ARIMA-Based Time Series Model of Stochastic Wind Power Generation
DEFF Research Database (Denmark)
Chen, Peiyuan; Pedersen, Troels; Bak-Jensen, Birgitte;
2010-01-01
This paper proposes a stochastic wind power model based on an autoregressive integrated moving average (ARIMA) process. The model takes into account the nonstationarity and physical limits of stochastic wind power generation. The model is constructed based on wind power measurement of one year from...... the Nysted offshore wind farm in Denmark. The proposed limited-ARIMA (LARIMA) model introduces a limiter and characterizes the stochastic wind power generation by mean level, temporal correlation and driving noise. The model is validated against the measurement in terms of temporal correlation and...
Forecasting inflation in Montenegro using univariate time series models
Directory of Open Access Journals (Sweden)
Milena Lipovina-Božović
2015-04-01
Full Text Available The analysis of price trends and their prognosis is one of the key tasks of the economic authorities in each country. Due to the nature of the Montenegrin economy as small and open economy with euro as currency, forecasting inflation is very specific which is more difficult due to low quality of the data. This paper analyzes the utility and applicability of univariate time series models for forecasting price index in Montenegro. Data analysis of key macroeconomic movements in previous decades indicates the presence of many possible determinants that could influence forecasting result. This paper concludes that the forecasting models (ARIMA based only on its own previous values cannot adequately cover the key factors that determine the price level in the future, probably because of the existence of numerous external factors that influence the price movement in Montenegro.
DEFF Research Database (Denmark)
Moskowitz, Tobias J.; Ooi, Yao Hua; Heje Pedersen, Lasse
2012-01-01
We document significant “time series momentum” in equity index, currency, commodity, and bond futures for each of the 58 liquid instruments we consider. We find persistence in returns for one to 12 months that partially reverses over longer horizons, consistent with sentiment theories of initial...... under-reaction and delayed over-reaction. A diversified portfolio of time series momentum strategies across all asset classes delivers substantial abnormal returns with little exposure to standard asset pricing factors and performs best during extreme markets. Examining the trading activities...... of speculators and hedgers, we find that speculators profit from time series momentum at the expense of hedgers....
Loredo, Thomas
The key, central objectives of the proposed Time Series Explorer project are to develop an organized collection of software tools for analysis of time series data in current and future NASA astrophysics data archives, and to make the tools available in two ways: as a library (the Time Series Toolbox) that individual science users can use to write their own data analysis pipelines, and as an application (the Time Series Automaton) providing an accessible, data-ready interface to many Toolbox algorithms, facilitating rapid exploration and automatic processing of time series databases. A number of time series analysis methods will be implemented, including techniques that range from standard ones to state-of-the-art developments by the proposers and others. Most of the algorithms will be able to handle time series data subject to real-world problems such as data gaps, sampling that is otherwise irregular, asynchronous sampling (in multi-wavelength settings), and data with non-Gaussian measurement errors. The proposed research responds to the ADAP element supporting the development of tools for mining the vast reservoir of information residing in NASA databases. The tools that will be provided to the community of astronomers studying variability of astronomical objects (from nearby stars and extrasolar planets, through galactic and extragalactic sources) will revolutionize the quality of timing analyses that can be carried out, and greatly enhance the scientific throughput of all NASA astrophysics missions past, present, and future. The Automaton will let scientists explore time series - individual records or large data bases -- with the most informative and useful analysis methods available, without having to develop the tools themselves or understand the computational details. Both elements, the Toolbox and the Automaton, will enable deep but efficient exploratory time series data analysis, which is why we have named the project the Time Series Explorer. Science
Multivariate Time Series Search
National Aeronautics and Space Administration — Multivariate Time-Series (MTS) are ubiquitous, and are generated in areas as disparate as sensor recordings in aerospace systems, music and video streams, medical...
DEFF Research Database (Denmark)
Hisdal, H.; Holmqvist, E.; Hyvärinen, V.; Jónsson, P.; Kuusisto, E.; Larsen, S. E.; Lindström, G.; Ovesen, N. B.; Roald, L. A.
Awareness that emission of greenhouse gases will raise the global temperature and change the climate has led to studies trying to identify such changes in long-term climate and hydrologic time series. This report, written by the......Awareness that emission of greenhouse gases will raise the global temperature and change the climate has led to studies trying to identify such changes in long-term climate and hydrologic time series. This report, written by the...
DEFF Research Database (Denmark)
Fischer, Paul; Hilbert, Astrid
2012-01-01
We introduce a platform which supplies an easy-to-handle, interactive, extendable, and fast analysis tool for time series analysis. In contrast to other software suits like Maple, Matlab, or R, which use a command-line-like interface and where the user has to memorize/look-up the appropriate...... commands, our application is select-and-click-driven. It allows to derive many different sequences of deviations for a given time series and to visualize them in different ways in order to judge their expressive power and to reuse the procedure found. For many transformations or model-ts, the user may...... choose between manual and automated parameter selection. The user can dene new transformations and add them to the system. The application contains efficient implementations of advanced and recent techniques for time series analysis including techniques related to extreme value analysis and filtering...
Madsen, Henrik
2007-01-01
""In this book the author gives a detailed account of estimation, identification methodologies for univariate and multivariate stationary time-series models. The interesting aspect of this introductory book is that it contains several real data sets and the author made an effort to explain and motivate the methodology with real data. … this introductory book will be interesting and useful not only to undergraduate students in the UK universities but also to statisticians who are keen to learn time-series techniques and keen to apply them. I have no hesitation in recommending the book.""-Journa
Woodward, Wayne A; Elliott, Alan C
2011-01-01
""There is scarcely a standard technique that the reader will find left out … this book is highly recommended for those requiring a ready introduction to applicable methods in time series and serves as a useful resource for pedagogical purposes.""-International Statistical Review (2014), 82""Current time series theory for practice is well summarized in this book.""-Emmanuel Parzen, Texas A&M University""What an extraordinary range of topics covered, all very insightfully. I like [the authors'] innovations very much, such as the AR factor table.""-David Findley, U.S. Census Bureau (retired)""…
Liang, X San
2014-01-01
Given two time series, can one tell, in a rigorous and quantitative way, the cause and effect between them? Based on a recently rigorized physical notion namely information flow, we arrive at a concise formula and give this challenging question, which is of wide concern in different disciplines, a positive answer. Here causality is measured by the time rate of change of information flowing from one series, say, X2, to another, X1. The measure is asymmetric between the two parties and, particularly, if the process underlying X1 does not depend on X2, then the resulting causality from X2 to X1 vanishes. The formula is tight in form, involving only the commonly used statistics, sample covariances. It has been validated with touchstone series purportedly generated with one-way causality. It has also been applied to the investigation of real world problems; an example presented here is the cause-effect relation between two climate modes, El Ni\\~no and Indian Ocean Dipole, which have been linked to the hazards in f...
International Nuclear Information System (INIS)
Many human-related activities show power-law decaying interevent time distribution with exponents usually varying between 1 and 2. We study a simple task-queuing model, which produces bursty time series due to the non-trivial dynamics of the task list. The model is characterized by a priority distribution as an input parameter, which describes the choice procedure from the list. We give exact results on the asymptotic behaviour of the model and we show that the interevent time distribution is power-law decaying for any kind of input distributions that remain normalizable in the infinite list limit, with exponents tunable between 1 and 2. The model satisfies a scaling law between the exponents of interevent time distribution (β) and autocorrelation function (α): α + β = 2. This law is general for renewal processes with power-law decaying interevent time distribution. We conclude that slowly decaying autocorrelation function indicates long-range dependence only if the scaling law is violated. (paper)
GPS Position Time Series @ JPL
Owen, Susan; Moore, Angelyn; Kedar, Sharon; Liu, Zhen; Webb, Frank; Heflin, Mike; Desai, Shailen
2013-01-01
Different flavors of GPS time series analysis at JPL - Use same GPS Precise Point Positioning Analysis raw time series - Variations in time series analysis/post-processing driven by different users. center dot JPL Global Time Series/Velocities - researchers studying reference frame, combining with VLBI/SLR/DORIS center dot JPL/SOPAC Combined Time Series/Velocities - crustal deformation for tectonic, volcanic, ground water studies center dot ARIA Time Series/Coseismic Data Products - Hazard monitoring and response focused center dot ARIA data system designed to integrate GPS and InSAR - GPS tropospheric delay used for correcting InSAR - Caltech's GIANT time series analysis uses GPS to correct orbital errors in InSAR - Zhen Liu's talking tomorrow on InSAR Time Series analysis
Bootstrapping High Dimensional Time Series
Zhang, Xianyang; Cheng, Guang
2014-01-01
This article studies bootstrap inference for high dimensional weakly dependent time series in a general framework of approximately linear statistics. The following high dimensional applications are covered: (1) uniform confidence band for mean vector; (2) specification testing on the second order property of time series such as white noise testing and bandedness testing of covariance matrix; (3) specification testing on the spectral property of time series. In theory, we first derive a Gaussi...
Autoencoding Time Series for Visualisation
Gianniotis, Nikolaos; Kügler, Dennis; Tino, Peter; Polsterer, Kai; Misra, Ranjeev
2015-01-01
We present an algorithm for the visualisation of time series. To that end we employ echo state networks to convert time series into a suitable vector representation which is capable of capturing the latent dynamics of the time series. Subsequently, the obtained vector representations are put through an autoencoder and the visualisation is constructed using the activations of the bottleneck. The crux of the work lies with defining an objective function that quantifies the reconstruction error ...
Allan, Alasdair
2014-06-01
FROG performs time series analysis and display. It provides a simple user interface for astronomers wanting to do time-domain astrophysics but still offers the powerful features found in packages such as PERIOD (ascl:1406.005). FROG includes a number of tools for manipulation of time series. Among other things, the user can combine individual time series, detrend series (multiple methods) and perform basic arithmetic functions. The data can also be exported directly into the TOPCAT (ascl:1101.010) application for further manipulation if needed.
Advances in time series forecasting
Cagdas, Hakan Aladag
2012-01-01
Readers will learn how these methods work and how these approaches can be used to forecast real life time series. The hybrid forecasting model is also explained. Data presented in this e-book is problem based and is taken from real life situations. It is a valuable resource for students, statisticians and working professionals interested in advanced time series analysis.
Models for dependent time series
Tunnicliffe Wilson, Granville; Haywood, John
2015-01-01
Models for Dependent Time Series addresses the issues that arise and the methodology that can be applied when the dependence between time series is described and modeled. Whether you work in the economic, physical, or life sciences, the book shows you how to draw meaningful, applicable, and statistically valid conclusions from multivariate (or vector) time series data.The first four chapters discuss the two main pillars of the subject that have been developed over the last 60 years: vector autoregressive modeling and multivariate spectral analysis. These chapters provide the foundational mater
Autoencoding Time Series for Visualisation
Gianniotis, Nikolaos; Tino, Peter; Polsterer, Kai; Misra, Ranjeev
2015-01-01
We present an algorithm for the visualisation of time series. To that end we employ echo state networks to convert time series into a suitable vector representation which is capable of capturing the latent dynamics of the time series. Subsequently, the obtained vector representations are put through an autoencoder and the visualisation is constructed using the activations of the bottleneck. The crux of the work lies with defining an objective function that quantifies the reconstruction error of these representations in a principled manner. We demonstrate the method on synthetic and real data.
Time Series with Tailored Nonlinearities
Raeth, C
2015-01-01
It is demonstrated how to generate time series with tailored nonlinearities by inducing well- defined constraints on the Fourier phases. Correlations between the phase information of adjacent phases and (static and dynamic) measures of nonlinearities are established and their origin is explained. By applying a set of simple constraints on the phases of an originally linear and uncor- related Gaussian time series, the observed scaling behavior of the intensity distribution of empirical time series can be reproduced. The power law character of the intensity distributions being typical for e.g. turbulence and financial data can thus be explained in terms of phase correlations.
Multivariate Time Series Similarity Searching
Jimin Wang; Yuelong Zhu; Shijin Li; Dingsheng Wan; Pengcheng Zhang
2014-01-01
Multivariate time series (MTS) datasets are very common in various financial, multimedia, and hydrological fields. In this paper, a dimension-combination method is proposed to search similar sequences for MTS. Firstly, the similarity of single-dimension series is calculated; then the overall similarity of the MTS is obtained by synthesizing each of the single-dimension similarity based on weighted BORDA voting method. The dimension-combination method could use the existing similarity searchin...
Random time series in astronomy.
Vaughan, Simon
2013-02-13
Progress in astronomy comes from interpreting the signals encoded in the light received from distant objects: the distribution of light over the sky (images), over photon wavelength (spectrum), over polarization angle and over time (usually called light curves by astronomers). In the time domain, we see transient events such as supernovae, gamma-ray bursts and other powerful explosions; we see periodic phenomena such as the orbits of planets around nearby stars, radio pulsars and pulsations of stars in nearby galaxies; and we see persistent aperiodic variations ('noise') from powerful systems such as accreting black holes. I review just a few of the recent and future challenges in the burgeoning area of time domain astrophysics, with particular attention to persistently variable sources, the recovery of reliable noise power spectra from sparsely sampled time series, higher order properties of accreting black holes, and time delays and correlations in multi-variate time series. PMID:23277606
Stochastic Time-Series Spectroscopy
Scoville, John
2015-01-01
Spectroscopically measuring low levels of non-equilibrium phenomena (e.g. emission in the presence of a large thermal background) can be problematic due to an unfavorable signal-to-noise ratio. An approach is presented to use time-series spectroscopy to separate non-equilibrium quantities from slowly varying equilibria. A stochastic process associated with the non-equilibrium part of the spectrum is characterized in terms of its central moments or cumulants, which may vary over time. This parameterization encodes information about the non-equilibrium behavior of the system. Stochastic time-series spectroscopy (STSS) can be implemented at very little expense in many settings since a series of scans are typically recorded in order to generate a low-noise averaged spectrum. Higher moments or cumulants may be readily calculated from this series, enabling the observation of quantities that would be difficult or impossible to determine from an average spectrum or from prinicipal components analysis (PCA). This meth...
ACCURATE TIME SERIES CLASSIFICATION USING SHAPELETS
M. Arathi; A. GOVARDHAN
2014-01-01
Time series data are sequences of values measured o ver time. One of the most recent approaches to classification of time series data is to find shape lets within a data set. Time series shapelets are time series subsequences which represent a class. In order to compare two time series sequences, existing work use s Euclidean distance measure. The problem with Euclid ean distance is that it requires data to be standardized if scales ...
Nonlinear time series analysis methods and applications
Diks, Cees
1999-01-01
Methods of nonlinear time series analysis are discussed from a dynamical systems perspective on the one hand, and from a statistical perspective on the other. After giving an informal overview of the theory of dynamical systems relevant to the analysis of deterministic time series, time series generated by nonlinear stochastic systems and spatio-temporal dynamical systems are considered. Several statistical methods for the analysis of nonlinear time series are presented and illustrated with applications to physical and physiological time series.
Trend prediction of chaotic time series
Institute of Scientific and Technical Information of China (English)
Li Aiguo; Zhao Cai; Li Zhanhuai
2007-01-01
To predict the trend of chaotic time series in time series analysis and time series data mining fields, a novel predicting algorithm of chaotic time series trend is presented, and an on-line segmenting algorithm is proposed to convert a time series into a binary string according to ascending or descending trend of each subsequence. The on-line segmenting algorithm is independent of the prior knowledge about time series. The naive Bayesian algorithm is then employed to predict the trend of chaotic time series according to the binary string. The experimental results of three chaotic time series demonstrate that the proposed method predicts the ascending or descending trend of chaotic time series with few error.
A Course in Time Series Analysis
Peña, Daniel; Tsay, Ruey S
2011-01-01
New statistical methods and future directions of research in time series A Course in Time Series Analysis demonstrates how to build time series models for univariate and multivariate time series data. It brings together material previously available only in the professional literature and presents a unified view of the most advanced procedures available for time series model building. The authors begin with basic concepts in univariate time series, providing an up-to-date presentation of ARIMA models, including the Kalman filter, outlier analysis, automatic methods for building ARIMA models, a
Effective Feature Preprocessing for Time Series Forecasting
DEFF Research Database (Denmark)
Zhao, Junhua; Dong, Zhaoyang; Xu, Zhao
2006-01-01
Time series forecasting is an important area in data mining research. Feature preprocessing techniques have significant influence on forecasting accuracy, therefore are essential in a forecasting model. Although several feature preprocessing techniques have been applied in time series forecasting...
Effective Feature Preprocessing for Time Series Forecasting
DEFF Research Database (Denmark)
Zhao, Junhua; Dong, Zhaoyang; Xu, Zhao
Time series forecasting is an important area in data mining research. Feature preprocessing techniques have significant influence on forecasting accuracy, therefore are essential in a forecasting model. Although several feature preprocessing techniques have been applied in time series forecasting...
Time Series Analysis and Forecasting by Example
Bisgaard, Soren
2011-01-01
An intuition-based approach enables you to master time series analysis with ease Time Series Analysis and Forecasting by Example provides the fundamental techniques in time series analysis using various examples. By introducing necessary theory through examples that showcase the discussed topics, the authors successfully help readers develop an intuitive understanding of seemingly complicated time series models and their implications. The book presents methodologies for time series analysis in a simplified, example-based approach. Using graphics, the authors discuss each presented example in
A review of subsequence time series clustering.
Zolhavarieh, Seyedjamal; Aghabozorgi, Saeed; Teh, Ying Wah
2014-01-01
Clustering of subsequence time series remains an open issue in time series clustering. Subsequence time series clustering is used in different fields, such as e-commerce, outlier detection, speech recognition, biological systems, DNA recognition, and text mining. One of the useful fields in the domain of subsequence time series clustering is pattern recognition. To improve this field, a sequence of time series data is used. This paper reviews some definitions and backgrounds related to subsequence time series clustering. The categorization of the literature reviews is divided into three groups: preproof, interproof, and postproof period. Moreover, various state-of-the-art approaches in performing subsequence time series clustering are discussed under each of the following categories. The strengths and weaknesses of the employed methods are evaluated as potential issues for future studies. PMID:25140332
Data mining in time series databases
Kandel, Abraham; Bunke, Horst
2004-01-01
Adding the time dimension to real-world databases produces Time SeriesDatabases (TSDB) and introduces new aspects and difficulties to datamining and knowledge discovery. This book covers the state-of-the-artmethodology for mining time series databases. The novel data miningmethods presented in the book include techniques for efficientsegmentation, indexing, and classification of noisy and dynamic timeseries. A graph-based method for anomaly detection in time series isdescribed and the book also studies the implications of a novel andpotentially useful representation of time series as strings. Theproblem of detecting changes in data mining models that are inducedfrom temporal databases is additionally discussed.
International Work-Conference on Time Series
Pomares, Héctor
2016-01-01
This volume presents selected peer-reviewed contributions from The International Work-Conference on Time Series, ITISE 2015, held in Granada, Spain, July 1-3, 2015. It discusses topics in time series analysis and forecasting, advanced methods and online learning in time series, high-dimensional and complex/big data time series as well as forecasting in real problems. The International Work-Conferences on Time Series (ITISE) provide a forum for scientists, engineers, educators and students to discuss the latest ideas and implementations in the foundations, theory, models and applications in the field of time series analysis and forecasting. It focuses on interdisciplinary and multidisciplinary research encompassing the disciplines of computer science, mathematics, statistics and econometrics.
Coupling between time series: a network view
Mehraban, Saeed; Zamani, Maryam; Jafari, Gholamreza
2013-01-01
Recently, the visibility graph has been introduced as a novel view for analyzing time series, which maps it to a complex network. In this paper, we introduce new algorithm of visibility, "cross-visibility", which reveals the conjugation of two coupled time series. The correspondence between the two time series is mapped to a network, "the cross-visibility graph", to demonstrate the correlation between them. We applied the algorithm to several correlated and uncorrelated time series, generated by the linear stationary ARFIMA process. The results demonstrate that the cross-visibility graph associated with correlated time series with power-law auto-correlation is scale-free. If the time series are uncorrelated, the degree distribution of their cross-visibility network deviates from power-law. For more clarifying the process, we applied the algorithm to real-world data from the financial trades of two companies, and observed significant small-scale coupling in their dynamics.
Random time series in Astronomy
Vaughan, Simon
2013-01-01
Progress in astronomy comes from interpreting the signals encoded in the light received from distant objects: the distribution of light over the sky (images), over photon wavelength (spectrum), over polarization angle, and over time (usually called light curves by astronomers). In the time domain we see transient events such as supernovae, gamma-ray bursts, and other powerful explosions; we see periodic phenomena such as the orbits of planets around nearby stars, radio pulsars, and pulsations...
Hurst Exponent Analysis of Financial Time Series
Institute of Scientific and Technical Information of China (English)
无
2001-01-01
Statistical properties of stock market time series and the implication of their Hurst exponents are discussed. Hurst exponents of DJ1A (Dow Jones Industrial Average) components are tested using re-scaled range analysis. In addition to the original stock return series, the linear prediction errors of the daily returns are also tested. Numerical results show that the Hurst exponent analysis can provide some information about the statistical properties of the financial time series.
The Foundations of Modern Time Series Analysis
Mills, Professor Terence C
2011-01-01
This book develops the analysis of Time Series from its formal beginnings in the 1890s through to the publication of Box and Jenkins' watershed publication in 1970, showing how these methods laid the foundations for the modern techniques of Time Series analysis that are in use today.
Lag space estimation in time series modelling
DEFF Research Database (Denmark)
Goutte, Cyril
1997-01-01
The purpose of this article is to investigate some techniques for finding the relevant lag-space, i.e. input information, for time series modelling. This is an important aspect of time series modelling, as it conditions the design of the model through the regressor vector a.k.a. the input layer...
Network structure of multivariate time series
Lacasa, Lucas; Nicosia, Vincenzo; Latora, Vito
2015-10-01
Our understanding of a variety of phenomena in physics, biology and economics crucially depends on the analysis of multivariate time series. While a wide range tools and techniques for time series analysis already exist, the increasing availability of massive data structures calls for new approaches for multidimensional signal processing. We present here a non-parametric method to analyse multivariate time series, based on the mapping of a multidimensional time series into a multilayer network, which allows to extract information on a high dimensional dynamical system through the analysis of the structure of the associated multiplex network. The method is simple to implement, general, scalable, does not require ad hoc phase space partitioning, and is thus suitable for the analysis of large, heterogeneous and non-stationary time series. We show that simple structural descriptors of the associated multiplex networks allow to extract and quantify nontrivial properties of coupled chaotic maps, including the transition between different dynamical phases and the onset of various types of synchronization. As a concrete example we then study financial time series, showing that a multiplex network analysis can efficiently discriminate crises from periods of financial stability, where standard methods based on time-series symbolization often fail.
Homogenising time series: beliefs, dogmas and facts
Domonkos, P.
2011-06-01
In the recent decades various homogenisation methods have been developed, but the real effects of their application on time series are still not known sufficiently. The ongoing COST action HOME (COST ES0601) is devoted to reveal the real impacts of homogenisation methods more detailed and with higher confidence than earlier. As a part of the COST activity, a benchmark dataset was built whose characteristics approach well the characteristics of real networks of observed time series. This dataset offers much better opportunity than ever before to test the wide variety of homogenisation methods, and analyse the real effects of selected theoretical recommendations. Empirical results show that real observed time series usually include several inhomogeneities of different sizes. Small inhomogeneities often have similar statistical characteristics than natural changes caused by climatic variability, thus the pure application of the classic theory that change-points of observed time series can be found and corrected one-by-one is impossible. However, after homogenisation the linear trends, seasonal changes and long-term fluctuations of time series are usually much closer to the reality than in raw time series. Some problems around detecting multiple structures of inhomogeneities, as well as that of time series comparisons within homogenisation procedures are discussed briefly in the study.
Testing Mean Stability of Heteroskedastic Time Series
Violetta Dalla; Liudas Giraitis; Phillips, Peter C. B.
2015-01-01
Time series models are often fitted to the data without preliminary checks for stability of the mean and variance, conditions that may not hold in much economic and financial data, particularly over long periods. Ignoring such shifts may result in fitting models with spurious dynamics that lead to unsupported and controversial conclusions about time dependence, causality, and the effects of unanticipated shocks. In spite of what may seem as obvious differences between a time series of indepen...
Testing mean stability of heteroskedastic time series
Dalla, Violetta; Giraitis, Liudas; Phillips, Peter C. B.
2015-01-01
Time series models are often fitted to the data without preliminary checks for stability of the mean and variance, conditions that may not hold in much economic and financial data, particularly over long periods. Ignoring such shifts may result in fitting models with spurious dynamics that lead to unsupported and controversial conclusions about time dependence, causality, and the effects of unanticipated shocks. In spite of what may seem as obvious differences between a time series of indepen...
Time Series Analysis Using Composite Multiscale Entropy
Kung-Yen Lee; Chun-Chieh Wang; Shiou-Gwo Lin; Chiu-Wen Wu; Shuen-De Wu
2013-01-01
Multiscale entropy (MSE) was recently developed to evaluate the complexity of time series over different time scales. Although the MSE algorithm has been successfully applied in a number of different fields, it encounters a problem in that the statistical reliability of the sample entropy (SampEn) of a coarse-grained series is reduced as a time scale factor is increased. Therefore, in this paper, the concept of a composite multiscale entropy (CMSE) is introduced to overcome this difficulty. S...
Time series modeling, computation, and inference
Prado, Raquel
2010-01-01
The authors systematically develop a state-of-the-art analysis and modeling of time series. … this book is well organized and well written. The authors present various statistical models for engineers to solve problems in time series analysis. Readers no doubt will learn state-of-the-art techniques from this book.-Hsun-Hsien Chang, Computing Reviews, March 2012My favorite chapters were on dynamic linear models and vector AR and vector ARMA models.-William Seaver, Technometrics, August 2011… a very modern entry to the field of time-series modelling, with a rich reference list of the current lit
Time Series Analysis Forecasting and Control
Box, George E P; Reinsel, Gregory C
2011-01-01
A modernized new edition of one of the most trusted books on time series analysis. Since publication of the first edition in 1970, Time Series Analysis has served as one of the most influential and prominent works on the subject. This new edition maintains its balanced presentation of the tools for modeling and analyzing time series and also introduces the latest developments that have occurred n the field over the past decade through applications from areas such as business, finance, and engineering. The Fourth Edition provides a clearly written exploration of the key methods for building, cl
Visibility Graph Based Time Series Analysis.
Directory of Open Access Journals (Sweden)
Mutua Stephen
Full Text Available Network based time series analysis has made considerable achievements in the recent years. By mapping mono/multivariate time series into networks, one can investigate both it's microscopic and macroscopic behaviors. However, most proposed approaches lead to the construction of static networks consequently providing limited information on evolutionary behaviors. In the present paper we propose a method called visibility graph based time series analysis, in which series segments are mapped to visibility graphs as being descriptions of the corresponding states and the successively occurring states are linked. This procedure converts a time series to a temporal network and at the same time a network of networks. Findings from empirical records for stock markets in USA (S&P500 and Nasdaq and artificial series generated by means of fractional Gaussian motions show that the method can provide us rich information benefiting short-term and long-term predictions. Theoretically, we propose a method to investigate time series from the viewpoint of network of networks.
Forecasting Daily Time Series using Periodic Unobserved Components Time Series Models
Koopman, Siem Jan; Ooms, Marius
2004-01-01
We explore a periodic analysis in the context of unobserved components time series models that decompose time series into components of interest such as trend and seasonal. Periodic time series models allow dynamic characteristics to depend on the period of the year, month, week or day. In the stand
Measuring nonlinear behavior in time series data
Wai, Phoong Seuk; Ismail, Mohd Tahir
2014-12-01
Stationary Test is an important test in detect the time series behavior since financial and economic data series always have missing data, structural change as well as jumps or breaks in the data set. Moreover, stationary test is able to transform the nonlinear time series variable to become stationary by taking difference-stationary process or trend-stationary process. Two different types of hypothesis testing of stationary tests that are Augmented Dickey-Fuller (ADF) test and Kwiatkowski-Philips-Schmidt-Shin (KPSS) test are examine in this paper to describe the properties of the time series variables in financial model. Besides, Least Square method is used in Augmented Dickey-Fuller test to detect the changes of the series and Lagrange multiplier is used in Kwiatkowski-Philips-Schmidt-Shin test to examine the properties of oil price, gold price and Malaysia stock market. Moreover, Quandt-Andrews, Bai-Perron and Chow tests are also use to detect the existence of break in the data series. The monthly index data are ranging from December 1989 until May 2012. Result is shown that these three series exhibit nonlinear properties but are able to transform to stationary series after taking first difference process.
Complex network approach to fractional time series
International Nuclear Information System (INIS)
In order to extract correlation information inherited in stochastic time series, the visibility graph algorithm has been recently proposed, by which a time series can be mapped onto a complex network. We demonstrate that the visibility algorithm is not an appropriate one to study the correlation aspects of a time series. We then employ the horizontal visibility algorithm, as a much simpler one, to map fractional processes onto complex networks. The degree distributions are shown to have parabolic exponential forms with Hurst dependent fitting parameter. Further, we take into account other topological properties such as maximum eigenvalue of the adjacency matrix and the degree assortativity, and show that such topological quantities can also be used to predict the Hurst exponent, with an exception for anti-persistent fractional Gaussian noises. To solve this problem, we take into account the Spearman correlation coefficient between nodes' degrees and their corresponding data values in the original time series
Advanced spectral methods for climatic time series
Ghil, M.; Allen, M.R.; Dettinger, M.D.; Ide, K.; Kondrashov, D.; Mann, M.E.; Robertson, A.W.; Saunders, A.; Tian, Y.; Varadi, F.; Yiou, P.
2002-01-01
The analysis of univariate or multivariate time series provides crucial information to describe, understand, and predict climatic variability. The discovery and implementation of a number of novel methods for extracting useful information from time series has recently revitalized this classical field of study. Considerable progress has also been made in interpreting the information so obtained in terms of dynamical systems theory. In this review we describe the connections between time series analysis and nonlinear dynamics, discuss signal- to-noise enhancement, and present some of the novel methods for spectral analysis. The various steps, as well as the advantages and disadvantages of these methods, are illustrated by their application to an important climatic time series, the Southern Oscillation Index. This index captures major features of interannual climate variability and is used extensively in its prediction. Regional and global sea surface temperature data sets are used to illustrate multivariate spectral methods. Open questions and further prospects conclude the review.
Complex network approach to fractional time series
Manshour, Pouya
2015-10-01
In order to extract correlation information inherited in stochastic time series, the visibility graph algorithm has been recently proposed, by which a time series can be mapped onto a complex network. We demonstrate that the visibility algorithm is not an appropriate one to study the correlation aspects of a time series. We then employ the horizontal visibility algorithm, as a much simpler one, to map fractional processes onto complex networks. The degree distributions are shown to have parabolic exponential forms with Hurst dependent fitting parameter. Further, we take into account other topological properties such as maximum eigenvalue of the adjacency matrix and the degree assortativity, and show that such topological quantities can also be used to predict the Hurst exponent, with an exception for anti-persistent fractional Gaussian noises. To solve this problem, we take into account the Spearman correlation coefficient between nodes' degrees and their corresponding data values in the original time series.
Applied time series analysis and innovative computing
Ao, Sio-Iong
2010-01-01
This text is a systematic, state-of-the-art introduction to the use of innovative computing paradigms as an investigative tool for applications in time series analysis. It includes frontier case studies based on recent research.
Detecting nonlinear structure in time series
International Nuclear Information System (INIS)
We describe an approach for evaluating the statistical significance of evidence for nonlinearity in a time series. The formal application of our method requires the careful statement of a null hypothesis which characterizes a candidate linear process, the generation of an ensemble of ''surrogate'' data sets which are similar to the original time series but consistent with the null hypothesis, and the computation of a discriminating statistic for the original and for each of the surrogate data sets. The idea is to test the original time series against the null hypothesis by checking whether the discriminating statistic computed for the original time series differs significantly from the statistics computed for each of the surrogate sets. While some data sets very cleanly exhibit low-dimensional chaos, there are many cases where the evidence is sketchy and difficult to evaluate. We hope to provide a framework within which such claims of nonlinearity can be evaluated. 5 refs., 4 figs
Bayes linear variance adjustment for time series
Wilkinson, Darren J
2008-01-01
This paper exhibits quadratic products of linear combinations of observables which identify the covariance structure underlying the univariate locally linear time series dynamic linear model. The first- and second-order moments for the joint distribution over these observables are given, allowing Bayes linear learning for the underlying covariance structure for the time series model. An example is given which illustrates the methodology and highlights the practical implications of the theory.
FATS: Feature Analysis for Time Series
Nun, Isadora; Sim, Brandon; Zhu, Ming; Dave, Rahul; Castro, Nicolas; Pichara, Karim
2015-01-01
In this paper, we present the FATS (Feature Analysis for Time Series) library. FATS is a Python library which facilitates and standardizes feature extraction for time series data. In particular, we focus on one application: feature extraction for astronomical light curve data, although the library is generalizable for other uses. We detail the methods and features implemented for light curve analysis, and present examples for its usage.
Combination prediction method of chaotic time series
Institute of Scientific and Technical Information of China (English)
ZHAO DongHua; RUAN Jiong; CAI ZhiJie
2007-01-01
In the present paper, we propose an approach of combination prediction of chaotic time series. The method is based on the adding-weight one-rank local-region method of chaotic time series. The method allows us to define an interval containing a future value with a given probability, which is obtained by studying the prediction error distribution. Its effectiveness is shown with data generated by Logistic map.
Nonlinear time series: semiparametric and nonparametric methods
Gao, Jiti
2007-01-01
Useful in the theoretical and empirical analysis of nonlinear time series data, semiparametric methods have received extensive attention in the economics and statistics communities over the past twenty years. Recent studies show that semiparametric methods and models may be applied to solve dimensionality reduction problems arising from using fully nonparametric models and methods. Answering the call for an up-to-date overview of the latest developments in the field, "Nonlinear Time Series: S...
Introduction to time series analysis and forecasting
Montgomery, Douglas C; Kulahci, Murat
2008-01-01
An accessible introduction to the most current thinking in and practicality of forecasting techniques in the context of time-oriented data. Analyzing time-oriented data and forecasting are among the most important problems that analysts face across many fields, ranging from finance and economics to production operations and the natural sciences. As a result, there is a widespread need for large groups of people in a variety of fields to understand the basic concepts of time series analysis and forecasting. Introduction to Time Series Analysis and Forecasting presents the time series analysis branch of applied statistics as the underlying methodology for developing practical forecasts, and it also bridges the gap between theory and practice by equipping readers with the tools needed to analyze time-oriented data and construct useful, short- to medium-term, statistically based forecasts.
Time series irreversibility: a visibility graph approach
Lacasa, Lucas; Roldán, Édgar; Parrondo, Juan M R; Luque, Bartolo
2011-01-01
We propose a method to measure real-valued time series irreversibility which combines two differ- ent tools: the horizontal visibility algorithm and the Kullback-Leibler divergence. This method maps a time series to a directed network according to a geometric criterion. The degree of irreversibility of the series is then estimated by the Kullback-Leibler divergence (i.e. the distinguishability) between the in and out degree distributions of the associated graph. The method is computationally effi- cient, does not require any ad hoc symbolization process, and naturally takes into account multiple scales. We find that the method correctly distinguishes between reversible and irreversible station- ary time series, including analytical and numerical studies of its performance for: (i) reversible stochastic processes (uncorrelated and Gaussian linearly correlated), (ii) irreversible stochastic pro- cesses (a discrete flashing ratchet in an asymmetric potential), (iii) reversible (conservative) and irreversible (di...
Multiscale entropy analysis of electroseismic time series
L. Guzmán-Vargas; Ramírez-Rojas, A.; Angulo-Brown, F.
2008-01-01
In this work we use the multiscale entropy method to analyse the variability of geo-electric time series monitored in two sites located in Mexico. In our analysis we consider a period of time from January 1995 to December 1995. We systematically calculate the sample entropy of electroseismic time series. Important differences in the entropy profile for several time scales are observed in records from the same station. In particular, a complex behaviour is observed in the vicinity of a
Time Series Forecasting with Missing Values
Directory of Open Access Journals (Sweden)
Shin-Fu Wu
2015-11-01
Full Text Available Time series prediction has become more popular in various kinds of applications such as weather prediction, control engineering, financial analysis, industrial monitoring, etc. To deal with real-world problems, we are often faced with missing values in the data due to sensor malfunctions or human errors. Traditionally, the missing values are simply omitted or replaced by means of imputation methods. However, omitting those missing values may cause temporal discontinuity. Imputation methods, on the other hand, may alter the original time series. In this study, we propose a novel forecasting method based on least squares support vector machine (LSSVM. We employ the input patterns with the temporal information which is defined as local time index (LTI. Time series data as well as local time indexes are fed to LSSVM for doing forecasting without imputation. We compare the forecasting performance of our method with other imputation methods. Experimental results show that the proposed method is promising and is worth further investigations.
Testing time symmetry in time series using data compression dictionaries
Kennel, Matthew B.
2004-01-01
Time symmetry, often called statistical time reversibility, in a dynamical process means that any segment of time-series output has the same probability of occurrence in the process as its time reversal. A technique, based on symbolic dynamics, is proposed to distinguish such symmetrical processes from asymmetrical ones, given a time-series observation of the otherwise unknown process. Because linear stochastic Gaussian processes, and static nonlinear transformations of them, are statisticall...
Feature Matching in Time Series Modelling
Xia, Yingcun
2011-01-01
Using a time series model to mimic an observed time series has a long history. However, with regard to this objective, conventional estimation methods for discrete-time dynamical models are frequently found to be wanting. In the absence of a true model, we prefer an alternative approach to conventional model fitting that typically involves one-step-ahead prediction errors. Our primary aim is to match the joint probability distribution of the observable time series, including long-term features of the dynamics that underpin the data, such as cycles, long memory and others, rather than short-term prediction. For want of a better name, we call this specific aim {\\it feature matching}. The challenges of model mis-specification, measurement errors and the scarcity of data are forever present in real time series modelling. In this paper, by synthesizing earlier attempts into an extended-likelihood, we develop a systematic approach to empirical time series analysis to address these challenges and to aim at achieving...
Introduction to time series analysis and forecasting
Montgomery, Douglas C; Kulahci, Murat
2015-01-01
Praise for the First Edition ""…[t]he book is great for readers who need to apply the methods and models presented but have little background in mathematics and statistics."" -MAA Reviews Thoroughly updated throughout, Introduction to Time Series Analysis and Forecasting, Second Edition presents the underlying theories of time series analysis that are needed to analyze time-oriented data and construct real-world short- to medium-term statistical forecasts. Authored by highly-experienced academics and professionals in engineering statistics, the Second Edition features discussions on both
Building Chaotic Model From Incomplete Time Series
Siek, Michael; Solomatine, Dimitri
2010-05-01
This paper presents a number of novel techniques for building a predictive chaotic model from incomplete time series. A predictive chaotic model is built by reconstructing the time-delayed phase space from observed time series and the prediction is made by a global model or adaptive local models based on the dynamical neighbors found in the reconstructed phase space. In general, the building of any data-driven models depends on the completeness and quality of the data itself. However, the completeness of the data availability can not always be guaranteed since the measurement or data transmission is intermittently not working properly due to some reasons. We propose two main solutions dealing with incomplete time series: using imputing and non-imputing methods. For imputing methods, we utilized the interpolation methods (weighted sum of linear interpolations, Bayesian principle component analysis and cubic spline interpolation) and predictive models (neural network, kernel machine, chaotic model) for estimating the missing values. After imputing the missing values, the phase space reconstruction and chaotic model prediction are executed as a standard procedure. For non-imputing methods, we reconstructed the time-delayed phase space from observed time series with missing values. This reconstruction results in non-continuous trajectories. However, the local model prediction can still be made from the other dynamical neighbors reconstructed from non-missing values. We implemented and tested these methods to construct a chaotic model for predicting storm surges at Hoek van Holland as the entrance of Rotterdam Port. The hourly surge time series is available for duration of 1990-1996. For measuring the performance of the proposed methods, a synthetic time series with missing values generated by a particular random variable to the original (complete) time series is utilized. There exist two main performance measures used in this work: (1) error measures between the actual
Fractal and natural time analysis of geoelectrical time series
Ramirez Rojas, A.; Moreno-Torres, L. R.; Cervantes, F.
2013-05-01
In this work we show the analysis of geoelectric time series linked with two earthquakes of M=6.6 and M=7.4. That time series were monitored at the South Pacific Mexican coast, which is the most important active seismic subduction zone in México. The geolectric time series were analyzed by using two complementary methods: a fractal analysis, by means of the detrended fluctuation analysis (DFA) in the conventional time, and the power spectrum defined in natural time domain (NTD). In conventional time we found long-range correlations prior to the EQ-occurrences and simultaneously in NTD, the behavior of the power spectrum suggest the possible existence of seismo electric signals (SES) similar with the previously reported in equivalent time series monitored in Greece prior to earthquakes of relevant magnitude.
Layered Ensemble Architecture for Time Series Forecasting.
Rahman, Md Mustafizur; Islam, Md Monirul; Murase, Kazuyuki; Yao, Xin
2016-01-01
Time series forecasting (TSF) has been widely used in many application areas such as science, engineering, and finance. The phenomena generating time series are usually unknown and information available for forecasting is only limited to the past values of the series. It is, therefore, necessary to use an appropriate number of past values, termed lag, for forecasting. This paper proposes a layered ensemble architecture (LEA) for TSF problems. Our LEA consists of two layers, each of which uses an ensemble of multilayer perceptron (MLP) networks. While the first ensemble layer tries to find an appropriate lag, the second ensemble layer employs the obtained lag for forecasting. Unlike most previous work on TSF, the proposed architecture considers both accuracy and diversity of the individual networks in constructing an ensemble. LEA trains different networks in the ensemble by using different training sets with an aim of maintaining diversity among the networks. However, it uses the appropriate lag and combines the best trained networks to construct the ensemble. This indicates LEAs emphasis on accuracy of the networks. The proposed architecture has been tested extensively on time series data of neural network (NN)3 and NN5 competitions. It has also been tested on several standard benchmark time series data. In terms of forecasting accuracy, our experimental results have revealed clearly that LEA is better than other ensemble and nonensemble methods. PMID:25751882
Climate Time Series Analysis and Forecasting
Young, P. C.; Fildes, R.
2009-04-01
This paper will discuss various aspects of climate time series data analysis, modelling and forecasting being carried out at Lancaster. This will include state-dependent parameter, nonlinear, stochastic modelling of globally averaged atmospheric carbon dioxide; the computation of emission strategies based on modern control theory; and extrapolative time series benchmark forecasts of annual average temperature, both global and local. The key to the forecasting evaluation will be the iterative estimation of forecast error based on rolling origin comparisons, as recommended in the forecasting research literature. The presentation will conclude with with a comparison of the time series forecasts with forecasts produced from global circulation models and a discussion of the implications for climate modelling research.
CALENDAR EFFECTS IN MONTHLY TIME SERIES MODELS
Institute of Scientific and Technical Information of China (English)
Gerhard THURY; Mi ZHOU
2005-01-01
It is not unusual for the level of a monthly economic time series, such as industrial production,retail and wholesale sales, monetary aggregates, telephone calls or road accidents, to be influenced by calendar effects. Such effects arise when changes occur in the level of activity resulting from differences in the composition of calendar between years. The two main sources of calendar effects are trading day variations and moving festivals. Ignoring such calendar effects will lead to substantial distortions in the identification stage of time series modeling. Therefore, it is mandatory to introduce calendar effects, when they are present in a time series, as the component of the model which one wants to estimate.
Fuzzy Information Granules in Time Series Data
HEIKO HOFER; ORTOLANI M; DAVID PATTERSON; FRANK HOEPPNER; ONDINE CALLAN; Berthold, Michael R
2004-01-01
Often, it is desirable to represent a set of time series through typical shapes in order to detect common patterns. The algorithm presented here compares pieces of a different time series in order to find such similar shapes. The use of a fuzzy clustering technique based on fuzzy c-means allows us to detect shapes that belong to a certain group of typical shapes with a degree of membership. Modifications to the original algorithm also allow this matching to be invariant with respect to a scal...
Case study in time series analysis
Zhongjie, Xie
1993-01-01
This book is a monograph on case studies using time series analysis, which includes the main research works applied to practical projects by the author in the past 15 years. The works cover different problems in broad fields, such as: engineering, labour protection, astronomy, physiology, endocrinology, oil development, etc. The first part of this book introduces some basic knowledge of time series analysis which is necessary for the reader to understand the methods and the theory used in the procedure for solving problems. The second part is the main part of this book - case studies in differ
Improving the prediction of chaotic time series
Institute of Scientific and Technical Information of China (English)
李克平; 高自友; 陈天仑
2003-01-01
One of the features of deterministic chaos is sensitive to initial conditions. This feature limits the prediction horizons of many chaotic systems. In this paper, we propose a new prediction technique for chaotic time series. In our method, some neighbouring points of the predicted point, for which the corresponding local Lyapunov exponent is particularly large, would be discarded during estimating the local dynamics, and thus the error accumulated by the prediction algorithm is reduced. The model is tested for the convection amplitude of Lorenz systems. The simulation results indicate that the prediction technique can improve the prediction of chaotic time series.
