Downloads & Free Reading Options - Results

An empirical algorithm is used here to study the stochastic and multifractal nature of nonlinear time series. A parameter can be defined to quantitatively measure the deviation of the time series from a Wiener process so that the stochasticity of different time series can be compared. The local volatility of the time series under study can be constructed using this algorithm and the multifractal structure of the time series can be analyzed by using this local volatility. As an example, we employ this method to analyze financial time series from different stock markets. The result shows that while developed markets evolve very much like an Ito process, the emergent markets are far from efficient. Differences about the multifractal structures and leverage effects between developed and emergent markets are discussed. The algorithm used here can be applied in a similar fashion to study time series of other complex systems.

We consider asymptotic problems in spectral analysis of stationary causal processes. Limiting distributions of periodograms and smoothed periodogram spectral density estimates are obtained and applications to the spectral domain bootstrap are given. Instead of the commonly used strong mixing conditions, in our asymptotic spectral theory we impose conditions only involving (conditional) moments, which are easily verifiable for a variety of nonlinear time series.

The surrogate data method is widely applied as a data dependent technique to test observed time series against a barrage of hypotheses. However, often the hypotheses one is able to address are not those of greatest interest, particularly for system known to be nonlinear. In the review we focus on techniques which overcome this shortcoming. We summarize a number of recently developed surrogate data methods. While our review of surrogate methods is not exhaustive, we do focus on methods which may be applied to experimental, and potentially nonlinear, data. In each case, the hypothesis being tested is one of the interests to the experimental scientist.

The surrogate data method is widely applied as a data dependent technique to test observed time series against a barrage of hypotheses. However, often the hypotheses one is able to address are not those of greatest interest, particularly for system known to be nonlinear. In the review we focus on techniques which overcome this shortcoming. We summarize a number of recently developed surrogate data methods. While our review of surrogate methods is not exhaustive, we do focus on methods which may be applied to experimental, and potentially nonlinear, data. In each case, the hypothesis being tested is one of the interests to the experimental scientist.

Title from cover

The problem of detecting specific features of microscopic dynamics in the macroscopic behavior of a many-degrees-of-freedom system is investigated by analyzing the position and momentum time series of a heavy impurity embedded in a chain of nearest-neighbor anharmonic Fermi-Pasta-Ulam oscillators. Results obtained in a previous work [M. Romero-Bastida, Phys. Rev. E {\bf69}, 056204 (2004)] suggest that the impurity does not contribute significantly to the dynamics of the chain and can be considered as a probe for the dynamics of the system to which the impurity is coupled. The ($r,\tau$) entropy, which measures the amount of information generated by unit time at different scales $\tau$ of time and $r$ of the observable, is numerically computed by methods of nonlinear time-series analysis using the position and momentum signals of the heavy impurity for various values of the energy density $\epsilon$ (energy per degree of freedom) of the system and some values of the impurity mass $M$. Results obtained from these two time series are compared and discussed.

When building linear or nonlinear models one is faced with the problem of selecting the best set of variable with which to predict the future dynamics. In nonlinear time series analysis the problem is to select the correct time delays in the time delay embedding. We propose a new technique which can quantify the suitability of a particular set of variables and we suggests a computationally efficient scheme to determine the best non-uniform time delay embedding for modeling of time series. Our results are based on the assumption that, in general, the variables which give the best local constant model will also give the best nonlinear model. In a wide variety of experimental and simulated systems we find that this method produces dynamics that are more realistic and predictions that are more accurate than standard uniform embeddings.

When building linear or nonlinear models one is faced with the problem of selecting the best set of variable with which to predict the future dynamics. In nonlinear time series analysis the problem is to select the correct time delays in the time delay embedding. We propose a new technique which can quantify the suitability of a particular set of variables and we suggests a computationally efficient scheme to determine the best non-uniform time delay embedding for modeling of time series. Our results are based on the assumption that, in general, the variables which give the best local constant model will also give the best nonlinear model. In a wide variety of experimental and simulated systems we find that this method produces dynamics that are more realistic and predictions that are more accurate than standard uniform embeddings.

