρ<ρ₂时,交通流时间序列具有长程相关性;而当ρ<ρ₁或ρ>ρ₂时,交通流时间序列具有短程相关性,即密度的变化影响着标度指数的变化.另外分析了在不同慢车比率条件下时间序列的标度指数,发现慢车比率的变化 关键词： 混合交通流 去趋势波动分析 时间序列 长程相关     

Characterising chaos-hyperchaos transition using correlation dimension

Transition to hyperchaos is uaually studied by computing the spectrum of Lyapunov Exponents (LE). But such a procedure can be employed mainly when the equations governing the dynamical system are known. However, if the information available on the system is only through time series, the method becomes difficult to implement. We show that the transition to hyperchaos is followed by a sudden change in the topological structure of the underlying attractor. Our numerical results indicate that the transition to hyperchaos can be characterized accurately through the computation of correlation dimension (D ₂) from time series. We use two standard time delayed hyperchaotic systems as examples since, for such systems, D ₂ varies smoothly as a function of the time delay τ which can be used as the control parameter.     

Nonlinear systems identification by combining regression with bootstrap resampling

A new parameter estimation method for nonlinear systems from time series data is proposed. For the purpose of unbiased estimation, we employ the idea of bootstrap method on regression problems. Our method can be applied into even short and noisy data and is expected to give us a robust estimation. Some benchmarks of estimating chaotic models show its practical applicability. We also try to apply this method to analysis for intermittent hormonal therapy for prostate cancer by using a mathematical model and real clinical data.     

Efficient single image stripe nonuniformity correction method for infrared focal plane arrays

We present a novel, stripe nonuniformity correction algorithm for infrared focal plane arrays. This method relies on the separation of nonuniformity and true scene, and the nonuniformity correction parameter is obtained by traversing the error function of two adjacent columns?? pixels in local template window. Based on the succession of two adjacent columns?? correlation, the stripe nonuniformity correction can be achieved in a single frame. Experimental results, to illustrate the performance of the method, include the use of infrared image sequences with simulated nonuniformity and a diverse set of real IR imagery.     

Globalization — Entropy unification through the Theil index

A time series is remapped onto an entropy concept, based on the Theil index. The Manhattan distance between these surrogate series is calculated, and contrasted to the usual correlation distance measure. The idea is applied to several Gross Domestic Product (relative increments) of rich countries. Such distances are calculated for various time window sizes. The role of time averaging in such finite size windows is discussed. We construct the locally minimum spanning tree (LMST) corresponding to the distance matrix. Another hierarchical network structure (Unidirectional Minimal Length Path) is compared with the LMST for confirming that the mean distance between the most developed countries on different networks actually decreases in time, — which we consider as a proof of economy globalization. It is stressed that this entropy distance measure seems more suitable in detecting some “phase transition” in time series, like a globalization process than the usual correlation based measure.     

Markov Properties of Electrical Discharge Current Fluctuations in Plasma

Using the Markovian method, we study the stochastic nature of electrical discharge current fluctuations in the Helium plasma. Sinusoidal trends are extracted from the data set by the Fourier-Detrended Fluctuation analysis and consequently cleaned data is retrieved. We determine the Markov time scale of the detrended data set by using likelihood analysis. We also estimate the Kramers-Moyal’s coefficients of the discharge current fluctuations and derive the corresponding Fokker-Planck equation. In addition, the obtained Langevin equation enables us to reconstruct discharge time series with similar statistical properties compared with the observed in the experiment. We also provide an exact decomposition of temporal correlation function by using Kramers-Moyal’s coefficients. We show that for the stationary time series, the two point temporal correlation function has an exponential decaying behavior with a characteristic correlation time scale. Our results confirm that, there is no definite relation between correlation and Markov time scales. However both of them behave as monotonic increasing function of discharge current intensity. Finally to complete our analysis, the multifractal behavior of reconstructed time series using its Keramers-Moyal’s coefficients and original data set are investigated. Extended self similarity analysis demonstrates that fluctuations in our experimental setup deviates from Kolmogorov (K41) theory for fully developed turbulence regime.     

Large dimension forecasting models and random singular value spectra

We present a general method to detect and extract from a finite time sample statistically meaningful correlations between input and output variables of large dimensionality. Our central result is derived from the theory of free random matrices, and gives an explicit expression for the interval where singular values are expected in the absence of any true correlations between the variables under study. Our result can be seen as the natural generalization of the Marčenko-Pastur distribution for the case of rectangular correlation matrices. We illustrate the interest of our method on a set of macroeconomic time series.     

Inverse problem for multivariate time series using dynamical latent variables

Factor analysis is a well known statistical method to describe the variability among observed variables in terms of a smaller number of unobserved latent variables called factors. While dealing with multivariate time series, the temporal correlation structure of data may be modeled by including correlations in latent factors, but a crucial choice is the covariance function to be implemented. We show that analyzing multivariate time series in terms of latent Gaussian processes, which are mutually independent but with each of them being characterized by exponentially decaying temporal correlations, leads to an efficient implementation of the expectation–maximization algorithm for the maximum likelihood estimation of parameters, due to the properties of block-tridiagonal matrices. The proposed approach solves an ambiguity known as the identifiability problem, which renders the solution of factor analysis determined only up to an orthogonal transformation. Samples with just two temporal points are sufficient for the parameter estimation: hence the proposed approach may be applied even in the absence of prior information about the correlation structure of latent variables by fitting the model to pairs of points with varying time delay. Our modeling allows one to make predictions of the future values of time series and we illustrate our method by applying it to an analysis of published gene expression data from cell culture HeLa.