AUTO-EXTRACTING TECHNIQUE OF DYNAMIC CHAOS FEATURES FOR NONLINEAR TIME SERIES

The main purpose of nonlinear time series analysis is based on the rebuilding theory of phase space, and to study how to transform the response signal to rebuilt phase space in order to extract dynamic feature information, and to provide effective approach for nonlinear signal analysis and fault diagnosis of nonlinear dynamic system. Now, it has already formed an important offset of nonlinear science. But, traditional method cannot extract chaos features automatically, and it needs man＇s participation in the whole process. A new method is put forward, which can implement auto-extracting of chaos features for nonlinear time series. Firstly, to confirm time delay r by autocorrelation method; Secondly, to compute embedded dimension m and correlation dimension D; Thirdly, to compute the maximum Lyapunov index λmax; Finally, to calculate the chaos degree Dch of Poincare map, and the non-circle degree Dnc and non-order degree Dno of quasi-phase orbit. Chaos features extracting has important meaning to fault diagnosis of nonlinear system based on nonlinear chaos features. Examples show validity of the proposed method.

Chaos in Time Series of Sakarya River Daily Flow Rate

In this study, possible low dimensional chaotic behavior of Sakarya river flow rates is investigated via nonlinear time series techniques. To reveal the chaotic dynamics, the maximal positive Lyapunov exponent is calculated from the reconstructed phase space, which is obtained using the phase space reconstruction method. The method reconstructs a phase space from the scalar time series, which depicts the real system’s invariants Positive values, because the Lyapunov exponent values calculated using the appropriate software program indicate possibility of chaotic behavior. Analyzed data involve the monthly average flow rates of eleven main branches of Sakarya River through the years 1960-2000.

Arrhythmia Detection by Using Chaos Theory with Machine Learning Algorithms

Heart monitoring improves life quality.Electrocardiograms(ECGs or EKGs)detect heart irregularities.Machine learning algorithms can create a few ECG diagnosis processing methods.The first method uses raw ECG and time-series data.The second method classifies the ECG by patient experience.The third technique translates ECG impulses into Q waves,R waves and S waves(QRS)features using richer information.Because ECG signals vary naturally between humans and activities,we will combine the three feature selection methods to improve classification accuracy and diagnosis.Classifications using all three approaches have not been examined till now.Several researchers found that Machine Learning(ML)techniques can improve ECG classification.This study will compare popular machine learning techniques to evaluate ECG features.Four algorithms—Support Vector Machine(SVM),Decision Tree,Naive Bayes,and Neural Network—compare categorization results.SVM plus prior knowledge has the highest accuracy(99%)of the four ML methods.QRS characteristics failed to identify signals without chaos theory.With 99.8%classification accuracy,the Decision Tree technique outperformed all previous experiments.

Transition to chaos in lid-driven square cavity flow

To date,there are very few studies on the transition beyond second Hopf bifurcation in a lid-driven square cavity,due to the difficulties in theoretical analysis and numerical simulations.In this paper,we study the characteristics of the third Hopf bifurcation in a driven square cavity by applying a consistent fourth-order compact finite difference scheme rectently developed by us.We numerically identify the critical Reynolds number of the third Hopf bifurcation located in the interval of(13944.7021,13946.5333)by the method of bisection.Through Fourier analysis,it is discovered that the flow becomes chaotic with a characteristic of period-doubling bifurcation when the Reynolds number is beyond the third bifurcation critical interval.Nonlinear time series analysis further ascertains the flow chaotic behaviors via the phase diagram,Kolmogorov entropy and maximal Lyapunov exponent.The phase diagram changes interestingly from a closed curve with self-intersection to an unclosed curve and the attractor eventually becomes strange when the flow becomes chaotic.

A Cross-Reference Method for Nonlinear Time Series Analysis in Semi-Blind Case

In this paper, we propose a cross reference method for nonlinear time series analyzing in semi blind case, that is, the dynamic equations modeling the time series are known but the corresponding parameters are not. The tasks of noise reduction and parameter estimation which were fulfilled separately before are combined iteratively. With the positive interaction between the two processing modules, the method is somewhat superior. Some prior work can be viewed as special cases of this general framework. The simulations for noise reduction and parameter estimation of contaminated chaotic time series show improved performance of our method compared with previous work.