When building linear or nonlinear models one is faced with the problem of selecting the best set of variable with which to predict the future dynamics. In nonlinear time series analysis the problem is to select the correct time delays in the time delay embedding. We propose a new technique which can quantify the suitability of a particular set of variables and we suggests a computationally efficient scheme to determine the best non-uniform time delay embedding for modeling of time series. Our results are based on the assumption that, in general, the variables which give the best local constant model will also give the best nonlinear model. In a wide variety of experimental and simulated systems we find that this method produces dynamics that are more realistic and predictions that are more accurate than standard uniform embeddings.

In this work we present 3 case studies of local temperature time series obtained from stations in Europe and Israel. The nonlinear nature of the series is presented along with model based forecasting. Data is nonlinearly filtered using high dimensional projection and analysis is performed on the filtered data. A lorenz type model of 3 first order ODEs is then fitted. Forecasts are shown for periods of 100 days ahead, outperforming any existing forecast method known today. While other models fail at forecasting periods above 11 days, ours shows remarkable stability 100 days ahead. Thus finally a local dynamical system if found for local temperature forecasting not requiring solution of Navier-Stokes equations. Thus saving computational costs.

In this work we present 3 case studies of local temperature time series obtained from stations in Europe and Israel. The nonlinear nature of the series is presented along with model based forecasting. Data is nonlinearly filtered using high dimensional projection and analysis is performed on the filtered data. A lorenz type model of 3 first order ODEs is then fitted. Forecasts are shown for periods of 100 days ahead, outperforming any existing forecast method known today. While other models fail at forecasting periods above 11 days, ours shows remarkable stability 100 days ahead. Thus finally a local dynamical system if found for local temperature forecasting not requiring solution of Navier-Stokes equations. Thus saving computational costs.

Bibliography: leaves 25-27

Bibliography: leaves 25-27

On the basis of a local-projective (LP) approach we develop a method of noise reduction in time series that makes use of nonlinear constraints appearing due to the deterministic character of the underlying dynamical system. The Delaunay triangulation approach is used to find the optimal nearest neighboring points in time series. The efficiency of our method is comparable to standard LP methods but our method is more robust to the input parameter estimation. The approach has been successfully applied for separating a signal from noise in the chaotic Henon and Lorenz models as well as for noisy experimental data obtained from an electronic Chua circuit. The method works properly for a mixture of additive and dynamical noise and can be used for the noise-level detection.

The dynamical properties of road traffic time series from North-Rhine Westphalian motorways are investigated. The article shows that road traffic dynamics is well described as a persistent stochastic process with two fixed points representing the freeflow (non-congested) and the congested state regime. These traffic states have different statistical properties, with respect to waiting time distribution, velocity distribution and autocorrelation. Logdifferences of velocity records reveal non-normal, obviously leptocurtic distribution. Further, linear and nonlinear phase-plane based analysis methods yield no evidence for any determinism or deterministic chaos to be involved in traffic dynamics on shorter than diurnal time scales. Several Hurst-exponent estimators indicate long-range dependence for the free flow state. Finally, our results are not in accordance to the typical heuristic fingerprints of self-organized criticality. We suggest the more simplistic assumption of a non-critical phase transition between freeflow and congested traffic.

GRS 1915+105 is a prominent black hole system exhibiting variability over a wide range of time scales and its observed light curves have been classified into 12 temporal states. Here we undertake a complete analysis of these light curves from all the states using various quantifiers from nonlinear time series analysis, such as, the correlation dimension (D_2), the correlation entropy (K_2), singular value decomposition (SVD) and the multifractal spectrum ($f(\alpha)$ spectrum). An important aspect of our analysis is that, for estimating these quantifiers, we use algorithmic schemes which we have proposed recently and tested successfully on synthetic as well as practical time series from various fields. Though the schemes are based on the conventional delay embedding technique, they are automated so that the above quantitative measures can be computed using conditions prescribed by the algorithm and without any intermediate subjective analysis. We show that nearly half of the 12 temporal states exhibit deviation from randomness and their complex temporal behavior could be approximated by a few (3 or 4) coupled ordinary nonlinear differential equations. These results could be important for a better understanding of the processes that generate the light curves and hence for modelling the temporal behavior of such complex systems. To our knowledge, this is the first complete analysis of an astrophysical object (let alone a black hole system) using various techniques from nonlinear dynamics.