Lecture notes for Advanced Time Series Analysis
DEFF Research Database (Denmark)
Madsen, Henrik; Holst, Jan
1997-01-01
A first version of this notes was used at the lectures in Grenoble, and they are now extended and improved (together with Jan Holst), and used in Ph.D. courses on Advanced Time Series Analysis at IMM and at the Department of Mathematical Statistics, University of Lund, 1994, 1997, ......A first version of this notes was used at the lectures in Grenoble, and they are now extended and improved (together with Jan Holst), and used in Ph.D. courses on Advanced Time Series Analysis at IMM and at the Department of Mathematical Statistics, University of Lund, 1994, 1997, ...
Dynamical networks reconstructed from time series
Levnajić, Zoran
2012-01-01
Novel method of reconstructing dynamical networks from empirically measured time series is proposed. By statistically examining the correlations between motions displayed by network nodes, we derive a simple equation that directly yields the adjacency matrix, assuming the intra-network interaction functions to be known. We illustrate the method's implementation on a simple example and discuss the dependence of the reconstruction precision on the properties of time series. Our method is applicable to any network, allowing for reconstruction precision to be maximized, and errors to be estimated.
Introduction to time series and forecasting
Brockwell, Peter J
2016-01-01
This book is aimed at the reader who wishes to gain a working knowledge of time series and forecasting methods as applied to economics, engineering and the natural and social sciences. It assumes knowledge only of basic calculus, matrix algebra and elementary statistics. This third edition contains detailed instructions for the use of the professional version of the Windows-based computer package ITSM2000, now available as a free download from the Springer Extras website. The logic and tools of time series model-building are developed in detail. Numerous exercises are included and the software can be used to analyze and forecast data sets of the user's own choosing. The book can also be used in conjunction with other time series packages such as those included in R. The programs in ITSM2000 however are menu-driven and can be used with minimal investment of time in the computational details. The core of the book covers stationary processes, ARMA and ARIMA processes, multivariate time series and state-space mod...
Time series tapering for short data samples
DEFF Research Database (Denmark)
Kaimal, J.C.; Kristensen, L.
We explore the effect of applying tapered windows on atmospheric data to eliminate overestimation inherent in spectra computed from short time series. Some windows are more effective than others in correcting this distortion. The Hamming window gave the best results with experimental data. The Ha...
Asymptotic spectral theory for nonlinear time series
Shao, Xiaofeng; Wu, Wei Biao
2007-01-01
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.
On Bayesian Nonparametric Continuous Time Series Models
Karabatsos, George; Walker, Stephen G.
2013-01-01
This paper is a note on the use of Bayesian nonparametric mixture models for continuous time series. We identify a key requirement for such models, and then establish that there is a single type of model which meets this requirement. As it turns out, the model is well known in multiple change-point problems.
Nonlinear Time Series Analysis via Neural Networks
Volná, Eva; Janošek, Michal; Kocian, Václav; Kotyrba, Martin
This article deals with a time series analysis based on neural networks in order to make an effective forex market [Moore and Roche, J. Int. Econ. 58, 387-411 (2002)] pattern recognition. Our goal is to find and recognize important patterns which repeatedly appear in the market history to adapt our trading system behaviour based on them.
Nonlinear time-series analysis revisited.
Bradley, Elizabeth; Kantz, Holger
2015-09-01
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. PMID:26428563
Inferring causality from noisy time series data
DEFF Research Database (Denmark)
Mønster, Dan; Fusaroli, Riccardo; Tylén, Kristian;
2016-01-01
even causality direction in synchronized time-series and in the presence of intermediate coupling. We find that the presence of noise deterministically reduces the level of cross-mapping fidelity, while the convergence rate exhibits higher levels of robustness. Finally, we propose that controlled noise...
Nonlinear time-series analysis revisited
Bradley, Elizabeth; Kantz, Holger
2015-09-01
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.
Time Series Prediction Based on Chaotic Attractor
Institute of Scientific and Technical Information of China (English)
LIKe-Ping; CHENTian-Lun; GAOZi-You
2003-01-01
A new prediction technique is proposed for chaotic time series. The usefulness of the technique is that it can kick off some false neighbor points which are not suitable for the local estimation of the dynamics systems. A time-delayed embedding is used to reconstruct the underlying attractor, and the prediction model is based on the time evolution of the topological neighboring in the phase space. We use a feedforward neural network to approximate the local dominant Lyapunov exponent, and choose the spatial neighbors by the Lyapunov exponent. The model is tested for the Mackey-Glass equation and the convection amplitude of lorenz systems. The results indicate that this prediction technique can improve the prediction of chaotic time series.
Multiscale entropy analysis of electroseismic time series
Directory of Open Access Journals (Sweden)
L. Guzmán-Vargas
2008-08-01
Full Text Available In this work we use the multiscale entropy method to analyse the variability of geo-electric time series monitored in two sites located in Mexico. In our analysis we consider a period of time from January 1995 to December 1995. We systematically calculate the sample entropy of electroseismic time series. Important differences in the entropy profile for several time scales are observed in records from the same station. In particular, a complex behaviour is observed in the vicinity of a M=7.4 EQ occurred on 14 September 1995. Besides, we also compare the changes in the entropy of the original data with their corresponding shuffled version.
Time Series Analysis Using Composite Multiscale Entropy
Directory of Open Access Journals (Sweden)
Kung-Yen Lee
2013-03-01
Full Text Available Multiscale entropy (MSE was recently developed to evaluate the complexity of time series over different time scales. Although the MSE algorithm has been successfully applied in a number of different fields, it encounters a problem in that the statistical reliability of the sample entropy (SampEn of a coarse-grained series is reduced as a time scale factor is increased. Therefore, in this paper, the concept of a composite multiscale entropy (CMSE is introduced to overcome this difficulty. Simulation results on both white noise and 1/f noise show that the CMSE provides higher entropy reliablity than the MSE approach for large time scale factors. On real data analysis, both the MSE and CMSE are applied to extract features from fault bearing vibration signals. Experimental results demonstrate that the proposed CMSE-based feature extractor provides higher separability than the MSE-based feature extractor.
Fractal Analysis On Internet Traffic Time Series
Chong, K B
2002-01-01
Fractal behavior and long-range dependence have been observed in tele-traffic measurement and characterization. In this paper we show results of application of the fractal analysis to internet traffic via various methods. Our result demonstrate that the internet traffic exhibits self-similarity. Time-scale analysis show to be an effective way to characterize the local irregularity. Based on the result of this study, these two Internet time series exhibit fractal characteristic with long-range dependence.
Time series regression studies in environmental epidemiology
Bhaskaran, Krishnan; Gasparrini, Antonio; Hajat, Shakoor; Smeeth, Liam; Armstrong, Ben
2013-01-01
Time series regression studies have been widely used in environmental epidemiology, notably in investigating the short-term associations between exposures such as air pollution, weather variables or pollen, and health outcomes such as mortality, myocardial infarction or disease-specific hospital admissions. Typically, for both exposure and outcome, data are available at regular time intervals (e.g. daily pollution levels and daily mortality counts) and the aim is to explore short-term associa...
TIME SERIES FORECASTING USING NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
BOGDAN OANCEA
2013-05-01
Full Text Available Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. Neural Networks have the advantage that can approximate nonlinear functions. In this paper we compared the performances of different feed forward and recurrent neural networks and training algorithms for predicting the exchange rate EUR/RON and USD/RON. We used data series with daily exchange rates starting from 2005 until 2013.
Time series regression studies in environmental epidemiology.
Bhaskaran, Krishnan; Gasparrini, Antonio; Hajat, Shakoor; Smeeth, Liam; Armstrong, Ben
2013-08-01
Time series regression studies have been widely used in environmental epidemiology, notably in investigating the short-term associations between exposures such as air pollution, weather variables or pollen, and health outcomes such as mortality, myocardial infarction or disease-specific hospital admissions. Typically, for both exposure and outcome, data are available at regular time intervals (e.g. daily pollution levels and daily mortality counts) and the aim is to explore short-term associations between them. In this article, we describe the general features of time series data, and we outline the analysis process, beginning with descriptive analysis, then focusing on issues in time series regression that differ from other regression methods: modelling short-term fluctuations in the presence of seasonal and long-term patterns, dealing with time varying confounding factors and modelling delayed ('lagged') associations between exposure and outcome. We finish with advice on model checking and sensitivity analysis, and some common extensions to the basic model. PMID:23760528
Sliced Inverse Regression for Time Series Analysis
Chen, Li-Sue
1995-11-01
In this thesis, general nonlinear models for time series data are considered. A basic form is x _{t} = f(beta_sp{1} {T}X_{t-1},beta_sp {2}{T}X_{t-1},... , beta_sp{k}{T}X_ {t-1},varepsilon_{t}), where x_{t} is an observed time series data, X_{t } is the first d time lag vector, (x _{t},x_{t-1},... ,x _{t-d-1}), f is an unknown function, beta_{i}'s are unknown vectors, varepsilon_{t }'s are independent distributed. Special cases include AR and TAR models. We investigate the feasibility applying SIR/PHD (Li 1990, 1991) (the sliced inverse regression and principal Hessian methods) in estimating beta _{i}'s. PCA (Principal component analysis) is brought in to check one critical condition for SIR/PHD. Through simulation and a study on 3 well -known data sets of Canadian lynx, U.S. unemployment rate and sunspot numbers, we demonstrate how SIR/PHD can effectively retrieve the interesting low-dimension structures for time series data.
Time Series Analysis Using Geometric Template Matching.
Frank, Jordan; Mannor, Shie; Pineau, Joelle; Precup, Doina
2013-03-01
We present a novel framework for analyzing univariate time series data. At the heart of the approach is a versatile algorithm for measuring the similarity of two segments of time series called geometric template matching (GeTeM). First, we use GeTeM to compute a similarity measure for clustering and nearest-neighbor classification. Next, we present a semi-supervised learning algorithm that uses the similarity measure with hierarchical clustering in order to improve classification performance when unlabeled training data are available. Finally, we present a boosting framework called TDEBOOST, which uses an ensemble of GeTeM classifiers. TDEBOOST augments the traditional boosting approach with an additional step in which the features used as inputs to the classifier are adapted at each step to improve the training error. We empirically evaluate the proposed approaches on several datasets, such as accelerometer data collected from wearable sensors and ECG data. PMID:22641699
Univariate time series forecasting algorithm validation
Ismail, Suzilah; Zakaria, Rohaiza; Muda, Tuan Zalizam Tuan
2014-12-01
Forecasting is a complex process which requires expert tacit knowledge in producing accurate forecast values. This complexity contributes to the gaps between end users and expert. Automating this process by using algorithm can act as a bridge between them. Algorithm is a well-defined rule for solving a problem. In this study a univariate time series forecasting algorithm was developed in JAVA and validated using SPSS and Excel. Two set of simulated data (yearly and non-yearly); several univariate forecasting techniques (i.e. Moving Average, Decomposition, Exponential Smoothing, Time Series Regressions and ARIMA) and recent forecasting process (such as data partition, several error measures, recursive evaluation and etc.) were employed. Successfully, the results of the algorithm tally with the results of SPSS and Excel. This algorithm will not just benefit forecaster but also end users that lacking in depth knowledge of forecasting process.
Multivariate Voronoi Outlier Detection for Time Series
Zwilling, Chris E.; Wang, Michelle Yongmei
2014-01-01
Outlier detection is a primary step in many data mining and analysis applications, including healthcare and medical research. This paper presents a general method to identify outliers in multivariate time series based on a Voronoi diagram, which we call Multivariate Voronoi Outlier Detection (MVOD). The approach copes with outliers in a multivariate framework, via designing and extracting effective attributes or features from the data that can take parametric or nonparametric forms. Voronoi d...
Estimation and Forecasting in Time Series Models
Zhang, Ru
2013-01-01
This dissertation covers several topics in estimation and forecasting in time series models. Chapter one is about estimation and feasible conditional forecasts properties from the predictive regressions, which extends previous results of OLS estimation bias in the predictive regression model by considering predictive regressions with possible zero intercepts, and also allowing the regressor to follow either a stationary AR(1) process or unit root process. The main thrust of this chapter is t...
Bayes analysis of time series with covariates
Czech Academy of Sciences Publication Activity Database
Volf, Petr
Hradec Králové : Gaudeamus, 2005 - (Skalská, H.), s. 421-426 ISBN 978-80-7041-535-1. [Mathematical Methods in Economics 2005 /23./. Hradec Králové (CZ), 14.09.2005-16.09.2005] R&D Projects: GA ČR GA402/04/1294 Institutional research plan: CEZ:AV0Z10750506 Keywords : Bayes analysis * time series * unemployment data Subject RIV: BB - Applied Statistics, Operational Research
Revisiting algorithms for generating surrogate time series
Raeth, C; Papadakis, I E; Brinkmann, W
2011-01-01
The method of surrogates is one of the key concepts of nonlinear data analysis. Here, we demonstrate that commonly used algorithms for generating surrogates often fail to generate truly linear time series. Rather, they create surrogate realizations with Fourier phase correlations leading to non-detections of nonlinearities. We argue that reliable surrogates can only be generated, if one tests separately for static and dynamic nonlinearities.
Applying time series analysis to performance logs
Kubacki, Marcin; Sosnowski, Janusz
2015-09-01
Contemporary computer systems provide mechanisms for monitoring various performance parameters (e.g. processor or memory usage, disc or network transfers), which are collected and stored in performance logs. An important issue is to derive characteristic features describing normal and abnormal behavior of the systems. For this purpose we use various schemes of analyzing time series. They have been adapted to the specificity of performance logs and verified using data collected from real systems. The presented approach is useful in evaluating system dependability.
On clustering fMRI time series
DEFF Research Database (Denmark)
Goutte, Cyril; Toft, Peter Aundal; Rostrup, E.;
1999-01-01
Analysis of fMRI time series is often performed by extracting one or more parameters for the individual voxels. Methods based, e.g., on various statistical tests are then used to yield parameters corresponding to probability of activation or activation strength. However, these methods do not...... between the activation stimulus and the fMRI signal. We present two different clustering algorithms and use them to identify regions of similar activations in an fMRI experiment involving a visual stimulus....
Time-series models in marketing.
Dekimpe, Marnik; Hanssens, DM
2000-01-01
Leeflang and Wittink (2000) identify three past stages in marketing model building and implementation, review the current status, and provide some intriguing thoughts on how the model-building process may evolve in response to ongoing and anticipated developments in the marketing environment. It is interesting to note that time-series techniques are not mentioned in their review of the past, receive considerable attention in their assessment of the current situation (mainly in the context of ...
Nonparametric inference for unbalance time series data
Oliver Linton
2004-01-01
Estimation of heteroskedasticity and autocorrelation consistent covariance matrices (HACs) is a well established problem in time series. Results have been established under a variety of weak conditions on temporal dependence and heterogeneity that allow one to conduct inference on a variety of statistics, see Newey and West (1987), Hansen (1992), de Jong and Davidson (2000), and Robinson (2004). Indeed there is an extensive literature on automating these procedures starting with Andrews (1991...
Nonparametric inference for unbalanced time series data
Linton, Oliver Bruce
2004-01-01
Estimation of heteroskedasticity and autocorrelation consistent covariance matrices (HACs) is a well established problem in time series. Results have been established under a variety of weak conditions on temporal dependence and heterogeneity that allow one to conduct inference on a variety of statistics, see Newey and West (1987), Hansen (1992), de Jong and Davidson (2000), and Robinson (2004). Indeed there is an extensive literature on automating these procedures starting with Andrews (1991...
Evolving time series forecasting ARMA models
Cortez, Paulo; Rocha, Miguel
2004-01-01
Nowadays, the ability to forecast the future, based only on past data, leads to strategic advantages, which may be the key to success in organizations. Time Series Forecasting (TSF) allows the modeling of complex systems as ``black-boxes'', being a focus of attention in several research arenas such as Operational Research, Statistics or Computer Science. Alternative TSF approaches emerged from the Artificial Intelligence arena, where optimization algorithms inspired on natural selection pr...
Time Series Forecasting with Missing Values
Shin-Fu Wu; Chia-Yung Chang; Shie-Jue Lee
2015-01-01
Time series prediction has become more popular in various kinds of applications such as weather prediction, control engineering, financial analysis, industrial monitoring, etc. To deal with real-world problems, we are often faced with missing values in the data due to sensor malfunctions or human errors. Traditionally, the missing values are simply omitted or replaced by means of imputation methods. However, omitting those missing values may cause temporal discontinuity. Imputation methods, o...
Analysis of Polyphonic Musical Time Series
Sommer, Katrin; Weihs, Claus
A general model for pitch tracking of polyphonic musical time series will be introduced. Based on a model of Davy and Godsill (Bayesian harmonic models for musical pitch estimation and analysis, Technical Report 431, Cambridge University Engineering Department, 2002) Davy and Godsill (2002) the different pitches of the musical sound are estimated with MCMC methods simultaneously. Additionally a preprocessing step is designed to improve the estimation of the fundamental frequencies (A comparative study on polyphonic musical time series using MCMC methods. In C. Preisach et al., editors, Data Analysis, Machine Learning, and Applications, Springer, Berlin, 2008). The preprocessing step compares real audio data with an alphabet constructed from the McGill Master Samples (Opolko and Wapnick, McGill University Master Samples [Compact disc], McGill University, Montreal, 1987) and consists of tones of different instruments. The tones with minimal Itakura-Saito distortion (Gray et al., Transactions on Acoustics, Speech, and Signal Processing ASSP-28(4):367-376, 1980) are chosen as first estimates and as starting points for the MCMC algorithms. Furthermore the implementation of the alphabet is an approach for the recognition of the instruments generating the musical time series. Results are presented for mixed monophonic data from McGill and for self recorded polyphonic audio data.
Time Series Forecasting: A Multivariate Stochastic Approach
Sello, Stefano
1999-01-01
This note deals with a multivariate stochastic approach to forecast the behaviour of a cyclic time series. Particular attention is devoted to the problem of the prediction of time behaviour of sunspot numbers for the current 23th cycle. The idea is to consider the previous known n cycles as n particular realizations of a given stochastic process. The aim is to predict the future behaviour of the current n+1th realization given a portion of the curve and the structure of the previous n realiza...
Normalizing the causality between time series
Liang, X San
2015-01-01
Recently, a rigorous yet concise formula has been derived to evaluate the information flow, and hence the causality in a quantitative sense, between time series. To assess the importance of a resulting causality, it needs to be normalized. The normalization is achieved through distinguishing three types of fundamental mechanisms that govern the marginal entropy change of the flow recipient. A normalized or relative flow measures its importance relative to other mechanisms. In analyzing realistic series, both absolute and relative information flows need to be taken into account, since the normalizers for a pair of reverse flows belong to two different entropy balances; it is quite normal that two identical flows may differ a lot in relative importance in their respective balances. We have reproduced these results with several autoregressive models. We have also shown applications to a climate change problem and a financial analysis problem. For the former, reconfirmed is the role of the Indian Ocean Dipole as ...
Argos: An Optimized Time-Series Photometer
Indian Academy of Sciences (India)
Anjum S. Mukadam; R. E. Nather
2005-06-01
We designed a prime focus CCD photometer, Argos, optimized for high speed time-series measurements of blue variables (Nather & Mukadam 2004) for the 2.1 m telescope at McDonald Observatory. Lack of any intervening optics between the primary mirror and the CCD makes the instrument highly efficient.We measure an improvement in sensitivity by a factor of nine over the 3-channel PMT photometers used on the same telescope and for the same exposure time. The CCD frame transfer operation triggered by GPS synchronized pulses serves as an electronic shutter for the photometer. This minimizes the dead time between exposures, but more importantly, allows a precise control of the start and duration of the exposure. We expect the uncertainty in our timing to be less than 100 s.
Directed networks with underlying time structures from multivariate time series
Tanizawa, Toshihiro; Taya, Fumihiko
2014-01-01
In this paper we propose a method of constructing directed networks of time-dependent phenomena from multivariate time series. As the construction method is based on the linear model, the network fully reflects dynamical features of the system such as time structures of periodicities. Furthermore, this method can construct networks even if these time series show no similarity: situations in which common methods fail. We explicitly introduce a case where common methods do not work. This fact indicates the importance of constructing networks based on dynamical perspective, when we consider time-dependent phenomena. We apply the method to multichannel electroencephalography~(EEG) data and the result reveals underlying interdependency among the components in the brain system.
Fractal fluctuations in cardiac time series
West, B. J.; Zhang, R.; Sanders, A. W.; Miniyar, S.; Zuckerman, J. H.; Levine, B. D.; Blomqvist, C. G. (Principal Investigator)
1999-01-01
Human heart rate, controlled by complex feedback mechanisms, is a vital index of systematic circulation. However, it has been shown that beat-to-beat values of heart rate fluctuate continually over a wide range of time scales. Herein we use the relative dispersion, the ratio of the standard deviation to the mean, to show, by systematically aggregating the data, that the correlation in the beat-to-beat cardiac time series is a modulated inverse power law. This scaling property indicates the existence of long-time memory in the underlying cardiac control process and supports the conclusion that heart rate variability is a temporal fractal. We argue that the cardiac control system has allometric properties that enable it to respond to a dynamical environment through scaling.
Time Series Photometry of KZ Lacertae
Joner, Michael D.
2016-01-01
We present BVRI time series photometry of the high amplitude delta Scuti star KZ Lacertae secured using the 0.9-meter telescope located at the Brigham Young University West Mountain Observatory. In addition to the multicolor light curves that are presented, the V data from the last six years of observations are used to plot an O-C diagram in order to determine the ephemeris and evaluate evidence for period change. We wish to thank the Brigham Young University College of Physical and Mathematical Sciences as well as the Department of Physics and Astronomy for their continued support of the research activities at the West Mountain Observatory.
Fourier analysis of time series an introduction
Bloomfield, Peter
2000-01-01
A new, revised edition of a yet unrivaled work on frequency domain analysis Long recognized for his unique focus on frequency domain methods for the analysis of time series data as well as for his applied, easy-to-understand approach, Peter Bloomfield brings his well-known 1976 work thoroughly up to date. With a minimum of mathematics and an engaging, highly rewarding style, Bloomfield provides in-depth discussions of harmonic regression, harmonic analysis, complex demodulation, and spectrum analysis. All methods are clearly illustrated using examples of specific data sets, while ample
Forecasting with nonlinear time series models
DEFF Research Database (Denmark)
Kock, Anders Bredahl; Teräsvirta, Timo
In this paper, nonlinear models are restricted to mean nonlinear parametric models. Several such models popular in time series econo- metrics are presented and some of their properties discussed. This in- cludes two models based on universal approximators: the Kolmogorov- Gabor polynomial model a......- ular case where the data-generating process is a simple artificial neural network model. Suggestions for further reading conclude the paper....... and two versions of a simple artificial neural network model. Techniques for generating multi-period forecasts from nonlinear models recursively are considered, and the direct (non-recursive) method for this purpose is mentioned as well. Forecasting with com- plex dynamic systems, albeit less frequently...
Time series analysis of temporal networks
Sikdar, Sandipan; Ganguly, Niloy; Mukherjee, Animesh
2016-01-01
A common but an important feature of all real-world networks is that they are temporal in nature, i.e., the network structure changes over time. Due to this dynamic nature, it becomes difficult to propose suitable growth models that can explain the various important characteristic properties of these networks. In fact, in many application oriented studies only knowing these properties is sufficient. For instance, if one wishes to launch a targeted attack on a network, this can be done even without the knowledge of the full network structure; rather an estimate of some of the properties is sufficient enough to launch the attack. We, in this paper show that even if the network structure at a future time point is not available one can still manage to estimate its properties. We propose a novel method to map a temporal network to a set of time series instances, analyze them and using a standard forecast model of time series, try to predict the properties of a temporal network at a later time instance. To our aim, we consider eight properties such as number of active nodes, average degree, clustering coefficient etc. and apply our prediction framework on them. We mainly focus on the temporal network of human face-to-face contacts and observe that it represents a stochastic process with memory that can be modeled as Auto-Regressive-Integrated-Moving-Average (ARIMA). We use cross validation techniques to find the percentage accuracy of our predictions. An important observation is that the frequency domain properties of the time series obtained from spectrogram analysis could be used to refine the prediction framework by identifying beforehand the cases where the error in prediction is likely to be high. This leads to an improvement of 7.96% (for error level ≤20%) in prediction accuracy on an average across all datasets. As an application we show how such prediction scheme can be used to launch targeted attacks on temporal networks. Contribution to the Topical Issue
Time series modelling of surface pressure data
Al-Awadhi, Shafeeqah; Jolliffe, Ian
1998-03-01
In this paper we examine time series modelling of surface pressure data, as measured by a barograph, at Herne Bay, England, during the years 1981-1989. Autoregressive moving average (ARMA) models have been popular in many fields over the past 20 years, although applications in climatology have been rather less widespread than in some disciplines. Some recent examples are Milionis and Davies (Int. J. Climatol., 14, 569-579) and Seleshi et al. (Int. J. Climatol., 14, 911-923). We fit standard ARMA models to the pressure data separately for each of six 2-month natural seasons. Differences between the best fitting models for different seasons are discussed. Barograph data are recorded continuously, whereas ARMA models are fitted to discretely recorded data. The effect of different spacings between the fitted data on the models chosen is discussed briefly.Often, ARMA models can give a parsimonious and interpretable representation of a time series, but for many series the assumptions underlying such models are not fully satisfied, and more complex models may be considered. A specific feature of surface pressure data in the UK is that its behaviour is different at high and at low pressures: day-to-day changes are typically larger at low pressure levels than at higher levels. This means that standard assumptions used in fitting ARMA models are not valid, and two ways of overcoming this problem are investigated. Transformation of the data to better satisfy the usual assumptions is considered, as is the use of non-linear, specifically threshold autoregressive (TAR), models.
Ensemble vs. time averages in financial time series analysis
Seemann, Lars; Hua, Jia-Chen; McCauley, Joseph L.; Gunaratne, Gemunu H.
2012-12-01
Empirical analysis of financial time series suggests that the underlying stochastic dynamics are not only non-stationary, but also exhibit non-stationary increments. However, financial time series are commonly analyzed using the sliding interval technique that assumes stationary increments. We propose an alternative approach that is based on an ensemble over trading days. To determine the effects of time averaging techniques on analysis outcomes, we create an intraday activity model that exhibits periodic variable diffusion dynamics and we assess the model data using both ensemble and time averaging techniques. We find that ensemble averaging techniques detect the underlying dynamics correctly, whereas sliding intervals approaches fail. As many traded assets exhibit characteristic intraday volatility patterns, our work implies that ensemble averages approaches will yield new insight into the study of financial markets’ dynamics.
Nonlinear Time Series Analysis Since 1990:Some Personal Reflections
Institute of Scientific and Technical Information of China (English)
Howel Tong
2002-01-01
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.
Periodograms for multiband astronomical time series
Ivezic, Z.; VanderPlas, J. T.
2016-05-01
We summarize the multiband periodogram, a general extension of the well-known Lomb-Scargle approach for detecting periodic signals in time- domain data developed by VanderPlas & Ivezic (2015). A Python implementation of this method is available on GitHub. The multiband periodogram significantly improves period finding for randomly sampled multiband light curves (e.g., Pan-STARRS, DES, and LSST), and can treat non-uniform sampling and heteroscedastic errors. The light curves in each band are modeled as arbitrary truncated Fourier series, with the period and phase shared across all bands. The key aspect is the use of Tikhonov regularization which drives most of the variability into the so-called base model common to all bands, while fits for individual bands describe residuals relative to the base model and typically require lower-order Fourier series. We use simulated light curves and randomly subsampled SDSS Stripe 82 data to demonstrate the superiority of this method compared to other methods from the literature, and find that this method will be able to efficiently determine the correct period in the majority of LSST's bright RR Lyrae stars with as little as six months of LSST data.
Periodograms for Multiband Astronomical Time Series
VanderPlas, Jacob T
2015-01-01
This paper introduces the multiband periodogram, a general extension of the well-known Lomb-Scargle approach for detecting periodic signals in time-domain data. In addition to advantages of the Lomb-Scargle method such as treatment of non-uniform sampling and heteroscedastic errors, the multiband periodogram significantly improves period finding for randomly sampled multiband light curves (e.g., Pan-STARRS, DES and LSST). The light curves in each band are modeled as arbitrary truncated Fourier series, with the period and phase shared across all bands. The key aspect is the use of Tikhonov regularization which drives most of the variability into the so-called base model common to all bands, while fits for individual bands describe residuals relative to the base model and typically require lower-order Fourier series. This decrease in the effective model complexity is the main reason for improved performance. We use simulated light curves and randomly subsampled SDSS Stripe 82 data to demonstrate the superiority...
Load Forecasting Using Time Series Models
Directory of Open Access Journals (Sweden)
Mahendran Shitan
2009-09-01
Full Text Available Load forecasting is a process of predicting the future load demands. It is important for power systemplanners and demand controllers in ensuring that there would be enough generation to cope withthe increasing demand. Accurate model for load forecasting can lead to a better budget planning,maintenance scheduling and fuel management. This paper presents an attempt to forecast the maximumdemand of electricity by finding an appropriate time series model. The methods considered in this studyinclude the Naïve method, Exponential smoothing, Seasonal Holt-Winters, ARMA, ARAR algorithm, andRegression with ARMA Errors. The performance of these different methods was evaluated by using theforecasting accuracy criteria namely, the Mean Absolute Error (MAE, Root Mean Square Error (RMSE andMean Absolute Relative Percentage Error (MARPE. Based on these three criteria the pure autoregressivemodel with an order 2, or AR (2 under ARMA family emerged as the best model for forecasting electricitydemand.
Correlation filtering in financial time series
Aste, T; Tumminello, M; Mantegna, R N
2005-01-01
We apply a method to filter relevant information from the correlation coefficient matrix by extracting a network of relevant interactions. This method succeeds to generate networks with the same hierarchical structure of the Minimum Spanning Tree but containing a larger amount of links resulting in a richer network topology allowing loops and cliques. In Tumminello et al. \\cite{TumminielloPNAS05}, we have shown that this method, applied to a financial portfolio of 100 stocks in the USA equity markets, is pretty efficient in filtering relevant information about the clustering of the system and its hierarchical structure both on the whole system and within each cluster. In particular, we have found that triangular loops and 4 element cliques have important and significant relations with the market structure and properties. Here we apply this filtering procedure to the analysis of correlation in two different kind of interest rate time series (16 Eurodollars and 34 US interest rates).
Normalizing the causality between time series
Liang, X. San
2015-08-01
Recently, a rigorous yet concise formula was derived to evaluate information flow, and hence the causality in a quantitative sense, between time series. To assess the importance of a resulting causality, it needs to be normalized. The normalization is achieved through distinguishing a Lyapunov exponent-like, one-dimensional phase-space stretching rate and a noise-to-signal ratio from the rate of information flow in the balance of the marginal entropy evolution of the flow recipient. It is verified with autoregressive models and applied to a real financial analysis problem. An unusually strong one-way causality is identified from IBM (International Business Machines Corporation) to GE (General Electric Company) in their early era, revealing to us an old story, which has almost faded into oblivion, about "Seven Dwarfs" competing with a giant for the mainframe computer market.
Timing calibration and spectral cleaning of LOFAR time series data
Corstanje, A.; Buitink, S.; Enriquez, J. E.; Falcke, H.; Hörandel, J. R.; Krause, M.; Nelles, A.; Rachen, J. P.; Schellart, P.; Scholten, O.; ter Veen, S.; Thoudam, S.; Trinh, T. N. G.
2016-05-01
We describe a method for spectral cleaning and timing calibration of short time series data of the voltage in individual radio interferometer receivers. It makes use of phase differences in fast Fourier transform (FFT) spectra across antenna pairs. For strong, localized terrestrial sources these are stable over time, while being approximately uniform-random for a sum over many sources or for noise. Using only milliseconds-long datasets, the method finds the strongest interfering transmitters, a first-order solution for relative timing calibrations, and faulty data channels. No knowledge of gain response or quiescent noise levels of the receivers is required. With relatively small data volumes, this approach is suitable for use in an online system monitoring setup for interferometric arrays. We have applied the method to our cosmic-ray data collection, a collection of measurements of short pulses from extensive air showers, recorded by the LOFAR radio telescope. Per air shower, we have collected 2 ms of raw time series data for each receiver. The spectral cleaning has a calculated optimal sensitivity corresponding to a power signal-to-noise ratio of 0.08 (or -11 dB) in a spectral window of 25 kHz, for 2 ms of data in 48 antennas. This is well sufficient for our application. Timing calibration across individual antenna pairs has been performed at 0.4 ns precision; for calibration of signal clocks across stations of 48 antennas the precision is 0.1 ns. Monitoring differences in timing calibration per antenna pair over the course of the period 2011 to 2015 shows a precision of 0.08 ns, which is useful for monitoring and correcting drifts in signal path synchronizations. A cross-check method for timing calibration is presented, using a pulse transmitter carried by a drone flying over the array. Timing precision is similar, 0.3 ns, but is limited by transmitter position measurements, while requiring dedicated flights.
Time series models with a common stochastic variance for analysing economic time series
Koopman, S.J.; C.S. Bos
2002-01-01
This discussion paper led to an article in Statistica Neerlandica (2003). Vol. 57, issue 4, pages 439-469. The linear Gaussian state space model for which the common variance istreated as a stochastic time-varying variable is considered for themodelling of economic time series. The focus of this paper is on thesimultaneous estimation of parameters related to the stochasticprocesses of the mean part and the variance part of the model. Theestimation method is based on maximum likelihood and it ...
Timing calibration and spectral cleaning of LOFAR time series data
Corstanje, A; Enriquez, J E; Falcke, H; Hörandel, J R; Krause, M; Nelles, A; Rachen, J P; Schellart, P; Scholten, O; ter Veen, S; Thoudam, S; Trinh, T N G
2016-01-01
We describe a method for spectral cleaning and timing calibration of short voltage time series data from individual radio interferometer receivers. It makes use of the phase differences in Fast Fourier Transform (FFT) spectra across antenna pairs. For strong, localized terrestrial sources these are stable over time, while being approximately uniform-random for a sum over many sources or for noise. Using only milliseconds-long datasets, the method finds the strongest interfering transmitters, a first-order solution for relative timing calibrations, and faulty data channels. No knowledge of gain response or quiescent noise levels of the receivers is required. With relatively small data volumes, this approach is suitable for use in an online system monitoring setup for interferometric arrays. We have applied the method to our cosmic-ray data collection, a collection of measurements of short pulses from extensive air showers, recorded by the LOFAR radio telescope. Per air shower, we have collected 2 ms of raw tim...
Time series modeling for syndromic surveillance
Directory of Open Access Journals (Sweden)
Mandl Kenneth D
2003-01-01
Full Text Available Abstract Background Emergency department (ED based syndromic surveillance systems identify abnormally high visit rates that may be an early signal of a bioterrorist attack. For example, an anthrax outbreak might first be detectable as an unusual increase in the number of patients reporting to the ED with respiratory symptoms. Reliably identifying these abnormal visit patterns requires a good understanding of the normal patterns of healthcare usage. Unfortunately, systematic methods for determining the expected number of (ED visits on a particular day have not yet been well established. We present here a generalized methodology for developing models of expected ED visit rates. Methods Using time-series methods, we developed robust models of ED utilization for the purpose of defining expected visit rates. The models were based on nearly a decade of historical data at a major metropolitan academic, tertiary care pediatric emergency department. The historical data were fit using trimmed-mean seasonal models, and additional models were fit with autoregressive integrated moving average (ARIMA residuals to account for recent trends in the data. The detection capabilities of the model were tested with simulated outbreaks. Results Models were built both for overall visits and for respiratory-related visits, classified according to the chief complaint recorded at the beginning of each visit. The mean absolute percentage error of the ARIMA models was 9.37% for overall visits and 27.54% for respiratory visits. A simple detection system based on the ARIMA model of overall visits was able to detect 7-day-long simulated outbreaks of 30 visits per day with 100% sensitivity and 97% specificity. Sensitivity decreased with outbreak size, dropping to 94% for outbreaks of 20 visits per day, and 57% for 10 visits per day, all while maintaining a 97% benchmark specificity. Conclusions Time series methods applied to historical ED utilization data are an important tool
Peat conditions mapping using MODIS time series
Poggio, Laura; Gimona, Alessandro; Bruneau, Patricia; Johnson, Sally; McBride, Andrew; Artz, Rebekka
2016-04-01
Large areas of Scotland are covered in peatlands, providing an important sink of carbon in their near natural state but act as a potential source of gaseous and dissolved carbon emission if not in good conditions. Data on the condition of most peatlands in Scotland are, however, scarce and largely confined to sites under nature protection designations, often biased towards sites in better condition. The best information available at present is derived from labour intensive field-based monitoring of relatively few designated sites (Common Standard Monitoring Dataset). In order to provide a national dataset of peat conditions, the available point information from the CSM data was modelled with morphological features and information derived from MODIS sensor. In particular we used time series of indices describing vegetation greenness (Enhanced Vegetation Index), water availability (Normalised Water Difference index), Land Surface Temperature and vegetation productivity (Gross Primary productivity). A scorpan-kriging approach was used, in particular using Generalised Additive Models for the description of the trend. The model provided the probability of a site to be in favourable conditions and the uncertainty of the predictions was taken into account. The internal validation (leave-one-out) provided a mis-classification error of around 0.25. The derived dataset was then used, among others, in the decision making process for the selection of sites for restoration.
Climate Prediction Center (CPC) Global Temperature Time Series
National Oceanic and Atmospheric Administration, Department of Commerce — The global temperature time series provides time series charts using station based observations of daily temperature. These charts provide information about the...
Climate Prediction Center (CPC) Global Precipitation Time Series
National Oceanic and Atmospheric Administration, Department of Commerce — The global precipitation time series provides time series charts showing observations of daily precipitation as well as accumulated precipitation compared to normal...
Some results of analysis of source position time series
Malkin, Zinovy
2015-01-01
Source position time series produced by International VLBI Service for Geodesy and astrometry (IVS) Analysis Centers were analyzed. These series was computed using different software and analysis strategy. Comparison of this series showed that they have considerably different scatter and systematic behavior. Based on the inspection of all the series, new sources were identified as sources with irregular (non-random) position variations. Two statistics used to estimate the noise level in the time series, namely RMS and ADEV were compared.
Deflation-based separation of uncorrelated stationary time series
Miettinen, Jari; Nordhausen, Klaus; Oja, Hannu; Taskinen, Sara
2014-01-01
In this paper we assume that the observed pp time series are linear combinations of pp latent uncorrelated weakly stationary time series. The problem is then to find an estimate for an unmixing matrix that transforms the observed time series back to uncorrelated time series. The so called SOBI (Second Order Blind Identification) estimate aims at a joint diagonalization of the covariance matrix and several autocovariance matrices with varying lags. In this paper, we propose a novel procedure t...
An introduction to state space time series analysis.
Commandeur, J.J.F. & Koopman, S.J.
2007-01-01
Providing a practical introduction to state space methods as applied to unobserved components time series models, also known as structural time series models, this book introduces time series analysis using state space methodology to readers who are neither familiar with time series analysis, nor with state space methods. The only background required in order to understand the material presented in the book is a basic knowledge of classical linear regression models, of which a brief review is...
Seasonal Time Series Analysis Based on Genetic Algorithm
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
Pattern discovery from the seasonal time-series is of importance. Traditionally, most of the algorithms of pattern discovery in time series are similar. A novel mode of time series is proposed which integrates the Genetic Algorithm (GA) for the actual problem. The experiments on the electric power yield sequence models show that this algorithm is practicable and effective.
Notes on time serie analysis, ARIMA models and signal extraction
Kaiser, Regina; Maravall, Agustín
2000-01-01
Present practice in applied time series work, mostly at economic policy or data producing agencies, relies heavily on using moving average filters to estimate unobserved components (or signals) in time series, such as the seasonally adjusted series, the trend, or the cycle. The purpose of the present paper is to provide an informal introduction to the time series analysis tools and concepts required by the user or analyst to understand the basic methodology behind the application of filters. ...
Generalized Framework for Similarity Measure of Time Series
Directory of Open Access Journals (Sweden)
Hongsheng Yin
2014-01-01
Full Text Available Currently, there is no definitive and uniform description for the similarity of time series, which results in difficulties for relevant research on this topic. In this paper, we propose a generalized framework to measure the similarity of time series. In this generalized framework, whether the time series is univariable or multivariable, and linear transformed or nonlinear transformed, the similarity of time series is uniformly defined using norms of vectors or matrices. The definitions of the similarity of time series in the original space and the transformed space are proved to be equivalent. Furthermore, we also extend the theory on similarity of univariable time series to multivariable time series. We present some experimental results on published time series datasets tested with the proposed similarity measure function of time series. Through the proofs and experiments, it can be claimed that the similarity measure functions of linear multivariable time series based on the norm distance of covariance matrix and nonlinear multivariable time series based on kernel function are reasonable and practical.
Outlier Detection in Structural Time Series Models
DEFF Research Database (Denmark)
Marczak, Martyna; Proietti, Tommaso
Structural change affects the estimation of economic signals, like the underlying growth rate or the seasonally adjusted series. An important issue, which has attracted a great deal of attention also in the seasonal adjustment literature, is its detection by an expert procedure. The general–to–sp...
Time and ensemble averaging in time series analysis
Latka, Miroslaw; Jernajczyk, Wojciech; West, Bruce J
2010-01-01
In many applications expectation values are calculated by partitioning a single experimental time series into an ensemble of data segments of equal length. Such single trajectory ensemble (STE) is a counterpart to a multiple trajectory ensemble (MTE) used whenever independent measurements or realizations of a stochastic process are available. The equivalence of STE and MTE for stationary systems was postulated by Wang and Uhlenbeck in their classic paper on Brownian motion (Rev. Mod. Phys. 17, 323 (1945)) but surprisingly has not yet been proved. Using the stationary and ergodic paradigm of statistical physics -- the Ornstein-Uhlenbeck (OU) Langevin equation, we revisit Wang and Uhlenbeck's postulate. In particular, we find that the variance of the solution of this equation is different for these two ensembles. While the variance calculated using the MTE quantifies the spreading of independent trajectories originating from the same initial point, the variance for STE measures the spreading of two correlated r...
Hidden Markov Models for Time Series An Introduction Using R
Zucchini, Walter
2009-01-01
Illustrates the flexibility of HMMs as general-purpose models for time series data. This work presents an overview of HMMs for analyzing time series data, from continuous-valued, circular, and multivariate series to binary data, bounded and unbounded counts and categorical observations.
Vyhnalek, Brian; Zurcher, Ulrich; O'Dwyer, Rebecca; Kaufman, Miron
2009-10-01
A wide range of heart rate irregularities have been reported in small studies of patients with temporal lobe epilepsy [TLE]. We hypothesize that patients with TLE display cardiac dysautonomia in either a subclinical or clinical manner. In a small study, we have retrospectively identified (2003-8) two groups of patients from the epilepsy monitoring unit [EMU] at the Cleveland Clinic. No patients were diagnosed with cardiovascular morbidities. The control group consisted of patients with confirmed pseudoseizures and the experimental group had confirmed right temporal lobe epilepsy through a seizure free outcome after temporal lobectomy. We quantified the heart rate variability using the approximate entropy [ApEn]. We found similar values of the ApEn in all three states of consciousness (awake, sleep, and proceeding seizure onset). In the TLE group, there is some evidence for greater variability in the awake than in either the sleep or proceeding seizure onset. Here we present results for mathematically-generated time series: the heart rate fluctuations ξ follow the γ statistics i.e., p(ξ)=γ-1(k) ξ^k exp(-ξ). This probability function has well-known properties and its Shannon entropy can be expressed in terms of the γ-function. The parameter k allows us to generate a family of heart rate time series with different statistics. The ApEn calculated for the generated time series for different values of k mimic the properties found for the TLE and pseudoseizure group. Our results suggest that the ApEn is an effective tool to probe differences in statistics of heart rate fluctuations.
Multiscale entropy to distinguish physiologic and synthetic RR time series.
Costa, M; Goldberger, A L; Peng, C-K
2002-01-01
We address the challenge of distinguishing physiologic interbeat interval time series from those generated by synthetic algorithms via a newly developed multiscale entropy method. Traditional measures of time series complexity only quantify the degree of regularity on a single time scale. However, many physiologic variables, such as heart rate, fluctuate in a very complex manner and present correlations over multiple time scales. We have proposed a new method to calculate multiscale entropy from complex signals. In order to distinguish between physiologic and synthetic time series, we first applied the method to a learning set of RR time series derived from healthy subjects. We empirically established selected criteria characterizing the entropy dependence on scale factor for these datasets. We then applied this algorithm to the CinC 2002 test datasets. Using only the multiscale entropy method, we correctly classified 48 of 50 (96%) time series. In combination with Fourier spectral analysis, we correctly classified all time series. PMID:14686448
Efficient Algorithms for Segmentation of Item-Set Time Series
Chundi, Parvathi; Rosenkrantz, Daniel J.