Correlation between detrended fluctuation analysis and the Lempel-Ziv complexity in nonlinear time series analysis

We study the correlation between detrended fluctuation analysis（DFA） and the Lempel-Ziv complexity（LZC） in nonlinear time series analysis in this paper.Typical dynamic systems including a logistic map and a Duffing model are investigated.Moreover,the influence of Gaussian random noise on both the DFA and LZC are analyzed.The results show a high correlation between the DFA and LZC,which can quantify the non-stationarity and the nonlinearity of the time series,respectively.With the enhancement of the random component,the exponent α and the normalized complexity index C show increasing trends.In addition,C is found to be more sensitive to the fluctuation in the nonlinear time series than α.Finally,the correlation between the DFA and LZC is applied to the extraction of vibration signals for a reciprocating compressor gas valve,and an effective fault diagnosis result is obtained.

Denoising Nonlinear Time Series Using Singular Spectrum Analysis and Fuzzy Entropy

We present a hybrid singular spectrum analysis （SSA） and fuzzy entropy method to filter noisy nonlinear time series. With this approach, SSA decomposes the noisy time series into its constituent components including both the deterministic behavior and noise, while fuzzy entropy automatically differentiates the optimal dominant components from the noise based on the complexity of each component. We demonstrate the effectiveness of the hybrid approach in reconstructing the Lorenz and Mackey--Class attractors, as well as improving the multi-step prediction quality of these two series in noisy environments.

Study of Polluted Insulator Flashover Forecasting Based on Nonlinear Time Series Analysis

To solve the problem of the flashover forecasting of contaminated or polluted insulator,a flashover forecasting model of contaminated insulators based on nonlinear time series analysis is proposed in the paper.The ESDD is the key of flashover on polluted insulator.The ESDD value of insulator can be forecasted by the method of nonlinear time series analysis of the ESDD time series and a forecasting model of polluted insulator flashover is proposed in the paper.The forecasting model consists of two artificial neural networks that reflect relationship of environment,ESDD and flashover probability.The first is used to estimate the ESDD time series of insulator and the second is employed to calculate the probability of the flashover.A series of artificial pollution tests show that the results of the forecasting model is acceptable.

Nonlinear Analysis of Physiological Time Series

The heart rate variability could be explained by a low-dimensional governing mechanism. There has been increasing interest in verifying and understanding the coupling between the respiration and the heart rate. In this paper we use the nonlinear detection method to detect the nonlinear deterministic component in the physiological time series by a single variable series and two variables series respectively, and use the conditional information entropy to analyze the correlation between the heart rate, the respiration and the blood oxygen concentration. The conclusions are that there is the nonlinear deterministic component in the heart rate data and respiration data, and the heart rate and the respiration are two variables originating from the same underlying dynamics.

RESEARCH ON NONLINEAR MODELS OF TIME SERIES

This paper presents some nonlinear models for time series. The structures and training methods for each model have been analyzed and studied. Experimental results for some common time series are given.

A Nonlinear Autoregressive Scheme for Time Series Prediction via Artificial Neural Networks

This article is devoted to a time series prediction scheme involving the nonlinear autoregressive algorithm and its applications. The scheme is implemented by means of an artificial neural network containing a hidden layer. As a training algorithm we use scaled conjugate gradient (SCG) method and the Bayesian regularization (BReg) method. The first method is applied to time series without noise, while the second one can also be applied for noisy datasets. We apply the suggested scheme for prediction of time series arising in oil and gas pricing using 50 and 100 past values. Results of numerical simulations are presented and discussed.

Genetic programming-based chaotic time series modeling

This paper proposes a Genetic Programming-Based Modeling (GPM) algorithm on chaotic time series. GP is used here to search for appropriate model structures in function space, and the Particle Swarm Optimization (PSO) algorithm is used for Nonlinear Parameter Estimation (NPE) of dynamic model structures. In addition, GPM integrates the results of Nonlinear Time Series Analysis (NTSA) to adjust the parameters and takes them as the criteria of established models. Experiments showed the effectiveness of such improvements on chaotic time series modeling.

Feature Selection for Time Series Modeling

In machine learning, selecting useful features and rejecting redundant features is the prerequisite for better modeling and prediction. In this paper, we first study representative feature selection methods based on correlation analysis, and demonstrate that they do not work well for time series though they can work well for static systems. Then, theoretical analysis for linear time series is carried out to show why they fail. Based on these observations, we propose a new correlation-based feature selection method. Our main idea is that the features highly correlated with progressive response while lowly correlated with other features should be selected, and for groups of selected features with similar residuals, the one with a smaller number of features should be selected. For linear and nonlinear time series, the proposed method yields high accuracy in both feature selection and feature rejection.