This thesis uses multiple layer perceptrons (MLP) neural networks and Kohonen clustering networks to predict and assign confidence to nonlinear time series classifications. The nonlinear time series used for analysis is the Standard and Poor's 100 (S&P 100) index. The target prediction is classification of the daily index change. Financial indicators were evaluated to determine the most useful combination of features for input into the networks. After evaluation it was determined that net changes in the index over time and three short-term indicators result in better accuracy. A back-propagation trained MLP neural network was then trained with these features to get a daily classification prediction of up or down. Next, a Kohonen clustering network was trained to develop 30 different clusters. The predictions from the MLP network were labeled as correct or incorrect within each classification and counted in each category to determine a confidence for a given cluster. Test data was then run through both networks and predictions were assigned a confidence based on which cluster they belonged to. The results of these tests show that this method can improve the accuracy of predictions from 51% to 73%. Within a cluster accuracy is near 100% for some classifications.

MARS is a new methodology, due to Friedman, for nonlinear regression modeling. MARS can be conceptualized as a generalization of recursive partitioning that uses spline fitting in lieu of other simple functions. Given a set of predictor variables, MARS fits a model in a form of an expansion of product spline basis functions of predictors chosen during a forward and backward recursive partitioning strategy. MARS produces continuous models for discrete data that can have multiple partitions and multilinear terms. Predictor variable contributions and interactions in a MARS model may be analyzed using an ANOVA style decomposition. By letting the predictor variables in MARS be lagged values of a time series, one obtains a new method for nonlinear autoregressive threshold modeling of time series. A significant feature of this extension of MARS is its ability to produce models with limit cycles when modeling time series data that exhibit periodic behavior. In a physical context, limit cycles represent a stationary state of sustained oscillations, a satisfying behavior for any model of a time series with periodic behavior. Analysis of the Wolf sunspot numbers with MARS appears to give an improvement over existing nonlinear Threshold and Bilinear models. (kr)

The paper describes the application of some numerical techniques to analyze and to characterize the observed dynamical behaviour of fluidized bed systems. The preliminary results showed clearly that the dynamics of the considered process can be nonrecurrent and governed by chaotic deterministic rules rather than by stochastic ones. This significant conclusion was allowed by the application of a proper filtering procedure which was able to reduce the unwanted influence of significant broadband noise detected in the sampled experimental data.

The paper describes the application of some numerical techniques to analyze and to characterize the observed dynamical behaviour of fluidized bed systems. The preliminary results showed clearly that the dynamics of the considered process can be nonrecurrent and governed by chaotic deterministic rules rather than by stochastic ones. This significant conclusion was allowed by the application of a proper filtering procedure which was able to reduce the unwanted influence of significant broadband noise detected in the sampled experimental data.

In 1980 and 1981, two pioneering papers laid the foundation for what became known as nonlinear time-series analysis: the analysis of observed data---typically univariate---via dynamical systems theory. Based on the concept of state-space reconstruction, this set of methods allows us to compute characteristic quantities such as Lyapunov exponents and fractal dimensions, to predict the future course of the time series, and even to reconstruct the equations of motion in some cases. In practice, however, there are a number of issues that restrict the power of this approach: whether the signal accurately and thoroughly samples the dynamics, for instance, and whether it contains noise. Moreover, the numerical algorithms that we use to instantiate these ideas are not perfect; they involve approximations, scale parameters, and finite-precision arithmetic, among other things. Even so, nonlinear time-series analysis has been used to great advantage on thousands of real and synthetic data sets from a wide variety of systems ranging from roulette wheels to lasers to the human heart. Even in cases where the data do not meet the mathematical or algorithmic requirements to assure full topological conjugacy, the results of nonlinear time-series analysis can be helpful in understanding, characterizing, and predicting dynamical systems.