We propose a special type of time series, which we call an item-set time series, to facilitate the temporal analysis of software version histories, email logs, stock market data, etc. In an item-set time series, each observed data value is a set of discrete items. We formalize the concept of an item-set time series and present efficient algorithms for segmenting a given item-set time series. Segmentation of a time series partitions the time series into a sequence of segments where each segment is constructed by combining consecutive time points of the time series. Each segment is associated with an item set that is computed from the item sets of the time points in that segment, using a function which we call a measure function. We then define a concept called the segment difference, which measures the difference between the item set of a segment and the item sets of the time points in that segment. The segment difference values are required to construct an optimal segmentation of the time series. We describe novel and efficient algorithms to compute segment difference values for each of the measure functions described in the paper. We outline a dynamic programming based scheme to construct an optimal segmentation of the given item-set time series. We use the item-set time series segmentation techniques to analyze the temporal content of three different data sets—Enron email, stock market data, and a synthetic data set. The experimental results show that an optimal segmentation of item-set time series data captures much more temporal content than a segmentation constructed based on the number of time points in each segment, without examining the item set data at the time points, and can be used to analyze different types of temporal data.
TIME SERIES ANALYSIS USING A UNIQUE MODEL OF TRANSFORMATION
Directory of Open Access Journals (Sweden)
Goran Klepac
2007-12-01
Full Text Available REFII1 model is an authorial mathematical model for time series data mining. The main purpose of that model is to automate time series analysis, through a unique transformation model of time series. An advantage of this approach of time series analysis is the linkage of different methods for time series analysis, linking traditional data mining tools in time series, and constructing new algorithms for analyzing time series. It is worth mentioning that REFII model is not a closed system, which means that we have a finite set of methods. At first, this is a model for transformation of values of time series, which prepares data used by different sets of methods based on the same model of transformation in a domain of problem space. REFII model gives a new approach in time series analysis based on a unique model of transformation, which is a base for all kind of time series analysis. The advantage of REFII model is its possible application in many different areas such as finance, medicine, voice recognition, face recognition and text mining.
Multifractal Analysis of Aging and Complexity in Heartbeat Time Series
Muñoz D., Alejandro; Almanza V., Victor H.; del Río C., José L.
2004-09-01
Recently multifractal analysis has been used intensively in the analysis of physiological time series. In this work we apply the multifractal analysis to the study of heartbeat time series from healthy young subjects and other series obtained from old healthy subjects. We show that this multifractal formalism could be a useful tool to discriminate these two kinds of series. We used the algorithm proposed by Chhabra and Jensen that provides a highly accurate, practical and efficient method for the direct computation of the singularity spectrum. Aging causes loss of multifractality in the heartbeat time series, it means that heartbeat time series of elderly persons are less complex than the time series of young persons. This analysis reveals a new level of complexity characterized by the wide range of necessary exponents to characterize the dynamics of young people.
Ruin Probability in Linear Time Series Model
Institute of Scientific and Technical Information of China (English)
ZHANG Lihong
2005-01-01
This paper analyzes a continuous time risk model with a linear model used to model the claim process. The time is discretized stochastically using the times when claims occur, using Doob's stopping time theorem and martingale inequalities to obtain expressions for the ruin probability as well as both exponential and non-exponential upper bounds for the ruin probability for an infinite time horizon. Numerical results are included to illustrate the accuracy of the non-exponential bound.
Visibility graph network analysis of gold price time series
Long, Yu
2013-08-01
Mapping time series into a visibility graph network, the characteristics of the gold price time series and return temporal series, and the mechanism underlying the gold price fluctuation have been explored from the perspective of complex network theory. The network degree distribution characters, which change from power law to exponent law when the series was shuffled from original sequence, and the average path length characters, which change from L∼lnN into lnL∼lnN as the sequence was shuffled, demonstrate that price series and return series are both long-rang dependent fractal series. The relations of Hurst exponent to the power-law exponent of degree distribution demonstrate that the logarithmic price series is a fractal Brownian series and the logarithmic return series is a fractal Gaussian series. Power-law exponents of degree distribution in a time window changing with window moving demonstrates that a logarithmic gold price series is a multifractal series. The Power-law average clustering coefficient demonstrates that the gold price visibility graph is a hierarchy network. The hierarchy character, in light of the correspondence of graph to price fluctuation, means that gold price fluctuation is a hierarchy structure, which appears to be in agreement with Elliot’s experiential Wave Theory on stock price fluctuation, and the local-rule growth theory of a hierarchy network means that the hierarchy structure of gold price fluctuation originates from persistent, short term factors, such as short term speculation.
On correlations and fractal characteristics of time series
Vitanov, N K; Yankulova, E D; Vitanov, Nikolay K.; Sakai, kenschi; Yankulova, Elka D.
2005-01-01
Correlation analysis is convenient and frequently used tool for investigation of time series from complex systems. Recently new methods such as the multifractal detrended fluctuation analysis (MFDFA) and the wavelet transform modulus maximum method (WTMM) have been developed. By means of these methods (i) we can investigate long-range correlations in time series and (ii) we can calculate fractal spectra of these time series. But opposite to the classical tool for correlation analysis - the autocorrelation function, the newly developed tools are not applicable to all kinds of time series. The unappropriate application of MFDFA or WTMM leads to wrong results and conclusions. In this article we discuss the opportunities and risks connected to the application of the MFDFA method to time series from a random number generator and to experimentally measured time series (i) for accelerations of an agricultural tractor and (ii) for the heartbeat activity of {\\sl Drosophila melanogaster}. Our main goal is to emphasize ...
Non-parametric causal inference for bivariate time series
McCracken, James M
2015-01-01
We introduce new quantities for exploratory causal inference between bivariate time series. The quantities, called penchants and leanings, are computationally straightforward to apply, follow directly from assumptions of probabilistic causality, do not depend on any assumed models for the time series generating process, and do not rely on any embedding procedures; these features may provide a clearer interpretation of the results than those from existing time series causality tools. The penchant and leaning are computed based on a structured method for computing probabilities.
Intrusion Detection Forecasting Using Time Series for Improving Cyber Defence
Abdullah, Azween Bin; Pillai, Thulasyammal Ramiah; Cai, Long Zheng
2015-01-01
The strength of time series modeling is generally not used in almost all current intrusion detection and prevention systems. By having time series models, system administrators will be able to better plan resource allocation and system readiness to defend against malicious activities. In this paper, we address the knowledge gap by investigating the possible inclusion of a statistical based time series modeling that can be seamlessly integrated into existing cyber defense system. Cyber-attack ...
Power-weighted densities for time series data
McCarthy, Daniel M.; Jensen, Shane T.
2016-01-01
While time series prediction is an important, actively studied problem, the predictive accuracy of time series models is complicated by non-stationarity. We develop a fast and effective approach to allow for non-stationarity in the parameters of a chosen time series model. In our power-weighted density (PWD) approach, observations in the distant past are down-weighted in the likelihood function relative to more recent observations, while still giving the practitioner control over the choice o...
Efficient use of correlation entropy for analysing time series data
Indian Academy of Sciences (India)
K P Harikrishnan; R Misra; G Ambika
2009-02-01
The correlation dimension 2 and correlation entropy 2 are both important quantifiers in nonlinear time series analysis. However, use of 2 has been more common compared to 2 as a discriminating measure. One reason for this is that 2 is a static measure and can be easily evaluated from a time series. However, in many cases, especially those involving coloured noise, 2 is regarded as a more useful measure. Here we present an efficient algorithmic scheme to compute 2 directly from a time series data and show that 2 can be used as a more effective measure compared to 2 for analysing practical time series involving coloured noise.
Interpretable Early Classification of Multivariate Time Series
Ghalwash, Mohamed F.
2013-01-01
Recent advances in technology have led to an explosion in data collection over time rather than in a single snapshot. For example, microarray technology allows us to measure gene expression levels in different conditions over time. Such temporal data grants the opportunity for data miners to develop algorithms to address domain-related problems,…
Time Series Properties of Expectation Biases
Kinari, Yusuke
2011-01-01
This study exammes time senes properties of expectation biases usmg a highfrequency survey on stock price forecasts, which required participants to forecast the Nikkei 225 over three forecasting horizons: one day, one week, and one month ahead. Constructing proxies for overconfidence and optimism as the expectation biases, this study shows that overconfidence is likely to remain stable over time while optimism is not. Moreover, a relationship exists between optimism and stock price movement, ...
Studies on time series applications in environmental sciences
Bărbulescu, Alina
2016-01-01
Time series analysis and modelling represent a large study field, implying the approach from the perspective of the time and frequency, with applications in different domains. Modelling hydro-meteorological time series is difficult due to the characteristics of these series, as long range dependence, spatial dependence, the correlation with other series. Continuous spatial data plays an important role in planning, risk assessment and decision making in environmental management. In this context, in this book we present various statistical tests and modelling techniques used for time series analysis, as well as applications to hydro-meteorological series from Dobrogea, a region situated in the south-eastern part of Romania, less studied till now. Part of the results are accompanied by their R code. .
Volatility modeling of rainfall time series
Yusof, Fadhilah; Kane, Ibrahim Lawal
2013-07-01
Networks of rain gauges can provide a better insight into the spatial and temporal variability of rainfall, but they tend to be too widely spaced for accurate estimates. A way to estimate the spatial variability of rainfall between gauge points is to interpolate between them. This paper evaluates the spatial autocorrelation of rainfall data in some locations in Peninsular Malaysia using geostatistical technique. The results give an insight on the spatial variability of rainfall in the area, as such, two rain gauges were selected for an in-depth study of the temporal dependence of the rainfall data-generating process. It could be shown that rainfall data are affected by nonlinear characteristics of the variance often referred to as variance clustering or volatility, where large changes tend to follow large changes and small changes tend to follow small changes. The autocorrelation structure of the residuals and the squared residuals derived from autoregressive integrated moving average (ARIMA) models were inspected, the residuals are uncorrelated but the squared residuals show autocorrelation, and the Ljung-Box test confirmed the results. A test based on the Lagrange multiplier principle was applied to the squared residuals from the ARIMA models. The results of this auxiliary test show a clear evidence to reject the null hypothesis of no autoregressive conditional heteroskedasticity (ARCH) effect. Hence, it indicates that generalized ARCH (GARCH) modeling is necessary. An ARIMA error model is proposed to capture the mean behavior and a GARCH model for modeling heteroskedasticity (variance behavior) of the residuals from the ARIMA model. Therefore, the composite ARIMA-GARCH model captures the dynamics of daily rainfall in the study area. On the other hand, seasonal ARIMA model became a suitable model for the monthly average rainfall series of the same locations treated.
Recovery of the Time-Evolution Equation of Time-Delay Systems from Time Series
Bünner, M J; Kittel, A; Parisi, J; Meyer, Th.
1997-01-01
We present a method for time series analysis of both, scalar and nonscalar time-delay systems. If the dynamics of the system investigated is governed by a time-delay induced instability, the method allows to determine the delay time. In a second step, the time-delay differential equation can be recovered from the time series. The method is a generalization of our recently proposed method suitable for time series analysis of {\\it scalar} time-delay systems. The dynamics is not required to be settled on its attractor, which also makes transient motion accessible to the analysis. If the motion actually takes place on a chaotic attractor, the applicability of the method does not depend on the dimensionality of the chaotic attractor - one main advantage over all time series analysis methods known until now. For demonstration, we analyze time series, which are obtained with the help of the numerical integration of a two-dimensional time-delay differential equation. After having determined the delay time, we recover...
Fitting dynamic fator models to nonstationary time series
Eichler, M.; Motta, Giovanni; Von Sachs, Rainer
2008-01-01
Factor modelling of a large time series panel has widely proven useful to reduce its cross-sectional dimensionality. This is done by explaining common co-movements in the panel through the existence of a small number of common components, up to some idiosyncratic behaviour of each individual series. To capture serial correlation in the common components, a dynamic structure is used as in traditional (uni- or multivariate) time series analysis of second order structure,i.e. allowing f...
Fitting dynamic factor models to non-stationary time series
Eichler Michael; Motta Giovanni; Sachs Rainer von
2009-01-01
Factor modelling of a large time series panel has widely proven useful to reduce its cross-sectional dimensionality. This is done by explaining common co-movements in the panel through the existence of a small number of common components, up to some idiosyncratic behaviour of each individual series. To capture serial correlation in the common components, a dynamic structure is used as in traditional (uni- or multivariate) time series analysis of second order structure, i.e. allowing for infin...
Time series prediction using wavelet process neural network
Institute of Scientific and Technical Information of China (English)
Ding Gang; Zhong Shi-Sheng; Li Yang
2008-01-01
In the real world, the inputs of many complicated systems are time-varying functions or processes. In order to predict the outputs of these systems with high speed and accuracy, this paper proposes a time series prediction model based on the wavelet process neural network, and develops the corresponding learning algorithm based on the expansion of the orthogonal basis functions. The effectiveness of the proposed time series prediction model and its learning algorithm is proved by the Mackey-Glass time series prediction, and the comparative prediction results indicate that the proposed time series prediction model based on the wavelet process neural network seems to perform well and appears suitable for using as a good tool to predict the highly complex nonlinear time series.
Robust Forecasting of Non-Stationary Time Series
Croux, C.; Fried, R.; Gijbels, I.; Mahieu, K.
2010-01-01
This paper proposes a robust forecasting method for non-stationary time series. The time series is modelled using non-parametric heteroscedastic regression, and fitted by a localized MM-estimator, combining high robustness and large efficiency. The proposed method is shown to produce reliable foreca
A Computer Evolution in Teaching Undergraduate Time Series
Hodgess, Erin M.
2004-01-01
In teaching undergraduate time series courses, we have used a mixture of various statistical packages. We have finally been able to teach all of the applied concepts within one statistical package; R. This article describes the process that we use to conduct a thorough analysis of a time series. An example with a data set is provided. We compare…
Two-fractal overlap time series: Earthquakes and market crashes
Indian Academy of Sciences (India)
Bikas K Chakrabarti; Arnab Chatterjee; Pratip Bhattacharyya
2008-08-01
We find prominent similarities in the features of the time series for the (model earthquakes or) overlap of two Cantor sets when one set moves with uniform relative velocity over the other and time series of stock prices. An anticipation method for some of the crashes have been proposed here, based on these observations.
Stata: The language of choice for time series analysis?
Christopher F. Baum
2004-01-01
This paper discusses the use of Stata for the analysis of time series and panel data. The evolution of time-series capabilities in Stata is reviewed. Facilities for data management, graphics, and econometric analysis from both official Stata and the user community are discussed. A new routine to provide moving-window regression estimates, rollreg, is described, and its use illustrated.
Parameterizing unconditional skewness in models for financial time series
DEFF Research Database (Denmark)
He, Changli; Silvennoinen, Annastiina; Teräsvirta, Timo
In this paper we consider the third-moment structure of a class of time series models. It is often argued that the marginal distribution of financial time series such as returns is skewed. Therefore it is of importance to know what properties a model should possess if it is to accommodate...
Using Time-Series Regression to Predict Academic Library Circulations.
Brooks, Terrence A.
1984-01-01
Four methods were used to forecast monthly circulation totals in 15 midwestern academic libraries: dummy time-series regression, lagged time-series regression, simple average (straight-line forecasting), monthly average (naive forecasting). In tests of forecasting accuracy, dummy regression method and monthly mean method exhibited smallest average…
Two Fractal Overlap Time Series: Earthquakes and Market Crashes
Chakrabarti, Bikas K.; Arnab Chatterjee; Pratip Bhattacharyya
2007-01-01
We find prominent similarities in the features of the time series for the (model earthquakes or) overlap of two Cantor sets when one set moves with uniform relative velocity over the other and time series of stock prices. An anticipation method for some of the crashes have been proposed here, based on these observations.
Reprocessed height time series for GPS stations
S. Rudenko; Schön, N.; Uhlemann, M; G. Gendt
2013-01-01
Precise weekly positions of 403 Global Positioning System (GPS) stations located worldwide are obtained by reprocessing GPS data of these stations for the time span from 4 January 1998 until 29 December 2007. The processing algorithms and models used as well as the solution and results obtained are presented. Vertical velocities of 266 GPS stations having a tracking history longer than 2.5 yr are computed; 107 of them are GPS stations located at tide gauges (TIGA observing stations). The vert...
Using wavelets for time series forecasting: Does it pay off?
Schlüter, Stephan; Deuschle, Carola
2010-01-01
By means of wavelet transform a time series can be decomposed into a time dependent sum of frequency components. As a result we are able to capture seasonalities with time-varying period and intensity, which nourishes the belief that incorporating the wavelet transform in existing forecasting methods can improve their quality. The article aims to verify this by comparing the power of classical and wavelet based techniques on the basis of four time series, each of them having individual charac...
Time-Series Photometric Surveys: Some Musings
Howell, S. B.
We live in the era of large astronomical surveys aimed at collecting high photometric precision, high time resolution, and long term (near) continuous observations. Such surveys discover many variable sources and their study has led to new paradigms in observational astronomy. Periodic variables have a long and venerable history in astronomy being highly useful as distance ladders, to investigate stellar interior physics and to map out Galactic structure. However, typically less than 10% of all variable sources are periodic and a detailed understanding of the majority of variables, the non-periodic sources, is lacking. What can we learn from non-periodic variables? Are there alternative techniques or types of study that may help elucidate their true nature? This talk will attempt to provide a short review of our understanding of variable sources and provide some suggestions for a methodology toward the study of non-variable astronomical sources.
Useful Pattern Mining on Time Series
DEFF Research Database (Denmark)
Goumatianos, Nikitas; Christou, Ioannis T; Lindgren, Peter
2013-01-01
We present the architecture of a “useful pattern” mining system that is capable of detecting thousands of different candlestick sequence patterns at the tick or any higher granularity levels. The system architecture is highly distributed and performs most of its highly compute-intensive aggregation......% or higher increase (or, alternatively, decrease) in a chosen property of the stock (e.g. close-value) within a given time-window (e.g. 5 days). Initial results from a first prototype implementation of the architecture show that after training on a large set of stocks, the system is capable of finding...... a significant number of candlestick sequences whose output signals (measured against an unseen set of stocks) have predictive accuracy which varies between 60% and 95% depended on the type of pattern....
Interactive analysis of gappy bivariate time series using AGSS
Lewis, Peter A.W.; Ray, Bonnie K.
1992-01-01
Bivariate time series which display nonstationary behavior, such as cycles or long-term trends, are common in fields such as oceanography and meteorology. These are usually very large-scale data sets and often may contain long gaps of missing values in one or both series, with the gaps perhaps occurring at different time periods in the two series. We present a simplified but effective method of interactively examining and filling in the missing values in such series using extensions of the me...
Comparison of New and Old Sunspot Number Time Series
Cliver, E. W.
2016-06-01
Four new sunspot number time series have been published in this Topical Issue: a backbone-based group number in Svalgaard and Schatten (Solar Phys., 2016; referred to here as SS, 1610 - present), a group number series in Usoskin et al. (Solar Phys., 2016; UEA, 1749 - present) that employs active day fractions from which it derives an observational threshold in group spot area as a measure of observer merit, a provisional group number series in Cliver and Ling (Solar Phys., 2016; CL, 1841 - 1976) that removed flaws in the Hoyt and Schatten (Solar Phys. 179, 189, 1998a; 181, 491, 1998b) normalization scheme for the original relative group sunspot number ( RG, 1610 - 1995), and a corrected Wolf (international, RI) number in Clette and Lefèvre (Solar Phys., 2016; SN, 1700 - present). Despite quite different construction methods, the four new series agree well after about 1900. Before 1900, however, the UEA time series is lower than SS, CL, and SN, particularly so before about 1885. Overall, the UEA series most closely resembles the original RG series. Comparison of the UEA and SS series with a new solar wind B time series (Owens et al. in J. Geophys. Res., 2016; 1845 - present) indicates that the UEA time series is too low before 1900. We point out incongruities in the Usoskin et al. (Solar Phys., 2016) observer normalization scheme and present evidence that this method under-estimates group counts before 1900. In general, a correction factor time series, obtained by dividing an annual group count series by the corresponding yearly averages of raw group counts for all observers, can be used to assess the reliability of new sunspot number reconstructions.
Application of p-adic analysis to time series
Khrennikov, A. Yu.; Kozyrev, S. V.; Oleschko, K. (collab.); Jaramillo, A. G.; Lopez, M. de Jesus Correa
2013-01-01
Time series defined by a p-adic pseudo-differential equation is investigated using the expansion of the time series over p-adic wavelets. Quadratic correlation function is computed. This correlation function shows a degree--like behavior and is locally constant for some time periods. It is natural to apply this kind of models for the investigation of avalanche processes and punctuated equilibrium as well as fractal-like analysis of time series generated by measurement of pressure in oil wells.
Time series analysis and inverse theory for geophysicists
Institute of Scientific and Technical Information of China (English)
Junzo Kasahara
2006-01-01
@@ Thanks to the advances in geophysical measurement technologies, most geophysical data are now recorded in digital form. But to extract the ‘Earth's nature’ from observed data, it is necessary to apply the signal-processing method to the time-series data, seismograms and geomagnetic records being the most common. The processing of time-series data is one of the major subjects of this book.By the processing of time series data, numerical values such as travel-times are obtained.The first stage of data analysis is forward modeling, but the more advanced step is the inversion method. This is the second subject of this book.
Performance of multifractal detrended fluctuation analysis on short time series
Lopez, Juan Luis
2013-01-01
The performance of the multifractal detrended analysis on short time series is evaluated for synthetic samples of several mono- and multifractal models. The reconstruction of the generalized Hurst exponents is used to determine the range of applicability of the method and the precision of its results as a function of the decreasing length of the series. As an application the series of the daily exchange rate between the U.S. dollar and the euro is studied.
Database for Hydrological Time Series of Inland Waters (DAHITI)
Schwatke, Christian; Dettmering, Denise
2016-04-01
Satellite altimetry was designed for ocean applications. However, since some years, satellite altimetry is also used over inland water to estimate water level time series of lakes, rivers and wetlands. The resulting water level time series can help to understand the water cycle of system earth and makes altimetry to a very useful instrument for hydrological applications. In this poster, we introduce the "Database for Hydrological Time Series of Inland Waters" (DAHITI). Currently, the database contains about 350 water level time series of lakes, reservoirs, rivers, and wetlands which are freely available after a short registration process via http://dahiti.dgfi.tum.de. In this poster, we introduce the product of DAHITI and the functionality of the DAHITI web service. Furthermore, selected examples of inland water targets are presented in detail. DAHITI provides time series of water level heights of inland water bodies and their formal errors . These time series are available within the period of 1992-2015 and have varying temporal resolutions depending on the data coverage of the investigated water body. The accuracies of the water level time series depend mainly on the extent of the investigated water body and the quality of the altimeter measurements. Hereby, an external validation with in-situ data reveals RMS differences between 5 cm and 40 cm for lakes and 10 cm and 140 cm for rivers, respectively.
Piecewise Trend Approximation: A Ratio-Based Time Series Representation
Directory of Open Access Journals (Sweden)
Jingpei Dan
2013-01-01
Full Text Available A time series representation, piecewise trend approximation (PTA, is proposed to improve efficiency of time series data mining in high dimensional large databases. PTA represents time series in concise form while retaining main trends in original time series; the dimensionality of original data is therefore reduced, and the key features are maintained. Different from the representations that based on original data space, PTA transforms original data space into the feature space of ratio between any two consecutive data points in original time series, of which sign and magnitude indicate changing direction and degree of local trend, respectively. Based on the ratio-based feature space, segmentation is performed such that each two conjoint segments have different trends, and then the piecewise segments are approximated by the ratios between the first and last points within the segments. To validate the proposed PTA, it is compared with classical time series representations PAA and APCA on two classical datasets by applying the commonly used K-NN classification algorithm. For ControlChart dataset, PTA outperforms them by 3.55% and 2.33% higher classification accuracy and 8.94% and 7.07% higher for Mixed-BagShapes dataset, respectively. It is indicated that the proposed PTA is effective for high dimensional time series data mining.
Forecasting Compositional Time Series with Exponential Smoothing Methods
Anne B. Koehler; Ralph D Snyder; J Keith Ord; Adrian Beaumont
2010-01-01
Compositional time series are formed from measurements of proportions that sum to one in each period of time. We might be interested in forecasting the proportion of home loans that have adjustable rates, the proportion of nonagricultural jobs in manufacturing, the proportion of a rock's geochemical composition that is a specific oxide, or the proportion of an election betting market choosing a particular candidate. A problem may involve many related time series of proportions. There could be...
Image-Based Learning Approach Applied to Time Series Forecasting
J. C. Chimal-Eguía; K. Ramírez-Amáro
2012-01-01
In this paper, a new learning approach based on time-series image information is presented. In order to implementthis new learning technique, a novel time-series input data representation is also defined. This input data representation is based on information obtained by image axis division into boxes. The difference between this new input data representation and the classical is that this technique is not time-dependent. This new information is implemented in the new Image-Based Learning A...
Artificial neural networks applied to forecasting time series
Montaño Moreno, Juan José; Palmer Pol, Alfonso; Muñoz Gracia, María del Pilar
2011-01-01
This study offers a description and comparison of the main models of Artificial Neural Networks (ANN) which have proved to be useful in time series forecasting, and also a standard procedure for the practical application of ANN in this type of task. The Multilayer Perceptron (MLP), Radial Base Function (RBF), Generalized Regression Neural Network (GRNN), and Recurrent Neural Network (RNN) models are analyzed. With this aim in mind, we use a time series made up of 244 time points. A comparativ...
Analysis of multidimensional geophysical monitoring time series for earthquake prediction
Lyubushin, A. A.
1999-01-01
A method is presented for detection of synchronous signals in multidimensional time series data. It is based on estimation of eigenvalues of spectral matrices and canonical coherences in moving time windows and extraction of an aggregated signal (a scalar signal, which accumulates in its own variations only those spectral components which are present simultaneously in each scalar time series). It is known that an increase in the collective behavior of the components of some systems and an enl...
Detecting temporal and spatial correlations in pseudoperiodic time series
Zhang, Jie; Luo, Xiaodong; Nakamura, Tomomichi; Sun, Junfeng; Small, Michael
2007-01-01
Recently there has been much attention devoted to exploring the complicated possibly chaotic dynamics in pseudoperiodic time series. Two methods [Zhang , Phys. Rev. E 73, 016216 (2006); Zhang and Small, Phys. Rev. Lett. 96, 238701 (2006)] have been forwarded to reveal the chaotic temporal and spatial correlations, respectively, among the cycles in the time series. Both these methods treat the cycle as the basic unit and design specific statistics that indicate the presence of chaotic dynamics. In this paper, we verify the validity of these statistics to capture the chaotic correlation among cycles by using the surrogate data method. In particular, the statistics computed for the original time series are compared with those from its surrogates. The surrogate data we generate is pseudoperiodic type (PPS), which preserves the inherent periodic components while destroying the subtle nonlinear (chaotic) structure. Since the inherent chaotic correlations among cycles, either spatial or temporal (which are suitably characterized by the proposed statistics), are eliminated through the surrogate generation process, we expect the statistics from the surrogate to take significantly different values than those from the original time series. Hence the ability of the statistics to capture the chaotic correlation in the time series can be validated. Application of this procedure to both chaotic time series and real world data clearly demonstrates the effectiveness of the statistics. We have found clear evidence of chaotic correlations among cycles in human electrocardiogram and vowel time series. Furthermore, we show that this framework is more sensitive to examine the subtle changes in the dynamics of the time series due to the match between PPS surrogate and the statistics adopted. It offers a more reliable tool to reveal the possible correlations among cycles intrinsic to the chaotic nature of the pseudoperiodic time series.
Investigating effects in GNSS station coordinate time series
Haritonova, Diana; Balodis, Janis; Janpaule, Inese
2014-01-01
The vertical and horizontal displacements of the Earth can be measured to a high degree of precision using GNSS. Time series of Latvian GNSS station positions of both the EUPOS®-Riga and LatPos networks have been developed at the Institute of Geodesy and Geoinformation of the University of Latvia (LU GGI). In this study the main focus is made on the noise analysis of the obtained time series and site displacement identification. The results of time series have been analysed and distinctive be...
Analysis of complex time series using refined composite multiscale entropy
Energy Technology Data Exchange (ETDEWEB)
Wu, Shuen-De; Wu, Chiu-Wen [Department of Mechatronic Technology, National Taiwan Normal University, Taipei 10610, Taiwan (China); Lin, Shiou-Gwo [Department of Communications, Navigation and Control Engineering, National Taiwan Ocean University, Keelung 20224, Taiwan (China); Lee, Kung-Yen [Department of Engineering Science and Ocean Engineering, National Taiwan University, Taipei 10617, Taiwan (China); Peng, Chung-Kang [College of Health Sciences and Technology, National Central University, Chung-Li 32001, Taiwan (China); Division of Interdisciplinary Medicine and Biotechnology, Beth Israel Deaconess Medical Center/Harvard Medical School, Boston (United States)
2014-04-01
Multiscale entropy (MSE) is an effective algorithm for measuring the complexity of a time series that has been applied in many fields successfully. However, MSE may yield an inaccurate estimation of entropy or induce undefined entropy because the coarse-graining procedure reduces the length of a time series considerably at large scales. Composite multiscale entropy (CMSE) was recently proposed to improve the accuracy of MSE, but it does not resolve undefined entropy. Here we propose a refined composite multiscale entropy (RCMSE) to improve CMSE. For short time series analyses, we demonstrate that RCMSE increases the accuracy of entropy estimation and reduces the probability of inducing undefined entropy.
On the detection of superdiffusive behaviour in time series
Gottwald, Georg A
2016-01-01
We present a new method for detecting superdiffusive behaviour and for determining rates of superdiffusion in time series data. Our method applies equally to stochastic and deterministic time series data and relies on one realisation (ie one sample path) of the process. Linear drift effects are automatically removed without any preprocessing. We show numerical results for time series constructed from i.i.d. $\\alpha$-stable random variables and from deterministic weakly chaotic maps. We compare our method with the standard method of estimating the growth rate of the mean-square displacement as well as the $p$-variation method.
Estimation of connectivity measures in gappy time series
Papadopoulos, G
2015-01-01
A new method is proposed to compute connectivity measures on multivariate time series with gaps. Rather than removing or filling the gaps, the rows of the joint data matrix containing empty entries are removed and the calculations are done on the remainder matrix. The method, called measure adapted gap removal (MAGR), can be applied to any connectivity measure that uses a joint data matrix, such as cross correlation, cross mutual information and transfer entropy. MAGR is favorably compared using these three measures to a number of known gap-filling techniques, as well as the gap closure. The superiority of MAGR is illustrated on time series from synthetic systems and financial time series.
Segmentation of Nonstationary Time Series with Geometric Clustering
DEFF Research Database (Denmark)
Bocharov, Alexei; Thiesson, Bo
2013-01-01
We introduce a non-parametric method for segmentation in regimeswitching time-series models. The approach is based on spectral clustering of target-regressor tuples and derives a switching regression tree, where regime switches are modeled by oblique splits. Such models can be learned efficiently...... from data, where clustering is used to propose one single split candidate at each split level. We use the class of ART time series models to serve as illustration, but because of the non-parametric nature of our segmentation approach, it readily generalizes to a wide range of time-series models that go...
Multivariate time series analysis with R and financial applications
Tsay, Ruey S
2013-01-01
Since the publication of his first book, Analysis of Financial Time Series, Ruey Tsay has become one of the most influential and prominent experts on the topic of time series. Different from the traditional and oftentimes complex approach to multivariate (MV) time series, this sequel book emphasizes structural specification, which results in simplified parsimonious VARMA modeling and, hence, eases comprehension. Through a fundamental balance between theory and applications, the book supplies readers with an accessible approach to financial econometric models and their applications to real-worl
Multi-dimensional sparse time series: feature extraction
Franciosi, Marco
2008-01-01
We show an analysis of multi-dimensional time series via entropy and statistical linguistic techniques. We define three markers encoding the behavior of the series, after it has been translated into a multi-dimensional symbolic sequence. The leading component and the trend of the series with respect to a mobile window analysis result from the entropy analysis and label the dynamical evolution of the series. The diversification formalizes the differentiation in the use of recurrent patterns, from a Zipf law point of view. These markers are the starting point of further analysis such as classification or clustering of large database of multi-dimensional time series, prediction of future behavior and attribution of new data. We also present an application to economic data. We deal with measurements of money investments of some business companies in advertising market for different media sources.
Fast and Flexible Multivariate Time Series Subsequence Search
National Aeronautics and Space Administration — Multivariate Time-Series (MTS) are ubiquitous, and are generated in areas as disparate as sensor recordings in aerospace systems, music and video streams, medical...
Phenotyping of Clinical Time Series with LSTM Recurrent Neural Networks
Lipton, Zachary C.; Kale, David C.; Wetzell, Randall C.
2015-01-01
We present a novel application of LSTM recurrent neural networks to multilabel classification of diagnoses given variable-length time series of clinical measurements. Our method outperforms a strong baseline on a variety of metrics.
A mixed time series model of binomial counts
Khoo, Wooi Chen; Ong, Seng Huat
2015-10-01
Continuous time series modelling has been an active research in the past few decades. However, time series data in terms of correlated counts appear in many situations such as the counts of rainy days and access downloading. Therefore, the study on count data has become popular in time series modelling recently. This article introduces a new mixture model, which is an univariate non-negative stationary time series model with binomial marginal distribution, arising from the combination of the well-known binomial thinning and Pegram's operators. A brief review of important properties will be carried out and the EM algorithm is applied in parameter estimation. A numerical study is presented to show the performance of the model. Finally, a potential real application will be presented to illustrate the advantage of the new mixture model.
Lagrangian Time Series Models for Ocean Surface Drifter Trajectories
Sykulski, Adam M; Lilly, Jonathan M; Danioux, Eric
2016-01-01
This paper proposes stochastic models for the analysis of ocean surface trajectories obtained from freely-drifting satellite-tracked instruments. The proposed time series models are used to summarise large multivariate datasets and infer important physical parameters of inertial oscillations and other ocean processes. Nonstationary time series methods are employed to account for the spatiotemporal variability of each trajectory. Because the datasets are large, we construct computationally efficient methods through the use of frequency-domain modelling and estimation, with the data expressed as complex-valued time series. We detail how practical issues related to sampling and model misspecification may be addressed using semi-parametric techniques for time series, and we demonstrate the effectiveness of our stochastic models through application to both real-world data and to numerical model output.
AFSC/ABL: Naknek sockeye salmon scale time series
National Oceanic and Atmospheric Administration, Department of Commerce — A time series of scale samples (1956 2002) collected from adult sockeye salmon returning to Naknek River were retrieved from the Alaska Department of Fish and Game....
AFSC/ABL: Ugashik sockeye salmon scale time series
National Oceanic and Atmospheric Administration, Department of Commerce — A time series of scale samples (1956 b?? 2002) collected from adult sockeye salmon returning to Ugashik River were retrieved from the Alaska Department of Fish and...
The Ohio economy: using time series characteristics in forecasting
James G. Hoehn; James J. Balazsy
1985-01-01
The premise of this study is that the regional economist can better understand the Ohio economy by studying the properties of important Ohio time series that can be identified and quantified through simple regression methods.
Residual diagnostics for cross-section time series regression models
Baum, Christopher F
2001-01-01
These routines support the diagnosis of groupwise heteroskedasticity and cross-sectional correlation in the context of a regression model fit to pooled cross-section time series (xt) data. Copyright 2001 by Stata Corporation.
Review of English textbooks in time series analysis (in Russian)
Stanislav Anatolyev
2008-01-01
This is a survey of most notable time series econometrics texts written in English. The essay reflects the author's opinion, as well as opinions of econometricians expressed in published book reviews.
A Matlab Code for Univariate Time Series Forecasting
Shapour Mohammadi; Hossein Abbasi- Nejad
2005-01-01
This M-File forecasts univariate time series such as stock prices with a feedforward neural networks. It finds best (minimume RMSE) network automatically and uses early stopping method for solving overfitting problem.
Effect of two dead times in series on coincidence measurements
Energy Technology Data Exchange (ETDEWEB)
Funck, E.
1987-01-01
Dead times in series occur in any counting device where detector signals are electronically amplified, selected for pulse height by a discriminator (or pulse-height analyzer) and fed through a dead-time unit producing a dead time, which has very often been designed to establish definite dead time losses. The problem of two dead times in series has been treated by J.W. Muller. No attempt, however, seems to have been made up to now to investigate this problem for the electronics of a coincidence system. In the paper presented here two dead times in series are considered that are found either in one or in both channels of a coincidence system. Correction formulas with experimental evidence are given which allow the deviations from results, which were calculated by taking only one dead time per channel into account, to be estimated.
Neural Networks, Game Theory and Time Series Generation
Metzler, Richard
2002-01-01
This dissertation highlights connections between the fields of neural networks, game theory and time series generation. The concept of antipredictability is explained, and the properties of time series that are antipredictable for several prototypical prediction algorithms (neural networks, Boolean funtions etc.) are studied. The Minority Game provides a framework in which antipredictability arises naturally. Several variations of the MG are introduced and compared, including extensions to mo...
The use of synthetic input sequences in time series modeling
Energy Technology Data Exchange (ETDEWEB)
Oliveira, Dair Jose de [Programa de Pos-Graduacao em Engenharia Eletrica, Universidade Federal de Minas Gerais, Av. Antonio Carlos 6627, 31.270-901 Belo Horizonte, MG (Brazil); Letellier, Christophe [CORIA/CNRS UMR 6614, Universite et INSA de Rouen, Av. de l' Universite, BP 12, F-76801 Saint-Etienne du Rouvray cedex (France); Gomes, Murilo E.D. [Programa de Pos-Graduacao em Engenharia Eletrica, Universidade Federal de Minas Gerais, Av. Antonio Carlos 6627, 31.270-901 Belo Horizonte, MG (Brazil); Aguirre, Luis A. [Programa de Pos-Graduacao em Engenharia Eletrica, Universidade Federal de Minas Gerais, Av. Antonio Carlos 6627, 31.270-901 Belo Horizonte, MG (Brazil)], E-mail: aguirre@cpdee.ufmg.br
2008-08-04
In many situations time series models obtained from noise-like data settle to trivial solutions under iteration. This Letter proposes a way of producing a synthetic (dummy) input, that is included to prevent the model from settling down to a trivial solution, while maintaining features of the original signal. Simulated benchmark models and a real time series of RR intervals from an ECG are used to illustrate the procedure.
Stacked Heterogeneous Neural Networks for Time Series Forecasting
Directory of Open Access Journals (Sweden)
Florin Leon
2010-01-01
Full Text Available A hybrid model for time series forecasting is proposed. It is a stacked neural network, containing one normal multilayer perceptron with bipolar sigmoid activation functions, and the other with an exponential activation function in the output layer. As shown by the case studies, the proposed stacked hybrid neural model performs well on a variety of benchmark time series. The combination of weights of the two stack components that leads to optimal performance is also studied.
Model-Coupled Autoencoder for Time Series Visualisation
Gianniotis, Nikolaos; Kügler, Sven D.; Tiňo, Peter; Polsterer, Kai L.
2016-01-01
We present an approach for the visualisation of a set of time series that combines an echo state network with an autoencoder. For each time series in the dataset we train an echo state network, using a common and fixed reservoir of hidden neurons, and use the optimised readout weights as the new representation. Dimensionality reduction is then performed via an autoencoder on the readout weight representations. The crux of the work is to equip the autoencoder with a loss function that correctl...
On the prediction of stationary functional time series
Aue, A.; Norinho, DD; Hörmann, S
2012-01-01
© 2015, American Statistical Association. This article addresses the prediction of stationary functional time series. Existing contributions to this problem have largely focused on the special case of first-order functional autoregressive processes because of their technical tractability and the current lack of advanced functional time series methodology. It is shown here how standard multivariate prediction techniques can be used in this context. The connection between functional and multiva...
Trimmed Granger causality between two groups of time series
Hung, Ying-Chao; Tseng, Neng-Fang; Balakrishnan, Narayanaswamy
2014-01-01
The identification of causal effects between two groups of time series has been an important topic in a wide range of applications such as economics, engineering, medicine, neuroscience, and biology. In this paper, a simplified causal relationship (called trimmed Granger causality) based on the context of Granger causality and vector autoregressive (VAR) model is introduced. The idea is to characterize a subset of “important variables” for both groups of time series so that the underlying cau...
Time series analysis of age related cataract hospitalizations and phacoemulsification
2006-01-01
Background Cataract surgery remains a commonly performed elective surgical procedure in the aging and the elderly. The purpose of this study was to utilize time series methodology to determine the temporal and seasonal variations and the strength of the seasonality in age-related (senile) cataract hospitalizations and phacoemulsification surgeries. Methods A retrospective, cross-sectional time series analysis was used to assess the presence and strength of seasonal and temporal patterns of ag...
Gaussian Processes for Local Polynomial Forecasting of Time Series
Fendick, Kerry
2016-01-01
The samples of a signal obscured by noise constitute an example of a time series frequently encountered in applications. We consider here the feasibility of accurately forecasting the signals of multiple such time series considering jointly when the number of historic samples is inadequate for accurately forecasting the signal of each considered in isolation. We develop a new forecasting methodology based on Gaussian process regression that is successful in doing so in examples for which the ...
Time Series Estimates of the Italian Consumer Confidence Indicator
Paradiso, Antonio; Rao, B. Bhaskara; Margani, Patrizia
2011-01-01
This work shows that Italian consumer confidence indicator (CCI) is non-stationary and, therefore, can be estimated with the time series methods. It is found that a long-run relationship exists between CCI, short-term interest rate, industrial production index and the difference between perceived and measured inflation. The use of time series methods to estimate CCI for Italy is a novelty in the literature.
From Local to Global Analysis of Music Time Series
Ligges, Uwe; Weihs, Claus
2004-01-01
Local and more and more global musical structure is analyzed from audio time series by time-series-event analysis with the aim of automatic sheet music production and comparison of singers. Note events are determined and classified based on local spectra, and rules of bar events are identified based on accentuation events related to local energy. In order to compare the performances of different singers global summary measures are defined characterizing the overall performance.
Multiple Time Series Ising Model for Financial Market Simulations
International Nuclear Information System (INIS)
In this paper we propose an Ising model which simulates multiple financial time series. Our model introduces the interaction which couples to spins of other systems. Simulations from our model show that time series exhibit the volatility clustering that is often observed in the real financial markets. Furthermore we also find non-zero cross correlations between the volatilities from our model. Thus our model can simulate stock markets where volatilities of stocks are mutually correlated
Geomechanical time series and its singularity spectrum analysis
Czech Academy of Sciences Publication Activity Database
Lyubushin, Alexei A.; Kaláb, Zdeněk; Lednická, Markéta
2012-01-01
Roč. 47, č. 1 (2012), s. 69-77. ISSN 1217-8977 R&D Projects: GA ČR GA105/09/0089 Institutional research plan: CEZ:AV0Z30860518 Keywords : geomechanical time series * singularity spectrum * time series segmentation * laser distance meter Subject RIV: DC - Siesmology, Volcanology, Earth Structure Impact factor: 0.347, year: 2012 http://www.akademiai.com/content/88v4027758382225/fulltext.pdf
Time Series Classification by Class-Specific Mahalanobis Distance Measures
Prekopcsák, Zoltán; Lemire, Daniel
2010-01-01
To classify time series by nearest neighbors, we need to specify or learn one or several distance measures. We consider variations of the Mahalanobis distance measures which rely on the inverse covariance matrix of the data. Unfortunately --- for time series data --- the covariance matrix has often low rank. To alleviate this problem we can either use a pseudoinverse, covariance shrinking or limit the matrix to its diagonal. We review these alternatives and benchmark them against competitive ...
Automated Feature Design for Time Series Classification by Genetic Programming
Harvey, Dustin Yewell
2014-01-01
Time series classification (TSC) methods discover and exploit patterns in time series and other one-dimensional signals. Although many accurate, robust classifiers exist for multivariate feature sets, general approaches are needed to extend machine learning techniques to make use of signal inputs. Numerous applications of TSC can be found in structural engineering, especially in the areas of structural health monitoring and non-destructive evaluation. Additionally, the fields of process contr...
Application of a Local Polynomial Approximation Chaotic Time Series Prediction
Orzeszko, Witold
2004-01-01
Chaos theory has become a new approach to financial processes analysis. Due to complicated dynamics, chaotic time series seem to be random and, in consequence, unpredictable. In fact, unlike truly random processes, chaotic dynamics can be forecasted very precisely in a short run. In this paper, a local polynomial approximation is presented. Its efficiency, as a method of building short-term predictors of chaotic time series, has been examined. The presented method has been applied to forecast...
Adaptive Fourier Analysis For Unequally-Spaced Time Series Data
Liang, Hong
2002-01-01
Adaptive Fourier Analysis For Unequally-Spaced Time Series Data by Hong Liang Robert V. Foutz, Chairman Statistics (ABSTRACT) Fourier analysis, Walsh-Fourier analysis, and wavelet analysis have often been used in time series analysis. Fourier analysis can be used to detect periodic components that have sinusoidal shape; however, it might be misleading when the periodic components are not sinusoidal. Walsh-Fourier analysis is suitable for revealing the rectangular ...
Locally adaptive factor processes for multivariate time series
Durante, Daniele; Scarpa, Bruno; Dunson, David B
2012-01-01
In modeling multivariate time series, it is important to allow time-varying smoothness in the mean and covariance process. In particular, there may be certain time intervals exhibiting rapid changes and others in which changes are slow. If such time-varying smoothness is not accounted for, one can obtain misleading inferences and predictions, with over-smoothing across erratic time intervals and under-smoothing across times exhibiting slow variation. This can lead to mis-calibration of predic...