Finding Chaos in Finnish GDP

The goal of this paper is to analyze the Finnish gross domestic product(GDP) and to find chaos in the Finnish GDP. We chose Finland where data has been available since 1975, because we needed the longest time series possible. At first we estimated the time delay and the embedding dimension, which is needed for the Lyapunov exponent estimation and for the phase space reconstruction.Subsequently, we computed the largest Lyapunov exponent, which is one of the important indicators of chaos. Then we calculated the 0-1 test for chaos. Finally we computed the Hurst exponent by rescaled range analysis and by dispersional analysis. The Hurst exponent is a numerical estimate of the predictability of a time series. In the end, we executed a recurrent analysis and displayed recurrence plots of detrended GDP time series. The results indicated that chaotic behaviors obviously exist in GDP.

Nonlinear Time Series Analysis Since 1990:Some Personal Reflections

I reflect upon the development of nonlinear time series analysis since 1990 by focusing on five major areas of development. These areas include the interface between nonlinear time series analysis and chaos, the nonparametric/semiparametric approach, nonlinear state space modelling, financial time series and nonlinear modelling of panels of time series.

Small-time scale network traffic prediction based on a local support vector machine regression model

In this paper we apply the nonlinear time series analysis method to small-time scale traffic measurement data. The prediction-based method is used to determine the embedding dimension of the traffic data. Based on the reconstructed phase space, the local support vector machine prediction method is used to predict the traffic measurement data, and the BIC-based neighbouring point selection method is used to choose the number of the nearest neighbouring points for the local support vector machine regression model. The experimental results show that the local support vector machine prediction method whose neighbouring points are optimized can effectively predict the small-time scale traffic measurement data and can reproduce the statistical features of real traffic measurements.

Measuring Nonlinear Dependence Between Time Series Based on Correlation Dimension

In this paper, it is proved that the correlation dimension estimate of a nonlinear dynamical system with its multivariate observation series is the same as that with its univariate observation series. Based on this result, an inference method is presented, and the Nonlinear Dependence Coefficient is defined. This method is designed for testing nonlinear dependence between time series, and can be used in economic analysis and forecasting. Numerical results show the method is effective.

Principal component cluster analysis of ECG time series based on Lyapunov exponent spectrum

In this paper we propose an approach of prin-cipal component cluster analysis based on Lyapunov expo-nent spectrum (LES) to analyze the ECG time series. Analy-sis results of 22 sample-files of ECG from the MIT-BIH da-tabase confirmed the validity of our approach. Another technique named improved teacher selecting student (TSS) algorithm is presented to analyze unknown samples by means of some known ones, which is of better accuracy. This technique combines the advantages of both statistical and nonlinear dynamical methods and is shown to be significant to the analysis of nonlinear ECG time series.

Cross and joint ordinal partition transition networks for multivariate time series analysis

We propose the construction of cross and joint ordinal pattern transition networks from multivariate time series for two coupled systems, where synchronizations are often present. In particular, we focus on phase synchronization, which is a prototypical scenario in dynamical systems. We systematically show that cross and joint ordinal pattern transition networks are sensitive to phase synchronization. Furthermore, we find that some particular missing ordinal patterns play crucial roles in forming the detailed structures in the parameter space, whereas the calculations of permutation entropy measures often do not. We conclude that cross and joint ordinal partition transition network approaches provide complementary insights into the traditional symbolic analysis of synchronization transitions.

快速流化床提升管中气固流动行为的非线性分析

对10 0mm× 16m、FCC固体颗粒的快速流化床提升管内环 -核流动区局部颗粒含量脉动行为进行了非线性分析 ,用Kolmogorov熵表征了其气固流动行为 .结果表明 ,Kolmogorov熵沿提升管环 -核流动区径向有3个显著变化区域 ,以此为依据将提升管环 核流动区的气固流动行为沿径向分成 3个流域 :单颗粒随机运动控制的核心流域 ;单颗粒混沌控制的过渡流域 ;边壁控制的环形流域 .同时 ,从颗粒对垂直气固流动系统中气固湍动程度影响的角度 ,解释了Kolmogorov熵的径向分布特征及其与流动结构的关系 .