Interest in solar activity has grown in the past two decades for many reasons. Most importantly for flight dynamics, solar activity changes the atmospheric density, which has important implications for spacecraft trajectory and lifetime prediction. Building upon the previously developed Rayleigh-Benard nonlinear dynamic solar model, which exhibits many dynamic behaviors observed in the Sun, this work introduces new chaotic solar forecasting techniques. Our attempt to use recently developed nonlinear chaotic techniques to model and forecast solar activity has uncovered highly entangled dynamics. Numerical techniques for decoupling additive and multiplicative white noise from deterministic dynamics and examines falloff of the power spectra at high frequencies as a possible means of distinguishing deterministic chaos from noise than spectrally white or colored are presented. The power spectral techniques presented are less cumbersome than current methods for identifying deterministic chaos, which require more computationally intensive calculations, such as those involving Lyapunov exponents and attractor dimension.

Contents: Coherent structures and turbulence; Prediction and noise I; Symmetry; Wavelets; Characterizing turbulence; Is it chaos or noise?; Prediction and noise II; Prediction and control I; A question of dimension; Prediction and control II.

286p

286p

Bibliography: p. 44-46

Bibliography: p. 44-46

We introduce the \texttt{pyunicorn} (Pythonic unified complex network and recurrence analysis toolbox) open source software package for applying and combining modern methods of data analysis and modeling from complex network theory and nonlinear time series analysis. \texttt{pyunicorn} is a fully object-oriented and easily parallelizable package written in the language Python. It allows for the construction of functional networks such as climate networks in climatology or functional brain networks in neuroscience representing the structure of statistical interrelationships in large data sets of time series and, subsequently, investigating this structure using advanced methods of complex network theory such as measures and models for spatial networks, networks of interacting networks, node-weighted statistics or network surrogates. Additionally, \texttt{pyunicorn} provides insights into the nonlinear dynamics of complex systems as recorded in uni- and multivariate time series from a non-traditional perspective by means of recurrence quantification analysis (RQA), recurrence networks, visibility graphs and construction of surrogate time series. The range of possible applications of the library is outlined, drawing on several examples mainly from the field of climatology.

We introduce the \texttt{pyunicorn} (Pythonic unified complex network and recurrence analysis toolbox) open source software package for applying and combining modern methods of data analysis and modeling from complex network theory and nonlinear time series analysis. \texttt{pyunicorn} is a fully object-oriented and easily parallelizable package written in the language Python. It allows for the construction of functional networks such as climate networks in climatology or functional brain networks in neuroscience representing the structure of statistical interrelationships in large data sets of time series and, subsequently, investigating this structure using advanced methods of complex network theory such as measures and models for spatial networks, networks of interacting networks, node-weighted statistics or network surrogates. Additionally, \texttt{pyunicorn} provides insights into the nonlinear dynamics of complex systems as recorded in uni- and multivariate time series from a non-traditional perspective by means of recurrence quantification analysis (RQA), recurrence networks, visibility graphs and construction of surrogate time series. The range of possible applications of the library is outlined, drawing on several examples mainly from the field of climatology.

Nonlinear time series analysis is becoming a more and more reliable tool for the study of complicated dynamics from measurements. The concept of low-dimensional chaos has proven to be fruitful in the understanding of many complex phenomena despite the fact that very few natural systems have actually been found to be low dimensional deterministic in the sense of the theory. In order to evaluate the long term usefulness of the nonlinear time series approach as inspired by chaos theory, it will be important that the corresponding methods become more widely accessible. This paper, while not a proper review on nonlinear time series analysis, tries to make a contribution to this process by describing the actual implementation of the algorithms, and their proper usage. Most of the methods require the choice of certain parameters for each specific time series application. We will try to give guidance in this respect. The scope and selection of topics in this article, as well as the implementational choices that have been made, correspond to the contents of the software package TISEAN which is publicly available from http://www.mpipks-dresden.mpg.de/~tisean . In fact, this paper can be seen as an extended manual for the TISEAN programs. It fills the gap between the technical documentation and the existing literature, providing the necessary entry points for a more thorough study of the theoretical background.

Previous studies indicate that nonlinear properties of Gaussian time series with long-range correlations, $u_i$, can be detected and quantified by studying the correlations in the magnitude series $|u_i|$, i.e., the ``volatility''. However, the origin for this empirical observation still remains unclear, and the exact relation between the correlations in $u_i$ and the correlations in $|u_i|$ is still unknown. Here we find analytical relations between the scaling exponent of linear series $u_i$ and its magnitude series $|u_i|$. Moreover, we find that nonlinear time series exhibit stronger (or the same) correlations in the magnitude time series compared to linear time series with the same two-point correlations. Based on these results we propose a simple model that generates multifractal time series by explicitly inserting long range correlations in the magnitude series; the nonlinear multifractal time series is generated by multiplying a long-range correlated time series (that represents the magnitude series) with uncorrelated time series [that represents the sign series $sgn(u_i)$]. Our results of magnitude series correlations may help to identify linear and nonlinear processes in experimental records.