Time series modelling and forecasting of Sarawak black pepper price
Liew, Venus Khim-Sen; Shitan, Mahendran; Hussain, Huzaimi
2000-01-01
Pepper is an important agriculture commodity especially for the state of Sarawak. It is important to forecast its price, as this could help the policy makers in coming up with production and marketing plan to improve the Sarawak’s economy as well as the farmers’welfare. In this paper, we take up time series modelling and forecasting of the Sarawak black pepper price. Our empirical results show that Autoregressive Moving Average (ARMA) time series models fit the price series well and they have...
Time Series Analysis of Insar Data: Methods and Trends
Osmanoglu, Batuhan; Sunar, Filiz; Wdowinski, Shimon; Cano-Cabral, Enrique
2015-01-01
Time series analysis of InSAR data has emerged as an important tool for monitoring and measuring the displacement of the Earth's surface. Changes in the Earth's surface can result from a wide range of phenomena such as earthquakes, volcanoes, landslides, variations in ground water levels, and changes in wetland water levels. Time series analysis is applied to interferometric phase measurements, which wrap around when the observed motion is larger than one-half of the radar wavelength. Thus, the spatio-temporal ''unwrapping" of phase observations is necessary to obtain physically meaningful results. Several different algorithms have been developed for time series analysis of InSAR data to solve for this ambiguity. These algorithms may employ different models for time series analysis, but they all generate a first-order deformation rate, which can be compared to each other. However, there is no single algorithm that can provide optimal results in all cases. Since time series analyses of InSAR data are used in a variety of applications with different characteristics, each algorithm possesses inherently unique strengths and weaknesses. In this review article, following a brief overview of InSAR technology, we discuss several algorithms developed for time series analysis of InSAR data using an example set of results for measuring subsidence rates in Mexico City.
Time-varying parameter auto-regressive models for autocovariance nonstationary time series
Institute of Scientific and Technical Information of China (English)
无
2009-01-01
In this paper, autocovariance nonstationary time series is clearly defined on a family of time series. We propose three types of TVPAR (time-varying parameter auto-regressive) models: the full order TVPAR model, the time-unvarying order TVPAR model and the time-varying order TV-PAR model for autocovariance nonstationary time series. Related minimum AIC (Akaike information criterion) estimations are carried out.
Time-varying parameter auto-regressive models for autocovariance nonstationary time series
Institute of Scientific and Technical Information of China (English)
FEI WanChun; BAI Lun
2009-01-01
In this paper,autocovariance nonstationary time series is clearly defined on a family of time series.We propose three types of TVPAR (time-varying parameter auto-regressive) models:the full order TVPAR model,the time-unvarying order TVPAR model and the time-varying order TVPAR model for autocovariance nonstationary time series.Related minimum AIC (Akaike information criterion) estimations are carried out.
Comparison of New and Old Sunspot Number Time Series
Cliver, Edward W.; Clette, Frédéric; Lefévre, Laure; Svalgaard, Leif
2016-05-01
As a result of the Sunspot Number Workshops, five new sunspot series have recently been proposed: a revision of the original Wolf or international sunspot number (Lockwood et al., 2014), a backbone-based group sunspot number (Svalgaard and Schatten, 2016), a revised group number series that employs active day fractions (Usoskin et al., 2016), a provisional group sunspot number series (Cliver and Ling, 2016) that removes flaws in the normalization scheme for the original group sunspot number (Hoyt and Schatten,1998), and a revised Wolf or international number (termed SN) published on the SILSO website as a replacement for the original Wolf number (Clette and Lefèvre, 2016; thttp://www.sidc.be/silso/datafiles). Despite quite different construction methods, the five new series agree reasonably well after about 1900. From 1750 to ~1875, however, the Lockwood et al. and Usoskin et al. time series are lower than the other three series. Analysis of the Hoyt and Schatten normalization factors used to scale secondary observers to their Royal Greenwich Observatory primary observer reveals a significant inhomogeneity spanning the divergence in ~1885 of the group number from the original Wolf number. In general, a correction factor time series, obtained by dividing an annual group count series by the corresponding yearly averages of raw group counts for all observers, can be used to assess the reliability of new sunspot number reconstructions.
Symplectic geometry spectrum regression for prediction of noisy time series
Xie, Hong-Bo; Dokos, Socrates; Sivakumar, Bellie; Mengersen, Kerrie
2016-05-01
We present the symplectic geometry spectrum regression (SGSR) technique as well as a regularized method based on SGSR for prediction of nonlinear time series. The main tool of analysis is the symplectic geometry spectrum analysis, which decomposes a time series into the sum of a small number of independent and interpretable components. The key to successful regularization is to damp higher order symplectic geometry spectrum components. The effectiveness of SGSR and its superiority over local approximation using ordinary least squares are demonstrated through prediction of two noisy synthetic chaotic time series (Lorenz and Rössler series), and then tested for prediction of three real-world data sets (Mississippi River flow data and electromyographic and mechanomyographic signal recorded from human body).
Similarity estimators for irregular and age uncertain time series
Directory of Open Access Journals (Sweden)
K. Rehfeld
2013-09-01
Full Text Available Paleoclimate time series are often irregularly sampled and age uncertain, which is an important technical challenge to overcome for successful reconstruction of past climate variability and dynamics. Visual comparison and interpolation-based linear correlation approaches have been used to infer dependencies from such proxy time series. While the first is subjective, not measurable and not suitable for the comparison of many datasets at a time, the latter introduces interpolation bias, and both face difficulties if the underlying dependencies are nonlinear. In this paper we investigate similarity estimators that could be suitable for the quantitative investigation of dependencies in irregular and age uncertain time series. We compare the Gaussian-kernel based cross correlation (gXCF, Rehfeld et al., 2011 and mutual information (gMI, Rehfeld et al., 2013 against their interpolation-based counterparts and the new event synchronization function (ESF. We test the efficiency of the methods in estimating coupling strength and coupling lag numerically, using ensembles of synthetic stalagmites with short, autocorrelated, linear and nonlinearly coupled proxy time series, and in the application to real stalagmite time series. In the linear test case coupling strength increases are identified consistently for all estimators, while in the nonlinear test case the correlation-based approaches fail. The lag at which the time series are coupled is identified correctly as the maximum of the similarity functions in around 60–55% (in the linear case to 53–42% (for the nonlinear processes of the cases when the dating of the synthetic stalagmite is perfectly precise. If the age uncertainty increases beyond 5% of the time series length, however, the true coupling lag is not identified more often than the others for which the similarity function was estimated. Age uncertainty contributes up to half of the uncertainty in the similarity estimation process. Time
Detection of flood events in hydrological discharge time series
Seibert, S. P.; Ehret, U.
2012-04-01
The shortcomings of mean-squared-error (MSE) based distance metrics are well known (Beran 1999, Schaeffli & Gupta 2007) and the development of novel distance metrics (Pappenberger & Beven 2004, Ehret & Zehe 2011) and multi-criteria-approaches enjoy increasing popularity (Reusser 2009, Gupta et al. 2009). Nevertheless, the hydrological community still lacks metrics which identify and thus, allow signature based evaluations of hydrological discharge time series. Signature based information/evaluations are required wherever specific time series features, such as flood events, are of special concern. Calculation of event based runoff coefficients or precise knowledge on flood event characteristics (like onset or duration of rising limp or the volume of falling limp, etc.) are possible applications. The same applies for flood forecasting/simulation models. Directly comparing simulated and observed flood event features may reveal thorough insights into model dynamics. Compared to continuous space-and-time-aggregated distance metrics, event based evaluations may provide answers like the distributions of event characteristics or the percentage of the events which were actually reproduced by a hydrological model. It also may help to provide information on the simulation accuracy of small, medium and/or large events in terms of timing and magnitude. However, the number of approaches which expose time series features is small and their usage is limited to very specific questions (Merz & Blöschl 2009, Norbiato et al. 2009). We believe this is due to the following reasons: i) a generally accepted definition of the signature of interest is missing or difficult to obtain (in our case: what makes a flood event a flood event?) and/or ii) it is difficult to translate such a definition into a equation or (graphical) procedure which exposes the feature of interest in the discharge time series. We reviewed approaches which detect event starts and/or ends in hydrological discharge time
Wavelet matrix transform for time-series similarity measurement
Institute of Scientific and Technical Information of China (English)
HU Zhi-kun; XU Fei; GUI Wei-hua; YANG Chun-hua
2009-01-01
A time-series similarity measurement method based on wavelet and matrix transform was proposed, and its anti-noise ability, sensitivity and accuracy were discussed. The time-series sequences were compressed into wavelet subspace, and sample feature vector and orthogonal basics of sample time-series sequences were obtained by K-L transform. Then the inner product transform was carried out to project analyzed time-series sequence into orthogonal basics to gain analyzed feature vectors. The similarity was calculated between sample feature vector and analyzed feature vector by the Euclid distance. Taking fault wave of power electronic devices for example, the experimental results show that the proposed method has low dimension of feature vector, the anti-noise ability of proposed method is 30 times as large as that of plain wavelet method, the sensitivity of proposed method is 1/3 as large as that of plain wavelet method, and the accuracy of proposed method is higher than that of the wavelet singular value decomposition method. The proposed method can be applied in similarity matching and indexing for lager time series databases.
Discovering shared and individual latent structure in multiple time series
Saria, Suchi; Penn, Anna
2010-01-01
This paper proposes a nonparametric Bayesian method for exploratory data analysis and feature construction in continuous time series. Our method focuses on understanding shared features in a set of time series that exhibit significant individual variability. Our method builds on the framework of latent Diricihlet allocation (LDA) and its extension to hierarchical Dirichlet processes, which allows us to characterize each series as switching between latent ``topics'', where each topic is characterized as a distribution over ``words'' that specify the series dynamics. However, unlike standard applications of LDA, we discover the words as we learn the model. We apply this model to the task of tracking the physiological signals of premature infants; our model obtains clinically significant insights as well as useful features for supervised learning tasks.
Forecasting Compositional Time Series: A State Space Approach
Ralph D Snyder; J. Keith Ord; Anne B. Koehler; Keith R. McLaren; Adrian Beaumont
2015-01-01
A method is proposed for forecasting composite time series such as the market shares for multiple brands. Its novel feature is that it relies on multi-series adaptations of exponential smoothing combined with the log-ratio transformation for the conversion of proportions onto the real line. It is designed to produce forecasts that are both non-negative and sum to one; are invariant to the choice of the base series in the log-ratio transformation; recognized and exploit features such as serial...
Arbitrage, market definition and monitoring a time series approach
Burke, S.; Hunter, J
2012-01-01
This article considers the application to regional price data of time series methods to test stationarity, multivariate cointegration and exogeneity. The discovery of stationary price differentials in a bivariate setting implies that the series are rendered stationary by capturing a common trend and we observe through this mechanism long-run arbitrage. This is indicative of a broader market definition and efficiency. The problem is considered in relation to more than 700 weekly data points on...
Detecting structural breaks in time series via genetic algorithms
DEFF Research Database (Denmark)
Doerr, Benjamin; Fischer, Paul; Hilbert, Astrid;
2016-01-01
Detecting structural breaks is an essential task for the statistical analysis of time series, for example, for fitting parametric models to it. In short, structural breaks are points in time at which the behaviour of the time series substantially changes. Typically, no solid background knowledge of...... crossover and mutation operations for this problem, we conduct extensive experiments to determine good choices for the parameters and operators of the genetic algorithm. One surprising observation is that use of uniform and one-point crossover together gave significantly better results than using either...... crossover operator alone. Moreover, we present a specific fitness function which exploits the sparse structure of the break points and which can be evaluated particularly efficiently. The experiments on artificial and real-world time series show that the resulting algorithm detects break points with high...
Weighted statistical parameters for irregularly sampled time series
Rimoldini, Lorenzo
2014-01-01
Unevenly spaced time series are common in astronomy because of the day-night cycle, weather conditions, dependence on the source position in the sky, allocated telescope time, corrupt measurements, for example, or be inherent to the scanning law of satellites like Hipparcos and the forthcoming Gaia. This paper aims at improving the accuracy of common statistical parameters for the characterization of irregularly sampled signals. The uneven representation of time series, often including clumps of measurements and gaps with no data, can severely disrupt the values of estimators. A weighting scheme adapting to the sampling density and noise level of the signal is formulated. Its application to time series from the Hipparcos periodic catalogue led to significant improvements in the overall accuracy and precision of the estimators with respect to the unweighted counterparts and those weighted by inverse-squared uncertainties. Automated classification procedures employing statistical parameters weighted by the sugg...
Rules extraction in short memory time series using genetic algorithms
Fong, L. Y.; Szeto, K. Y.
2001-04-01
Data mining is performed using genetic algorithm on artificially generated time series data with short memory. The extraction of rules from a training set and the subsequent testing of these rules provide a basis for the predictions on the test set. The artificial time series are generated using the inverse whitening transformation, and the correlation function has an exponential form with given time constant indicative of short memory. A vector quantization technique is employed to classify the daily rate of return of this artificial time series into four categories. A simple genetic algorithm based on a fixed format of rules is introduced to do the forecasting. Comparing to the benchmark tests with random walk and random guess, genetic algorithms yield substantially better prediction rates, between 50% to 60%. This is an improvement compared with the 47% for random walk prediction and 25% for random guessing method.
A refined fuzzy time series model for stock market forecasting
Jilani, Tahseen Ahmed; Burney, Syed Muhammad Aqil
2008-05-01
Time series models have been used to make predictions of stock prices, academic enrollments, weather, road accident casualties, etc. In this paper we present a simple time-variant fuzzy time series forecasting method. The proposed method uses heuristic approach to define frequency-density-based partitions of the universe of discourse. We have proposed a fuzzy metric to use the frequency-density-based partitioning. The proposed fuzzy metric also uses a trend predictor to calculate the forecast. The new method is applied for forecasting TAIEX and enrollments’ forecasting of the University of Alabama. It is shown that the proposed method work with higher accuracy as compared to other fuzzy time series methods developed for forecasting TAIEX and enrollments of the University of Alabama.
Generalized Dynamic Factor Models for Mixed-Measurement Time Series.
Cui, Kai; Dunson, David B
2014-02-12
In this article, we propose generalized Bayesian dynamic factor models for jointly modeling mixed-measurement time series. The framework allows mixed-scale measurements associated with each time series, with different measurements having different distributions in the exponential family conditionally on time-varying latent factor(s). Efficient Bayesian computational algorithms are developed for posterior inference on both the latent factors and model parameters, based on a Metropolis Hastings algorithm with adaptive proposals. The algorithm relies on a Greedy Density Kernel Approximation (GDKA) and parameter expansion with latent factor normalization. We tested the framework and algorithms in simulated studies and applied them to the analysis of intertwined credit and recovery risk for Moody's rated firms from 1982-2008, illustrating the importance of jointly modeling mixed-measurement time series. The article has supplemental materials available online. PMID:24791133
Minimum entropy density method for the time series analysis
Lee, Jeong Won; Park, Joongwoo Brian; Jo, Hang-Hyun; Yang, Jae-Suk; Moon, Hie-Tae
2009-01-01
The entropy density is an intuitive and powerful concept to study the complicated nonlinear processes derived from physical systems. We develop the minimum entropy density method (MEDM) to detect the structure scale of a given time series, which is defined as the scale in which the uncertainty is minimized, hence the pattern is revealed most. The MEDM is applied to the financial time series of Standard and Poor’s 500 index from February 1983 to April 2006. Then the temporal behavior of structure scale is obtained and analyzed in relation to the information delivery time and efficient market hypothesis.
Multiscale entropy analysis of complex physiologic time series.
Costa, Madalena; Goldberger, Ary L; Peng, C-K
2002-08-01
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. PMID:12190613
Wavelet analysis for non-stationary, nonlinear time series
Schulte, Justin A.
2016-08-01
Methods for detecting and quantifying nonlinearities in nonstationary time series are introduced and developed. In particular, higher-order wavelet analysis was applied to an ideal time series and the quasi-biennial oscillation (QBO) time series. Multiple-testing problems inherent in wavelet analysis were addressed by controlling the false discovery rate. A new local autobicoherence spectrum facilitated the detection of local nonlinearities and the quantification of cycle geometry. The local autobicoherence spectrum of the QBO time series showed that the QBO time series contained a mode with a period of 28 months that was phase coupled to a harmonic with a period of 14 months. An additional nonlinearly interacting triad was found among modes with periods of 10, 16 and 26 months. Local biphase spectra determined that the nonlinear interactions were not quadratic and that the effect of the nonlinearities was to produce non-smoothly varying oscillations. The oscillations were found to be skewed so that negative QBO regimes were preferred, and also asymmetric in the sense that phase transitions between the easterly and westerly phases occurred more rapidly than those from westerly to easterly regimes.
The Photoplethismographic Signal Processed with Nonlinear Time Series Analysis Tools
International Nuclear Information System (INIS)
Finger photoplethismography (PPG) signals were submitted to nonlinear time series analysis. The applied analytical techniques were: (i) High degree polynomial fitting for baseline estimation; (ii) FFT analysis for estimating power spectra; (iii) fractal dimension estimation via the Higuchi's time-domain method, and (iv) kernel nonparametric estimation for reconstructing noise free-attractors and also for estimating signal's stochastic components
Sparse time series chain graphical models for reconstructing genetic networks
Abegaz, Fentaw; Wit, Ernst
2013-01-01
We propose a sparse high-dimensional time series chain graphical model for reconstructing genetic networks from gene expression data parametrized by a precision matrix and autoregressive coefficient matrix. We consider the time steps as blocks or chains. The proposed approach explores patterns of co
AMP: a new time-frequency feature extraction method for intermittent time-series data
Barrack, Duncan; Goulding, James; Hopcraft, Keith; Preston, Simon; Smith, Gavin
2015-01-01
The characterisation of time-series data via their most salient features is extremely important in a range of machine learning task, not least of all with regards to classification and clustering. While there exist many feature extraction techniques suitable for non-intermittent time-series data, these approaches are not always appropriate for intermittent time-series data, where intermittency is characterized by constant values for large periods of time punctuated by sharp and transient incr...
Real Time Clustering of Time Series Using Triangular Potentials
Directory of Open Access Journals (Sweden)
Aldo Pacchiano
2015-01-01
Full Text Available Motivated by the problem of computing investment portfolio weightin gs we investigate various methods of clustering as alternatives to traditional mean-v ariance approaches. Such methods can have significant benefits from a practical point of view since they remove the need to invert a sample covariance matrix, which can suffer from estimation error and will almost certainly be non-stationary. The general idea is to find groups of assets w hich share similar return characteristics over time and treat each group as a singl e composite asset. We then apply inverse volatility weightings to these new composite assets. In the course of our investigation we devise a method of clustering based on triangular potentials and we present as sociated theoretical results as well as various examples based on synthetic data.
Time Series Outlier Detection Based on Sliding Window Prediction
Directory of Open Access Journals (Sweden)
Yufeng Yu
2014-01-01
Full Text Available In order to detect outliers in hydrological time series data for improving data quality and decision-making quality related to design, operation, and management of water resources, this research develops a time series outlier detection method for hydrologic data that can be used to identify data that deviate from historical patterns. The method first built a forecasting model on the history data and then used it to predict future values. Anomalies are assumed to take place if the observed values fall outside a given prediction confidence interval (PCI, which can be calculated by the predicted value and confidence coefficient. The use of PCI as threshold is mainly on the fact that it considers the uncertainty in the data series parameters in the forecasting model to address the suitable threshold selection problem. The method performs fast, incremental evaluation of data as it becomes available, scales to large quantities of data, and requires no preclassification of anomalies. Experiments with different hydrologic real-world time series showed that the proposed methods are fast and correctly identify abnormal data and can be used for hydrologic time series analysis.
Entropy measure of stepwise component in GPS time series
Lyubushin, A. A.; Yakovlev, P. V.
2016-01-01
A new method for estimating the stepwise component in the time series is suggested. The method is based on the application of a pseudo-derivative. The advantage of this method lies in the simplicity of its practical implementation compared to the more common methods for identifying the peculiarities in the time series against the noise. The need for automatic detection of the jumps in the noised signal and for introducing a quantitative measure of a stepwise behavior of the signal arises in the problems of the GPS time series analysis. The interest in the jumps in the mean level of the GPS signal is associated with the fact that they may reflect the typical earthquakes or the so-called silent earthquakes. In this paper, we offer the criteria for quantifying the degree of the stepwise behavior of the noised time series. These criteria are based on calculating the entropy for the auxiliary series of averaged stepwise approximations, which are constructed with the use of pseudo-derivatives.
Multi-Scale Dissemination of Time Series Data
DEFF Research Database (Denmark)
Guo, Qingsong; Zhou, Yongluan; Su, Li
2013-01-01
, which is an abstract indicator for both the physical limits and the amount of data that the subscriber would like to handle. To handle this problem, we propose a system framework for multi-scale time series data dissemination that employs a typical tree-based dissemination network and existing time......In this paper, we consider the problem of continuous dissemination of time series data, such as sensor measurements, to a large number of subscribers. These subscribers fall into multiple subscription levels, where each subscription level is specified by the bandwidth constraint of a subscriber......-series compression models. Due to the bandwidth limits regarding to potentially sheer speed of data, it is inevitable to compress and re-compress data along the dissemination paths according to the subscription level of each node. Compression would caused the accuracy loss of data, thus we devise several algorithms...
Grammar-based feature generation for time-series prediction
De Silva, Anthony Mihirana
2015-01-01
This book proposes a novel approach for time-series prediction using machine learning techniques with automatic feature generation. Application of machine learning techniques to predict time-series continues to attract considerable attention due to the difficulty of the prediction problems compounded by the non-linear and non-stationary nature of the real world time-series. The performance of machine learning techniques, among other things, depends on suitable engineering of features. This book proposes a systematic way for generating suitable features using context-free grammar. A number of feature selection criteria are investigated and a hybrid feature generation and selection algorithm using grammatical evolution is proposed. The book contains graphical illustrations to explain the feature generation process. The proposed approaches are demonstrated by predicting the closing price of major stock market indices, peak electricity load and net hourly foreign exchange client trade volume. The proposed method ...
Increment Entropy as a Measure of Complexity for Time Series
Directory of Open Access Journals (Sweden)
Xiaofeng Liu
2016-01-01
Full Text Available Entropy has been a common index to quantify the complexity of time series in a variety of fields. Here, we introduce an increment entropy to measure the complexity of time series in which each increment is mapped onto a word of two letters, one corresponding to the sign and the other corresponding to the magnitude. Increment entropy (IncrEn is defined as the Shannon entropy of the words. Simulations on synthetic data and tests on epileptic electroencephalogram (EEG signals demonstrate its ability of detecting abrupt changes, regardless of the energetic (e.g., spikes or bursts or structural changes. The computation of IncrEn does not make any assumption on time series, and it can be applicable to arbitrary real-world data.
Detection of "noisy" chaos in a time series
DEFF Research Database (Denmark)
Chon, K H; Kanters, J K; Cohen, R J; Holstein-Rathlou, N H
Time series from biological system often displays fluctuations in the measured variables. Much effort has been directed at determining whether this variability reflects deterministic chaos, or whether it is merely "noise". The output from most biological systems is probably the result of both the...... internal dynamics of the systems, and the input to the system from the surroundings. This implies that the system should be viewed as a mixed system with both stochastic and deterministic components. We present a method that appears to be useful in deciding whether determinism is present in a time series......, and if this determinism has chaotic attributes. The method relies on fitting a nonlinear autoregressive model to the time series followed by an estimation of the characteristic exponents of the model over the observed probability distribution of states for the system. The method is tested by computer...
Increment entropy as a measure of complexity for time series
Liu, Xiaofeng; Xu, Ning; Xue, Jianru
2015-01-01
Entropy has been a common index to quantify the complexity of time series in a variety of fields. Here, we introduce increment entropy to measure the complexity of time series in which each increment is mapped into a word of two letters, one letter corresponding to direction and the other corresponding to magnitude. The Shannon entropy of the words is termed as increment entropy (IncrEn). Simulations on synthetic data and tests on epileptic EEG signals have demonstrated its ability of detecting the abrupt change, regardless of energetic (e.g. spikes or bursts) or structural changes. The computation of IncrEn does not make any assumption on time series and it can be applicable to arbitrary real-world data.
Feature-preserving interpolation and filtering of environmental time series
Mariethoz, Gregoire; Jougnot, Damien; Rezaee, Hassan
2015-01-01
We propose a method for filling gaps and removing interferences in time series for applications involving continuous monitoring of environmental variables. The approach is non-parametric and based on an iterative pattern-matching between the affected and the valid parts of the time series. It considers several variables jointly in the pattern matching process and allows preserving linear or non-linear dependences between variables. The uncertainty in the reconstructed time series is quantified through multiple realizations. The method is tested on self-potential data that are affected by strong interferences as well as data gaps, and the results show that our approach allows reproducing the spectral features of the original signal. Even in the presence of intense signal perturbations, it significantly improves the signal and corrects bias introduced by asymmetrical interferences. Potential applications are wide-ranging, including geophysics, meteorology and hydrology.
Learning of time series through neuron-to-neuron instruction
International Nuclear Information System (INIS)
A model neuron with delayline feedback connections can learn a time series generated by another model neuron. It has been known that some student neurons that have completed such learning under the instruction of a teacher's quasi-periodic sequence mimic the teacher's time series over a long interval, even after instruction has ceased. We found that in addition to such faithful students, there are unfaithful students whose time series eventually diverge exponentially from that of the teacher. In order to understand the circumstances that allow for such a variety of students, the orbit dimension was estimated numerically. The quasi-periodic orbits in question were found to be confined in spaces with dimensions significantly smaller than that of the full phase space
Asymptotics for Nonlinear Transformations of Fractionally Integrated Time Series
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
The asymptotic theory for nonlinear transformations of fractionally integrated time series is developed. By the use of fractional Occupation Times Formula, various nonlinear functions of fractionally integrated series such as ARFIMA time series are studied, and the asymptotic distributions of the sample moments of such functions are obtained and analyzed. The transformations considered in this paper includes a variety of functions such as regular functions, integrable functions and asymptotically homogeneous functions that are often used in practical nonlinear econometric analysis. It is shown that the asymptotic theory of nonlinear transformations of original and normalized fractionally integrated processes is different from that of fractionally integrated processes, but is similar to the asymptotic theory of nonlinear transformations of integrated processes.
Reconstruction of tritium time series in precipitation of Beijing
International Nuclear Information System (INIS)
Human nuclear activities, especially intensive nuclear tests during the 1960s in the world, caused atmospheric tritium concentration increasing significantly, which provided convenient condition for global water cycle research, especially for tracer dating research of groundwater. However, due to the layout of monitoring sites and other reasons, most parts of the world are lack of monitoring data of tritium concentration in precipitation, which brought difficulties in determining the input function which is essential for groundwater tracer dating technique. Based on the analysis of principles and applicability of present reconstruction methods of tritium time series, the tritium time series in precipitation in Beijing during 1953-2002 was reconstructed using combined methods, including Guanbingjun method, trend surface analysis method, trigonometric interpolation method and correlation method. Furthermore, the best method and the best time series curve were elected through comparison of results of different methods. (authors)
Time series analysis in astronomy: Limits and potentialities
DEFF Research Database (Denmark)
Vio, R.; Kristensen, N.R.; Madsen, Henrik; Wamsteker, W.
2005-01-01
priori physical model there are not many possibilities to obtain interpretable results. For this reason, the practice to develop more and more sophisticated statistical methods of time series analysis is not productive. Only techniques of data analysis developed in a specific physical context can be......In this paper we consider the problem of the limits concerning the physical information that can be extracted from the analysis of one or more time series ( light curves) typical of astrophysical objects. On the basis of theoretical considerations and numerical simulations, we show that with no a...... expected to provide useful results. The field of stochastic dynamics appears to be an interesting framework for such an approach. In particular, it is shown that modelling the experimental time series by means of the stochastic differential equations (SDE) represents a valuable tool of analysis. For...
The time series forecasting: from the aspect of network
Chen, S; Hu, Y; Liu, Q; Deng, Y
2014-01-01
Forecasting can estimate the statement of events according to the historical data and it is considerably important in many disciplines. At present, time series models have been utilized to solve forecasting problems in various domains. In general, researchers use curve fitting and parameter estimation methods (moment estimation, maximum likelihood estimation and least square method) to forecast. In this paper, a new sight is given to the forecasting and a completely different method is proposed to forecast time series. Inspired by the visibility graph and link prediction, this letter converts time series into network and then finds the nodes which are mostly likelihood to link with the predicted node. Finally, the predicted value will be obtained according to the state of the link. The TAIEX data set is used in the case study to illustrate that the proposed method is effectiveness. Compared with ARIMA model, the proposed shows a good forecasting performance when there is a small amount of data.
A multidisciplinary database for geophysical time series management
Montalto, P.; Aliotta, M.; Cassisi, C.; Prestifilippo, M.; Cannata, A.
2013-12-01
The variables collected by a sensor network constitute a heterogeneous data source that needs to be properly organized in order to be used in research and geophysical monitoring. With the time series term we refer to a set of observations of a given phenomenon acquired sequentially in time. When the time intervals are equally spaced one speaks of period or sampling frequency. Our work describes in detail a possible methodology for storage and management of time series using a specific data structure. We designed a framework, hereinafter called TSDSystem (Time Series Database System), in order to acquire time series from different data sources and standardize them within a relational database. The operation of standardization provides the ability to perform operations, such as query and visualization, of many measures synchronizing them using a common time scale. The proposed architecture follows a multiple layer paradigm (Loaders layer, Database layer and Business Logic layer). Each layer is specialized in performing particular operations for the reorganization and archiving of data from different sources such as ASCII, Excel, ODBC (Open DataBase Connectivity), file accessible from the Internet (web pages, XML). In particular, the loader layer performs a security check of the working status of each running software through an heartbeat system, in order to automate the discovery of acquisition issues and other warning conditions. Although our system has to manage huge amounts of data, performance is guaranteed by using a smart partitioning table strategy, that keeps balanced the percentage of data stored in each database table. TSDSystem also contains modules for the visualization of acquired data, that provide the possibility to query different time series on a specified time range, or follow the realtime signal acquisition, according to a data access policy from the users.
Fuzzy Time Series: An Application to Tourism Demand Forecasting
Directory of Open Access Journals (Sweden)
Muhammad H. Lee
2012-01-01
Full Text Available Problem statement: Forecasting is very important in many types of organizations since predictions of future events must be incorporated into the decision-making process. In the case of tourism demand, better forecast would help directors and investors make operational, tactical and strategic decisions. Besides that, government bodies need accurate tourism demand forecasts to plan required tourism infrastructures, such as accommodation site planning and transportation development, among other needs. There are many types of forecasting methods. Generally, time series forecasting can be divided into classical method and modern methods. Recent studies show that the newer and more advanced forecasting techniques tend to result in improved forecast accuracy, but no clear evidence shows that any one model can consistently outperform other models in the forecasting competition. Approach: In this study, the performance of forecasting between classical methods (Box-Jenkins methods Seasonal Auto-Regressive Integrated Moving Average (SARIMA, Holt Winters and time series regression and modern methods (fuzzy time series has been compared by using data of tourist arrivals to Bali and Soekarno-Hatta gate in Indonesia as case study. Results: The empirical results show that modern methods give more accurate forecasts compare to classical methods. Chens fuzzy time series method outperforms all the classical methods and others more advance fuzzy time series methods. We also found that the performance of fuzzy time series methods can be improve by using transformed data. Conclusion: It is found that the best method to forecast the tourist arrivals to Bali and Soekarno-Hatta was to be the FTS i.e., method after using data transformation. Although this method known to be the simplest or conventional methods of FTS, yet this result should not be odd since several previous studies also have shown that simple method could outperform more advance or complicated methods.
Multifractal regime detecting method for financial time series
International Nuclear Information System (INIS)
Highlights: • A multifractal regime detecting method (MRDM) introduced based on generalized Hurst exponent. • Multifractal regimes in the KOSPI from 1990 through 2012 are identified. • Surrogated tests are performed for the validation of MRDM. - Abstract: We focus on time varying multifractality in time series and introduce a multifractal regime detecting method (MRDM) adopting a nonparametric statistical test for multifractality based on generalized Hurst exponent (GHE). MRDM is a practical method to discriminate multifractal regimes in a time series of any length using a moving time window approach with the adjustable time window size and the moving interval. MRDM is applied to simulations consisting of both multifractal and monofractal regimes, and the results confirm its validity. Using MRDM, we identify multifractal regimes in the time series of Korea composite stock price index (KOSPI) from 1990 through 2012 and observe the distinct stylized facts of the KOSPI return values in multifractal regimes such as the heavy tail distribution, high kurtosis, and the long memory in volatility. Surrogate tests based on improved amplitude adjusted Fourier transformation (IAAFT) algorithm, normal distribution, and generalized student t distribution are performed for the validation of MDRM, and the probable causes of multifractality in the KOSPI series are discussed
Change detection in a time series of polarimetric SAR images
DEFF Research Database (Denmark)
Skriver, Henning; Nielsen, Allan Aasbjerg; Conradsen, Knut
a certain point can be used to detect at which points changes occur in the time series. [1] T. W. Anderson, An Introduction to Multivariate Statistical Analysis, John Wiley, New York, third edition, 2003. [2] K. Conradsen, A. A. Nielsen, J. Schou, and H. Skriver, “A test statistic in the complex...... to the complex Wishart distribution and demonstrate its application to change detection in truly multi-temporal, polarimetric SAR data. Results will be shown that demonstrate the difference between applying to time series of polarimetric SAR images, pairwise comparisons or the new omnibus test...
Cross-correlation between time series of vehicles and passengers
Zebende, G. F.; Filho, A. Machado
2009-12-01
We study in this paper a cross-correlation between time series of vehicles and passengers collected in the ferry-boat system (sea route that connects the city of Salvador and Itaparica island, Bahia, Brazil), this study is based on the detrended cross-correlation analysis (DCCA) method. The DCCA method is designed to investigate power-law cross correlations between different simultaneously recorded time series in the presence of nonstationarity. Here in this paper we show that is possible to discriminate cross-correlation between vehicles and passengers and also identify seasonal components.
Time series analysis of banking share returns in Thailand
Directory of Open Access Journals (Sweden)
Sunari Saejiang
2001-06-01
Full Text Available An index is constructed based on an equally weighted portfolio of seven major banking shares in Thailand. A GARCH (1,1 model is fitted to the time series of returns on this index for successive trading day from January 1994 to December 1999. During this period the logarithm of the volatility is well fitted by a stationary time series model comprising an additive combination of a single sinusoidal function with a period of six years, and an ARMA (1,1 model.
Nonlinear Time Series Forecast Using Radial Basis Function Neural Networks
Institute of Scientific and Technical Information of China (English)
ZHENGXin; CHENTian-Lun
2003-01-01
In the research of using Radial Basis Function Neural Network (RBF NN) forecasting nonlinear time series, we investigate how the different clusterings affect the process of learning and forecasting. We find that k-means clustering is very suitable. In order to increase the precision we introduce a nonlinear feedback term to escape from the local minima of energy, then we use the model to forecast the nonlinear time series which are produced by Mackey-Glass equation and stocks. By selecting the k-means clustering and the suitable feedback term, much better forecasting results are obtained.
Application of nonlinear time series models to driven systems
Energy Technology Data Exchange (ETDEWEB)
Hunter, N.F. Jr.
1990-01-01
In our laboratory we have been engaged in an effort to model nonlinear systems using time series methods. Our objectives have been, first, to understand how the time series response of a nonlinear system unfolds as a function of the underlying state variables, second, to model the evolution of the state variables, and finally, to predict nonlinear system responses. We hope to address the relationship between model parameters and system parameters in the near future. Control of nonlinear systems based on experimentally derived parameters is also a planned topic of future research. 28 refs., 15 figs., 2 tabs.
Mining Rules from Electrical Load Time Series Data Set
Institute of Scientific and Technical Information of China (English)
无
2002-01-01
The mining of the rules from the electrical load time series data which are collected from the EMS (Energy Management System) is discussed. The data from the EMS are too huge and sophisticated to be understood and used by the power system engineer, while useful information is hidden in the electrical load data. The authors discuss the use of fuzzy linguistic summary as data mining method to induce the rules from the electrical load time series. The data preprocessing techniques are also discussed in the paper.
Scaling analysis of multi-variate intermittent time series
Kitt, Robert; Kalda, Jaan
2005-08-01
The scaling properties of the time series of asset prices and trading volumes of stock markets are analysed. It is shown that similar to the asset prices, the trading volume data obey multi-scaling length-distribution of low-variability periods. In the case of asset prices, such scaling behaviour can be used for risk forecasts: the probability of observing next day a large price movement is (super-universally) inversely proportional to the length of the ongoing low-variability period. Finally, a method is devised for a multi-factor scaling analysis. We apply the simplest, two-factor model to equity index and trading volume time series.
Characterizing Weak Chaos using Time Series of Lyapunov Exponents
da Silva, R. M.; Manchein, C.; Beims, M. W.; Altmann, E. G.
2015-01-01
We investigate chaos in mixed-phase-space Hamiltonian systems using time series of the finite- time Lyapunov exponents. The methodology we propose uses the number of Lyapunov exponents close to zero to define regimes of ordered (stickiness), semi-ordered (or semi-chaotic), and strongly chaotic motion. The dynamics is then investigated looking at the consecutive time spent in each regime, the transition between different regimes, and the regions in the phase-space associated to them. Applying ...
On the estimation of correlations for irregularly spaced time series
Andersson, Jonas
2007-01-01
In this paper, the problem of calculating covariances and correlations between time series which are observed irregularly and at different points in time, is treated. The problem of dependence between the time stamp process and the return process is especially highlighted and the solution to this problem for a special case is given. Furthermore, estimators based on different interpolation methods are investigated. The covariances are in turn used to estimate a simple regression on such data. ...
Studies in Astronomical Time Series Analysis. VI. Bayesian Block Representations
Scargle, Jeffrey D; Jackson, Brad; Chiang, James
2012-01-01
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it - an improved and generalized version of Bayesian Blocks (Scargle 1998) - that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piecewise linear and piecewise exponential representations, multi-variate time series data, analysis of vari...
A Novel Approach for Nonstationary Time Series Analysis with Time-Invariant Correlation Coefficient
Chengrui Liu; Zhihua Wang; Huimin Fu; Yongbo Zhang
2014-01-01
We will concentrate on the modeling and analysis of a class of nonstationary time series, called correlation coefficient stationary series, which commonly exists in practical engineering. First, the concept and scope of correlation coefficient stationary series are discussed to get a better understanding. Second, a theorem is proposed to determine standard deviation function for correlation coefficient stationary series. Third, we propose a moving multiple-point average method to determine th...
Stochastic generation of hourly wind speed time series
International Nuclear Information System (INIS)
In the present study hourly wind speed data of Kuala Terengganu in Peninsular Malaysia are simulated by using transition matrix approach of Markovian process. The wind speed time series is divided into various states based on certain criteria. The next wind speed states are selected based on the previous states. The cumulative probability transition matrix has been formed in which each row ends with 1. Using the uniform random numbers between 0 and 1, a series of future states is generated. These states have been converted to the corresponding wind speed values using another uniform random number generator. The accuracy of the model has been determined by comparing the statistical characteristics such as average, standard deviation, root mean square error, probability density function and autocorrelation function of the generated data to those of the original data. The generated wind speed time series data is capable to preserve the wind speed characteristics of the observed data
Learning time series evolution by unsupervised extraction of correlations
International Nuclear Information System (INIS)
As a consequence, we are able to model chaotic and nonchaotic time series. Furthermore, one critical point in modeling time series is the determination of the dimension of the embedding vector used, i.e., the number of components of the past that are needed to predict the future. With this method we can detect the embedding dimension by extracting the influence of the past on the future, i.e., the correlation of remote past and future. Optimal embedding dimensions are obtained for the Henon map and the Mackey-Glass series. When noisy data corrupted by colored noise are used, a model is still possible. The noise will then be decorrelated by the network. In the case of modeling a chemical reaction, the most natural architecture that conserves the volume is a symplectic network which describes a system that conserves the entropy and therefore the transmitted information
Turbulent-Like Behavior of Seismic Time Series
Manshour, P; Sahimi, Muhammad; Peinke, J; Pacheco, Amalio F; Tabar, M Reza Rahimi
2009-01-01
We report on a novel stochastic analysis of seismic time series for the Earth's vertical velocity, by using methods originally developed for complex hierarchical systems, and in particular for turbulent flows. Analysis of the fluctuations of the detrended increments of the series reveals a pronounced change of the shapes of the probability density functions (PDF) of the series' increments. Before and close to an earthquake the shape of the PDF and the long-range correlation in the increments both manifest significant changes. For a moderate or large-size earthquake the typical time at which the PDF undergoes the transition from a Gaussian to a non-Gaussian is about 5-10 hours. Thus, the transition represents a new precursor for detecting such earthquakes.
A multiscale statistical model for time series forecasting
Wang, W.; Pollak, I.
2007-02-01
We propose a stochastic grammar model for random-walk-like time series that has features at several temporal scales. We use a tree structure to model these multiscale features. The inside-outside algorithm is used to estimate the model parameters. We develop an algorithm to forecast the sign of the first difference of a time series. We illustrate the algorithm using log-price series of several stocks and compare with linear prediction and a neural network approach. We furthermore illustrate our algorithm using synthetic data and show that it significantly outperforms both the linear predictor and the neural network. The construction of our synthetic data indicates what types of signals our algorithm is well suited for.
Segmentation of time series with long-range fractal correlations
Bernaola-Galván, P.; Oliver, J.L.; Hackenberg, M.; Coronado, A.V.; Ivanov, P.Ch.; Carpena, P.
2012-01-01
Segmentation is a standard method of data analysis to identify change-points dividing a nonstationary time series into homogeneous segments. However, for long-range fractal correlated series, most of the segmentation techniques detect spurious change-points which are simply due to the heterogeneities induced by the correlations and not to real nonstationarities. To avoid this oversegmentation, we present a segmentation algorithm which takes as a reference for homogeneity, instead of a random i.i.d. series, a correlated series modeled by a fractional noise with the same degree of correlations as the series to be segmented. We apply our algorithm to artificial series with long-range correlations and show that it systematically detects only the change-points produced by real nonstationarities and not those created by the correlations of the signal. Further, we apply the method to the sequence of the long arm of human chromosome 21, which is known to have long-range fractal correlations. We obtain only three segments that clearly correspond to the three regions of different G + C composition revealed by means of a multi-scale wavelet plot. Similar results have been obtained when segmenting all human chromosome sequences, showing the existence of previously unknown huge compositional superstructures in the human genome. PMID:23645997
Practical implementation of nonlinear time series methods The TISEAN package
Hegger, R; Schreiber, T; Hegger, Rainer; Kantz, Holger; Schreiber, Thomas
1998-01-01
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 ...
The application of the transfer entropy to gappy time series
Energy Technology Data Exchange (ETDEWEB)
Kulp, C.W. [Department of Physics and Astronomy, Lycoming College, Williamsport, PA 17701 (United States)], E-mail: kulp@lycoming.edu; Tracy, E.R. [Department of Physics, The College of William and Mary, Williamsburg, VA 23187-8795 (United States)], E-mail: ertrac@wm.edu
2009-03-23
The application of the transfer entropy to gappy symbolic time series is discussed. Although the transfer entropy can fail to correctly identify the drive-response relationship, it is able to robustly detect phase relationships. Hence, it might still be of use in applications requiring the detection of changes in these relationships.
The application of the transfer entropy to gappy time series
International Nuclear Information System (INIS)
The application of the transfer entropy to gappy symbolic time series is discussed. Although the transfer entropy can fail to correctly identify the drive-response relationship, it is able to robustly detect phase relationships. Hence, it might still be of use in applications requiring the detection of changes in these relationships
Quality Quandaries- Time Series Model Selection and Parsimony
DEFF Research Database (Denmark)
Bisgaard, Søren; Kulahci, Murat
2009-01-01
Some of the issues involved in selecting adequate models for time series data are discussed using an example concerning the number of users of an Internet server. The process of selecting an appropriate model is subjective and requires experience and judgment. The authors believe an important...
Time series analysis in astronomy: Limits and potentialities
DEFF Research Database (Denmark)
Vio, R.; Kristensen, N.R.; Madsen, Henrik;
2005-01-01
In this paper we consider the problem of the limits concerning the physical information that can be extracted from the analysis of one or more time series ( light curves) typical of astrophysical objects. On the basis of theoretical considerations and numerical simulations, we show that with no a...
Long-memory time series theory and methods
Palma, Wilfredo
2007-01-01
Wilfredo Palma, PhD, is Chairman and Professor of Statistics in the Department of Statistics at Pontificia Universidad Católica de Chile. Dr. Palma has published several refereed articles and has received over a dozen academic honors and awards. His research interests include time series analysis, prediction theory, state space systems, linear models, and econometrics.
Application of bootstrap to detecting chaos in financial time series
Brzozowska-Rup, Katarzyna; Orłowski, Arkadiusz
2004-12-01
A moving blocks bootstrap procedure is used to investigate the dynamics of nominal exchange rates and the return rates of the US Dollar against the Polish Zloty. The problem if these financial time series exhibit chaotic behavior is undertaken. A possibility of detecting the presence of a positive Lyapunov exponent is studied.
On the Identifiability Conditions in Some Nonlinear Time Series Models
Noh, Jungsik; Lee, Sangyeol
2013-01-01
In this study, we consider the identifiability problem for nonlinear time series models. Special attention is paid to smooth transition GARCH, nonlinear Poisson autoregressive, and multiple regime smooth transition autoregressive models. Some sufficient conditions are obtained to establish the identifiability of these models.
Testing for asymmetry in economic time series using bootstrap methods
Claudio Lupi; Patrizia Ordine
2001-01-01
In this paper we show that phase-scrambling bootstrap offers a natural framework for asymmetry testing in economic time series. A comparison with other bootstrap schemes is also sketched. A Monte Carlo analysis is carried out to evaluate the size and power properties of the phase-scrambling bootstrap-based test.
Time Series Data Visualization in World Wide Telescope
Fay, J.
WorldWide Telescope provides a rich set of timer series visualization for both archival and real time data. WWT consists of both interactive desktop tools for interactive immersive visualization and HTML5 web based controls that can be utilized in customized web pages. WWT supports a range of display options including full dome, power walls, stereo and virtual reality headsets.
Notes on economic time series analysis system theoretic perspectives
Aoki, Masanao
1983-01-01
In seminars and graduate level courses I have had several opportunities to discuss modeling and analysis of time series with economists and economic graduate students during the past several years. These experiences made me aware of a gap between what economic graduate students are taught about vector-valued time series and what is available in recent system literature. Wishing to fill or narrow the gap that I suspect is more widely spread than my personal experiences indicate, I have written these notes to augment and reor ganize materials I have given in these courses and seminars. I have endeavored to present, in as much a self-contained way as practicable, a body of results and techniques in system theory that I judge to be relevant and useful to economists interested in using time series in their research. I have essentially acted as an intermediary and interpreter of system theoretic results and perspectives in time series by filtering out non-essential details, and presenting coherent accounts of wha...
A test of conditional heteroscedasticity in time series
Institute of Scientific and Technical Information of China (English)
陈敏; 安鸿志
1999-01-01
A new test of conditional heteroscedasticity for time series is proposed. The new testing method is based on a goodness of fit type test statistics and a Cramer-von Mises type test statistic. The asymptotic properties of the new test statistic is establised. The results demonstrate that such a test is consistent.
FIXED-DESIGN SEMIPARAMETRIC REGRESSION FOR LINEAR TIME SERIES
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
This article studies parametric component and nonparametric component estimators in a semiparametric regression model with linear time series errors; their r-th mean consistency and complete consistency are obtained under suitable conditions. Finally, the author shows that the usual weight functions based on nearest neighbor methods satisfy the designed assumptions imposed.
Deriving dynamic marketing effectiveness from econometric time series models
C. Horváth (Csilla); Ph.H.B.F. Franses (Philip Hans)
2003-01-01
textabstractTo understand the relevance of marketing efforts, it has become standard practice to estimate the long-run and short-run effects of the marketing-mix, using, say, weekly scanner data. A common vehicle for this purpose is an econometric time series model. Issues that are addressed in the
Time Series, Stochastic Processes and Completeness of Quantum Theory
International Nuclear Information System (INIS)
Most of physical experiments are usually described as repeated measurements of some random variables. Experimental data registered by on-line computers form time series of outcomes. The frequencies of different outcomes are compared with the probabilities provided by the algorithms of quantum theory (QT). In spite of statistical predictions of QT a claim was made that it provided the most complete description of the data and of the underlying physical phenomena. This claim could be easily rejected if some fine structures, averaged out in the standard descriptive statistical analysis, were found in time series of experimental data. To search for these structures one has to use more subtle statistical tools which were developed to study time series produced by various stochastic processes. In this talk we review some of these tools. As an example we show how the standard descriptive statistical analysis of the data is unable to reveal a fine structure in a simulated sample of AR (2) stochastic process. We emphasize once again that the violation of Bell inequalities gives no information on the completeness or the non locality of QT. The appropriate way to test the completeness of quantum theory is to search for fine structures in time series of the experimental data by means of the purity tests or by studying the autocorrelation and partial autocorrelation functions.
Time series model based on global structure of complete genome
Yu, Z G; Anh, Vo
2001-01-01
A time series model based on the global structure of the complete genome is proposed. Three kinds of length sequences of the complete genome are considered. The correlation dimensions and Hurst exponents of the length sequences are calculated. Using these two exponents, some interesting results related to the problem of classification and evolution relationship of bacteria are obtained.
Estimating measurement noise in a time series by exploiting nonstationarity
International Nuclear Information System (INIS)
A measured time series is always corrupted by noise to some degree. Even a rough estimation of the level of noise contained in an experimental time series is valuable. This is so, for example, when one wishes to apply techniques from nonlinear dynamics theory to analyze a time series. However, this is a very difficult problem. It becomes even harder when the measured signal is nonstationary, which is often true in practice. Detecting nonstationarity has been a hot research topic in recent years. However, many researchers stop when they find the time series under study is indeed nonstationary. Here, we exploit the very nature of nonstationarity in a signal to formulate a method for quantitatively estimating the amount of noise contained in the signal. The approach is first verified using computer simulated signals based on the chaotic Lorenz attractors and the Mackey-Glass equations with different parameters and then applied to the clinically measured intracranial EEG signals. It is found that the amount of noise in the EEG signals is around 8.0-8.5% in terms of amplitude. Implications to whether EEG signals are chaotic or not are discussed
Chaotic time series prediction using artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Bartlett, E.B.
1991-01-01
This paper describes the use of artificial neural networks to model the complex oscillations defined by a chaotic Verhuist animal population dynamic. A predictive artificial neural network model is developed and tested, and results of computer simulations are given. These results show that the artificial neural network model predicts the chaotic time series with various initial conditions, growth parameters, or noise.
Chaotic time series prediction using artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Bartlett, E.B.
1991-12-31
This paper describes the use of artificial neural networks to model the complex oscillations defined by a chaotic Verhuist animal population dynamic. A predictive artificial neural network model is developed and tested, and results of computer simulations are given. These results show that the artificial neural network model predicts the chaotic time series with various initial conditions, growth parameters, or noise.
Outlier detection algorithms for least squares time series regression
DEFF Research Database (Denmark)
Johansen, Søren; Nielsen, Bent
We review recent asymptotic results on some robust methods for multiple regression. The regressors include stationary and non-stationary time series as well as polynomial terms. The methods include the Huber-skip M-estimator, 1-step Huber-skip M-estimators, in particular the Impulse Indicator...
Time Series Classification by Class-Based Mahalanobis Distances
Prekopcsák, Zoltán
2010-01-01
To classify time series by nearest neighbor, we need to specify or learn a distance. We consider several variations of the Mahalanobis distance and the related Large Margin Nearest Neighbor Classification (LMNN). We find that the conventional Mahalanobis distance is counterproductive. However, both LMNN and the class-based diagonal Mahalanobis distance are competitive.
Time Series Analysis for the Drac River Basin (france)
Parra-Castro, K.; Donado-Garzon, L. D.; Rodriguez, E.
2013-12-01
This research is based on analyzing of discharge time-series in four stream flow gage stations located in the Drac River basin in France: (i) Guinguette Naturelle, (ii) Infernet, (iii) Parassat and the stream flow gage (iv) Villard Loubière. In addition, time-series models as the linear regression (single and multiple) and the MORDOR model were implemented to analyze the behavior the Drac River from year 1969 until year 2010. Twelve different models were implemented to assess the daily and monthly discharge time-series for the four flow gage stations. Moreover, five selection criteria were use to analyze the models: average division, variance division, the coefficient R2, Kling-Gupta Efficiency (KGE) and the Nash Number. The selection of the models was made to have the strongest models with an important level confidence. In this case, according to the best correlation between the time-series of stream flow gage stations and the best fitting models. Four of the twelve models were selected: two models for the stream flow gage station Guinguette Naturel, one for the station Infernet and one model for the station Villard Loubière. The R2 coefficients achieved were 0.87, 0.95, 0.85 and 0.87 respectively. Consequently, both confidence levels (the modeled and the empirical) were tested in the selected model, leading to the best fitting of both discharge time-series and models with the empirical confidence interval. Additionally, a procedure for validation of the models was conducted using the data for the year 2011, where extreme hydrologic and changes in hydrologic regimes events were identified. Furthermore, two different forms of estimating uncertainty through the use of confidence levels were studied: the modeled and the empirical confidence levels. This research was useful to update the used procedures and validate time-series in the four stream flow gage stations for the use of the company Électricité de France. Additionally, coefficients for both the models and
Assessing coupling dynamics from an ensemble of time series
Gomez-Herrero, German; Rutanen, Kalle; Soriano, Miguel C; Pipa, Gordon; Vicente, Raul
2010-01-01
Finding interdependency relations between (possibly multivariate) time series provides valuable knowledge about the processes that generate the signals. Information theory sets a natural framework for non-parametric measures of several classes of statistical dependencies. However, a reliable estimation from information-theoretic functionals is hampered when the dependency to be assessed is brief or evolves in time. Here, we show that these limitations can be overcome when we have access to an ensemble of independent repetitions of the time series. In particular, we gear a data-efficient estimator of probability densities to make use of the full structure of trial-based measures. By doing so, we can obtain time-resolved estimates for a family of entropy combinations (including mutual information, transfer entropy, and their conditional counterparts) which are more accurate than the simple average of individual estimates over trials. We show with simulated and real data that the proposed approach allows to reco...
Irreversibility of financial time series: A graph-theoretical approach
Flanagan, Ryan; Lacasa, Lucas
2016-04-01
The relation between time series irreversibility and entropy production has been recently investigated in thermodynamic systems operating away from equilibrium. In this work we explore this concept in the context of financial time series. We make use of visibility algorithms to quantify, in graph-theoretical terms, time irreversibility of 35 financial indices evolving over the period 1998-2012. We show that this metric is complementary to standard measures based on volatility and exploit it to both classify periods of financial stress and to rank companies accordingly. We then validate this approach by finding that a projection in principal components space of financial years, based on time irreversibility features, clusters together periods of financial stress from stable periods. Relations between irreversibility, efficiency and predictability are briefly discussed.
Multiple imputation for time series data with Amelia package.
Zhang, Zhongheng
2016-02-01
Time series data are common in medical researches. Many laboratory variables or study endpoints could be measured repeatedly over time. Multiple imputation (MI) without considering time trend of a variable may cause it to be unreliable. The article illustrates how to perform MI by using Amelia package in a clinical scenario. Amelia package is powerful in that it allows for MI for time series data. External information on the variable of interest can also be incorporated by using prior or bound argument. Such information may be based on previous published observations, academic consensus, and personal experience. Diagnostics of imputation model can be performed by examining the distributions of imputed and observed values, or by using over-imputation technique. PMID:26904578
Classification of time series patterns from complex dynamic systems
Energy Technology Data Exchange (ETDEWEB)
Schryver, J.C.; Rao, N.
1998-07-01
An increasing availability of high-performance computing and data storage media at decreasing cost is making possible the proliferation of large-scale numerical databases and data warehouses. Numeric warehousing enterprises on the order of hundreds of gigabytes to terabytes are a reality in many fields such as finance, retail sales, process systems monitoring, biomedical monitoring, surveillance and transportation. Large-scale databases are becoming more accessible to larger user communities through the internet, web-based applications and database connectivity. Consequently, most researchers now have access to a variety of massive datasets. This trend will probably only continue to grow over the next several years. Unfortunately, the availability of integrated tools to explore, analyze and understand the data warehoused in these archives is lagging far behind the ability to gain access to the same data. In particular, locating and identifying patterns of interest in numerical time series data is an increasingly important problem for which there are few available techniques. Temporal pattern recognition poses many interesting problems in classification, segmentation, prediction, diagnosis and anomaly detection. This research focuses on the problem of classification or characterization of numerical time series data. Highway vehicles and their drivers are examples of complex dynamic systems (CDS) which are being used by transportation agencies for field testing to generate large-scale time series datasets. Tools for effective analysis of numerical time series in databases generated by highway vehicle systems are not yet available, or have not been adapted to the target problem domain. However, analysis tools from similar domains may be adapted to the problem of classification of numerical time series data.
Mixed Spectrum Analysis on fMRI Time-Series.
Kumar, Arun; Lin, Feng; Rajapakse, Jagath C
2016-06-01
Temporal autocorrelation present in functional magnetic resonance image (fMRI) data poses challenges to its analysis. The existing approaches handling autocorrelation in fMRI time-series often presume a specific model of autocorrelation such as an auto-regressive model. The main limitation here is that the correlation structure of voxels is generally unknown and varies in different brain regions because of different levels of neurogenic noises and pulsatile effects. Enforcing a universal model on all brain regions leads to bias and loss of efficiency in the analysis. In this paper, we propose the mixed spectrum analysis of the voxel time-series to separate the discrete component corresponding to input stimuli and the continuous component carrying temporal autocorrelation. A mixed spectral analysis technique based on M-spectral estimator is proposed, which effectively removes autocorrelation effects from voxel time-series and identify significant peaks of the spectrum. As the proposed method does not assume any prior model for the autocorrelation effect in voxel time-series, varying correlation structure among the brain regions does not affect its performance. We have modified the standard M-spectral method for an application on a spatial set of time-series by incorporating the contextual information related to the continuous spectrum of neighborhood voxels, thus reducing considerably the computation cost. Likelihood of the activation is predicted by comparing the amplitude of discrete component at stimulus frequency of voxels across the brain by using normal distribution and modeling spatial correlations among the likelihood with a conditional random field. We also demonstrate the application of the proposed method in detecting other desired frequencies. PMID:26800533
Forecasting Framework for Open Access Time Series in Energy
Barta, Gergo; Nagy, Gabor; Simon, Gabor; Papp, Gyozo
2016-01-01
In this paper we propose a framework for automated forecasting of energy-related time series using open access data from European Network of Transmission System Operators for Electricity (ENTSO-E). The framework provides forecasts for various European countries using publicly available historical data only. Our solution was benchmarked using the actual load data and the country provided estimates (where available). We conclude that the proposed system can produce timely forecasts with compara...
Quantile Spectral Analysis for Locally Stationary Time Series
Birr, Stefan; Volgushev, Stanislav; Kley, Tobias; Dette, Holger; Hallin, Marc
2014-01-01
Classical spectral methods are subject to two fundamental limitations: they only can account for covariance-related serial dependencies, and they require second-order stationarity. Much attention has been devoted recently to quantile-based spectral methods that go beyond covariance-based serial dependence features. At the same time, covariance-based methods relaxing stationarity into much weaker local stationarity conditions have been developed for a variety of time-series models. Here, we ar...
Time Series Factor Analysis with an Application to Measuring Money
Gilbert, Paul D.; Meijer, Erik
2005-01-01
Time series factor analysis (TSFA) and its associated statistical theory is developed. Unlike dynamic factor analysis (DFA), TSFA obviates the need for explicitly modeling the process dynamics of the underlying phenomena. It also differs from standard factor analysis (FA) in important respects: the factor model has a nontrivial mean structure, the observations are allowed to be dependent over time, and the data does not need to be covariance stationary as long as differenced data satisfies a ...
Assemblage time series reveal biodiversity change but not systematic loss
Dornelas, Maria; Nicholas J. Gotelli; McGill, Brian; Shimadzu, Hideyasu; Moyes, Faye; Sievers, Caya; Magurran, Anne E.
2014-01-01
The extent to which biodiversity change in local assemblages contributes to global biodiversity loss is poorly understood. We analyzed 100 time series from biomes across Earth to ask how diversity within assemblages is changing through time. We quantified patterns of temporal α diversity, measured as change in local diversity, and temporal β diversity, measured as change in community composition. Contrary to our expectations, we did not detect systematic loss of α diversity. However, communit...
Financial Time Series Forecasting Using Directed-Weighted Chunking SVMs
Yongming Cai; Lei Song; Tingwei Wang; Qing Chang
2014-01-01
Support vector machines (SVMs) are a promising alternative to traditional regression estimation approaches. But, when dealing with massive-scale data set, there exist many problems, such as the long training time and excessive demand of memory space. So, the SVMs algorithm is not suitable to deal with financial time series data. In order to solve these problems, directed-weighted chunking SVMs algorithm is proposed. In this algorithm, the whole training data set is split into several chunks, ...
Displaying time series, spatial, and space-time data with R
Perpinan Lamigueiro, Oscar
2014-01-01
Code and Methods for Creating High-Quality Data GraphicsA data graphic is not only a static image, but it also tells a story about the data. It activates cognitive processes that are able to detect patterns and discover information not readily available with the raw data. This is particularly true for time series, spatial, and space-time datasets.Focusing on the exploration of data with visual methods, Displaying Time Series, Spatial, and Space-Time Data with R presents methods and R code for producing high-quality graphics of time series, spatial, and space-time data. Practical examples using
Deterministics, initial conditions and breaks in long memory time series
Rachinger, Heiko
2012-01-01
En mi tesis doctoral, se modelizan series temporales con memoria larga y con un componente determinista que potencialmente sufre rupturas. Se consideran contrastes para rupturas y la estimación de los parámetros. Finalmente, se analiza la estimación e ciente de tendencias lineales y su impacto proveniente de la presencia y la longitud de de la pre-muestra. En el primer capítulo, Multiple Breaks in Long Memory Time Series , se propone un enfoque uni cado para la modelización de...
Adaptively Sharing Time-Series with Differential Privacy
Fan, Liyue
2012-01-01
Sharing real-time aggregate statistics of private data has given much benefit to the public to perform data mining for understanding important phenomena, such as Influenza outbreaks and traffic congestions. We propose an adaptive approach with sampling and estimation to release aggregated time series under differential privacy, the key innovation of which is that we utilize feedback loops based on observed (perturbed) values to dynamically adjust the estimation model as well as the sampling rate. To minimize the overall privacy cost, our solution uses the PID controller to adaptively sample long time-series according to detected data dynamics. To improve the accuracy of data release per timestamp, the Kalman filter is used to predict data values at non-sampling points and to estimate true values from perturbed query answers at sampling points. Our experiments with three real data sets show that it is beneficial to incorporate feedback into both the estimation model and the sampling process. The results confir...
Time series segmentation with shifting means hidden markov models
Directory of Open Access Journals (Sweden)
Ath. Kehagias
2006-01-01
Full Text Available We present a new family of hidden Markov models and apply these to the segmentation of hydrological and environmental time series. The proposed hidden Markov models have a discrete state space and their structure is inspired from the shifting means models introduced by Chernoff and Zacks and by Salas and Boes. An estimation method inspired from the EM algorithm is proposed, and we show that it can accurately identify multiple change-points in a time series. We also show that the solution obtained using this algorithm can serve as a starting point for a Monte-Carlo Markov chain Bayesian estimation method, thus reducing the computing time needed for the Markov chain to converge to a stationary distribution.
Time series segmentation with shifting means hidden markov models
Kehagias, Ath.; Fortin, V.
2006-08-01
We present a new family of hidden Markov models and apply these to the segmentation of hydrological and environmental time series. The proposed hidden Markov models have a discrete state space and their structure is inspired from the shifting means models introduced by Chernoff and Zacks and by Salas and Boes. An estimation method inspired from the EM algorithm is proposed, and we show that it can accurately identify multiple change-points in a time series. We also show that the solution obtained using this algorithm can serve as a starting point for a Monte-Carlo Markov chain Bayesian estimation method, thus reducing the computing time needed for the Markov chain to converge to a stationary distribution.
A comprehensive characterization of recurrences in time series
Chicheportiche, Rémy
2013-01-01
Study of recurrences in earthquakes, climate, financial time-series, etc. is crucial to better forecast disasters and limit their consequences. However, almost all the previous phenomenological studies involved only a long-ranged autocorrelation function, or disregarded the multi-scaling properties induced by potential higher order dependencies. Consequently, they missed the facts that non-linear dependences do impact both the statistics and dynamics of recurrence times, and that scaling arguments for the unconditional distribution may not be applicable. We argue that copulas is the correct model-free framework to study non-linear dependencies in time series and related concepts like recurrences. Fitting and/or simulating the intertemporal distribution of recurrence intervals is very much system specific, and cannot actually benefit from universal features, in contrast to the previous claims. This has important implications in epilepsy prognosis and financial risk management applications.
Cross Recurrence Plot Based Synchronization of Time Series
Marwan, N; Nowaczyk, N R
2002-01-01
The method of recurrence plots is extended to the cross recurrence plots (CRP), which among others enables the study of synchronization or time differences in two time series. This is emphasized in a distorted main diagonal in the cross recurrence plot, the line of synchronization (LOS). A non-parametrical fit of this LOS can be used to rescale the time axis of the two data series (whereby one of it is e.g. compressed or stretched) so that they are synchronized. An application of this method to geophysical sediment core data illustrates its suitability for real data. The rock magnetic data of two different sediment cores from the Makarov Basin can be adjusted to each other by using this method, so that they are comparable.
Minimum Entropy Density Method for the Time Series Analysis
Lee, J W; Moon, H T; Park, J B; Yang, J S; Jo, Hang-Hyun; Lee, Jeong Won; Moon, Hie-Tae; Park, Joongwoo Brian; Yang, Jae-Suk
2006-01-01
The entropy density is an intuitive and powerful concept to study the complicated nonlinear processes derived from physical systems. We develop the minimum entropy density method (MEDM) to detect the most correlated time interval of a given time series and define the effective delay of information (EDI) as the correlation length that minimizes the entropy density in relation to the velocity of information flow. The MEDM is applied to the financial time series of Standard and Poor's 500 (S&P500) index from February 1983 to April 2006. It is found that EDI of S&P500 index has decreased for the last twenty years, which suggests that the efficiency of the U.S. market dynamics became close to the efficient market hypothesis.
Institute of Scientific and Technical Information of China (English)
Zhao Feng; Li Qinghua
2005-01-01
A new real-time model based on parallel time-series mining is proposed to improve the accuracy and efficiency of the network intrusion detection systems. In this model, multidimensional dataset is constructed to describe network events, and sliding window updating algorithm is used to maintain network stream. Moreover, parallel frequent patterns and frequent episodes mining algorithms are applied to implement parallel time-series mining engineer which can intelligently generate rules to distinguish intrusions from normal activities. Analysis and study on the basis of DAWNING 3000 indicate that this parallel time-series mining-based model provides a more accurate and efficient way to building real-time NIDS.
TimeSeriesStreaming.vi: LabVIEW program for reliable data streaming of large analog time series
Czerwinski, Fabian
2010-01-01
With modern data acquisition devices that work fast and very precise, scientists often face the task of dealing with huge amounts of data. These need to be rapidly processed and stored onto a hard disk. We present a LabVIEW program which reliably streams analog time series of MHz sampling. Its run time has virtually no limitation. We explicitly show how to use the program to extract time series from two experiments: For a photodiode detection system that tracks the position of an optically trapped particle and for a measurement of ionic current through a glass capillary. The program is easy to use and versatile as the input can be any type of analog signal. Also, the data streaming software is simple, highly reliable, and can be easily customized to include, e.g., real-time power spectral analysis and Allan variance noise quantification.
Times series averaging from a probabilistic interpretation of time-elastic kernel
Marteau, Pierre-François
2015-01-01
At the light of regularized dynamic time warping kernels, this paper reconsider the concept of time elastic centroid (TEC) for a set of time series. From this perspective, we show first how TEC can easily be addressed as a preimage problem. Unfortunately this preimage problem is ill-posed, may suffer from over-fitting especially for long time series and getting a sub-optimal solution involves heavy computational costs. We then derive two new algorithms based on a probabilistic interpretation ...
Assessing spatial covariance among time series of abundance.
Jorgensen, Jeffrey C; Ward, Eric J; Scheuerell, Mark D; Zabel, Richard W
2016-04-01
For species of conservation concern, an essential part of the recovery planning process is identifying discrete population units and their location with respect to one another. A common feature among geographically proximate populations is that the number of organisms tends to covary through time as a consequence of similar responses to exogenous influences. In turn, high covariation among populations can threaten the persistence of the larger metapopulation. Historically, explorations of the covariance in population size of species with many (>10) time series have been computationally difficult. Here, we illustrate how dynamic factor analysis (DFA) can be used to characterize diversity among time series of population abundances and the degree to which all populations can be represented by a few common signals. Our application focuses on anadromous Chinook salmon (Oncorhynchus tshawytscha), a species listed under the US Endangered Species Act, that is impacted by a variety of natural and anthropogenic factors. Specifically, we fit DFA models to 24 time series of population abundance and used model selection to identify the minimum number of latent variables that explained the most temporal variation after accounting for the effects of environmental covariates. We found support for grouping the time series according to 5 common latent variables. The top model included two covariates: the Pacific Decadal Oscillation in spring and summer. The assignment of populations to the latent variables matched the currently established population structure at a broad spatial scale. At a finer scale, there was more population grouping complexity. Some relatively distant populations were grouped together, and some relatively close populations - considered to be more aligned with each other - were more associated with populations further away. These coarse- and fine-grained examinations of spatial structure are important because they reveal different structural patterns not evident
Dynamical analysis and visualization of tornadoes time series.
Directory of Open Access Journals (Sweden)
António M Lopes
Full Text Available In this paper we analyze the behavior of tornado time-series in the U.S. from the perspective of dynamical systems. A tornado is a violently rotating column of air extending from a cumulonimbus cloud down to the ground. Such phenomena reveal features that are well described by power law functions and unveil characteristics found in systems with long range memory effects. Tornado time series are viewed as the output of a complex system and are interpreted as a manifestation of its dynamics. Tornadoes are modeled as sequences of Dirac impulses with amplitude proportional to the events size. First, a collection of time series involving 64 years is analyzed in the frequency domain by means of the Fourier transform. The amplitude spectra are approximated by power law functions and their parameters are read as an underlying signature of the system dynamics. Second, it is adopted the concept of circular time and the collective behavior of tornadoes analyzed. Clustering techniques are then adopted to identify and visualize the emerging patterns.
Dynamical analysis and visualization of tornadoes time series.
Lopes, António M; Tenreiro Machado, J A
2015-01-01
In this paper we analyze the behavior of tornado time-series in the U.S. from the perspective of dynamical systems. A tornado is a violently rotating column of air extending from a cumulonimbus cloud down to the ground. Such phenomena reveal features that are well described by power law functions and unveil characteristics found in systems with long range memory effects. Tornado time series are viewed as the output of a complex system and are interpreted as a manifestation of its dynamics. Tornadoes are modeled as sequences of Dirac impulses with amplitude proportional to the events size. First, a collection of time series involving 64 years is analyzed in the frequency domain by means of the Fourier transform. The amplitude spectra are approximated by power law functions and their parameters are read as an underlying signature of the system dynamics. Second, it is adopted the concept of circular time and the collective behavior of tornadoes analyzed. Clustering techniques are then adopted to identify and visualize the emerging patterns. PMID:25790281
Learning time series evolution by unsupervised extraction of correlations
Deco, Gustavo; Schürmann, Bernd
1995-03-01
We focus on the problem of modeling time series by learning statistical correlations between the past and present elements of the series in an unsupervised fashion. This kind of correlation is, in general, nonlinear, especially in the chaotic domain. Therefore the learning algorithm should be able to extract statistical correlations, i.e., higher-order correlations between the elements of the time signal. This problem can be viewed as a special case of factorial learning. Factorial learning may be formulated as an unsupervised redundancy reduction between the output components of a transformation that conserves the transmitted information. An information-theoretic-based architecture and learning paradigm are introduced. The neural architecture has only one layer and a triangular structure in order to transform elements by observing only the past and to conserve the volume. In this fashion, a transformation that guarantees transmission of information without loss is formulated. The learning rule decorrelates the output components of the network. Two methods are used: higher-order decorrelation by explicit evaluation of higher-order cumulants of the output distributions, and minimization of the sum of entropies of each output component in order to minimize the mutual information between them, assuming that the entropies have an upper bound given by Gibbs second theorem. After decorrelation between the output components, the correlation between the elements of the time series can be extracted by analyzing the trained neural architecture. As a consequence, we are able to model chaotic and nonchaotic time series. Furthermore, one critical point in modeling time series is the determination of the dimension of the embedding vector used, i.e., the number of components of the past that are needed to predict the future. With this method we can detect the embedding dimension by extracting the influence of the past on the future, i.e., the correlation of remote past and future
TESTING FOR OUTLIERS IN TIME SERIES USING WAVELETS
Institute of Scientific and Technical Information of China (English)
ZHANG Tong; ZHANG Xibin; ZHANG Shiying
2003-01-01
One remarkable feature of wavelet decomposition is that the wavelet coefficients are localized, and any singularity in the input signals can only affect the wavelet coefficients at the point near the singularity. The localized property of the wavelet coefficients allows us to identify the singularities in the input signals by studying the wavelet coefficients at different resolution levels. This paper considers wavelet-based approaches for the detection of outliers in time series. Outliers are high-frequency phenomena which are associated with the wavelet coefficients with large absolute values at different resolution levels. On the basis of the first-level wavelet coefficients, this paper presents a diagnostic to identify outliers in a time series. Under the null hypothesis that there is no outlier, the proposed diagnostic is distributed as a X12. Empirical examples are presented to demonstrate the application of the proposed diagnostic.
Deviations from uniform power law scaling in nonstationary time series
Viswanathan, G. M.; Peng, C. K.; Stanley, H. E.; Goldberger, A. L.
1997-01-01
A classic problem in physics is the analysis of highly nonstationary time series that typically exhibit long-range correlations. Here we test the hypothesis that the scaling properties of the dynamics of healthy physiological systems are more stable than those of pathological systems by studying beat-to-beat fluctuations in the human heart rate. We develop techniques based on the Fano factor and Allan factor functions, as well as on detrended fluctuation analysis, for quantifying deviations from uniform power-law scaling in nonstationary time series. By analyzing extremely long data sets of up to N = 10(5) beats for 11 healthy subjects, we find that the fluctuations in the heart rate scale approximately uniformly over several temporal orders of magnitude. By contrast, we find that in data sets of comparable length for 14 subjects with heart disease, the fluctuations grow erratically, indicating a loss of scaling stability.
Time series prediction by feedforward neural networks - is it difficult?
International Nuclear Information System (INIS)
The difficulties that a neural network faces when trying to learn from a quasi-periodic time series are studied analytically using a teacher-student scenario where the random input is divided into two macroscopic regions with different variances, 1 and 1/γ2 (γ >> 1). The generalization error is found to decrease as εg ∝ exp(-α/γ2), where α is the number of examples per input dimension. In contradiction to this very slow vanishing generalization error, the next output prediction is found to be almost free of mistakes. This picture is consistent with learning quasi-periodic time series produced by feedforward neural networks, which is dominated by enhanced components of the Fourier spectrum of the input. Simulation results are in good agreement with the analytical results
Model-Coupled Autoencoder for Time Series Visualisation
Gianniotis, Nikolaos; Tiňo, Peter; Polsterer, Kai L
2016-01-01
We present an approach for the visualisation of a set of time series that combines an echo state network with an autoencoder. For each time series in the dataset we train an echo state network, using a common and fixed reservoir of hidden neurons, and use the optimised readout weights as the new representation. Dimensionality reduction is then performed via an autoencoder on the readout weight representations. The crux of the work is to equip the autoencoder with a loss function that correctly interprets the reconstructed readout weights by associating them with a reconstruction error measured in the data space of sequences. This essentially amounts to measuring the predictive performance that the reconstructed readout weights exhibit on their corresponding sequences when plugged back into the echo state network with the same fixed reservoir. We demonstrate that the proposed visualisation framework can deal both with real valued sequences as well as binary sequences. We derive magnification factors in order t...
Fast Nonparametric Clustering of Structured Time-Series.
Hensman, James; Rattray, Magnus; Lawrence, Neil D
2015-02-01
In this publication, we combine two Bayesian nonparametric models: the Gaussian Process (GP) and the Dirichlet Process (DP). Our innovation in the GP model is to introduce a variation on the GP prior which enables us to model structured time-series data, i.e., data containing groups where we wish to model inter- and intra-group variability. Our innovation in the DP model is an implementation of a new fast collapsed variational inference procedure which enables us to optimize our variational approximation significantly faster than standard VB approaches. In a biological time series application we show how our model better captures salient features of the data, leading to better consistency with existing biological classifications, while the associated inference algorithm provides a significant speed-up over EM-based variational inference. PMID:26353249
The multiscale analysis between stock market time series
Shi, Wenbin; Shang, Pengjian
2015-11-01
This paper is devoted to multiscale cross-correlation analysis on stock market time series, where multiscale DCCA cross-correlation coefficient as well as multiscale cross-sample entropy (MSCE) is applied. Multiscale DCCA cross-correlation coefficient is a realization of DCCA cross-correlation coefficient on multiple scales. The results of this method present a good scaling characterization. More significantly, this method is able to group stock markets by areas. Compared to multiscale DCCA cross-correlation coefficient, MSCE presents a more remarkable scaling characterization and the value of each log return of financial time series decreases with the increasing of scale factor. But the results of grouping is not as good as multiscale DCCA cross-correlation coefficient.
Chaotic time series. Part II. System Identification and Prediction
Directory of Open Access Journals (Sweden)
Bjørn Lillekjendlie
1994-10-01
Full Text Available This paper is the second in a series of two, and describes the current state of the art in modeling and prediction of chaotic time series. Sample data from deterministic non-linear systems may look stochastic when analysed with linear methods. However, the deterministic structure may be uncovered and non-linear models constructed that allow improved prediction. We give the background for such methods from a geometrical point of view, and briefly describe the following types of methods: global polynomials, local polynomials, multilayer perceptrons and semi-local methods including radial basis functions. Some illustrative examples from known chaotic systems are presented, emphasising the increase in prediction error with time. We compare some of the algorithms with respect to prediction accuracy and storage requirements, and list applications of these methods to real data from widely different areas.
Modeling Philippine Stock Exchange Composite Index Using Time Series Analysis
Gayo, W. S.; Urrutia, J. D.; Temple, J. M. F.; Sandoval, J. R. D.; Sanglay, J. E. A.
2015-06-01
This study was conducted to develop a time series model of the Philippine Stock Exchange Composite Index and its volatility using the finite mixture of ARIMA model with conditional variance equations such as ARCH, GARCH, EG ARCH, TARCH and PARCH models. Also, the study aimed to find out the reason behind the behaviorof PSEi, that is, which of the economic variables - Consumer Price Index, crude oil price, foreign exchange rate, gold price, interest rate, money supply, price-earnings ratio, Producers’ Price Index and terms of trade - can be used in projecting future values of PSEi and this was examined using Granger Causality Test. The findings showed that the best time series model for Philippine Stock Exchange Composite index is ARIMA(1,1,5) - ARCH(1). Also, Consumer Price Index, crude oil price and foreign exchange rate are factors concluded to Granger cause Philippine Stock Exchange Composite Index.
Time Series Analysis, Modeling and Applications A Computational Intelligence Perspective
Chen, Shyi-Ming
2013-01-01
Temporal and spatiotemporal data form an inherent fabric of the society as we are faced with streams of data coming from numerous sensors, data feeds, recordings associated with numerous areas of application embracing physical and human-generated phenomena (environmental data, financial markets, Internet activities, etc.). A quest for a thorough analysis, interpretation, modeling and prediction of time series comes with an ongoing challenge for developing models that are both accurate and user-friendly (interpretable). The volume is aimed to exploit the conceptual and algorithmic framework of Computational Intelligence (CI) to form a cohesive and comprehensive environment for building models of time series. The contributions covered in the volume are fully reflective of the wealth of the CI technologies by bringing together ideas, algorithms, and numeric studies, which convincingly demonstrate their relevance, maturity and visible usefulness. It reflects upon the truly remarkable diversity of methodological a...
A Non-standard Empirical Likelihood for Time Series
DEFF Research Database (Denmark)
Nordman, Daniel J.; Bunzel, Helle; Lahiri, Soumendra N.
Standard blockwise empirical likelihood (BEL) for stationary, weakly dependent time series requires specifying a fixed block length as a tuning parameter for setting confidence regions. This aspect can be difficult and impacts coverage accuracy. As an alternative, this paper proposes a new version......-standard asymptotics and requires a significantly different development compared to standard BEL. We establish the large-sample distribution of log-ratio statistics from the new BEL method for calibrating confidence regions for mean or smooth function parameters of time series. This limit law is not the usual chi......-square one, but is distribution-free and can be reproduced through straightforward simulations. Numerical studies indicate that the proposed method generally exhibits better coverage accuracy than standard BEL....
A Comparative Study of Portmanteau Tests for Univariate Time Series Models
Directory of Open Access Journals (Sweden)
Sohail Chand
2006-07-01
Full Text Available Time series model diagnostic checking is the most important stage of time series model building. In this paper the comparison among several suggested diagnostic tests has been made using the simulation time series data.
DEM error retrieval by analyzing time series of differential interferograms
Bombrun, Lionel; Gay, Michel; Trouvé, Emmanuel; Vasile, Gabriel; Mars, Jerome,
2009-01-01
2-pass Differential Synthetic Aperture Radar Interferometry (D-InSAR) processing have been successfully used by the scientific community to derive velocity fields. Nevertheless, a precise Digital Elevation Model (DEM) is necessary to remove the topographic component from the interferograms. This letter presents a novel method to detect and retrieve DEM errors by analyzing time series of differential interferograms. The principle of the method is based on the comparison of fringe patterns with...
A New Hybrid Methodology for Nonlinear Time Series Forecasting
Mehdi Khashei; Mehdi Bijari
2011-01-01
Artificial neural networks (ANNs) are flexible computing frameworks and universal approximators that can be applied to a wide range of forecasting problems with a high degree of accuracy. However, using ANNs to model linear problems have yielded mixed results, and hence; it is not wise to apply them blindly to any type of data. This is the reason that hybrid methodologies combining linear models such as ARIMA and nonlinear models such as ANNs have been proposed in the literature of time serie...
Data-driven simulation of complex multidimensional time series
Lee W. Schruben; Singham, Dashi I.
2014-01-01
This article introduces a new framework for resampling general time series data. The approach, inspired by computer agent flocking algorithms, can be used to generate inputs to complex simulation models or for generating pseudo-replications of expensive simulation outputs. The method has the flexibility to enable replicated sensitivity analysis for trace-driven simulation, which is critical for risk assessment. The article includes two simple implementations to illustrate the approach. Th...
A data-fitting procedure for chaotic time series
Energy Technology Data Exchange (ETDEWEB)
McDonough, J.M.; Mukerji, S. [Univ. of Kentucky, Lexington, KY (United States). Dept. of Mechanical Engineering; Chung, S. [Univ. of Illinois, Urbana, IL (United States)
1998-10-01
In this paper the authors introduce data characterizations for fitting chaotic data to linear combinations of one-dimensional maps (say, of the unit interval) for use in subgrid-scale turbulence models. They test the efficacy of these characterizations on data generated by a chaotically-forced Burgers` equation and demonstrate very satisfactory results in terms of modeled time series, power spectra and delay maps.
Clustering Time-Series Energy Data from Smart Meters
Lavin, Alexander; Klabjan, Diego
2016-01-01
Investigations have been performed into using clustering methods in data mining time-series data from smart meters. The problem is to identify patterns and trends in energy usage profiles of commercial and industrial customers over 24-hour periods, and group similar profiles. We tested our method on energy usage data provided by several U.S. power utilities. The results show accurate grouping of accounts similar in their energy usage patterns, and potential for the method to be utilized in en...
Automated analysis of protein subcellular location in time series images
Hu, Yanhua; Osuna-Highley, Elvira; Hua, Juchang; Nowicki, Theodore Scott; Stolz, Robert; McKayle, Camille; Murphy, Robert F.
2010-01-01
Motivation: Image analysis, machine learning and statistical modeling have become well established for the automatic recognition and comparison of the subcellular locations of proteins in microscope images. By using a comprehensive set of features describing static images, major subcellular patterns can be distinguished with near perfect accuracy. We now extend this work to time series images, which contain both spatial and temporal information. The goal is to use temporal features to improve...
High frequency financial time series prediction: machine learning approach
Zankova, Ekaterina
2016-01-01
Machine learning is a rapidly evolving subfield of computer science. It has enormous amount of applications. One of the application domains is financial data analysis. Machine learning was usually applied for analysis and forecasting of daily financial time series. Availability of high frequency financial data became another challenge with its own specifics and difficulties. Regressors, being a significant part of machine learning field, have been selected as study subjects for this project. ...
Properties of batch means from stationary ARMA time series
Kang, Keebom; Schmeiser, Bruce
1986-01-01
The batch means process arising from an arbitrary autoregressive moving-average (ARMA) process time series is derived. As side results, the variance and correlation structures of the batch means process as functions of the batch size and parameters of the original process are obtained. Except for the first-order ARMA process, for which a closed-form expression is obtained, the parameters of the batch-means process are determined numerically. Keywords: Monte Carlo method; Simulation. (Author)
Time series clustering based on nonparametric multidimensional forecast densities
Vilar, José A.; Vilar, Juan M.
2013-01-01
A new time series clustering method based on comparing forecast densities for a sequence of $k>1$ consecutive horizons is proposed. The unknown $k$-dimensional forecast densities can be non-parametrically approximated by using bootstrap procedures that mimic the generating processes without parametric restrictions. However, the difficulty of constructing accurate kernel estimators of multivariate densities is well known. To circumvent the high dimensionality problem, the bootstrap prediction ...
Evaluation of Time Series Techniques to Characterise Domestic Electricity Demand
McLoughlin, Fintan; Duffy, Aidan; Conlon, Michael
2013-01-01
This paper discusses time series approaches, often used by Transmission System Operators (TSOs) to forecast system demand, and applies them at an individual dwelling level. In particular, two techniques, Fourier transforms and Gaussian processes were evaluated and used to characterise individual household electricity demand. The performance of the characterisation approaches were evaluated based on Pearson correlation coefficient, descriptive statistics and paired sample t-tests for electrica...
On Clustering Time Series Using Euclidean Distance and Pearson Correlation
MICHAEL R BERTHOLD; Höppner, Frank
2016-01-01
For time series comparisons, it has often been observed that z-score normalized Euclidean distances far outperform the unnormalized variant. In this paper we show that a z-score normalized, squared Euclidean Distance is, in fact, equal to a distance based on Pearson Correlation. This has profound impact on many distance-based classification or clustering methods. In addition to this theoretically sound result we also show that the often used k-Means algorithm formally needs a mod ification to...
Review on Periodicity Mining Techniques in Time Series Data
Yogesh Malode , Rahila Patel
2012-01-01
The rapid growth in data and databases increased a need of powerful data mining technique that will guide to analyze, forecast and predict behaviour of events. Periodicity mining needs to give more attention as its increased need in real life applications. In this paper, we are going to discuss on various periodicity mining techniques in Time Series Databases as well as symbolization. Here, we propose a periodicity mining technique that will detect various periodic patterns (symbol periodici...
Surrogate data method applied to nonlinear time series
Luo, Xiaodong; Nakamura, Tomomichi; Small, Michael
2006-01-01
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 m...
Mode Analysis with Autocorrelation Method (Single Time Series) in Tokamak
Saadat, Shervin; Salem, Mohammad K.; Goranneviss, Mahmoud; Khorshid, Pejman
2010-08-01
In this paper plasma mode analyzed with statistical method that designated Autocorrelation function. Auto correlation function used from one time series, so for this purpose we need one Minov coil. After autocorrelation analysis on mirnov coil data, spectral density diagram is plotted. Spectral density diagram from symmetries and trends can analyzed plasma mode. RHF fields effects with this method ate investigated in IR-T1 tokamak and results corresponded with multichannel methods such as SVD and FFT.
Time series regression model for infectious disease and weather.
Imai, Chisato; Armstrong, Ben; Chalabi, Zaid; Mangtani, Punam; Hashizume, Masahiro
2015-10-01
Time series regression has been developed and long used to evaluate the short-term associations of air pollution and weather with mortality or morbidity of non-infectious diseases. The application of the regression approaches from this tradition to infectious diseases, however, is less well explored and raises some new issues. We discuss and present potential solutions for five issues often arising in such analyses: changes in immune population, strong autocorrelations, a wide range of plausible lag structures and association patterns, seasonality adjustments, and large overdispersion. The potential approaches are illustrated with datasets of cholera cases and rainfall from Bangladesh and influenza and temperature in Tokyo. Though this article focuses on the application of the traditional time series regression to infectious diseases and weather factors, we also briefly introduce alternative approaches, including mathematical modeling, wavelet analysis, and autoregressive integrated moving average (ARIMA) models. Modifications proposed to standard time series regression practice include using sums of past cases as proxies for the immune population, and using the logarithm of lagged disease counts to control autocorrelation due to true contagion, both of which are motivated from "susceptible-infectious-recovered" (SIR) models. The complexity of lag structures and association patterns can often be informed by biological mechanisms and explored by using distributed lag non-linear models. For overdispersed models, alternative distribution models such as quasi-Poisson and negative binomial should be considered. Time series regression can be used to investigate dependence of infectious diseases on weather, but may need modifying to allow for features specific to this context. PMID:26188633
Time series prediction using artificial neural network for power stabilization
International Nuclear Information System (INIS)
Time series prediction has been applied to many business and scientific applications. Prominent among them are stock market prediction, weather forecasting, etc. Here, this technique has been applied to forecast plasma torch voltages to stabilize power using a backpropagation, a model of artificial neural network. The Extended-Delta-Bar-Delta algorithm is used to improve the convergence rate of the network and also to avoid local minima. Results from off-line data was quite promising to use in on-line
A Novel Adaptive Predictor for Chaotic Time Series
Institute of Scientific and Technical Information of China (English)
BU Yun; WEN Guang-Jun; ZHOU Xiao-Jia; ZHANG Qiang
2009-01-01
Many chaotic time series show non-Gaussian distribution, and non-Gaussianity can be characterized not only by higher-order cumulants but also by negative entropy.Since negative entropy can be accurately approximated by some special non-polynomial functions, which also can form an orthogonal system, these functions are used to construct an adaptive predictor to replace higher-order cumulants.Simulation shows the algorithm performs well for different chaotic systems.