Identifying causal relations among simultaneously acquired signals is an important problem in multivariate time series analysis. For linear stochastic systems Granger proposed a simple procedure called the Granger causality to detect such relations. In this work we consider nonlinear extensions of Granger's idea and refer to the result as Extended Granger Causality. A simple approach implementing the Extended Granger Causality is presented and applied to multiple chaotic time series and other types of nonlinear signals. In addition, for situations with three or more time series we propose a conditional Extended Granger Causality measure that enables us to determine whether the causal relation between two signals is direct or mediated by another process.

My new book [Nonlinear Ocean Waves and the Inverse Scattering Transform, Osborne, 2010] discusses the physics, nonlinear time series analysis, data assimilation and hyperfast modeling of nonlinear ocean waves. Some of the material in this book consists of mathematics not always familiar to oceanographers and may require an investment of the reader's time to take full advantage of the methods introduced there. This book, in many ways, may be compared to the book Ocean Wave Spectra [ONR, 1962], which was published in a revolutionary time for the field of wind waves (the 1950s and 60s). New data analysis procedures were being developed by Pierson, Longuet-Higgins, Munk, Hasselmann and others. The concept of the power spectrum was quite new to physical oceanographers. It is useful in this context to recall the work of Paley, Weiner and Rice in the 1930s and 1940s and the subsequent application to power spectra and wind waves in the 1950s and 1960s: This work was based upon the integrable of the square root of dx ! I recall well the consternation of physical oceanographers at that time about this seemingly impossibly difficult mathematics (see Kinsmann's book for aid in understanding what was at that time the new mathematics). Likewise the introduction of the Hasselmann equation in 1961 was based on the derivation of kinetic equations from the Euler equations, also rather esoteric mathematics at that time. Now of course these areas of mathematics have been absorbed into the mainstream of wind/wave research and have lead to the development of modern forecasting and hindcasting models. Indeed the mathematics of 1960 seems mainstream today.

My new book [Nonlinear Ocean Waves and the Inverse Scattering Transform, Osborne, 2010] discusses the physics, nonlinear time series analysis, data assimilation and hyperfast modeling of nonlinear ocean waves. Some of the material in this book consists of mathematics not always familiar to oceanographers and may require an investment of the reader's time to take full advantage of the methods introduced there. This book, in many ways, may be compared to the book Ocean Wave Spectra [ONR, 1962], which was published in a revolutionary time for the field of wind waves (the 1950s and 60s). New data analysis procedures were being developed by Pierson, Longuet-Higgins, Munk, Hasselmann and others. The concept of the power spectrum was quite new to physical oceanographers. It is useful in this context to recall the work of Paley, Weiner and Rice in the 1930s and 1940s and the subsequent application to power spectra and wind waves in the 1950s and 1960s: This work was based upon the integrable of the square root of dx ! I recall well the consternation of physical oceanographers at that time about this seemingly impossibly difficult mathematics (see Kinsmann's book for aid in understanding what was at that time the new mathematics). Likewise the introduction of the Hasselmann equation in 1961 was based on the derivation of kinetic equations from the Euler equations, also rather esoteric mathematics at that time. Now of course these areas of mathematics have been absorbed into the mainstream of wind/wave research and have lead to the development of modern forecasting and hindcasting models. Indeed the mathematics of 1960 seems mainstream today.

Title from cover

This book presents recent developments in nonlinear time series which have been motivated by present day problems in geosciences. Modern methods of spatio-temporal data analysis, time-frequency analysis, dimension analysis, nonlinear correlation and synchronization analysis and other nonlinear concepts are used to study emerging questions in climatology, geophysics, solar-terrestrial physics and related scientific disciplines. This volume collects contributions of some of the world's leading experts in geoscientific time series analysis. The methods presented may help researchers as well as practitioners to significantly improve their understanding of the data.