Time series prediction using a rational fraction neural networks
Energy Technology Data Exchange (ETDEWEB)
Lee, K.; Lee, Y.C.; Barnes, C.; Aldrich, C.H.; Kindel, J.
1988-01-01
An efficient neural network based on a rational fraction representation has been trained to perform time series prediction. The network is a generalization of the Volterra-Wiener network while still retaining the computational efficiency of the latter. Because of the second order convergent nature of the learning algorithm, the rational net is computationally far more efficient than multilayer networks. The rational fractional representation is, however, more restrictive than the multilayer networks.
River flow time series using least squares support vector machines
R. Samsudin; P. Saad; A. Shabri
2011-01-01
This paper proposes a novel hybrid forecasting model known as GLSSVM, which combines the group method of data handling (GMDH) and the least squares support vector machine (LSSVM). The GMDH is used to determine the useful input variables which work as the time series forecasting for the LSSVM model. Monthly river flow data from two stations, the Selangor and Bernam rivers in Selangor state of Peninsular Malaysia were taken into consideration in the development of this hybrid model. The perform...
Multifractal analysis of time series generated by discrete Ito equations
Energy Technology Data Exchange (ETDEWEB)
Telesca, Luciano [National Research Council, Institute of Methodologies for Environmental Analysis, C.da S. Loja, 85050 Tito (PZ) (Italy); Czechowski, Zbigniew [Institute of Geophysics Polish Academy of Sciences, 01-452 Warsaw, Ks. Janusza 64 (Poland); Lovallo, Michele [ARPAB, 85100 Potenza (Italy)
2015-06-15
In this study, we show that discrete Ito equations with short-tail Gaussian marginal distribution function generate multifractal time series. The multifractality is due to the nonlinear correlations, which are hidden in Markov processes and are generated by the interrelation between the drift and the multiplicative stochastic forces in the Ito equation. A link between the range of the generalized Hurst exponents and the mean of the squares of all averaged net forces is suggested.
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks
Directory of Open Access Journals (Sweden)
Jie Wang
2016-01-01
(ERNN, the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices.
Using Artificial Neural Networks To Forecast Financial Time Series
Aamodt, Rune
2010-01-01
This thesis investigates the application of artificial neural networks (ANNs) for forecasting financial time series (e.g. stock prices).The theory of technical analysis dictates that there are repeating patterns that occur in the historic prices of stocks, and that identifying these patterns can be of help in forecasting future price developments. A system was therefore developed which contains several ``agents'', each producing recommendations on the stock price based on some aspect of techn...
Forecasting Stock Prices by Using Alternative Time Series Models
Kivilcim Metin; Gulnur Muradoglu
2000-01-01
The purpose of this paper is to compare the forecast performance of alternative time series models, namely VAR in levels, stochastic seasonal models (SSM) and error correction models (ECM) at the Istanbul Stock Exchange (ISE). Considering the emerging market characteristic of the ISE, stock prices are estimated by using, money supply, inflation rate, interest rates, exchange rates and budget deficits. Then, in an out-of-sample forecasting exercise from January 1995 through December 1995, comp...
Seasonal modulation mixed models for time series forecasting
Durbán, María; Lee, Dae-Jin
2012-01-01
We propose an extension of a seasonal modulation smooth model with P-splines for times series data using a mixed model formulation. A smooth trend with seasonality decomposition can be estimated simultaneously. We extend the model to consider the forecasting of new future observations in the mixed model framework. Two different approaches are used for forecasting in the context of mixed models, and the equivalence of both methods is shown. The methodology is illustrated with mo...
Improved nonparametric confidence intervals in time series regressions
Romano, Joseph P.; Wolf, Michael
2002-01-01
Confidence intervals in time series regressions suffer from notorious coverage problems. This is especially true when the dependence in the data is noticeable and sample sizes are small to moderate, as is often the case in empirical studies. This paper proposes a method that combines prewhitening and the studentized bootstrap. While both prewhitening and the studentized bootstrap each provides improvement over standard normal theory intervals, one can achieve a further improvement by conjoini...
Factor models in high-dimensional time series
Hallin, Marc; Lippi, Marco
2013-01-01
High-dimensional time series may well be the most common type of dataset in the so-called "big data" revolution, and have entered current practice in many areas, including meteorology, genomics, chemometrics, connectomics, complex physics simulations, biological and environmental research, finance and econometrics. The analysis of such datasets poses significant challenges, both from a statistical as from a numerical point of view. The most successful procedures so far have bee...
Phillips, D. A.; Meertens, C. M.; Hodgkinson, K. M.; Puskas, C. M.; Boler, F. M.; Snett, L.; Mattioli, G. S.
2013-12-01
We present an overview of time series data, tools and services available from UNAVCO along with two specific and compelling examples of geodetic time series analysis. UNAVCO provides a diverse suite of geodetic data products and cyberinfrastructure services to support community research and education. The UNAVCO archive includes data from 2500+ continuous GPS stations, borehole geophysics instruments (strainmeters, seismometers, tiltmeters, pore pressure sensors), and long baseline laser strainmeters. These data span temporal scales from seconds to decades and provide global spatial coverage with regionally focused networks including the EarthScope Plate Boundary Observatory (PBO) and COCONet. This rich, open access dataset is a tremendous resource that enables the exploration, identification and analysis of time varying signals associated with crustal deformation, reference frame determinations, isostatic adjustments, atmospheric phenomena, hydrologic processes and more. UNAVCO provides a suite of time series exploration and analysis resources including static plots, dynamic plotting tools, and data products and services designed to enhance time series analysis. The PBO GPS network allow for identification of ~1 mm level deformation signals. At some GPS stations seasonal signals and longer-term trends in both the vertical and horizontal components can be dominated by effects of hydrological loading from natural and anthropogenic sources. Modeling of hydrologic deformation using GLDAS and a variety of land surface models (NOAH, MOSAIC, VIC and CLM) shows promise for independently modeling hydrologic effects and separating them from tectonic deformation as well as anthropogenic loading sources. A major challenge is to identify where loading is dominant and corrections from GLDAS can apply and where pumping is the dominant signal and corrections are not possible without some other data. In another arena, the PBO strainmeter network was designed to capture small short
Detection of "hidden Regimes" In Stochastic Cyclostationary Time Series
Wirth, V.
Idealized descriptions of geophysical systems sometimes lead to stochastic differential equations characterized by a deterministic part and a stochastic part. In the case of nonlinearity the deterministic part may support multiple equilibria. For nonstationary processes such multiple equilibria are not necessarily reflected as relative maxima of the probability density function (PDF). This occurs when the duration of a regime is too short for the PDF to adjust, and such regimes are dubbed "hidden". This work focuses on cyclostationary Markovian processes. An example is given derived from a simplified model for the seasonal evolution of soil moisture. Although in summer the system is attracted to either a dry or a moist state, the evolution is slow enough for the PDF to remain unimodal throughout the year. An algorithm is presented which allows one to detect such hidden regimes given the data of the time series only. The method involves the analysis of an appropriately windowed time series, from which the drift and diffusion coefficients of the associated Fokker-Planck equation are estimated. The success of the algorithm is illustrated using synthetic time series.
Modeling financial time series with S-plus
Zivot, Eric
2003-01-01
The field of financial econometrics has exploded over the last decade This book represents an integration of theory, methods, and examples using the S-PLUS statistical modeling language and the S+FinMetrics module to facilitate the practice of financial econometrics This is the first book to show the power of S-PLUS for the analysis of time series data It is written for researchers and practitioners in the finance industry, academic researchers in economics and finance, and advanced MBA and graduate students in economics and finance Readers are assumed to have a basic knowledge of S-PLUS and a solid grounding in basic statistics and time series concepts Eric Zivot is an associate professor and Gary Waterman Distinguished Scholar in the Economics Department at the University of Washington, and is co-director of the nascent Professional Master's Program in Computational Finance He regularly teaches courses on econometric theory, financial econometrics and time series econometrics, and is the recipient of the He...
Clustering Multivariate Time Series Using Hidden Markov Models
Directory of Open Access Journals (Sweden)
Shima Ghassempour
2014-03-01
Full Text Available In this paper we describe an algorithm for clustering multivariate time series with variables taking both categorical and continuous values. Time series of this type are frequent in health care, where they represent the health trajectories of individuals. The problem is challenging because categorical variables make it difficult to define a meaningful distance between trajectories. We propose an approach based on Hidden Markov Models (HMMs, where we first map each trajectory into an HMM, then define a suitable distance between HMMs and finally proceed to cluster the HMMs with a method based on a distance matrix. We test our approach on a simulated, but realistic, data set of 1,255 trajectories of individuals of age 45 and over, on a synthetic validation set with known clustering structure, and on a smaller set of 268 trajectories extracted from the longitudinal Health and Retirement Survey. The proposed method can be implemented quite simply using standard packages in R and Matlab and may be a good candidate for solving the difficult problem of clustering multivariate time series with categorical variables using tools that do not require advanced statistic knowledge, and therefore are accessible to a wide range of researchers.
Time series analysis of age related cataract hospitalizations and phacoemulsification
Directory of Open Access Journals (Sweden)
Moineddin Rahim
2006-01-01
Full Text Available Abstract Background Cataract surgery remains a commonly performed elective surgical procedure in the aging and the elderly. The purpose of this study was to utilize time series methodology to determine the temporal and seasonal variations and the strength of the seasonality in age-related (senile cataract hospitalizations and phacoemulsification surgeries. Methods A retrospective, cross-sectional time series analysis was used to assess the presence and strength of seasonal and temporal patterns of age-related cataract hospitalizations and phacoemulsification surgeries from April 1, 1991 to March 31, 2002. Hospital admission rates for senile cataract (n = 70,281 and phacoemulsification (n = 556,431 were examined to determine monthly rates of hospitalization per 100,000 population. Time series methodology was then applied to the monthly aggregates. Results During the study period, age-related cataract hospitalizations in Ontario have declined from approximately 40 per 100,000 to only one per 100,000. Meanwhile, the use of phacoemulsification procedures has risen dramatically. The study found evidence of biannual peaks in both procedures during the spring and autumn months, and summer and winter troughs. Statistical analysis revealed significant overall seasonal patterns for both age-related cataract hospitalizations and phacoemulsifications (p Conclusion This study illustrates the decline in age-related cataract hospitalizations in Ontario resulting from the shift to outpatient phacoemulsification surgery, and demonstrates the presence of biannual peaks (a characteristic indicative of seasonality, in hospitalization and phacoemulsification during the spring and autumn throughout the study period.
Complexity analysis of the UV radiation dose time series
Mihailovic, Dragutin T
2013-01-01
We have used the Lempel-Ziv and sample entropy measures to assess the complexity in the UV radiation activity in the Vojvodina region (Serbia) for the period 1990-2007. In particular, we have examined the reconstructed daily sum (dose) of the UV-B time series from seven representative places in this region and calculated the Lempel-Ziv Complexity (LZC) and Sample Entropy (SE) values for each time series. The results indicate that the LZC values in some places are close to each other while in others they differ. We have devided the period 1990-2007 into two subintervals: (a) 1990-1998 and (b) 1999-2007 and calculated LZC and SE values for the various time series in these subintervals. It is found that during the period 1999-2007, there is a decrease in their complexities, and corresponding changes in the SE, in comparison to the period 1990-1998. This complexity loss may be attributed to increased (i) human intervention in the post civil war period (land and crop use and urbanization) and military activities i...
A method for generating high resolution satellite image time series
Guo, Tao
2014-10-01
There is an increasing demand for satellite remote sensing data with both high spatial and temporal resolution in many applications. But it still is a challenge to simultaneously improve spatial resolution and temporal frequency due to the technical limits of current satellite observation systems. To this end, much R&D efforts have been ongoing for years and lead to some successes roughly in two aspects, one includes super resolution, pan-sharpen etc. methods which can effectively enhance the spatial resolution and generate good visual effects, but hardly preserve spectral signatures and result in inadequate analytical value, on the other hand, time interpolation is a straight forward method to increase temporal frequency, however it increase little informative contents in fact. In this paper we presented a novel method to simulate high resolution time series data by combing low resolution time series data and a very small number of high resolution data only. Our method starts with a pair of high and low resolution data set, and then a spatial registration is done by introducing LDA model to map high and low resolution pixels correspondingly. Afterwards, temporal change information is captured through a comparison of low resolution time series data, and then projected onto the high resolution data plane and assigned to each high resolution pixel according to the predefined temporal change patterns of each type of ground objects. Finally the simulated high resolution data is generated. A preliminary experiment shows that our method can simulate a high resolution data with a reasonable accuracy. The contribution of our method is to enable timely monitoring of temporal changes through analysis of time sequence of low resolution images only, and usage of costly high resolution data can be reduces as much as possible, and it presents a highly effective way to build up an economically operational monitoring solution for agriculture, forest, land use investigation
Forecasting economic time series with unconditional time-varying variance. Int. J. Forecast.
Van Bellegem, Sébastien
2004-01-01
The classical forecasting theory of stationary time series exploits the second-order structure (variance, autocovariance, and spectral density) of an observed process in order to construct some prediction intervals. However, some economic time series show a time-varying unconditional second-order structure. This article focuses on a simple and meaningful model allowing this nonstationary behaviour. We show that this model satisfactorily explains the nonstationary behaviour of several economic...
STUDIES IN ASTRONOMICAL TIME SERIES ANALYSIS. VI. BAYESIAN BLOCK REPRESENTATIONS
International Nuclear Information System (INIS)
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it—an improved and generalized version of Bayesian Blocks—that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piecewise linear and piecewise exponential representations, multivariate time series data, analysis of variance, data on the circle, other data modes, and dispersed data. Simulations provide evidence that the detection efficiency for weak signals is close to a theoretical asymptotic limit derived by Arias-Castro et al. In the spirit of Reproducible Research all of the code and data necessary to reproduce all of the figures in this paper are included as supplementary material.
STUDIES IN ASTRONOMICAL TIME SERIES ANALYSIS. VI. BAYESIAN BLOCK REPRESENTATIONS
Energy Technology Data Exchange (ETDEWEB)
Scargle, Jeffrey D. [Space Science and Astrobiology Division, MS 245-3, NASA Ames Research Center, Moffett Field, CA 94035-1000 (United States); Norris, Jay P. [Physics Department, Boise State University, 2110 University Drive, Boise, ID 83725-1570 (United States); Jackson, Brad [The Center for Applied Mathematics and Computer Science, Department of Mathematics, San Jose State University, One Washington Square, MH 308, San Jose, CA 95192-0103 (United States); Chiang, James, E-mail: jeffrey.d.scargle@nasa.gov [W. W. Hansen Experimental Physics Laboratory, Kavli Institute for Particle Astrophysics and Cosmology, Department of Physics and SLAC National Accelerator Laboratory, Stanford University, Stanford, CA 94305 (United States)
2013-02-20
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it-an improved and generalized version of Bayesian Blocks-that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piecewise linear and piecewise exponential representations, multivariate time series data, analysis of variance, data on the circle, other data modes, and dispersed data. Simulations provide evidence that the detection efficiency for weak signals is close to a theoretical asymptotic limit derived by Arias-Castro et al. In the spirit of Reproducible Research all of the code and data necessary to reproduce all of the figures in this paper are included as supplementary material.
Studies in Astronomical Time Series Analysis. VI. Bayesian Block Representations
Scargle, Jeffrey D.; Norris, Jay P.; Jackson, Brad; Chiang, James
2013-01-01
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it-an improved and generalized version of Bayesian Blocks [Scargle 1998]-that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piece- wise linear and piecewise exponential representations, multivariate time series data, analysis of variance, data on the circle, other data modes, and dispersed data. Simulations provide evidence that the detection efficiency for weak signals is close to a theoretical asymptotic limit derived by [Arias-Castro, Donoho and Huo 2003]. In the spirit of Reproducible Research [Donoho et al. (2008)] all of the code and data necessary to reproduce all of the figures in this paper are included as auxiliary material.
Assessing Coupling Dynamics from an Ensemble of Time Series
Directory of Open Access Journals (Sweden)
Germán Gómez-Herrero
2015-04-01
Full Text Available Finding interdependency relations between time series provides valuable knowledge about the processes that generated the signals. Information theory sets a natural framework for important classes of statistical dependencies. However, a reliable estimation from information-theoretic functionals is hampered when the dependency to be assessed is brief or evolves in time. Here, we show that these limitations can be partly alleviated when we have access to an ensemble of independent repetitions of the time series. In particular, we gear a data-efficient estimator of probability densities to make use of the full structure of trial-based measures. By doing so, we can obtain time-resolved estimates for a family of entropy combinations (including mutual information, transfer entropy and their conditional counterparts, which are more accurate than the simple average of individual estimates over trials. We show with simulated and real data generated by coupled electronic circuits that the proposed approach allows one to recover the time-resolved dynamics of the coupling between different subsystems.
Nonlinear time-series-based adaptive control applications
Mohler, R. R.; Rajkumar, V.; Zakrzewski, R. R.
1991-01-01
A control design methodology based on a nonlinear time-series reference model is presented. It is indicated by highly nonlinear simulations that such designs successfully stabilize troublesome aircraft maneuvers undergoing large changes in angle of attack as well as large electric power transients due to line faults. In both applications, the nonlinear controller was significantly better than the corresponding linear adaptive controller. For the electric power network, a flexible AC transmission system with series capacitor power feedback control is studied. A bilinear autoregressive moving average reference model is identified from system data, and the feedback control is manipulated according to a desired reference state. The control is optimized according to a predictive one-step quadratic performance index. A similar algorithm is derived for control of rapid changes in aircraft angle of attack over a normally unstable flight regime. In the latter case, however, a generalization of a bilinear time-series model reference includes quadratic and cubic terms in angle of attack.
Satellite Image Time Series Decomposition Based on EEMD
Directory of Open Access Journals (Sweden)
Yun-long Kong
2015-11-01
Full Text Available Satellite Image Time Series (SITS have recently been of great interest due to the emerging remote sensing capabilities for Earth observation. Trend and seasonal components are two crucial elements of SITS. In this paper, a novel framework of SITS decomposition based on Ensemble Empirical Mode Decomposition (EEMD is proposed. EEMD is achieved by sifting an ensemble of adaptive orthogonal components called Intrinsic Mode Functions (IMFs. EEMD is noise-assisted and overcomes the drawback of mode mixing in conventional Empirical Mode Decomposition (EMD. Inspired by these advantages, the aim of this work is to employ EEMD to decompose SITS into IMFs and to choose relevant IMFs for the separation of seasonal and trend components. In a series of simulations, IMFs extracted by EEMD achieved a clear representation with physical meaning. The experimental results of 16-day compositions of Moderate Resolution Imaging Spectroradiometer (MODIS, Normalized Difference Vegetation Index (NDVI, and Global Environment Monitoring Index (GEMI time series with disturbance illustrated the effectiveness and stability of the proposed approach to monitoring tasks, such as applications for the detection of abrupt changes.
Time-Series Analysis of Supergranule Characterstics at Solar Minimum
Williams, Peter E.; Pesnell, W. Dean
2013-01-01
Sixty days of Doppler images from the Solar and Heliospheric Observatory (SOHO) / Michelson Doppler Imager (MDI) investigation during the 1996 and 2008 solar minima have been analyzed to show that certain supergranule characteristics (size, size range, and horizontal velocity) exhibit fluctuations of three to five days. Cross-correlating parameters showed a good, positive correlation between supergranulation size and size range, and a moderate, negative correlation between size range and velocity. The size and velocity do exhibit a moderate, negative correlation, but with a small time lag (less than 12 hours). Supergranule sizes during five days of co-temporal data from MDI and the Solar Dynamics Observatory (SDO) / Helioseismic Magnetic Imager (HMI) exhibit similar fluctuations with a high level of correlation between them. This verifies the solar origin of the fluctuations, which cannot be caused by instrumental artifacts according to these observations. Similar fluctuations are also observed in data simulations that model the evolution of the MDI Doppler pattern over a 60-day period. Correlations between the supergranule size and size range time-series derived from the simulated data are similar to those seen in MDI data. A simple toy-model using cumulative, uncorrelated exponential growth and decay patterns at random emergence times produces a time-series similar to the data simulations. The qualitative similarities between the simulated and the observed time-series suggest that the fluctuations arise from stochastic processes occurring within the solar convection zone. This behavior, propagating to surface manifestations of supergranulation, may assist our understanding of magnetic-field-line advection, evolution, and interaction.
Soil radon time series: Surveys in seismic and volcanic areas
International Nuclear Information System (INIS)
Soil radon surveys have been performed in a long term monitoring basis with SSNTD (LR 115 type II), in order to observe possible fluctuations due to high magnitude seismic events and volcanic eruptions. Five-year radon time series are available in stations located in an intense seismic zone located along the Pacific coast of Mexico. The series analyses have been performed as a function of the local seismicity and geological characteristics. A discussion is intended to explain the lack of biunivocal relation between single radon peaks and earthquakes for the long term monitoring data using SSNTDs. Examples of short term radon anomalies obtained with continuous probes are also discussed as a function of local earthquakes and meteorological perturbations. Additionally, complementary results from recent changes in the activity pattern of an active volcano indicate that degassing processes induced anomalous soil radon emanation correlated with the volcanic activity changes
Research on time series mining based on shape concept time warping
Institute of Scientific and Technical Information of China (English)
翁颖钧; 朱仲英
2004-01-01
Time series is an important kind of complex data, while a growing attention has been paid to mining time series knowledge recently. Typically Euclidean distance measure is used for comparing time series. However, it may be a brittle distance measure because of less robustness. Dynamic time warp is a pattern matching algorithm based on nonlinear dynamic programming technique, however it is computationally expensive and suffered from the local shape variance. A modification algorithm named by shape DTW is presented, which uses linguistic variable concept to describe the slope feather of time series. The concept tree is developed by cloud models theory which integrates randomness and probability of uncertainty, so that it makes conversion between qualitative and quantitive knowledge. Experiments about cluster analysis on the basis of this algorithm, compared with Euclidean measure, are implemented on synthetic control chart time series. The results show that this method has strong robustness to loss of feature data due to piecewise segment preprocessing. Moreover, after the construction of shape concept tree, we can discovery knowledge of time series on different time granularity.
Time series analysis of the behavior of brazilian natural rubber
Directory of Open Access Journals (Sweden)
Antônio Donizette de Oliveira
2009-03-01
Full Text Available The natural rubber is a non-wood product obtained of the coagulation of some lattices of forest species, being Hevea brasiliensis the main one. Native from the Amazon Region, this species was already known by the Indians before the discovery of America. The natural rubber became a product globally valued due to its multiple applications in the economy, being its almost perfect substitute the synthetic rubber derived from the petroleum. Similarly to what happens with other countless products the forecast of future prices of the natural rubber has been object of many studies. The use of models of forecast of univariate timeseries stands out as the more accurate and useful to reduce the uncertainty in the economic decision making process. This studyanalyzed the historical series of prices of the Brazilian natural rubber (R$/kg, in the Jan/99 - Jun/2006 period, in order tocharacterize the rubber price behavior in the domestic market; estimated a model for the time series of monthly natural rubberprices; and foresaw the domestic prices of the natural rubber, in the Jul/2006 - Jun/2007 period, based on the estimated models.The studied models were the ones belonging to the ARIMA family. The main results were: the domestic market of the natural rubberis expanding due to the growth of the world economy; among the adjusted models, the ARIMA (1,1,1 model provided the bestadjustment of the time series of prices of the natural rubber (R$/kg; the prognosis accomplished for the series supplied statistically adequate fittings.
Monitoring Forest Regrowth Using a Multi-Platform Time Series
Sabol, Donald E., Jr.; Smith, Milton O.; Adams, John B.; Gillespie, Alan R.; Tucker, Compton J.
1996-01-01
Over the past 50 years, the forests of western Washington and Oregon have been extensively harvested for timber. This has resulted in a heterogeneous mosaic of remaining mature forests, clear-cuts, new plantations, and second-growth stands that now occur in areas that formerly were dominated by extensive old-growth forests and younger forests resulting from fire disturbance. Traditionally, determination of seral stage and stand condition have been made using aerial photography and spot field observations, a methodology that is not only time- and resource-intensive, but falls short of providing current information on a regional scale. These limitations may be solved, in part, through the use of multispectral images which can cover large areas at spatial resolutions in the order of tens of meters. The use of multiple images comprising a time series potentially can be used to monitor land use (e.g. cutting and replanting), and to observe natural processes such as regeneration, maturation and phenologic change. These processes are more likely to be spectrally observed in a time series composed of images taken during different seasons over a long period of time. Therefore, for many areas, it may be necessary to use a variety of images taken with different imaging systems. A common framework for interpretation is needed that reduces topographic, atmospheric, instrumental, effects as well as differences in lighting geometry between images. The present state of remote-sensing technology in general use does not realize the full potential of the multispectral data in areas of high topographic relief. For example, the primary method for analyzing images of forested landscapes in the Northwest has been with statistical classifiers (e.g. parallelepiped, nearest-neighbor, maximum likelihood, etc.), often applied to uncalibrated multispectral data. Although this approach has produced useful information from individual images in some areas, landcover classes defined by these
Multi-scale description and prediction of financial time series
International Nuclear Information System (INIS)
A new method is proposed that allows a reconstruction of time series based on higher order multi-scale statistics given by a hierarchical process. This method is able to model financial time series not only on a specific scale but for a range of scales. The method itself is based on the general n-scale joint probability density, which can be extracted directly from given data. It is shown how based on this n-scale statistics, general n-point probabilities can be estimated from which predictions can be achieved. Exemplary results are shown for the German DAX index. The ability to model correctly the behaviour of the original process for different scales simultaneously and in time is demonstrated. As a main result it is shown that this method is able to reproduce the known volatility cluster, although the model contains no explicit time dependence. Thus a new mechanism is shown how, in a stationary multi-scale process, volatility clustering can emerge.
Identifying multiple periodicities in sparse photon event time series
Koen, Chris
2016-07-01
The data considered are event times (e.g. photon arrival times, or the occurrence of sharp pulses). The source is multiperiodic, or the data could be multiperiodic because several unresolved sources contribute to the time series. Most events may be unobserved, either because the source is intermittent, or because some events are below the detection limit. The data may also be contaminated by spurious pulses. The problem considered is the determination of the periods in the data. A two-step procedure is proposed: in the first, a likely period is identified; in the second, events associated with this periodicity are removed from the time series. The steps are repeated until the remaining events do not exhibit any periodicity. A number of period-finding methods from the literature are reviewed, and a new maximum likelihood statistic is also introduced. It is shown that the latter is competitive compared to other techniques. The proposed methodology is tested on simulated data. Observations of two rotating radio transients are discussed, but contrary to claims in the literature, no evidence for multiperiodicity could be found.
Identifying Multiple Periodicities in Sparse Photon Event Time Series
Koen, Chris
2016-04-01
The data considered are event times (e.g. photon arrival times, or the occurrence of sharp pulses). The source is multiperiodic, or the data could be multiperiodic because several unresolved sources contribute to the time series. Most events may be unobserved, either because the source is intermittent, or because some events are below the detection limit. The data may also be contaminated by spurious pulses. The problem considered is the determination of the periods in the data. A two-step procedure is proposed: in the first, a likely period is identified; in the second, events associated with this periodicity are removed from the time series. The steps are repeated until the remaining events do not exhibit any periodicity. A number of period-finding methods from the literature are reviewed, and a new maximum likelihood statistic is also introduced. It is shown that the latter is competitive compared to other techniques. The proposed methodology is tested on simulated data. Observations of two rotating radio transients are discussed, but contrary to claims in the literature, no evidence for multiperiodicity could be found.
Analysing time-varying trends in stratospheric ozone time series using the state space approach
M. Laine; N. Latva-Pukkila; E. Kyrölä
2014-01-01
We describe a hierarchical statistical state space model for ozone profile time series. The time series are from satellite measurements by the Stratospheric Aerosol and Gas Experiment (SAGE) II and the Global Ozone Monitoring by Occultation of Stars (GOMOS) instruments spanning the years 1984–2011. Vertical ozone profiles were linearly interpolated on an altitude grid with 1 km resolution covering 20–60 km. Monthly averages were calculated for each altitude level and 10° wid...
Analysis of Multipsectral Time Series for supporting Forest Management Plans
Simoniello, T.; Carone, M. T.; Costantini, G.; Frattegiani, M.; Lanfredi, M.; Macchiato, M.
2010-05-01
Adequate forest management requires specific plans based on updated and detailed mapping. Multispectral satellite time series have been largely applied to forest monitoring and studies at different scales tanks to their capability of providing synoptic information on some basic parameters descriptive of vegetation distribution and status. As a low expensive tool for supporting forest management plans in operative context, we tested the use of Landsat-TM/ETM time series (1987-2006) in the high Agri Valley (Southern Italy) for planning field surveys as well as for the integration of existing cartography. As preliminary activity to make all scenes radiometrically consistent the no-change regression normalization was applied to the time series; then all the data concerning available forest maps, municipal boundaries, water basins, rivers, and roads were overlapped in a GIS environment. From the 2006 image we elaborated the NDVI map and analyzed the distribution for each land cover class. To separate the physiological variability and identify the anomalous areas, a threshold on the distributions was applied. To label the non homogenous areas, a multitemporal analysis was performed by separating heterogeneity due to cover changes from that linked to basilar unit mapping and classification labelling aggregations. Then a map of priority areas was produced to support the field survey plan. To analyze the territorial evolution, the historical land cover maps were elaborated by adopting a hybrid classification approach based on a preliminary segmentation, the identification of training areas, and a subsequent maximum likelihood categorization. Such an analysis was fundamental for the general assessment of the territorial dynamics and in particular for the evaluation of the efficacy of past intervention activities.
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.
Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli
2016-01-01
In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423
VARTOOLS: A Program for Analyzing Astronomical Time-Series Data
Hartman, Joel D
2016-01-01
This paper describes the VARTOOLS program, which is an open-source command-line utility, written in C, for analyzing astronomical time-series data, especially light curves. The program provides a general-purpose set of tools for processing light curves including signal identification, filtering, light curve manipulation, time conversions, and modeling and simulating light curves. Some of the routines implemented include the Generalized Lomb-Scargle periodogram, the Box-Least Squares transit search routine, the Analysis of Variance periodogram, the Discrete Fourier Transform including the CLEAN algorithm, the Weighted Wavelet Z-Transform, light curve arithmetic, linear and non-linear optimization of analytic functions including support for Markov Chain Monte Carlo analyses with non-trivial covariances, characterizing and/or simulating time-correlated noise, and the TFA and SYSREM filtering algorithms, among others. A mechanism is also provided for incorporating a user's own compiled processing routines into th...
Detecting and characterising ramp events in wind power time series
International Nuclear Information System (INIS)
In order to implement accurate models for wind power ramp forecasting, ramps need to be previously characterised. This issue has been typically addressed by performing binary ramp/non-ramp classifications based on ad-hoc assessed thresholds. However, recent works question this approach. This paper presents the ramp function, an innovative wavelet- based tool which detects and characterises ramp events in wind power time series. The underlying idea is to assess a continuous index related to the ramp intensity at each time step, which is obtained by considering large power output gradients evaluated under different time scales (up to typical ramp durations). The ramp function overcomes some of the drawbacks shown by the aforementioned binary classification and permits forecasters to easily reveal specific features of the ramp behaviour observed at a wind farm. As an example, the daily profile of the ramp-up and ramp-down intensities are obtained for the case of a wind farm located in Spain
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks
Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli
2016-01-01
In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423
Time series prediction of mining subsidence based on a SVM
Institute of Scientific and Technical Information of China (English)
Li Peixian; Tan Zhixiang; Yah Lili; Deng Kazhong
2011-01-01
In order to study dynamic laws of surface movements over coal mines due to mining activities,a dynamic prediction model of surface movements was established,based on the theory of support vector machines (SVM) and times-series analysis.An engineering application was used to verify the correctness of the model.Measurements from observation stations were analyzed and processed to obtain equal-time interval surface movement data and subjected to tests of stationary,zero means and normality.Then the data were used to train the SVM model.A time series model was established to predict mining subsidence by rational choices of embedding dimensions and SVM parameters.MAPE and WIA were used asindicators to evaluate the accuracy of the model and for generalization performance.In the end,the model was used to predict future surface movements.Data from observation stations in Huaibei coal mining area were used as an example.The results show that the maximum absolute error of subsidence is 9 mm,the maximum relative error 1.5％.the maximum absolute error of displacement 7 mm and the maximum relative error 1.8％.The accuracy and reliability of the model meet the requirements of on-site engineering.The results of the study provide a new approach to investigate the dynamics of surface movements.
GPS time series at Campi Flegrei caldera (2000-2013
Directory of Open Access Journals (Sweden)
Prospero De Martino
2014-05-01
Full Text Available The Campi Flegrei caldera is an active volcanic system associated to a high volcanic risk, and represents a well known and peculiar example of ground deformations (bradyseism, characterized by intense uplift periods, followed by subsidence phases with some episodic superimposed mini-uplifts. Ground deformation is an important volcanic precursor, and, its continuous monitoring, is one of the main tool for short time forecast of eruptive activity. This paper provides an overview of the continuous GPS monitoring of the Campi Flegrei caldera from January 2000 to July 2013, including network operations, data recording and processing, and data products. In this period the GPS time series allowed continuous and accurate tracking of ground deformation of the area. Seven main uplift episodes were detected, and during each uplift period, the recurrent horizontal displacement pattern, radial from the “caldera center”, suggests no significant change in deformation source geometry and location occurs. The complete archive of GPS time series at Campi Flegrei area is reported in the Supplementary materials. These data can be usefull for the scientific community in improving the research on Campi Flegrei caldera dynamic and hazard assessment.
Reconstruction of Ordinary Differential Equations From Time Series Data
Mai, Manuel; O'Hern, Corey S
2016-01-01
We develop a numerical method to reconstruct systems of ordinary differential equations (ODEs) from time series data without {\\it a priori} knowledge of the underlying ODEs using sparse basis learning and sparse function reconstruction. We show that employing sparse representations provides more accurate ODE reconstruction compared to least-squares reconstruction techniques for a given amount of time series data. We test and validate the ODE reconstruction method on known 1D, 2D, and 3D systems of ODEs. The 1D system possesses two stable fixed points; the 2D system possesses an oscillatory fixed point with closed orbits; and the 3D system displays chaotic dynamics on a strange attractor. We determine the amount of data required to achieve an error in the reconstructed functions to less than $0.1\\%$. For the reconstructed 1D and 2D systems, we are able to match the trajectories from the original ODEs even at long times. For the 3D system with chaotic dynamics, as expected, the trajectories from the original an...
A New Correlation Coefficient for Bivariate Time-Series Data
Orhan Erdem; Elvan Ceyhan; Yusuf Varlı
2011-01-01
Correlation in time series has recently recieved a lot of attentions. Its usage has been getting an important role in Social Science and Finance. For example, pair trading in Finance is interested with the correlation between stock prices, returns etc. In general, Pearsonís correlation coefficient is seen in the area, although it has many assumptions which restrict its usage. In here, we introduce a new correlation coe¢ cient which takes account the lag difference of data points as a moment. ...
Estimation of dynamic flux profiles from metabolic time series data
Directory of Open Access Journals (Sweden)
Chou I-Chun
2012-07-01
Full Text Available Abstract Background Advances in modern high-throughput techniques of molecular biology have enabled top-down approaches for the estimation of parameter values in metabolic systems, based on time series data. Special among them is the recent method of dynamic flux estimation (DFE, which uses such data not only for parameter estimation but also for the identification of functional forms of the processes governing a metabolic system. DFE furthermore provides diagnostic tools for the evaluation of model validity and of the quality of a model fit beyond residual errors. Unfortunately, DFE works only when the data are more or less complete and the system contains as many independent fluxes as metabolites. These drawbacks may be ameliorated with other types of estimation and information. However, such supplementations incur their own limitations. In particular, assumptions must be made regarding the functional forms of some processes and detailed kinetic information must be available, in addition to the time series data. Results The authors propose here a systematic approach that supplements DFE and overcomes some of its shortcomings. Like DFE, the approach is model-free and requires only minimal assumptions. If sufficient time series data are available, the approach allows the determination of a subset of fluxes that enables the subsequent applicability of DFE to the rest of the flux system. The authors demonstrate the procedure with three artificial pathway systems exhibiting distinct characteristics and with actual data of the trehalose pathway in Saccharomyces cerevisiae. Conclusions The results demonstrate that the proposed method successfully complements DFE under various situations and without a priori assumptions regarding the model representation. The proposed method also permits an examination of whether at all, to what degree, or within what range the available time series data can be validly represented in a particular functional format of
Another Adaptive Approach to Novelty Detection in Time Series
Directory of Open Access Journals (Sweden)
Matous Cejnek
2014-02-01
Full Text Available This paper introduces a novel approach to novelty d etection of every individual sample of data in a time series. The novelty detection is based on the knowledge learned by neural networks and the consistency of data with contemporary gover ning law. In particular, the relationship of prediction error with the adaptive weight increment s by gradient decent is shown, as the modification of the recently introduced adaptive ap proach of novelty detection. Static and dynamic neural network models are shown on theoreti cal data as well as on a real ECG signal.
Optimization of recurrent neural networks for time series modeling
DEFF Research Database (Denmark)
Pedersen, Morten With
1997-01-01
solution obtained as well as computation time required. 3. A theoretical definition of the generalization error for recurrent networks is provided. This definition justifies a commonly adopted approach for estimating generalization ability. 4. The viability of pruning recurrent networks by the Optimal...... observed series. Two recurrent models rooted in statistical physics are considered in this respect, namely the ``Boltzmann chain'' and the ``Boltzmann zipper'' and a comprehensive tutorial on these models is provided. Boltzmann chains and zippers are found to benefit as well from second-order training and...
Multifractal Time Series Analysis Based on Detrended Fluctuation Analysis
Kantelhardt, Jan; Stanley, H. Eugene; Zschiegner, Stephan; Bunde, Armin; Koscielny-Bunde, Eva; Havlin, Shlomo
2002-03-01
In order to develop an easily applicable method for the multifractal characterization of non-stationary time series, we generalize the detrended fluctuation analysis (DFA), which is a well-established method for the determination of the monofractal scaling properties and the detection of long-range correlations. We relate the new multifractal DFA method to the standard partition function-based multifractal formalism, and compare it to the wavelet transform modulus maxima (WTMM) method which is a well-established, but more difficult procedure for this purpose. We employ the multifractal DFA method to determine if the heartrhythm during different sleep stages is characterized by different multifractal properties.
Time series analysis using semiparametric regression on oil palm production
Yundari, Pasaribu, U. S.; Mukhaiyar, U.
2016-04-01
This paper presents semiparametric kernel regression method which has shown its flexibility and easiness in mathematical calculation, especially in estimating density and regression function. Kernel function is continuous and it produces a smooth estimation. The classical kernel density estimator is constructed by completely nonparametric analysis and it is well reasonable working for all form of function. Here, we discuss about parameter estimation in time series analysis. First, we consider the parameters are exist, then we use nonparametrical estimation which is called semiparametrical. The selection of optimum bandwidth is obtained by considering the approximation of Mean Integrated Square Root Error (MISE).
Time series analysis for minority game simulations of financial markets
Ferreira, F F; Machado, B S; Muruganandam, P
2003-01-01
The minority game model introduced recently provides promising insights into the understanding of the evolution of prices, indices and rates in the financial markets. In this paper we perform a time series analysis of the model employing tools from statistics, dynamical systems theory and stochastic processes. Using benchmark systems and a financial index for comparison, we draw conclusions about the generating mechanism for this kind of evolution. The trajectories of the model are found to be similar to that of the first differences of the SP500 index: stochastic, nonlinear and (unit root) stationary.
Nonlinear Time Series Forecast Using Radial Basis Function Neural Networks
Institute of Scientific and Technical Information of China (English)
ZHENG Xin; CHEN Tian-Lun
2003-01-01
In the research of using Radial Basis Function Neural Network (RBF NN) forecasting nonlinear timeseries, we investigate how the different clusterings affect the process of learning and forecasting. We find that k-meansclustering is very suitable. In order to increase the precision we introduce a nonlinear feedback term to escape from thelocal minima of energy, then we use the model to forecast the nonlinear time series which are produced by Mackey-Glassequation and stocks. By selecting the k-means clustering and the suitable feedback term, much better forecasting resultsare obtained.
Forecasting incidence of dengue in Rajasthan, using time series analyses
Sunil Bhatnagar; Vivek Lal; Shiv D. Gupta; Om P Gupta
2012-01-01
Aim: To develop a prediction model for dengue fever/dengue haemorrhagic fever (DF/DHF) using time series data over the past decade in Rajasthan and to forecast monthly DF/DHF incidence for 2011. Materials and Methods: Seasonal autoregressive integrated moving average (SARIMA) model was used for statistical modeling. Results: During January 2001 to December 2010, the reported DF/DHF cases showed a cyclical pattern with seasonal variation. SARIMA (0,0,1) (0,1,1) 12 model had the lowest normaliz...
Testing for Changes in the Rank Correlation of Time Series
Dehling, Herold; Vogel, Daniel; Wendler, Martin; Wied, Dominik
2012-01-01
For a bivariate time series $((X_i,Y_i))_{i=1,...,n}$ we want to detect whether the correlation between $X_i$ and $Y_i$ stays constant for all $i = 1,...,n$. We propose a nonparametric change-point test statistic based on Kendall's tau and derive its asymptotic distribution under the null hypothesis of no change by means a new U-statistic invariance principle for dependent processes. The asymptotic distribution depends on the long run variance of Kendall's tau, for which we propose an estimat...
Albedo Pattern Recognition and Time-Series Analyses in Malaysia
Salleh, S. A.; Abd Latif, Z.; Mohd, W. M. N. Wan; Chan, A.
2012-07-01
Pattern recognition and time-series analyses will enable one to evaluate and generate predictions of specific phenomena. The albedo pattern and time-series analyses are very much useful especially in relation to climate condition monitoring. This study is conducted to seek for Malaysia albedo pattern changes. The pattern recognition and changes will be useful for variety of environmental and climate monitoring researches such as carbon budgeting and aerosol mapping. The 10 years (2000-2009) MODIS satellite images were used for the analyses and interpretation. These images were being processed using ERDAS Imagine remote sensing software, ArcGIS 9.3, the 6S code for atmospherical calibration and several MODIS tools (MRT, HDF2GIS, Albedo tools). There are several methods for time-series analyses were explored, this paper demonstrates trends and seasonal time-series analyses using converted HDF format MODIS MCD43A3 albedo land product. The results revealed significance changes of albedo percentages over the past 10 years and the pattern with regards to Malaysia's nebulosity index (NI) and aerosol optical depth (AOD). There is noticeable trend can be identified with regards to its maximum and minimum value of the albedo. The rise and fall of the line graph show a similar trend with regards to its daily observation. The different can be identified in term of the value or percentage of rises and falls of albedo. Thus, it can be concludes that the temporal behavior of land surface albedo in Malaysia have a uniform behaviours and effects with regards to the local monsoons. However, although the average albedo shows linear trend with nebulosity index, the pattern changes of albedo with respects to the nebulosity index indicates that there are external factors that implicates the albedo values, as the sky conditions and its diffusion plotted does not have uniform trend over the years, especially when the trend of 5 years interval is examined, 2000 shows high negative linear
Chaotic time series analysis in economics: Balance and perspectives
International Nuclear Information System (INIS)
The aim of the paper is not to review the large body of work concerning nonlinear time series analysis in economics, about which much has been written, but rather to focus on the new techniques developed to detect chaotic behaviours in economic data. More specifically, our attention will be devoted to reviewing some of these techniques and their application to economic and financial data in order to understand why chaos theory, after a period of growing interest, appears now not to be such an interesting and promising research area
DMC modified algorithm based on time series prediction principle
Institute of Scientific and Technical Information of China (English)
齐维贵; 朱学莉
2002-01-01
The application of heating load prediction and predictive control to the heat supply system for energysaving and high quality heat supply is discussed by first introducing the time series prediction principle, and thesequence model, parameter identification and least variance prediction principle, and then giving the heatingload and model error prediction based on this principle. As an improvement of DMC algorithm, the load predic-tion is used as a set point of DMC, and the prediction error is used as a corrected value of predictive control.Finally, the simulation results of two prediction methods to heat supply system are given.