This book presents recent developments in nonlinear time series which have been motivated by present day problems in geosciences. Modern methods of spatio-temporal data analysis, time-frequency analysis, dimension analysis, nonlinear correlation and synchronization analysis and other nonlinear concepts are used to study emerging questions in climatology, geophysics, solar-terrestrial physics and related scientific disciplines. This volume collects contributions of some of the world's leading experts in geoscientific time series analysis. The methods presented may help researchers as well as practitioners to significantly improve their understanding of the data.

This article discusses a partially adapted particle filter for estimating the likelihood of a nonlinear structural econometric state space models whose state transition density cannot be expressed in closed form. The filter generates the disturbances in the state transition equation and allows for multiple modes in the conditional disturbance distribution. The particle filter produces an unbiased estimate of the likelihood and so can be used to carry out Bayesian inference in a particle Markov chain Monte Carlo framework. We show empirically that when the signal to noise ratio is high, the new filter can be much more efficient than the standard particle filter, in the sense that it requires far fewer particles to give the same accuracy. The new filter is applied to several simulated and real examples and in particular to a dynamic stochastic general equilibrium model.

This article discusses a partially adapted particle filter for estimating the likelihood of a nonlinear structural econometric state space models whose state transition density cannot be expressed in closed form. The filter generates the disturbances in the state transition equation and allows for multiple modes in the conditional disturbance distribution. The particle filter produces an unbiased estimate of the likelihood and so can be used to carry out Bayesian inference in a particle Markov chain Monte Carlo framework. We show empirically that when the signal to noise ratio is high, the new filter can be much more efficient than the standard particle filter, in the sense that it requires far fewer particles to give the same accuracy. The new filter is applied to several simulated and real examples and in particular to a dynamic stochastic general equilibrium model.

In this paper we consider tests for nonlinear time series, which are motivated by the notion of serial dependence. The proposed tests are based on comparisons with the quantile spectral density, which can be considered as a quantile version of the usual spectral density function. The quantile spectral density 'measures' sequential dependence structure of a time series, and is well defined under relatively weak mixing conditions. We propose an estimator for the quantile spectral density and derive its asympototic sampling properties. We use the quantile spectral density to construct a goodness of fit test for time series and explain how this test can also be used for comparing the sequential dependence structure of two time series. The method is illustrated with simulations and some real data examples.

We generalize a previously proposed approach for nonlinear Granger causality of time series, based on radial basis function. The proposed model is not constrained to be additive in variables from the two time series and can approximate any function of these variables, still being suitable to evaluate causality. Usefulness of this measure of causality is shown in a physiological example and in the study of the feed-back loop in a model of excitatory and inhibitory neurons.

This study aims to determine an automatic forecasting method of univariate time series, using the nonlinear autoregressive neural network model with exogenous input (NARX). In this automatic setting, users only need to supply the input of time series. Then, an automatic forecasting algorithm sets up the appropriate features, estimate the parameters in the model, and calculate forecasts, without the users’ intervention. The algorithm method used include preprocessing, tests for trends, and the application of first differences. The time series were tested for seasonality, and seasonal differences were obtained from a successful analysis. These series were also linearly scaled to [−1, +1]. The autoregressive lags and hidden neurons were further selected through the stepwise and optimization algorithms, respectively. The 20 NARX models were fitted with different random starting weights, and the forecasts were combined using the ensemble operator, in order to obtain the final product. This proposed method was applied to real data, and its performance was compared with several available automatic models in the literature. The forecasting accuracy was also measured by mean squared error (MSE) and mean absolute percent error (MAPE), and the results showed that the proposed method outperformed the other automatic models.

This study aims to determine an automatic forecasting method of univariate time series, using the nonlinear autoregressive neural network model with exogenous input (NARX). In this automatic setting, users only need to supply the input of time series. Then, an automatic forecasting algorithm sets up the appropriate features, estimate the parameters in the model, and calculate forecasts, without the users’ intervention. The algorithm method used include preprocessing, tests for trends, and the application of first differences. The time series were tested for seasonality, and seasonal differences were obtained from a successful analysis. These series were also linearly scaled to [−1, +1]. The autoregressive lags and hidden neurons were further selected through the stepwise and optimization algorithms, respectively. The 20 NARX models were fitted with different random starting weights, and the forecasts were combined using the ensemble operator, in order to obtain the final product. This proposed method was applied to real data, and its performance was compared with several available automatic models in the literature. The forecasting accuracy was also measured by mean squared error (MSE) and mean absolute percent error (MAPE), and the results showed that the proposed method outperformed the other automatic models.