Univariate time series in geosciences theory and examples
Gilgen, Hans
2006-01-01
The author introduces the statistical analysis of geophysical time series. The book includes also a chapter with an introduction to geostatistics, many examples and exercises which help the reader to work with typical problems. More complex derivations are provided in appendix-like supplements to each chapter. Readers are assumed to have a basic grounding in statistics and analysis. The reader is invited to learn actively from genuine geophysical data. He has to consider the applicability of statistical methods, to propose, estimate, evaluate and compare statistical models, and to draw conclus
Wavelet Space Partitioning for Symbolic Time Series Analysis
Institute of Scientific and Technical Information of China (English)
Venkatesh Rajagopalan; Asok Ray
2006-01-01
@@ A crucial step in symbolic time series analysis (STSA) of observed data is symbol sequence generation that relies on partitioning the phase-space of the underlying dynamical system. We present a novel partitioning method,called wavelet-space (WS) partitioning, as an alternative to symbolic false nearest neighbour (SFNN) partitioning.While the WS and SFNN partitioning methods have been demonstrated to yield comparable performance for anomaly detection on laboratory apparatuses, computation of WS partitioning is several orders of magnitude faster than that of the SFNN partitioning.
Chaotic time series analysis in economics: Balance and perspectives
Energy Technology Data Exchange (ETDEWEB)
Faggini, Marisa, E-mail: mfaggini@unisa.it [Dipartimento di Scienze Economiche e Statistiche, Università di Salerno, Fisciano 84084 (Italy)
2014-12-15
The aim of the paper is not to review the large body of work concerning nonlinear time series analysis in economics, about which much has been written, but rather to focus on the new techniques developed to detect chaotic behaviours in economic data. More specifically, our attention will be devoted to reviewing some of these techniques and their application to economic and financial data in order to understand why chaos theory, after a period of growing interest, appears now not to be such an interesting and promising research area.
A parametric model for discrete- valued time series
Czech Academy of Sciences Publication Activity Database
Janžura, Martin; Fialová, Lucie
Bratislava : Mathematical institute, Slovak Academy of Sciences, 2008 - (Pázman, A.; Volaufová, J.; Witkovský, V.), s. 155-163 ISSN 1210-3195. - (Tatra Mountains Mathematical Publications. 39). [Probastat 06. Smolenice (SK), 05.06.2006-09.06.2006] R&D Projects: GA ČR GA201/06/1323 Institutional research plan: CEZ:AV0Z10750506 Keywords : Markov Chains * Gibbs distributions * statistical estimation Subject RIV: BA - General Mathematics http://library.utia.cas.cz/separaty/2008/SI/janzura-a parametric model for discrete- valued time series.pdf
Time series ARIMA models for daily price of palm oil
Ariff, Noratiqah Mohd; Zamhawari, Nor Hashimah; Bakar, Mohd Aftar Abu
2015-02-01
Palm oil is deemed as one of the most important commodity that forms the economic backbone of Malaysia. Modeling and forecasting the daily price of palm oil is of great interest for Malaysia's economic growth. In this study, time series ARIMA models are used to fit the daily price of palm oil. The Akaike Infromation Criterion (AIC), Akaike Infromation Criterion with a correction for finite sample sizes (AICc) and Bayesian Information Criterion (BIC) are used to compare between different ARIMA models being considered. It is found that ARIMA(1,2,1) model is suitable for daily price of crude palm oil in Malaysia for the year 2010 to 2012.
van den Broek, PLC; van Egmond, J; van Rijn, CM; Takens, F; Coenen, AML; Booij, LHDJ
2005-01-01
Background: This study assessed the feasibility of online calculation of the correlation integral (C(r)) aiming to apply C(r)derived statistics. For real-time application it is important to reduce calculation time. It is shown how our method works for EEG time series. Methods: To achieve online calc
Broek, P.L.C. van den; Egmond, J. van; Rijn, C.M. van; Takens, F.; Coenen, A.M.L.; Booij, L.H.D.J.
2005-01-01
This study assessed the feasibility of online calculation of the correlation integral (C(r)) aiming to apply C(r)-derived statistics. For real-time application it is important to reduce calculation time. It is shown how our method works for EEG time series. Methods: To achieve online calculation of
Detection of intermittent events in atmospheric time series
Paradisi, P.; Cesari, R.; Palatella, L.; Contini, D.; Donateo, A.
2009-04-01
associated with the occurrence of critical events in the atmospheric dynamics. The critical events are associated with transitions between meta-stable configurations. Consequently, this approach could give some effort in the study of Extreme Events in meteorology and climatology and in weather classification schemes. Then, the renewal approach could give some effort in the modelling of non-Gaussian closures for turbulent fluxes [3]. In the proposed approach the main features that need to be estimated are: (a) the distribution of life-times of a given atmospheric meta-stable structure (Waiting Times between two critical events); (b) the statistical distribution of fluctuations; (c) the presence of memory in the time series. These features are related to the evaluation of memory content and scaling from the time series. In order to analyze these features, in recent years some novel statistical techniques have been developed. In particular, the analysis of Diffusion Entropy [4] was shown to be a robust method for the determination of the dynamical scaling. This property is related to the power-law behaviour of the life-time statistics and to the memory properties of the time series. The analysis of Renewal Aging [5], based on renewal theory [2], allows to estimate the content of memory in a time series that is related to the amount of critical events in the time series itself. After a brief review of the statistical techniques (Diffusion Entropy and Renewal Aging), an application to experimental atmospheric time series will be illustrated. References [1] Weiss G.H., Rubin R.J., Random Walks: theory and selected applications, Advances in Chemical Physics,1983, 52, 363-505 (1983). [2] D.R. Cox, Renewal Theory, Methuen, London (1962). [3] P. Paradisi, R. Cesari, F. Mainardi, F. Tampieri: The fractional Fick's law for non-local transport processes, Physica A, 293, p. 130-142 (2001). [4] P. Grigolini, L. Palatella, G. Raffaelli, Fractals 9 (2001) 439. [5] P. Allegrini, F. Barbi, P
A new complexity measure for time series analysis and classification
Nagaraj, Nithin; Balasubramanian, Karthi; Dey, Sutirth
2013-07-01
Complexity measures are used in a number of applications including extraction of information from data such as ecological time series, detection of non-random structure in biomedical signals, testing of random number generators, language recognition and authorship attribution etc. Different complexity measures proposed in the literature like Shannon entropy, Relative entropy, Lempel-Ziv, Kolmogrov and Algorithmic complexity are mostly ineffective in analyzing short sequences that are further corrupted with noise. To address this problem, we propose a new complexity measure ETC and define it as the "Effort To Compress" the input sequence by a lossless compression algorithm. Here, we employ the lossless compression algorithm known as Non-Sequential Recursive Pair Substitution (NSRPS) and define ETC as the number of iterations needed for NSRPS to transform the input sequence to a constant sequence. We demonstrate the utility of ETC in two applications. ETC is shown to have better correlation with Lyapunov exponent than Shannon entropy even with relatively short and noisy time series. The measure also has a greater rate of success in automatic identification and classification of short noisy sequences, compared to entropy and a popular measure based on Lempel-Ziv compression (implemented by Gzip).
A Markov switching model for annual hydrologic time series
Akıntuǧ, B.; Rasmussen, P. F.
2005-09-01
This paper investigates the properties of Markov switching (MS) models (also known as hidden Markov models) for generating annual time series. This type of model has been used in a number of recent studies in the water resources literature. The model considered here assumes that climate is switching between M states and that the state sequence can be described by a Markov chain. Observations are assumed to be drawn from a normal distribution whose parameters depend on the state variable. We present the stochastic properties of this class of models along with procedures for model identification and parameter estimation. Although, at a first glance, MS models appear to be quite different from ARMA models, we show that it is possible to find an ARMA model that has the same autocorrelation function and the same marginal distribution as any given MS model. Hence, despite the difference in model structure, there are strong similarities between MS and ARMA models. MS and ARMA models are applied to the time series of mean annual discharge of the Niagara River. Although it is difficult to draw any general conclusion from a single case study, it appears that MS models (and ARMA models derived from MS models) generally have stronger autocorrelation at higher lags than ARMA models estimated by conventional maximum likelihood. This may be an important property if the purpose of the study is the analysis of multiyear droughts.
Earth's Surface Displacements from the GPS Time Series
Haritonova, D.; Balodis, J.; Janpaule, I.; Morozova, K.
2015-11-01
The GPS observations of both Latvian permanent GNSS networks - EUPOS®-Riga and LatPos, have been collected for a period of 8 years - from 2007 to 2014. Local surface displacements have been derived from the obtained coordinate time series eliminating different impact sources. The Bernese software is used for data processing. The EUREF Permanent Network (EPN) stations in the surroundings of Latvia are selected as fiducial stations. The results have shown a positive tendency of vertical displacements in the western part of Latvia - station heights are increasing, and negative velocities are observed in the central and eastern parts. Station vertical velocities are ranging in diapason of 4 mm/year. In the case of horizontal displacements, site velocities are up to 1 mm/year and mostly oriented to the south. The comparison of the obtained results with data from the deformation model NKG_RF03vel has been made. Additionally, the purpose of this study is to analyse GPS time series obtained using two different data processing strategies: Precise Point Positioning (PPP) and estimation of station coordinates relatively to the positions of fiducial stations also known as Differential GNSS.
A New Hybrid Methodology for Nonlinear Time Series Forecasting
Directory of Open Access Journals (Sweden)
Mehdi Khashei
2011-01-01
Full Text Available Artificial neural networks (ANNs are flexible computing frameworks and universal approximators that can be applied to a wide range of forecasting problems with a high degree of accuracy. However, using ANNs to model linear problems have yielded mixed results, and hence; it is not wise to apply them blindly to any type of data. This is the reason that hybrid methodologies combining linear models such as ARIMA and nonlinear models such as ANNs have been proposed in the literature of time series forecasting. Despite of all advantages of the traditional methodologies for combining ARIMA and ANNs, they have some assumptions that will degenerate their performance if the opposite situation occurs. In this paper, a new methodology is proposed in order to combine the ANNs with ARIMA in order to overcome the limitations of traditional hybrid methodologies and yield more general and more accurate hybrid models. Empirical results with Canadian Lynx data set indicate that the proposed methodology can be a more effective way in order to combine linear and nonlinear models together than traditional hybrid methodologies. Therefore, it can be applied as an appropriate alternative methodology for hybridization in time series forecasting field, especially when higher forecasting accuracy is needed.
Time series clustering analysis of health-promoting behavior
Yang, Chi-Ta; Hung, Yu-Shiang; Deng, Guang-Feng
2013-10-01
Health promotion must be emphasized to achieve the World Health Organization goal of health for all. Since the global population is aging rapidly, ComCare elder health-promoting service was developed by the Taiwan Institute for Information Industry in 2011. Based on the Pender health promotion model, ComCare service offers five categories of health-promoting functions to address the everyday needs of seniors: nutrition management, social support, exercise management, health responsibility, stress management. To assess the overall ComCare service and to improve understanding of the health-promoting behavior of elders, this study analyzed health-promoting behavioral data automatically collected by the ComCare monitoring system. In the 30638 session records collected for 249 elders from January, 2012 to March, 2013, behavior patterns were identified by fuzzy c-mean time series clustering algorithm combined with autocorrelation-based representation schemes. The analysis showed that time series data for elder health-promoting behavior can be classified into four different clusters. Each type reveals different health-promoting needs, frequencies, function numbers and behaviors. The data analysis result can assist policymakers, health-care providers, and experts in medicine, public health, nursing and psychology and has been provided to Taiwan National Health Insurance Administration to assess the elder health-promoting behavior.
TIME SERIES FORECASTING WITH MULTIPLE CANDIDATE MODELS: SELECTING OR COMBINING?
Institute of Scientific and Technical Information of China (English)
YU Lean; WANG Shouyang; K. K. Lai; Y.Nakamori
2005-01-01
Various mathematical models have been commonly used in time series analysis and forecasting. In these processes, academic researchers and business practitioners often come up against two important problems. One is whether to select an appropriate modeling approach for prediction purposes or to combine these different individual approaches into a single forecast for the different/dissimilar modeling approaches. Another is whether to select the best candidate model for forecasting or to mix the various candidate models with different parameters into a new forecast for the same/similar modeling approaches. In this study, we propose a set of computational procedures to solve the above two issues via two judgmental criteria. Meanwhile, in view of the problems presented in the literature, a novel modeling technique is also proposed to overcome the drawbacks of existing combined forecasting methods. To verify the efficiency and reliability of the proposed procedure and modeling technique, the simulations and real data examples are conducted in this study.The results obtained reveal that the proposed procedure and modeling technique can be used as a feasible solution for time series forecasting with multiple candidate models.
Intermittency and multifractional Brownian character of geomagnetic time series
Directory of Open Access Journals (Sweden)
G. Consolini
2013-07-01
Full Text Available The Earth's magnetosphere exhibits a complex behavior in response to the solar wind conditions. This behavior, which is described in terms of mutifractional Brownian motions, could be the consequence of the occurrence of dynamical phase transitions. On the other hand, it has been shown that the dynamics of the geomagnetic signals is also characterized by intermittency at the smallest temporal scales. Here, we focus on the existence of a possible relationship in the geomagnetic time series between the multifractional Brownian motion character and the occurrence of intermittency. In detail, we investigate the multifractional nature of two long time series of the horizontal intensity of the Earth's magnetic field as measured at L'Aquila Geomagnetic Observatory during two years (2001 and 2008, which correspond to different conditions of solar activity. We propose a possible double origin of the intermittent character of the small-scale magnetic field fluctuations, which is related to both the multifractional nature of the geomagnetic field and the intermittent character of the disturbance level. Our results suggest a more complex nature of the geomagnetic response to solar wind changes than previously thought.
Hybrid perturbation methods based on statistical time series models
San-Juan, Juan Félix; San-Martín, Montserrat; Pérez, Iván; López, Rosario
2016-04-01
In this work we present a new methodology for orbit propagation, the hybrid perturbation theory, based on the combination of an integration method and a prediction technique. The former, which can be a numerical, analytical or semianalytical theory, generates an initial approximation that contains some inaccuracies derived from the fact that, in order to simplify the expressions and subsequent computations, not all the involved forces are taken into account and only low-order terms are considered, not to mention the fact that mathematical models of perturbations not always reproduce physical phenomena with absolute precision. The prediction technique, which can be based on either statistical time series models or computational intelligence methods, is aimed at modelling and reproducing missing dynamics in the previously integrated approximation. This combination results in the precision improvement of conventional numerical, analytical and semianalytical theories for determining the position and velocity of any artificial satellite or space debris object. In order to validate this methodology, we present a family of three hybrid orbit propagators formed by the combination of three different orders of approximation of an analytical theory and a statistical time series model, and analyse their capability to process the effect produced by the flattening of the Earth. The three considered analytical components are the integration of the Kepler problem, a first-order and a second-order analytical theories, whereas the prediction technique is the same in the three cases, namely an additive Holt-Winters method.
Financial time series prediction using spiking neural networks.
Reid, David; Hussain, Abir Jaafar; Tawfik, Hissam
2014-01-01
In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two "traditional", rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments. PMID:25170618
Exponential smoothing for financial time series data forecasting
Directory of Open Access Journals (Sweden)
Kuzhda, Tetyana Ivanivna
2014-05-01
Full Text Available The article begins with the formulation for predictive learning called exponential smoothing forecasting. The exponential smoothing is commonly applied to financial markets such as stock or bond, foreign exchange, insurance, credit, primary and secondary markets. The exponential smoothing models are useful in providing the valuable decision information for investors. Simple and double exponential smoothing models are two basic types of exponential smoothing method. The simple exponential smoothing method is suitable for financial time series forecasting for the specified time period. The simple exponential smoothing weights past observations with exponentially decreasing weights to forecast future values. The double exponential smoothing is a refinement of the simple exponential smoothing model but adds another component which takes into account any trend in the data. The double exponential smoothing is designed to address this type of data series by taking into account any trend in the data. Measurement of the forecast accuracy is described in this article. Finally, the quantitative value of the price per common share forecast using simple exponential smoothing is calculated. The applied recommendations concerning determination of the price per common share forecast using double exponential smoothing are shown in the article.
Blind source separation problem in GPS time series
Gualandi, A.; Serpelloni, E.; Belardinelli, M. E.
2016-04-01
A critical point in the analysis of ground displacement time series, as those recorded by space geodetic techniques, is the development of data-driven methods that allow the different sources of deformation to be discerned and characterized in the space and time domains. Multivariate statistic includes several approaches that can be considered as a part of data-driven methods. A widely used technique is the principal component analysis (PCA), which allows us to reduce the dimensionality of the data space while maintaining most of the variance of the dataset explained. However, PCA does not perform well in finding the solution to the so-called blind source separation (BSS) problem, i.e., in recovering and separating the original sources that generate the observed data. This is mainly due to the fact that PCA minimizes the misfit calculated using an L2 norm (χ 2), looking for a new Euclidean space where the projected data are uncorrelated. The independent component analysis (ICA) is a popular technique adopted to approach the BSS problem. However, the independence condition is not easy to impose, and it is often necessary to introduce some approximations. To work around this problem, we test the use of a modified variational Bayesian ICA (vbICA) method to recover the multiple sources of ground deformation even in the presence of missing data. The vbICA method models the probability density function (pdf) of each source signal using a mix of Gaussian distributions, allowing for more flexibility in the description of the pdf of the sources with respect to standard ICA, and giving a more reliable estimate of them. Here we present its application to synthetic global positioning system (GPS) position time series, generated by simulating deformation near an active fault, including inter-seismic, co-seismic, and post-seismic signals, plus seasonal signals and noise, and an additional time-dependent volcanic source. We evaluate the ability of the PCA and ICA decomposition
Satellite image time series simulation for environmental monitoring
Guo, Tao
2014-11-01
The performance of environmental monitoring heavily depends on the availability of consecutive observation data and it turns out an increasing demand in remote sensing community for satellite image data in the sufficient resolution with respect to both spatial and temporal requirements, which appear to be conflictive and hard to tune tradeoffs. Multiple constellations could be a solution if without concerning cost, and thus it is so far interesting but very challenging to develop a method which can simultaneously improve both spatial and temporal details. There are some research efforts to deal with the problem from various aspects, a type of approaches is to enhance the spatial resolution using techniques of super resolution, pan-sharpen etc. which can produce good visual effects, but mostly cannot preserve spectral signatures and result in losing analytical value. Another type is to fill temporal frequency gaps by adopting time interpolation, which actually doesn't increase informative context at all. In this paper we presented a novel method to generate satellite images in higher spatial and temporal details, which further enables satellite image time series simulation. Our method starts with a pair of high-low resolution data set, and then a spatial registration is done by introducing LDA model to map high and low resolution pixels correspondingly. Afterwards, temporal change information is captured through a comparison of low resolution time series data, and the temporal change is then projected onto high resolution data plane and assigned to each high resolution pixel referring the predefined temporal change patterns of each type of ground objects to generate a simulated high resolution data. A preliminary experiment shows that our method can simulate a high resolution data with a good accuracy. We consider the contribution of our method is to enable timely monitoring of temporal changes through analysis of low resolution images time series only, and usage of
A new correlation coefficient for bivariate time-series data
Erdem, Orhan; Ceyhan, Elvan; Varli, Yusuf
2014-11-01
The correlation in time series has received considerable attention in the literature. Its use has attained an important role in the social sciences and finance. For example, pair trading in finance is concerned with the correlation between stock prices, returns, etc. In general, Pearson’s correlation coefficient is employed in these areas although it has many underlying assumptions which restrict its use. Here, we introduce a new correlation coefficient which takes into account the lag difference of data points. We investigate the properties of this new correlation coefficient. We demonstrate that it is more appropriate for showing the direction of the covariation of the two variables over time. We also compare the performance of the new correlation coefficient with Pearson’s correlation coefficient and Detrended Cross-Correlation Analysis (DCCA) via simulated examples.
A quasi-global precipitation time series for drought monitoring
Funk, Chris C.; Peterson, Pete J.; Landsfeld, Martin F.; Pedreros, Diego H.; Verdin, James P.; Rowland, James D.; Romero, Bo E.; Husak, Gregory J.; Michaelsen, Joel C.; Verdin, Andrew P.
2014-01-01
Estimating precipitation variations in space and time is an important aspect of drought early warning and environmental monitoring. An evolving drier-than-normal season must be placed in historical context so that the severity of rainfall deficits may quickly be evaluated. To this end, scientists at the U.S. Geological Survey Earth Resources Observation and Science Center, working closely with collaborators at the University of California, Santa Barbara Climate Hazards Group, have developed a quasi-global (50°S–50°N, 180°E–180°W), 0.05° resolution, 1981 to near-present gridded precipitation time series: the Climate Hazards Group InfraRed Precipitation with Stations (CHIRPS) data archive.
Estimation of Hurst Exponent for the Financial Time Series
Kumar, J.; Manchanda, P.
2009-07-01
Till recently statistical methods and Fourier analysis were employed to study fluctuations in stock markets in general and Indian stock market in particular. However current trend is to apply the concepts of wavelet methodology and Hurst exponent, see for example the work of Manchanda, J. Kumar and Siddiqi, Journal of the Frankline Institute 144 (2007), 613-636 and paper of Cajueiro and B. M. Tabak. Cajueiro and Tabak, Physica A, 2003, have checked the efficiency of emerging markets by computing Hurst component over a time window of 4 years of data. Our goal in the present paper is to understand the dynamics of the Indian stock market. We look for the persistency in the stock market through Hurst exponent and fractal dimension of time series data of BSE 100 and NIFTY 50.
Reprocessed height time series of GPS stations at tide gauges
Directory of Open Access Journals (Sweden)
S. Rudenko
2012-07-01
Full Text Available Precise weekly positions of 403 Global Positioning System (GPS stations located worldwide are obtained by reprocessing GPS data of these stations at the time span from 4 January 1998 until 29 December 2007. The used processing algorithm and models as well as the solution and results obtained are presented. Vertical velocities of GPS stations having tracking history longer than 2.5 yr are computed and compared with the estimates from the colocated tide gauges and other GPS solutions. Examples of typical behavior of station height changes are given and interpreted. The derived time series and vertical motions of continuous GPS at tide gauges stations can be used for correcting tide gauge estimates of regional and global sea level changes.
Financial Time Series Forecasting Using Directed-Weighted Chunking SVMs
Directory of Open Access Journals (Sweden)
Yongming Cai
2014-01-01
Full Text Available Support vector machines (SVMs are a promising alternative to traditional regression estimation approaches. But, when dealing with massive-scale data set, there exist many problems, such as the long training time and excessive demand of memory space. So, the SVMs algorithm is not suitable to deal with financial time series data. In order to solve these problems, directed-weighted chunking SVMs algorithm is proposed. In this algorithm, the whole training data set is split into several chunks, and then the support vectors are obtained on each subset. Furthermore, the weighted support vector regressions are calculated to obtain the forecast model on the new working data set. Our directed-weighted chunking algorithm provides a new method of support vectors decomposing and combining according to the importance of chunks, which can improve the operation speed without reducing prediction accuracy. Finally, IBM stock daily close prices data are used to verify the validity of the proposed algorithm.
Time series power flow analysis for distribution connected PV generation.
Energy Technology Data Exchange (ETDEWEB)
Broderick, Robert Joseph; Quiroz, Jimmy Edward; Ellis, Abraham; Reno, Matthew J. [Georgia Institute of Technology, Atlanta, GA; Smith, Jeff [Electric Power Research Institute, Knoxville, TN; Dugan, Roger [Electric Power Research Institute, Knoxville, TN
2013-01-01
Distributed photovoltaic (PV) projects must go through an interconnection study process before connecting to the distribution grid. These studies are intended to identify the likely impacts and mitigation alternatives. In the majority of the cases, system impacts can be ruled out or mitigation can be identified without an involved study, through a screening process or a simple supplemental review study. For some proposed projects, expensive and time-consuming interconnection studies are required. The challenges to performing the studies are twofold. First, every study scenario is potentially unique, as the studies are often highly specific to the amount of PV generation capacity that varies greatly from feeder to feeder and is often unevenly distributed along the same feeder. This can cause location-specific impacts and mitigations. The second challenge is the inherent variability in PV power output which can interact with feeder operation in complex ways, by affecting the operation of voltage regulation and protection devices. The typical simulation tools and methods in use today for distribution system planning are often not adequate to accurately assess these potential impacts. This report demonstrates how quasi-static time series (QSTS) simulation and high time-resolution data can be used to assess the potential impacts in a more comprehensive manner. The QSTS simulations are applied to a set of sample feeders with high PV deployment to illustrate the usefulness of the approach. The report describes methods that can help determine how PV affects distribution system operations. The simulation results are focused on enhancing the understanding of the underlying technical issues. The examples also highlight the steps needed to perform QSTS simulation and describe the data needed to drive the simulations. The goal of this report is to make the methodology of time series power flow analysis readily accessible to utilities and others responsible for evaluating
Seismic assessment of a site using the time series method
International Nuclear Information System (INIS)
To increase the safety of a NPP located on a seismic site, the seismic acceleration level to which the NPP should be qualified must be as representative as possible for that site, with a conservative degree of safety but not too exaggerated. The consideration of the seismic events affecting the site as independent events and the use of statistic methods to define some safety levels with very low annual occurrence probability (10-4) may lead to some exaggerations of the seismic safety level. The use of some very high value for the seismic acceleration imposed by the seismic safety levels required by the hazard analysis may lead to very costly technical solutions that can make the plant operation more difficult and increase maintenance costs. The considerations of seismic events as a time series with dependence among the events produced, may lead to a more representative assessment of a NPP site seismic activity and consequently to a prognosis on the seismic level values to which the NPP would be ensured throughout its life-span. That prognosis should consider the actual seismic activity (including small earthquakes in real time) of the focuses that affect the plant site. The paper proposes the applications of Autoregressive Time Series to issue a prognosis on the seismic activity of a focus and presents the analysis on Vrancea focus that affects NPP Cernavoda site, by this method. The paper also presents the manner to analyse the focus activity as per the new approach and it assesses the maximum seismic acceleration that may affect NPP Cernavoda throughout its life-span (∼ 30 years). Development and applications of new mathematical analysis method, both for long - and short - time intervals, may lead to important contributions in the process of foretelling the seismic events in the future. (authors)
A SURVEY OF TIME SERIES DATA PREDICTION ON SHOPPING MALL
Directory of Open Access Journals (Sweden)
Mohammed Ali. Shaik
2013-04-01
Full Text Available Tremendous amount of data streams are often generated by dynamic environments such as stock’s and bond’s price indices, telecommunications data, audio and video data, Network traffic and data related to various Shopping malls. Mining regular patterns is one of the most important task in data mining. A time series databaseconsists of various sequences of values that are obtained over a stipulated period of time. The values are typically measured at equal time stamps (eg., hourly, daily, weekly which are sequence of ordered events, with or without concrete notations of time. The function is to mine all the transactional data which describes thebehavior of various transactions. In an online business or in a shopping mall, the customers can purchase more than one item at a time. Frequent patterns are those that appear most often in a data set as a collection of various item sets or its subsequences. The algorithms like Apriori and FP Growth are used to mine the frequent patterns of a item set. The Apriori algorithm generates candidate set during its each iteration. It reduces the dataset by removing all the irregular itemsets which does not meet the minimum threshold values from the candidate sets. The most expensive phase of FP Growth algorithm is to generate a candidate set and to mine the database [1].
Huang, Y X
2014-01-01
In the marine environment, many fields have fluctuations over a large range of different spatial and temporal scales. These quantities can be nonlinear \\red{and} non-stationary, and often interact with each other. A good method to study the multiple scale dynamics of such time series, and their correlations, is needed. In this paper an application of an empirical mode decomposition based time dependent intrinsic correlation, \\red{of} two coastal oceanic time series, temperature and dissolved oxygen (saturation percentage) is presented. The two time series are recorded every 20 minutes \\red{for} 7 years, from 2004 to 2011. The application of the Empirical Mode Decomposition on such time series is illustrated, and the power spectra of the time series are estimated using the Hilbert transform (Hilbert spectral analysis). Power-law regimes are found with slopes of 1.33 for dissolved oxygen and 1.68 for temperature at high frequencies (between 1.2 and 12 hours) \\red{with} both close to 1.9 for lower frequencies (t...
Model and requirements for a multiresolution time series database management system
Llusa Serra, Aleix; Escobet Canal, Teresa; Vila Marta, Sebastià
2012-01-01
In this paper we define a model for multiresolution time series database management systems. The main objective is to store compactly a time series and manage consistently its temporal dimension. It is achieved by extracting diferent resolutions and attributes summaries from the time series. Our work is concerned in putting together two areas of study: time series analysis and database management systems (DBMS). Time series analysis offers a great deal of methodologies and algorithms to pr...
Adaptive Sampling of Time Series During Remote Exploration
Thompson, David R.
2012-01-01
This work deals with the challenge of online adaptive data collection in a time series. A remote sensor or explorer agent adapts its rate of data collection in order to track anomalous events while obeying constraints on time and power. This problem is challenging because the agent has limited visibility (all its datapoints lie in the past) and limited control (it can only decide when to collect its next datapoint). This problem is treated from an information-theoretic perspective, fitting a probabilistic model to collected data and optimizing the future sampling strategy to maximize information gain. The performance characteristics of stationary and nonstationary Gaussian process models are compared. Self-throttling sensors could benefit environmental sensor networks and monitoring as well as robotic exploration. Explorer agents can improve performance by adjusting their data collection rate, preserving scarce power or bandwidth resources during uninteresting times while fully covering anomalous events of interest. For example, a remote earthquake sensor could conserve power by limiting its measurements during normal conditions and increasing its cadence during rare earthquake events. A similar capability could improve sensor platforms traversing a fixed trajectory, such as an exploration rover transect or a deep space flyby. These agents can adapt observation times to improve sample coverage during moments of rapid change. An adaptive sampling approach couples sensor autonomy, instrument interpretation, and sampling. The challenge is addressed as an active learning problem, which already has extensive theoretical treatment in the statistics and machine learning literature. A statistical Gaussian process (GP) model is employed to guide sample decisions that maximize information gain. Nonsta tion - ary (e.g., time-varying) covariance relationships permit the system to represent and track local anomalies, in contrast with current GP approaches. Most common GP models
United States Forest Disturbance Trends Observed Using Landsat Time Series
Masek, Jeffrey G.; Goward, Samuel N.; Kennedy, Robert E.; Cohen, Warren B.; Moisen, Gretchen G.; Schleeweis, Karen; Huang, Chengquan
2013-01-01
Disturbance events strongly affect the composition, structure, and function of forest ecosystems; however, existing U.S. land management inventories were not designed to monitor disturbance. To begin addressing this gap, the North American Forest Dynamics (NAFD) project has examined a geographic sample of 50 Landsat satellite image time series to assess trends in forest disturbance across the conterminous United States for 1985-2005. The geographic sample design used a probability-based scheme to encompass major forest types and maximize geographic dispersion. For each sample location disturbance was identified in the Landsat series using the Vegetation Change Tracker (VCT) algorithm. The NAFD analysis indicates that, on average, 2.77 Mha/yr of forests were disturbed annually, representing 1.09%/yr of US forestland. These satellite-based national disturbance rates estimates tend to be lower than those derived from land management inventories, reflecting both methodological and definitional differences. In particular the VCT approach used with a biennial time step has limited sensitivity to low-intensity disturbances. Unlike prior satellite studies, our biennial forest disturbance rates vary by nearly a factor of two between high and low years. High western US disturbance rates were associated with active fire years and insect activity, while variability in the east is more strongly related to harvest rates in managed forests. We note that generating a geographic sample based on representing forest type and variability may be problematic since the spatial pattern of disturbance does not necessarily correlate with forest type. We also find that the prevalence of diffuse, non-stand clearing disturbance in US forests makes the application of a biennial geographic sample problematic. Future satellite-based studies of disturbance at regional and national scales should focus on wall-to-wall analyses with annual time step for improved accuracy.
Established time series measure occurrence and frequency of episodic events.
Pebody, Corinne; Lampitt, Richard
2015-04-01
Established time series measure occurrence and frequency of episodic events. Episodic flux events occur in open oceans. Time series making measurements over significant time scales are one of the few methods that can capture these events and compare their impact with 'normal' flux. Seemingly rare events may be significant on local scales, but without the ability to measure the extent of flux on spatial and temporal scales and combine with the frequency of occurrence, it is difficult to constrain their impact. The Porcupine Abyssal Plain Sustained Observatory (PAP-SO) in the Northeast Atlantic (49 °N 16 °W, 5000m water depth) has measured particle flux since 1989 and zooplankton swimmers since 2000. Sediment traps at 3000m and 100 metres above bottom, collect material year round and we have identified close links between zooplankton and particle flux. Some of these larger animals, for example Diacria trispinosa, make a significant contribution to carbon flux through episodic flux events. D. trispinosa is a euthecosome mollusc which occurs in the Northeast Atlantic, though the PAP-SO is towards the northern limit of its distribution. Pteropods are comprised of aragonite shell, containing soft body parts excepting the muscular foot which extends beyond the mouth of the living animal. Pteropods, both live-on-entry animals and the empty shells are found year round in the 3000m trap. Generally the abundance varies with particle flux, but within that general pattern there are episodic events where significant numbers of these animals containing both organic and inorganic carbon are captured at depth and therefore could be defined as contributing to export flux. Whether the pulse of animals is as a result of the life cycle of D. trispinosa or the effects of the physics of the water column is unclear, but the complexity of the PAP-SO enables us not only to collect these animals but to examine them in parallel to the biogeochemical and physical elements measured by the
Aerosol Climate Time Series in ESA Aerosol_cci
Popp, Thomas; de Leeuw, Gerrit; Pinnock, Simon
2016-04-01
Within the ESA Climate Change Initiative (CCI) Aerosol_cci (2010 - 2017) conducts intensive work to improve algorithms for the retrieval of aerosol information from European sensors. Meanwhile, full mission time series of 2 GCOS-required aerosol parameters are completely validated and released: Aerosol Optical Depth (AOD) from dual view ATSR-2 / AATSR radiometers (3 algorithms, 1995 - 2012), and stratospheric extinction profiles from star occultation GOMOS spectrometer (2002 - 2012). Additionally, a 35-year multi-sensor time series of the qualitative Absorbing Aerosol Index (AAI) together with sensitivity information and an AAI model simulator is available. Complementary aerosol properties requested by GCOS are in a "round robin" phase, where various algorithms are inter-compared: fine mode AOD, mineral dust AOD (from the thermal IASI spectrometer, but also from ATSR instruments and the POLDER sensor), absorption information and aerosol layer height. As a quasi-reference for validation in few selected regions with sparse ground-based observations the multi-pixel GRASP algorithm for the POLDER instrument is used. Validation of first dataset versions (vs. AERONET, MAN) and inter-comparison to other satellite datasets (MODIS, MISR, SeaWIFS) proved the high quality of the available datasets comparable to other satellite retrievals and revealed needs for algorithm improvement (for example for higher AOD values) which were taken into account for a reprocessing. The datasets contain pixel level uncertainty estimates which were also validated and improved in the reprocessing. For the three ATSR algorithms the use of an ensemble method was tested. The paper will summarize and discuss the status of dataset reprocessing and validation. The focus will be on the ATSR, GOMOS and IASI datasets. Pixel level uncertainties validation will be summarized and discussed including unknown components and their potential usefulness and limitations. Opportunities for time series extension
Assimilation of LAI time-series in crop production models
Kooistra, Lammert; Rijk, Bert; Nannes, Louis
2014-05-01
Agriculture is worldwide a large consumer of freshwater, nutrients and land. Spatial explicit agricultural management activities (e.g., fertilization, irrigation) could significantly improve efficiency in resource use. In previous studies and operational applications, remote sensing has shown to be a powerful method for spatio-temporal monitoring of actual crop status. As a next step, yield forecasting by assimilating remote sensing based plant variables in crop production models would improve agricultural decision support both at the farm and field level. In this study we investigated the potential of remote sensing based Leaf Area Index (LAI) time-series assimilated in the crop production model LINTUL to improve yield forecasting at field level. The effect of assimilation method and amount of assimilated observations was evaluated. The LINTUL-3 crop production model was calibrated and validated for a potato crop on two experimental fields in the south of the Netherlands. A range of data sources (e.g., in-situ soil moisture and weather sensors, destructive crop measurements) was used for calibration of the model for the experimental field in 2010. LAI from cropscan field radiometer measurements and actual LAI measured with the LAI-2000 instrument were used as input for the LAI time-series. The LAI time-series were assimilated in the LINTUL model and validated for a second experimental field on which potatoes were grown in 2011. Yield in 2011 was simulated with an R2 of 0.82 when compared with field measured yield. Furthermore, we analysed the potential of assimilation of LAI into the LINTUL-3 model through the 'updating' assimilation technique. The deviation between measured and simulated yield decreased from 9371 kg/ha to 8729 kg/ha when assimilating weekly LAI measurements in the LINTUL model over the season of 2011. LINTUL-3 furthermore shows the main growth reducing factors, which are useful for farm decision support. The combination of crop models and sensor
A Time Series Modeling and Prediction of Wireless Network Traffic
Directory of Open Access Journals (Sweden)
S. Gowrishankar
2009-01-01
Full Text Available The number of users and their network utilization will enumerate the traffic of the network. The accurate and timely estimation of network traffic is increasingly becoming important in achieving guaranteed Quality of Service (QoS in a wireless network. The better QoS can be maintained in the network by admission control, inter or intra network handovers by knowing the network traffic in advance. Here wireless network traffic is modeled as a nonlinear and nonstationary time series. In this framework, network traffic is predicted using neural network and statistical methods. The results of both the methods are compared on different time scales or time granularity. The Neural Network(NN architectures used in this study are Recurrent Radial Basis Function Network (RRBFN and Echo state network (ESN.The statistical model used here in this work is Fractional Auto Regressive Integrated Moving Average (FARIMA model. The traffic prediction accuracy of neural network and statistical models are in the range of 96.4% to 98.3% and 78.5% to 80.2% respectively.
Crop Yield Forecasted Model Based on Time Series Techniques
Institute of Scientific and Technical Information of China (English)
Li Hong-ying; Hou Yan-lin; Zhou Yong-juan; Zhao Hui-ming
2012-01-01
Traditional studies on potential yield mainly referred to attainable yield： the maximum yield which could be reached by a crop in a given environment. The new concept of crop yield under average climate conditions was defined in this paper, which was affected by advancement of science and technology. Based on the new concept of crop yield, the time series techniques relying on past yield data was employed to set up a forecasting model. The model was tested by using average grain yields of Liaoning Province in China from 1949 to 2005. The testing combined dynamic n-choosing and micro tendency rectification, and an average forecasting error was 1.24%. In the trend line of yield change, and then a yield turning point might occur, in which case the inflexion model was used to solve the problem of yield turn point.
Practical measures of integrated information for time-series data.
Directory of Open Access Journals (Sweden)
Adam B Barrett
Full Text Available A recent measure of 'integrated information', Φ(DM, quantifies the extent to which a system generates more information than the sum of its parts as it transitions between states, possibly reflecting levels of consciousness generated by neural systems. However, Φ(DM is defined only for discrete Markov systems, which are unusual in biology; as a result, Φ(DM can rarely be measured in practice. Here, we describe two new measures, Φ(E and Φ(AR, that overcome these limitations and are easy to apply to time-series data. We use simulations to demonstrate the in-practice applicability of our measures, and to explore their properties. Our results provide new opportunities for examining information integration in real and model systems and carry implications for relations between integrated information, consciousness, and other neurocognitive processes. However, our findings pose challenges for theories that ascribe physical meaning to the measured quantities.
Indirect inference with time series observed with error
DEFF Research Database (Denmark)
Rossi, Eduardo; Santucci de Magistris, Paolo
estimation. We propose to solve this inconsistency by jointly estimating the nuisance and the structural parameters. Under standard assumptions, this estimator is consistent and asymptotically normal. A condition for the identification of ARMA plus noise is obtained. The proposed methodology is used to......We analyze the properties of the indirect inference estimator when the observed series are contaminated by measurement error. We show that the indirect inference estimates are asymptotically biased when the nuisance parameters of the measurement error distribution are neglected in the indirect...... estimate the parameters of continuous-time stochastic volatility models with auxiliary specifications based on realized volatility measures. Monte Carlo simulations shows the bias reduction of the indirect estimates obtained when the microstructure noise is explicitly modeled. Finally, an empirical...
Detecting Dynamical States from Noisy Time Series using Bicoherence
George, Sandip V; Misra, R
2016-01-01
Deriving meaningful information from observational data is often restricted by many limiting factors, the most important of which is the presence of noise. In this work, we present the use of the bicoherence function to extract information about the underlying nonlinearity from noisy time series. We show that a system evolving in the presence of noise which has its dynamical state concealed from quantifiers like the power spectrum and correlation dimension D2, can be revealed using the bicoherence function. We define an index called main peak bicoherence function as the bicoherence associated with the maximal power spectral peak. We show that this index is extremely useful while dealing with quasi-periodic data as it can distinguish strange non chaos from quasi periodicity even with added noise. We demonstrate this in a real world scenario, by taking the bicoherence of variable stars showing period doubling and strange non-chaotic behavior. Our results indicate that bicoherence analysis can also bypass the me...
On The Fourier And Wavelet Analysis Of Coronal Time Series
Auchère, F; Bocchialini, K; Buchlin, E; Solomon, J
2016-01-01
Using Fourier and wavelet analysis, we critically re-assess the significance of our detection of periodic pulsations in coronal loops. We show that the proper identification of the frequency dependence and statistical properties of the different components of the power spectra provies a strong argument against the common practice of data detrending, which tends to produce spurious detections around the cut-off frequency of the filter. In addition, the white and red noise models built into the widely used wavelet code of Torrence & Compo cannot, in most cases, adequately represent the power spectra of coronal time series, thus also possibly causing false positives. Both effects suggest that several reports of periodic phenomena should be re-examined. The Torrence & Compo code nonetheless effectively computes rigorous confidence levels if provided with pertinent models of mean power spectra, and we describe the appropriate manner in which to call its core routines. We recall the meaning of the default c...
Hybrid Perturbation methods based on Statistical Time Series models
San-Juan, Juan Félix; Pérez, Iván; López, Rosario
2016-01-01
In this work we present a new methodology for orbit propagation, the hybrid perturbation theory, based on the combination of an integration method and a prediction technique. The former, which can be a numerical, analytical or semianalytical theory, generates an initial approximation that contains some inaccuracies derived from the fact that, in order to simplify the expressions and subsequent computations, not all the involved forces are taken into account and only low-order terms are considered, not to mention the fact that mathematical models of perturbations not always reproduce physical phenomena with absolute precision. The prediction technique, which can be based on either statistical time series models or computational intelligence methods, is aimed at modelling and reproducing missing dynamics in the previously integrated approximation. This combination results in the precision improvement of conventional numerical, analytical and semianalytical theories for determining the position and velocity of a...
A Multivariate Time Series Method for Monte Carlo Reactor Analysis
International Nuclear Information System (INIS)
A robust multivariate time series method has been established for the Monte Carlo calculation of neutron multiplication problems. The method is termed Coarse Mesh Projection Method (CMPM) and can be implemented using the coarse statistical bins for acquisition of nuclear fission source data. A novel aspect of CMPM is the combination of the general technical principle of projection pursuit in the signal processing discipline and the neutron multiplication eigenvalue problem in the nuclear engineering discipline. CMPM enables reactor physicists to accurately evaluate major eigenvalue separations of nuclear reactors with continuous energy Monte Carlo calculation. CMPM was incorporated in the MCNP Monte Carlo particle transport code of Los Alamos National Laboratory. The great advantage of CMPM over the traditional Fission Matrix method is demonstrated for the three space-dimensional modeling of the initial core of a pressurized water reactor
Predictive Mining of Time Series Data in Astronomy
Perlman, E
2002-01-01
We discuss the development of a Java toolbox for astronomical time series data. Rather than using methods conventional in astronomy (e.g., power spectrum and cross-correlation analysis) we employ rule discovery techniques commonly used in analyzing stock-market data. By clustering patterns found within the data, rule discovery allows one to build predictive models, allowing one to forecast when a given event might occur or whether the occurrence of one event will trigger a second. We have tested the toolbox and accompanying display tool on datasets (representing several classes of objects) from the RXTE All Sky Monitor. We use these datasets to illustrate the methods and functionality of the toolbox. We also discuss issues that can come up in data analysis as well as the possible future development of the package.
PREDICTING CHAOTIC TIME SERIES WITH IMPROVED LOCAL APPROXIMATIONS
Institute of Scientific and Technical Information of China (English)
MU Xiaowu; LIN Lan; ZHOU Xiangdong
2004-01-01
In this paper, new approaches for chaotic time series prediction are introduced.We first summarize and evaluate the existing local prediction models, then propose optimization models and new algorithms to modify procedures of local approximations. The modification to the choice of sample sets is given, and the zeroth-order approximation is improved by a linear programming method. Four procedures of first-order approximation are compared, and corresponding modified methods are given. Lastly, the idea of nonlinear feedback to raise predicting accuracy is put forward. In the end, we discuss two important examples, i.e. Lorenz system and Rossler system, and the simulation experiments indicate that the modified algorithms are effective.
Multivariate time series with linear state space structure
Gómez, Víctor
2016-01-01
This book presents a comprehensive study of multivariate time series with linear state space structure. The emphasis is put on both the clarity of the theoretical concepts and on efficient algorithms for implementing the theory. In particular, it investigates the relationship between VARMA and state space models, including canonical forms. It also highlights the relationship between Wiener-Kolmogorov and Kalman filtering both with an infinite and a finite sample. The strength of the book also lies in the numerous algorithms included for state space models that take advantage of the recursive nature of the models. Many of these algorithms can be made robust, fast, reliable and efficient. The book is accompanied by a MATLAB package called SSMMATLAB and a webpage presenting implemented algorithms with many examples and case studies. Though it lays a solid theoretical foundation, the book also focuses on practical application, and includes exercises in each chapter. It is intended for researchers and students wor...