We use the methodology of singular spectrum analysis (SSA), principal component analysis (PCA), and multi-fractal detrended fluctuation analysis (MFDFA), for investigating characteristics of vibration time series data from a friction brake. SSA and PCA are used to study the long time-scale characteristics of the time series. MFDFA is applied for investigating all time scales up to the smallest recorded one. It turns out that the majority of the long time-scale dynamics, that is presumably dominated by the structural dynamics of the brake system, is dominated by very few active dimensions only and can well be understood in terms of low dimensional chaotic attractors. The multi-fractal analysis shows that the fast dynamical processes originating in the friction interface are in turn truly multi-scale in nature.

The variability of AVHRR calibration coefficient in time was analyzed using algorithms of linear and non-linear time series analysis. Specifically we have used the spline trend modeling, autoregressive process analysis, incremental neural network learning algorithm and redundancy functional testing. The analysis performed on available AVHRR data sets revealed that (1) the calibration data have nonlinear dependencies, (2) the calibration data depend strongly on the target temperature, (3) both calibration coefficients and the temperature time series can be modeled, in the first approximation, as autonomous dynamical systems, (4) the high frequency residuals of the analyzed data sets can be best modeled as an autoregressive process of the 10th degree. We have dealt with a nonlinear identification problem and the problem of noise filtering (data smoothing). The system identification and filtering are significant problems for AVHRR data sets. The algorithms outlined in this study can be used for the future EOS missions. Prediction and smoothing algorithms for time series of calibration data provide a functional characterization of the data. Those algorithms can be particularly useful when calibration data are incomplete or sparse.

xii, 227 p. : 24 cm

xii, 227 p. : 24 cm

This article is from Proceedings of the Royal Society B: Biological Sciences , volume 279 . Abstract Bipolar disorder is a psychiatric condition characterized by episodes of elevated mood interspersed with episodes of depression. While treatment developments and understanding the disruptive nature of this illness have focused on these episodes, it is also evident that some patients may have chronic week-to-week mood instability. This is also a major morbidity. The longitudinal pattern of this mood instability is poorly understood as it has, until recently, been difficult to quantify. We propose that understanding this mood variability is critical for the development of cognitive neuroscience-based treatments. In this study, we develop a time-series approach to capture mood variability in two groups of patients with bipolar disorder who appear on the basis of clinical judgement to show relatively stable or unstable illness courses. Using weekly mood scores based on a self-rated scale (quick inventory of depressive symptomatology—self-rated; QIDS-SR) from 23 patients over a 220-week period, we show that the observed mood variability is nonlinear and that the stable and unstable patient groups are described by different nonlinear time-series processes. We emphasize the necessity in combining both appropriate measures of the underlying deterministic processes (the QIDS-SR score) and noise (uncharacterized temporal variation) in understanding dynamical patterns of mood variability associated with bipolar disorder.

An approach to modelling and residual analysis of nonlinear autoregressive time series in exponential variables is presented; the approach is illustrated by analysis of a long series of wind velocity data which has first been detrended and then transformed into a stationary series with an exponential marginal distribution. The stationary series is modelled with a newly developed type of second order autoregressive process with random coefficients, called the NEAR(2) model; it has a second order autoregressive correlation structure but is nonlinear because its coefficients are random. The exponential distributional assumptions involved in this model highlight a very broad four parameter structure which combines five exponential random variables into a sixth exponential random variable; other applications of this structure are briefly considered. Dependency in the NEAR(2) process not accounted for by standard autocorrelations is explored by developing a residual analysis for time series having autoregressive correlation structure; this involves defining linear uncorrelated residuals which are dependent, and then assessing this higher order dependence by standard time series computations. Application of this residual analysis to the wind velocity data illustrates both the utility and difficulty of nonlinear time series modelling.

"NPS-55-90-10."