Single-Index Additive Vector Autoregressive Time Series Models
LI, YEHUA
2009-09-01
We study a new class of nonlinear autoregressive models for vector time series, where the current vector depends on single-indexes defined on the past lags and the effects of different lags have an additive form. A sufficient condition is provided for stationarity of such models. We also study estimation of the proposed model using P-splines, hypothesis testing, asymptotics, selection of the order of the autoregression and of the smoothing parameters and nonlinear forecasting. We perform simulation experiments to evaluate our model in various settings. We illustrate our methodology on a climate data set and show that our model provides more accurate yearly forecasts of the El Niño phenomenon, the unusual warming of water in the Pacific Ocean. © 2009 Board of the Foundation of the Scandinavian Journal of Statistics.
MODELLING GASOLINE DEMAND IN GHANA: A STRUCTURAL TIME SERIES ANALYSIS
Directory of Open Access Journals (Sweden)
Ishmael Ackah
2014-01-01
Full Text Available Concerns about the role of energy consumption in global warming have led to policy designs that seek to reduce fossil fuel consumption or find a less polluting alternative especiallyfor the transport sector. This study seeks to estimate the elasticities of price, income, education and technology on transport gasoline demand sector inGhana. The Structural Time Series Model reports a short-run price and income elasticities of -0.0088 and 0.713. Total factor productivity is -0.408 whilstthe elasticity for education is 2.33. In the long run, the reported price and income elasticities are -0.065 and 5.129 respectively. The long run elasticityfor productivity is -2.935. The study recommends that in order to enhanceefficiency in gasoline consumption in the transport sector, there should beinvestment in productivity.
Optimal estimation of recurrence structures from time series
beim Graben, Peter; Sellers, Kristin K.; Fröhlich, Flavio; Hutt, Axel
2016-05-01
Recurrent temporal dynamics is a phenomenon observed frequently in high-dimensional complex systems and its detection is a challenging task. Recurrence quantification analysis utilizing recurrence plots may extract such dynamics, however it still encounters an unsolved pertinent problem: the optimal selection of distance thresholds for estimating the recurrence structure of dynamical systems. The present work proposes a stochastic Markov model for the recurrent dynamics that allows for the analytical derivation of a criterion for the optimal distance threshold. The goodness of fit is assessed by a utility function which assumes a local maximum for that threshold reflecting the optimal estimate of the system's recurrence structure. We validate our approach by means of the nonlinear Lorenz system and its linearized stochastic surrogates. The final application to neurophysiological time series obtained from anesthetized animals illustrates the method and reveals novel dynamic features of the underlying system. We propose the number of optimal recurrence domains as a statistic for classifying an animals' state of consciousness.
Nonparametric inference of quantile curves for nonstationary time series
Zhou, Zhou
2010-01-01
The paper considers nonparametric specification tests of quantile curves for a general class of nonstationary processes. Using Bahadur representation and Gaussian approximation results for nonstationary time series, simultaneous confidence bands and integrated squared difference tests are proposed to test various parametric forms of the quantile curves with asymptotically correct type I error rates. A wild bootstrap procedure is implemented to alleviate the problem of slow convergence of the asymptotic results. In particular, our results can be used to test the trends of extremes of climate variables, an important problem in understanding climate change. Our methodology is applied to the analysis of the maximum speed of tropical cyclone winds. It was found that an inhomogeneous upward trend for cyclone wind speeds is pronounced at high quantile values. However, there is no trend in the mean lifetime-maximum wind speed. This example shows the effectiveness of the quantile regression technique.
Analytical framework for recurrence-network analysis of time series
Donges, Jonathan F; Donner, Reik V; Kurths, Jürgen
2012-01-01
Recurrence networks are a powerful nonlinear tool for time series analysis of complex dynamical systems. {While there are already many successful applications ranging from medicine to paleoclimatology, a solid theoretical foundation of the method has still been missing so far. Here, we interpret an $\\varepsilon$-recurrence network as a discrete subnetwork of a "continuous" graph with uncountably many vertices and edges corresponding to the system's attractor. This step allows us to show that various statistical measures commonly used in complex network analysis can be seen as discrete estimators of newly defined continuous measures of certain complex geometric properties of the attractor on the scale given by $\\varepsilon$.} In particular, we introduce local measures such as the $\\varepsilon$-clustering coefficient, mesoscopic measures such as $\\varepsilon$-motif density, path-based measures such as $\\varepsilon$-betweennesses, and global measures such as $\\varepsilon$-efficiency. This new analytical basis fo...
Polynomial harmonic GMDH learning networks for time series modeling.
Nikolaev, Nikolay Y; Iba, Hitoshi
2003-12-01
This paper presents a constructive approach to neural network modeling of polynomial harmonic functions. This is an approach to growing higher-order networks like these build by the multilayer GMDH algorithm using activation polynomials. Two contributions for enhancement of the neural network learning are offered: (1) extending the expressive power of the network representation with another compositional scheme for combining polynomial terms and harmonics obtained analytically from the data; (2) space improving the higher-order network performance with a backpropagation algorithm for further gradient descent learning of the weights, initialized by least squares fitting during the growing phase. Empirical results show that the polynomial harmonic version phGMDH outperforms the previous GMDH, a Neurofuzzy GMDH and traditional MLP neural networks on time series modeling tasks. Applying next backpropagation training helps to achieve superior polynomial network performances. PMID:14622880
Incorporating Satellite Time-Series Data into Modeling
Gregg, Watson
2008-01-01
In situ time series observations have provided a multi-decadal view of long-term changes in ocean biology. These observations are sufficiently reliable to enable discernment of even relatively small changes, and provide continuous information on a host of variables. Their key drawback is their limited domain. Satellite observations from ocean color sensors do not suffer the drawback of domain, and simultaneously view the global oceans. This attribute lends credence to their use in global and regional model validation and data assimilation. We focus on these applications using the NASA Ocean Biogeochemical Model. The enhancement of the satellite data using data assimilation is featured and the limitation of tongterm satellite data sets is also discussed.
Controlled, distributed data management of an Antarctic time series
Leadbetter, Adam; Connor, David; Cunningham, Nathan; Reynolds, Sarah
2010-05-01
The Rothera Time Series (RaTS) presents over ten years of oceanographic data collected off the Antarctic Peninsula comprising conductivity, temperature, depth cast data; current meter data; and bottle sample data. The data set has been extensively analysed and is well represented in the scientific literature. However, it has never been available to browse as a coherent entity. Work has been undertaken by both the data collecting organisation (the British Antarctic Survey, BAS) and the associated national data centre (the British Oceanographic Data Centre, BODC) to describe the parameters comprising the dataset in a consistent manner. To this end, each data point in the RaTS dataset has now been ascribed a parameter usage term, selected from the appropriate controlled vocabulary of the Natural Environment Research Council's Data Grid (NDG). By marking up the dataset in this way the semantic richness of the NDG vocabularies is fully accessible, and the dataset can be then explored using the Global Change Master Directory keyword set, the International Standards Organisation topic categories, SeaDataNet disciplines and agreed parameter groups, and the NDG parameter discovery vocabulary. We present a single data discovery and exploration tool, a web portal which allows the user to drill down through the dataset using their chosen keyword set. The spatial coverage of the chosen data is displayed through a Google Earth web plugin. Finally, as the time series data are held at BODC and the discrete sample data held at BAS (which are separate physical locations), a mechanism has been established to provide metadata from one site to another. This takes the form of an Open Geospatial Consortium Web Map Service server at BODC feeding information into the portal hosted at BAS.
Traffic time series analysis by using multiscale time irreversibility and entropy
Wang, Xuejiao; Shang, Pengjian; Fang, Jintang
2014-09-01
Traffic systems, especially urban traffic systems, are regulated by different kinds of interacting mechanisms which operate across multiple spatial and temporal scales. Traditional approaches fail to account for the multiple time scales inherent in time series, such as empirical probability distribution function and detrended fluctuation analysis, which have lead to different results. The role of multiscale analytical method in traffic time series is a frontier area of investigation. In this paper, our main purpose is to introduce a new method—multiscale time irreversibility, which is helpful to extract information from traffic time series we studied. In addition, to analyse the complexity of traffic volume time series of Beijing Ring 2, 3, 4 roads between workdays and weekends, which are from August 18, 2012 to October 26, 2012, we also compare the results by this new method and multiscale entropy method we have known well. The results show that the higher asymmetry index we get, the higher traffic congestion level will be, and accord with those which are obtained by multiscale entropy.
DEFF Research Database (Denmark)
Sørup, Hjalte Jomo Danielsen; Madsen, Henrik; Arnbjerg-Nielsen, Karsten
2011-01-01
A very fine temporal and volumetric resolution precipitation time series is modeled using Markov models. Both 1st and 2nd order Markov models as well as seasonal and diurnal models are investigated and evaluated using likelihood based techniques. The 2nd order Markov model is found to be insignif......A very fine temporal and volumetric resolution precipitation time series is modeled using Markov models. Both 1st and 2nd order Markov models as well as seasonal and diurnal models are investigated and evaluated using likelihood based techniques. The 2nd order Markov model is found to be...
Interglacial climate dynamics and advanced time series analysis
Mudelsee, Manfred; Bermejo, Miguel; Köhler, Peter; Lohmann, Gerrit
2013-04-01
Studying the climate dynamics of past interglacials (IGs) helps to better assess the anthropogenically influenced dynamics of the current IG, the Holocene. We select the IG portions from the EPICA Dome C ice core archive, which covers the past 800 ka, to apply methods of statistical time series analysis (Mudelsee 2010). The analysed variables are deuterium/H (indicating temperature) (Jouzel et al. 2007), greenhouse gases (Siegenthaler et al. 2005, Loulergue et al. 2008, L¨ü thi et al. 2008) and a model-co-derived climate radiative forcing (Köhler et al. 2010). We select additionally high-resolution sea-surface-temperature records from the marine sedimentary archive. The first statistical method, persistence time estimation (Mudelsee 2002) lets us infer the 'climate memory' property of IGs. Second, linear regression informs about long-term climate trends during IGs. Third, ramp function regression (Mudelsee 2000) is adapted to look on abrupt climate changes during IGs. We compare the Holocene with previous IGs in terms of these mathematical approaches, interprete results in a climate context, assess uncertainties and the requirements to data from old IGs for yielding results of 'acceptable' accuracy. This work receives financial support from the Deutsche Forschungsgemeinschaft (Project ClimSens within the DFG Research Priority Program INTERDYNAMIK) and the European Commission (Marie Curie Initial Training Network LINC, No. 289447, within the 7th Framework Programme). References Jouzel J, Masson-Delmotte V, Cattani O, Dreyfus G, Falourd S, Hoffmann G, Minster B, Nouet J, Barnola JM, Chappellaz J, Fischer H, Gallet JC, Johnsen S, Leuenberger M, Loulergue L, Luethi D, Oerter H, Parrenin F, Raisbeck G, Raynaud D, Schilt A, Schwander J, Selmo E, Souchez R, Spahni R, Stauffer B, Steffensen JP, Stenni B, Stocker TF, Tison JL, Werner M, Wolff EW (2007) Orbital and millennial Antarctic climate variability over the past 800,000 years. Science 317:793. Köhler P, Bintanja R
Time-series growth in the female labor force.
Smith, J P; Ward, M P
1985-01-01
This paper investigates the reasons for the growth in the female labor force in the US during the 20th century. Female labor force participation rates increased by 50% from 1950 to 1970. Real wages have played a significant but hardly exclusive role both in the long term growth in female employment and in the more accelerated growth after 1950. At the beginning of this century, fewer than 1 woman in 5 was a member of the labor force; by 1981 more than 6 in 10 were. Increases in female participation were slightly larger among younger women during the 1970s; for the next 20 years the age shape tilted toward older women. For US women 25-34 years old, labor force participation rates have been rising by more than 2 percentage points per year. Closely intertwined with decisions regarding women's work are those involving marriage and family formation. 2 demographic factors that would play a part in subsequent developments are: nuclearization of the US family and urbanization. Time-series trends in education are observed because schooling affects female labor supply independently of any influence through wages; increased years of schooling across birth cohorts shows that an increase of 1.33 years of schooling increased labor participation by 6.9 percentage points during the pre-World War II era. The swing in marriage rates also affects timing, especially for younger women. Based on disaggregated time series data across the period 1950-1981, mean values at single years of age of labor supply, education, work experience, weekly wages, and fertility are determined. Profiles indicate that female labor supply varies considerably not only across cohorts but also over life cycles within birth cohorts. Results show that: 1) relative female wages defined over the work force were lower in 1980 than in 1950, 2) children, especially when young, reduce labor supply, 3) large negative elasticities are linked to female wages, and 4) with all fertility induced effects included, real wage
Impact of Sensor Degradation on the MODIS NDVI Time Series
Wang, Dongdong; Morton, Douglas Christopher; Masek, Jeffrey; Wu, Aisheng; Nagol, Jyoteshwar; Xiong, Xiaoxiong; Levy, Robert; Vermote, Eric; Wolfe, Robert
2012-01-01
Time series of satellite data provide unparalleled information on the response of vegetation to climate variability. Detecting subtle changes in vegetation over time requires consistent satellite-based measurements. Here, the impact of sensor degradation on trend detection was evaluated using Collection 5 data from the Moderate Resolution Imaging Spectroradiometer (MODIS) sensors on the Terra and Aqua platforms. For Terra MODIS, the impact of blue band (Band 3, 470 nm) degradation on simulated surface reflectance was most pronounced at near-nadir view angles, leading to a 0.001-0.004 yr-1 decline in Normalized Difference Vegetation Index (NDVI) under a range of simulated aerosol conditions and surface types. Observed trends in MODIS NDVI over North America were consistentwith simulated results,with nearly a threefold difference in negative NDVI trends derived from Terra (17.4%) and Aqua (6.7%) MODIS sensors during 2002-2010. Planned adjustments to Terra MODIS calibration for Collection 6 data reprocessing will largely eliminate this negative bias in detection of NDVI trends.
Interrupted time-series analysis: studying trends in neurosurgery.
Wong, Ricky H; Smieliauskas, Fabrice; Pan, I-Wen; Lam, Sandi K
2015-12-01
OBJECT Neurosurgery studies traditionally have evaluated the effects of interventions on health care outcomes by studying overall changes in measured outcomes over time. Yet, this type of linear analysis is limited due to lack of consideration of the trend's effects both pre- and postintervention and the potential for confounding influences. The aim of this study was to illustrate interrupted time-series analysis (ITSA) as applied to an example in the neurosurgical literature and highlight ITSA's potential for future applications. METHODS The methods used in previous neurosurgical studies were analyzed and then compared with the methodology of ITSA. RESULTS The ITSA method was identified in the neurosurgical literature as an important technique for isolating the effect of an intervention (such as a policy change or a quality and safety initiative) on a health outcome independent of other factors driving trends in the outcome. The authors determined that ITSA allows for analysis of the intervention's immediate impact on outcome level and on subsequent trends and enables a more careful measure of the causal effects of interventions on health care outcomes. CONCLUSIONS ITSA represents a significant improvement over traditional observational study designs in quantifying the impact of an intervention. ITSA is a useful statistical procedure to understand, consider, and implement as the field of neurosurgery evolves in sophistication in big-data analytics, economics, and health services research. PMID:26621420
Time-series models for border inspection data.
Decrouez, Geoffrey; Robinson, Andrew
2013-12-01
We propose a new modeling approach for inspection data that provides a more useful interpretation of the patterns of detections of invasive pests, using cargo inspection as a motivating example. Methods that are currently in use generally classify shipments according to their likelihood of carrying biosecurity risk material, given available historical and contextual data. Ideally, decisions regarding which cargo containers to inspect should be made in real time, and the models used should be able to focus efforts when the risk is higher. In this study, we propose a dynamic approach that treats the data as a time series in order to detect periods of high risk. A regulatory organization will respond differently to evidence of systematic problems than evidence of random problems, so testing for serial correlation is of major interest. We compare three models that account for various degrees of serial dependence within the data. First is the independence model where the prediction of the arrival of a risky shipment is made solely on the basis of contextual information. We also consider a Markov chain that allows dependence between successive observations, and a hidden Markov model that allows further dependence on past data. The predictive performance of the models is then evaluated using ROC and leakage curves. We illustrate this methodology on two sets of real inspection data. PMID:23682814
Nonparametric directionality measures for time series and point process data.
Halliday, David M
2015-06-01
The need to determine the directionality of interactions between neural signals is a key requirement for analysis of multichannel recordings. Approaches most commonly used are parametric, typically relying on autoregressive models. A number of concerns have been expressed regarding parametric approaches, thus there is a need to consider alternatives. We present an alternative nonparametric approach for construction of directionality measures for bivariate random processes. The method combines time and frequency domain representations of bivariate data to decompose the correlation by direction. Our framework generates two sets of complementary measures, a set of scalar measures, which decompose the total product moment correlation coefficient summatively into three terms by direction and a set of functions which decompose the coherence summatively at each frequency into three terms by direction: forward direction, reverse direction and instantaneous interaction. It can be undertaken as an addition to a standard bivariate spectral and coherence analysis, and applied to either time series or point-process (spike train) data or mixtures of the two (hybrid data). In this paper, we demonstrate application to spike train data using simulated cortical neurone networks and application to experimental data from isolated muscle spindle sensory endings subject to random efferent stimulation. PMID:25958923
Forecasting incidence of dengue in Rajasthan, using time series analyses
Directory of Open Access Journals (Sweden)
Sunil Bhatnagar
2012-01-01
Full Text Available Aim: To develop a prediction model for dengue fever/dengue haemorrhagic fever (DF/DHF using time series data over the past decade in Rajasthan and to forecast monthly DF/DHF incidence for 2011. Materials and Methods: Seasonal autoregressive integrated moving average (SARIMA model was used for statistical modeling. Results: During January 2001 to December 2010, the reported DF/DHF cases showed a cyclical pattern with seasonal variation. SARIMA (0,0,1 (0,1,1 12 model had the lowest normalized Bayesian information criteria (BIC of 9.426 and mean absolute percentage error (MAPE of 263.361 and appeared to be the best model. The proportion of variance explained by the model was 54.3%. Adequacy of the model was established through Ljung-Box test (Q statistic 4.910 and P-value 0.996, which showed no significant correlation between residuals at different lag times. The forecast for the year 2011 showed a seasonal peak in the month of October with an estimated 546 cases. Conclusion: Application of SARIMA model may be useful for forecast of cases and impending outbreaks of DF/DHF and other infectious diseases, which exhibit seasonal pattern.
Mackenzie River Delta morphological change based on Landsat time series
Vesakoski, Jenni-Mari; Alho, Petteri; Gustafsson, David; Arheimer, Berit; Isberg, Kristina
2015-04-01
Arctic rivers are sensitive and yet quite unexplored river systems to which the climate change will impact on. Research has not focused in detail on the fluvial geomorphology of the Arctic rivers mainly due to the remoteness and wideness of the watersheds, problems with data availability and difficult accessibility. Nowadays wide collaborative spatial databases in hydrology as well as extensive remote sensing datasets over the Arctic are available and they enable improved investigation of the Arctic watersheds. Thereby, it is also important to develop and improve methods that enable detecting the fluvio-morphological processes based on the available data. Furthermore, it is essential to reconstruct and improve the understanding of the past fluvial processes in order to better understand prevailing and future fluvial processes. In this study we sum up the fluvial geomorphological change in the Mackenzie River Delta during the last ~30 years. The Mackenzie River Delta (~13 000 km2) is situated in the North Western Territories, Canada where the Mackenzie River enters to the Beaufort Sea, Arctic Ocean near the city of Inuvik. Mackenzie River Delta is lake-rich, productive ecosystem and ecologically sensitive environment. Research objective is achieved through two sub-objectives: 1) Interpretation of the deltaic river channel planform change by applying Landsat time series. 2) Definition of the variables that have impacted the most on detected changes by applying statistics and long hydrological time series derived from Arctic-HYPE model (HYdrologic Predictions for Environment) developed by Swedish Meteorological and Hydrological Institute. According to our satellite interpretation, field observations and statistical analyses, notable spatio-temporal changes have occurred in the morphology of the river channel and delta during the past 30 years. For example, the channels have been developing in braiding and sinuosity. In addition, various linkages between the studied
Estimation of vegetation cover resilience from satellite time series
Directory of Open Access Journals (Sweden)
T. Simoniello
2008-02-01
Full Text Available Resilience is a fundamental concept for understanding vegetation as a dynamic component of the climate system. It expresses the ability of ecosystems to tolerate disturbances and to recover their initial state. Recovery times are basic parameters of the vegetation's response to forcing and, therefore, are essential for describing realistic vegetation within dynamical models. Healthy vegetation tends to rapidly recover from shock and to persist in growth and expansion. On the contrary, climatic and anthropic stress can reduce resilience thus favouring persistent decrease in vegetation activity.
In order to characterize resilience, we analyzed the time series 1982–2003 of 8 km GIMMS AVHRR-NDVI maps of the Italian territory. Persistence probability of negative and positive trends was estimated according to the vegetation cover class, altitude, and climate. Generally, mean recovery times from negative trends were shorter than those estimated for positive trends, as expected for vegetation of healthy status. Some signatures of inefficient resilience were found in high-level mountainous areas and in the Mediterranean sub-tropical ones. This analysis was refined by aggregating pixels according to phenology. This multitemporal clustering synthesized information on vegetation cover, climate, and orography rather well. The consequent persistence estimations confirmed and detailed hints obtained from the previous analyses. Under the same climatic regime, different vegetation resilience levels were found. In particular, within the Mediterranean sub-tropical climate, clustering was able to identify features with different persistence levels in areas that are liable to different levels of anthropic pressure. Moreover, it was capable of enhancing reduced vegetation resilience also in the southern areas under Warm Temperate sub-continental climate. The general consistency of the obtained results showed that, with the help of suited analysis
Estimation of vegetation cover resilience from satellite time series
Directory of Open Access Journals (Sweden)
T. Simoniello
2008-07-01
Full Text Available Resilience is a fundamental concept for understanding vegetation as a dynamic component of the climate system. It expresses the ability of ecosystems to tolerate disturbances and to recover their initial state. Recovery times are basic parameters of the vegetation's response to forcing and, therefore, are essential for describing realistic vegetation within dynamical models. Healthy vegetation tends to rapidly recover from shock and to persist in growth and expansion. On the contrary, climatic and anthropic stress can reduce resilience thus favouring persistent decrease in vegetation activity.
In order to characterize resilience, we analyzed the time series 1982–2003 of 8 km GIMMS AVHRR-NDVI maps of the Italian territory. Persistence probability of negative and positive trends was estimated according to the vegetation cover class, altitude, and climate. Generally, mean recovery times from negative trends were shorter than those estimated for positive trends, as expected for vegetation of healthy status. Some signatures of inefficient resilience were found in high-level mountainous areas and in the Mediterranean sub-tropical ones. This analysis was refined by aggregating pixels according to phenology. This multitemporal clustering synthesized information on vegetation cover, climate, and orography rather well. The consequent persistence estimations confirmed and detailed hints obtained from the previous analyses. Under the same climatic regime, different vegetation resilience levels were found. In particular, within the Mediterranean sub-tropical climate, clustering was able to identify features with different persistence levels in areas that are liable to different levels of anthropic pressure. Moreover, it was capable of enhancing reduced vegetation resilience also in the southern areas under Warm Temperate sub-continental climate. The general consistency of the obtained results showed that, with the help of suited analysis
Academic Workload and Working Time: Retrospective Perceptions versus Time-Series Data
Kyvik, Svein
2013-01-01
The purpose of this article is to examine the validity of perceptions by academic staff about their past and present workload and working hours. Retrospective assessments are compared with time-series data. The data are drawn from four mail surveys among academic staff in Norwegian universities undertaken in the period 1982-2008. The findings show…
Li Wang; Zaiwen Liu; Chongchong Yu
2013-01-01
This paper proposes a reliability estimation method based on Step-Stress Accelerated Degradation Testing (SSADT) data analysis using unequal interval time series analysis. A Multi-Regression Time Varying Auto-Regressive (MRTVAR) degradation time series model is proposed. Product SSADT data are treated as unequal interval composite time series and described using MRTVAR time series model and utilized to predict long-term trend of degradation. By using the suggested method, product reliability ...
Madeira Sara C; Oliveira Arlindo L
2009-01-01
Abstract Background The ability to monitor the change in expression patterns over time, and to observe the emergence of coherent temporal responses using gene expression time series, obtained from microarray experiments, is critical to advance our understanding of complex biological processes. In this context, biclustering algorithms have been recognized as an important tool for the discovery of local expression patterns, which are crucial to unravel potential regulatory mechanisms. Although ...
E. Andres Houseman; Brent Coull; James Shine
2004-01-01
Boston Harbor has had a history of poor water quality, including by enteric pathogens. We conduct a statistical analysis of data collected by the Massachusetts Water Resources Authority (MWRA) between 1996 and 2002 to evaluate the effects of court-mandated improvements in sewage treatment. We propose a negative binomial model for time series of Enterococcus counts in Boston Harbor, where nonstationarity and autocorrelation are modeled using a nonparametric smooth function of time in the predi...
Forecasting Financial Time-Series using Artificial Market Models
Gupta, N; Johnson, N F; Gupta, Nachi; Hauser, Raphael; Johnson, Neil F.
2005-01-01
We discuss the theoretical machinery involved in predicting financial market movements using an artificial market model which has been trained on real financial data. This approach to market prediction - in particular, forecasting financial time-series by training a third-party or 'black box' game on the financial data itself -- was discussed by Johnson et al. in cond-mat/0105303 and cond-mat/0105258 and was based on some encouraging preliminary investigations of the dollar-yen exchange rate, various individual stocks, and stock market indices. However, the initial attempts lacked a clear formal methodology. Here we present a detailed methodology, using optimization techniques to build an estimate of the strategy distribution across the multi-trader population. In contrast to earlier attempts, we are able to present a systematic method for identifying 'pockets of predictability' in real-world markets. We find that as each pocket closes up, the black-box system needs to be 'reset' - which is equivalent to sayi...
Chaos Time Series Prediction Based on Membrane Optimization Algorithms
Directory of Open Access Journals (Sweden)
Meng Li
2015-01-01
Full Text Available This paper puts forward a prediction model based on membrane computing optimization algorithm for chaos time series; the model optimizes simultaneously the parameters of phase space reconstruction (τ,m and least squares support vector machine (LS-SVM (γ,σ by using membrane computing optimization algorithm. It is an important basis for spectrum management to predict accurately the change trend of parameters in the electromagnetic environment, which can help decision makers to adopt an optimal action. Then, the model presented in this paper is used to forecast band occupancy rate of frequency modulation (FM broadcasting band and interphone band. To show the applicability and superiority of the proposed model, this paper will compare the forecast model presented in it with conventional similar models. The experimental results show that whether single-step prediction or multistep prediction, the proposed model performs best based on three error measures, namely, normalized mean square error (NMSE, root mean square error (RMSE, and mean absolute percentage error (MAPE.
Scene Context Dependency of Pattern Constancy of Time Series Imagery
Woodell, Glenn A.; Jobson, Daniel J.; Rahman, Zia-ur
2008-01-01
A fundamental element of future generic pattern recognition technology is the ability to extract similar patterns for the same scene despite wide ranging extraneous variables, including lighting, turbidity, sensor exposure variations, and signal noise. In the process of demonstrating pattern constancy of this kind for retinex/visual servo (RVS) image enhancement processing, we found that the pattern constancy performance depended somewhat on scene content. Most notably, the scene topography and, in particular, the scale and extent of the topography in an image, affects the pattern constancy the most. This paper will explore these effects in more depth and present experimental data from several time series tests. These results further quantify the impact of topography on pattern constancy. Despite this residual inconstancy, the results of overall pattern constancy testing support the idea that RVS image processing can be a universal front-end for generic visual pattern recognition. While the effects on pattern constancy were significant, the RVS processing still does achieve a high degree of pattern constancy over a wide spectrum of scene content diversity, and wide ranging extraneousness variations in lighting, turbidity, and sensor exposure.
Industrial electricity demand for Turkey: A structural time series analysis
International Nuclear Information System (INIS)
This research investigates the relationship between Turkish industrial electricity consumption, industrial value added and electricity prices in order to forecast future Turkish industrial electricity demand. To achieve this, an industrial electricity demand function for Turkey is estimated by applying the structural time series technique to annual data over the period 1960 to 2008. In addition to identifying the size and significance of the price and industrial value added (output) elasticities, this technique also uncovers the electricity Underlying Energy Demand Trend (UEDT) for the Turkish industrial sector and is, as far as is known, the first attempt to do this. The results suggest that output and real electricity prices and a UEDT all have an important role to play in driving Turkish industrial electricity demand. Consequently, they should all be incorporated when modelling Turkish industrial electricity demand and the estimated UEDT should arguably be considered in future energy policy decisions concerning the Turkish electricity industry. The output and price elasticities are estimated to be 0.15 and - 0.16 respectively, with an increasing (but at a decreasing rate) UEDT and based on the estimated equation, and different forecast assumptions, it is predicted that Turkish industrial electricity demand will be somewhere between 97 and 148 TWh by 2020. -- Research Highlights: → Estimated output and price elasticities of 0.15 and -0.16 respectively. → Estimated upward sloping UEDT (i.e. energy using) but at a decreasing rate. → Predicted Turkish industrial electricity demand between 97 and 148 TWh in 2020.
Optimizing the search for transiting planets in long time series
Ofir, Aviv
2013-01-01
Context: Transit surveys, both ground- and space- based, have already accumulated a large number of light curves that span several years. Aims: The search for transiting planets in these long time series is computationally intensive. We wish to optimize the search for both detection and computational efficiencies. Methods: We assume that the searched systems can be well described by Keplerian orbits. We then propagate the effects of different system parameters to the detection parameters. Results: We show that the frequency information content of the light curve is primarily determined by the duty cycle of the transit signal, and thus the optimal frequency sampling is found to be cubic and not linear. Further optimization is achieved by considering duty-cycle dependent binning of the phased light curve. By using the (standard) BLS one is either rather insensitive to long-period planets, or less sensitive to short-period planets and computationally slower by a significant factor of ~330 (for a 3yr long dataset...
Fast Intrinsic Mode Decomposition of Time Series Data
Lu, Louis Yu
2008-01-01
A fast convergent iterative method is introduced in this paper to find the intrinsic mode function (IMF) components of time series data, which is faster and more predictable than the Empirical Mode Decomposition method devised by the author of Hilbert Huang Transform. The method iteratively adjust the control points on the data function corresponding to the extrema of the refining IMF, the control points of the residue function are calculated as the median of the straight line segments passing through the data control points, the residue function is then constructed as the cubic spline function of the median points. The initial residue function is simply constructed as the straight line segments passing through the extrema of the differential of the data function. The refining IMF is the difference between the data function and the improved residue function. The IMF found can also reveal the riding waves on the steep edge of the data. The program to demonstrate the method is distributed under BSD license.
River flow time series using least squares support vector machines
Directory of Open Access Journals (Sweden)
R. Samsudin
2011-06-01
Full Text Available This paper proposes a novel hybrid forecasting model known as GLSSVM, which combines the group method of data handling (GMDH and the least squares support vector machine (LSSVM. The GMDH is used to determine the useful input variables which work as the time series forecasting for the LSSVM model. Monthly river flow data from two stations, the Selangor and Bernam rivers in Selangor state of Peninsular Malaysia were taken into consideration in the development of this hybrid model. The performance of this model was compared with the conventional artificial neural network (ANN models, Autoregressive Integrated Moving Average (ARIMA, GMDH and LSSVM models using the long term observations of monthly river flow discharge. The root mean square error (RMSE and coefficient of correlation (R are used to evaluate the models' performances. In both cases, the new hybrid model has been found to provide more accurate flow forecasts compared to the other models. The results of the comparison indicate that the new hybrid model is a useful tool and a promising new method for river flow forecasting.
An observed 20 yr time-series of Agulhas leakage
Directory of Open Access Journals (Sweden)
D. Le Bars
2014-01-01
Full Text Available We provide a time series of Agulhas leakage anomalies over the last twenty years from satellite altimetry. Until now, measuring the interannual variability of Indo-Atlantic exchange has been the major barrier in the investigation of the dynamics and large scale impact of Agulhas leakage. We compute the difference of transport between Agulhas Current and Agulhas Return Current which allows to deduce Agulhas leakage. The main difficulty is to separate the Agulhas Return Current from the southern limb of the subtropical "supergyre" south of Africa. For this purpose, an algorithm that uses absolute dynamic topography data is developed. The algorithm is applied to a state-of-the-art ocean model. The comparison with a Lagrangian method to measure the leakage allows to validate the new method. An important result is that it is possible to measure Agulhas leakage in this model using the velocity field along a section that crosses both the Agulhas Current and the Agulhas Return Current. In the model a good correlation is found between measuring leakage using the full depth velocities and using only the surface geostrophic velocities. This allows us to extend the method to along-track absolute dynamic topography from satellites. It is shown that the accuracy of the mean dynamic topography does not allow to determine the mean leakage but that leakage anomalies can be accurately computed.
Presentations to Emergency Departments for COPD: A Time Series Analysis.
Rosychuk, Rhonda J; Youngson, Erik; Rowe, Brian H
2016-01-01
Background. Chronic obstructive pulmonary disease (COPD) is a common respiratory condition characterized by progressive dyspnea and acute exacerbations which may result in emergency department (ED) presentations. This study examines monthly rates of presentations to EDs in one Canadian province. Methods. Presentations for COPD made by individuals aged ≥55 years during April 1999 to March 2011 were extracted from provincial databases. Data included age, sex, and health zone of residence (North, Central, South, and urban). Crude rates were calculated. Seasonal autoregressive integrated moving average (SARIMA) time series models were developed. Results. ED presentations for COPD totalled 188,824 and the monthly rate of presentation remained relatively stable (from 197.7 to 232.6 per 100,000). Males and seniors (≥65 years) comprised 52.2% and 73.7% of presentations, respectively. The ARIMA(1,0, 0) × (1,0, 1)12 model was appropriate for the overall rate of presentations and for each sex and seniors. Zone specific models showed relatively stable or decreasing rates; the North zone had an increasing trend. Conclusions. ED presentation rates for COPD have been relatively stable in Alberta during the past decade. However, their increases in northern regions deserve further exploration. The SARIMA models quantified the temporal patterns and can help planning future health care service needs. PMID:27445514
Innovative techniques to analyze time series of geomagnetic activity indices
Balasis, Georgios; Papadimitriou, Constantinos; Daglis, Ioannis A.; Potirakis, Stelios M.; Eftaxias, Konstantinos
2016-04-01
Magnetic storms are undoubtedly among the most important phenomena in space physics and also a central subject of space weather. The non-extensive Tsallis entropy has been recently introduced, as an effective complexity measure for the analysis of the geomagnetic activity Dst index. The Tsallis entropy sensitively shows the complexity dissimilarity among different "physiological" (normal) and "pathological" states (intense magnetic storms). More precisely, the Tsallis entropy implies the emergence of two distinct patterns: (i) a pattern associated with the intense magnetic storms, which is characterized by a higher degree of organization, and (ii) a pattern associated with normal periods, which is characterized by a lower degree of organization. Other entropy measures such as Block Entropy, T-Complexity, Approximate Entropy, Sample Entropy and Fuzzy Entropy verify the above mentioned result. Importantly, the wavelet spectral analysis in terms of Hurst exponent, H, also shows the existence of two different patterns: (i) a pattern associated with the intense magnetic storms, which is characterized by a fractional Brownian persistent behavior (ii) a pattern associated with normal periods, which is characterized by a fractional Brownian anti-persistent behavior. Finally, we observe universality in the magnetic storm and earthquake dynamics, on a basis of a modified form of the Gutenberg-Richter law for the Tsallis statistics. This finding suggests a common approach to the interpretation of both phenomena in terms of the same driving physical mechanism. Signatures of discrete scale invariance in Dst time series further supports the aforementioned proposal.
Reconstructing Ocean Circulation using Coral (triangle)14C Time Series
Energy Technology Data Exchange (ETDEWEB)
Kashgarian, M; Guilderson, T P
2001-02-23
the invasion of fossil fuel CO{sub 2} and bomb {sup 14}C into the atmosphere and surface oceans. Therefore the {Delta}{sup 14}C data that are produced in this study can be used to validate the ocean uptake of fossil fuel CO2 in coupled ocean-atmosphere models. This study takes advantage of the quasi-conservative nature of {sup 14}C as a water mass tracer by using {Delta}{sup 14}C time series in corals to identify changes in the shallow circulation of the Pacific. Although the data itself provides fundamental information on surface water mass movement the true strength is a combined approach which is greater than the individual parts; the data helps uncover deficiencies in ocean circulation models and the model results place long {Delta}{sup 14}C time series in a dynamic framework which helps to identify those locations where additional observations are most needed.
Crop growth dynamics modeling using time-series satellite imagery
Zhao, Yu
2014-11-01
In modern agriculture, remote sensing technology plays an essential role in monitoring crop growth and crop yield prediction. To monitor crop growth and predict crop yield, accurate and timely crop growth information is significant, in particularly for large scale farming. As the high cost and low data availability of high-resolution satellite images such as RapidEye, we focus on the time-series low resolution satellite imagery. In this research, NDVI curve, which was retrieved from satellite images of MODIS 8-days 250m surface reflectance, was applied to monitor soybean's yield. Conventional model and vegetation index for yield prediction has problems on describing the growth basic processes affecting yield component formation. In our research, a novel method is developed to well model the Crop Growth Dynamics (CGD) and generate CGD index to describe the soybean's yield component formation. We analyze the standard growth stage of soybean and to model the growth process, we have two key calculate process. The first is normalization of the NDVI-curve coordinate and division of the crop growth based on the standard development stages using EAT (Effective accumulated temperature).The second is modeling the biological growth on each development stage through analyzing the factors of yield component formation. The evaluation was performed through the soybean yield prediction using the CGD Index in the growth stage when the whole dataset for modeling is available and we got precision of 88.5% which is about 10% higher than the conventional method. The validation results showed that prediction accuracy using our CGD modeling is satisfied and can be applied in practice of large scale soybean yield monitoring.
Staircase baker's map generates flaring-type time series
Directory of Open Access Journals (Sweden)
G. Radons
2000-01-01
Full Text Available The baker’s map, invented by Eberhard Hopf in 1937, is an intuitively accesible, two-dimensional chaos-generating discrete dynamical system. This map, which describes the transformation of an idealized two-dimensional dough by stretching, cutting and piling, is non-dissipative. Nevertheless the “x” variable is identical with the dissipative, one-dimensional Bernoulli-shift-generating map. The generalization proposed here takes up ideas of Yaacov Sinai in a modified form. It has a staircase-like shape, with every next step half as high as the preceding one. Each pair of neighboring elements exchanges an equal volume (area during every iteration step in a scaled manner. Since the density of iterated points is constant, the thin tail (to the right, say is visited only exponentially rarely. This observation already explains the map's main qualitative behavior: The “x” variable shows “flares”. The time series of this variable is closely analogous to that of a flaring-type dissipative dynamical system – like those recently described in an abstract economic model. An initial point starting its journey in the tale (or “antenna”, if we tilt the map upwards by 90 degrees is predictably attracted by the broad left hand (bottom part, in order to only very rarely venture out again to the tip. Yet whenever it does so, it thereby creates, with the top of a flare, a new “far-from-equilibrium” initial condition, in this reversible system. The system therefore qualifies as a discrete analogue to a far-from-equilibrium multiparticle Hamiltonian system. The height of the flare hereby corresponds to the momentary height of the H function of a gas. An observable which is even more closely related to the momentary negative entropy was recently described. Dependent on the numerical accuracy chosen, “Poincaré cycles” of two different types (periodic and nonperiodic can be observed for the first time.
Optimizing the search for transiting planets in long time series
Ofir, Aviv
2014-01-01
Context. Transit surveys, both ground- and space-based, have already accumulated a large number of light curves that span several years. Aims: The search for transiting planets in these long time series is computationally intensive. We wish to optimize the search for both detection and computational efficiencies. Methods: We assume that the searched systems can be described well by Keplerian orbits. We then propagate the effects of different system parameters to the detection parameters. Results: We show that the frequency information content of the light curve is primarily determined by the duty cycle of the transit signal, and thus the optimal frequency sampling is found to be cubic and not linear. Further optimization is achieved by considering duty-cycle dependent binning of the phased light curve. By using the (standard) BLS, one is either fairly insensitive to long-period planets or less sensitive to short-period planets and computationally slower by a significant factor of ~330 (for a 3 yr long dataset). We also show how the physical system parameters, such as the host star's size and mass, directly affect transit detection. This understanding can then be used to optimize the search for every star individually. Conclusions: By considering Keplerian dynamics explicitly rather than implicitly one can optimally search the BLS parameter space. The presented Optimal BLS enhances the detectability of both very short and very long period planets, while allowing such searches to be done with much reduced resources and time. The Matlab/Octave source code for Optimal BLS is made available. The MATLAB code is only available at the CDS via anonymous ftp to http://cdsarc.u-strasbg.fr (ftp://130.79.128.5) or via http://cdsarc.u-strasbg.fr/viz-bin/qcat?J/A+A/561/A138
Predicting forest structure across space and time using lidar and Landsat time series (Invited)
Cohen, W. B.; Pflugmacher, D.; Yang, Z.
2013-12-01
Lidar is unprecedented in its ability to provide detailed characterizations of forest structure. However, use of lidar is currently limited to relatively small areas associated with specific projects. Moreover, lidar data are even more severely limited historically, which inhibits retrospective analyses of structure change. Landsat data is commonly dismissed when considering a need to map forest structure due to its lack of sensitivity to structural variability. But with the opening of the archive by USGS, Landsat data can now be used in creative ways that take advantage of dense time series to describe historic disturbance and recovery. Because the condition and state of a forest at any given location is largely a function of its disturbance history, this provides an opportunity to use Landsat time series to inform statistical models that predict current forest structure. Additionally, because Landsat time series go back to 1972, it becomes possible to extend those models back in time to derive structure trajectories for retrospective analyses. We will present the results from one or two studies in the Pacific Northwest, USA that use disturbance history metrics derived from Landsat time series to demonstrate the new power of Landsat to predict forest structure (e.g., aboveground live biomass, height). The primary metrics used relate to the magnitude of the greatest disturbance, pre- and post- disturbance spectral trends, and current spectral properties. This is accomplished using a limited field dataset to translate a lidar coverage into the structure measures of interest, and then sampling the lidar data to build a robust statistical relationship between lidar-derived structure and disturbance history. We examined the effect of number of years of history on prediction strength and found that R2 increases and RMSE decreases for a period of ~20 years. This means we can predict forest structure as far back as 1992, using the 20 years of history information contained
Wavelet-Based Multi-Scale Entropy Analysis of Complex Rainfall Time Series
Chien-Ming Chou
2011-01-01
This paper presents a novel framework to determine the number of resolution levels in the application of a wavelet transformation to a rainfall time series. The rainfall time series are decomposed using the à trous wavelet transform. Then, multi-scale entropy (MSE) analysis that helps to elucidate some hidden characteristics of the original rainfall time series is applied to the decomposed rainfall time series. The analysis shows that the Mann-Kendall (MK) rank correlation test of MSE curves ...
Performance of Exchange Rate Forecast Using Distance-Based Fuzzy Time Series
Lazim Abdullah
2013-01-01
Fuzzy time series model has been employed by many researchers in forecasting activities such as students’ enrolment, temperature fluctuations and stock prices. The existing fuzzy time series modelsrequire exact match of the fuzzy logic relationships to calculate the forecasted value. However, in real life applications, the exact match of fuzzy logic relationships is not possible. Thus, an improved fuzzy time series model termed as distance-based fuzzy time series model was proposed to remedy ...
First-Order ARMA Type Fuzzy Time Series Method Based on Fuzzy Logic Relation Tables
Cem Kocak
2013-01-01
Fuzzy time series approaches have an important deficiency according to classical time series approaches. This deficiency comes from the fact that all of the fuzzy time series models developed in the literature use autoregressive (AR) variables, without any studies that also make use of moving averages (MAs) variables with the exception of only one study (Egrioglu et al. (2013)). In order to eliminate this deficiency, it is necessary to have many of daily life time series be expressed with Aut...
In aquatic systems, time series of dissolved oxygen (DO) have been used to compute estimates of ecosystem metabolism. Central to this open-water method is the assumption that the DO time series is a Lagrangian specification of the flow field. However, most DO time series are coll...
The Coral Data Time Series Need To Be Revisited
Juillet-Leclerc, A.
2004-12-01
Coral skeleton is formed under organism control and its geochemical properties are strongly influenced by biological effects embedding environmental signal. Geochemists have been puzzled by the diversity of geochemical responses showed by colonies grown in a same area. By revisiting the Weber and Woodhead data series (1972), gathering data from enough colonies developed in similar conditions to provide a statistical isotopic value representative of one site, we demonstrate that for Porites and Acropora, the expected isotopic thermometer is revealed when the "vital effect" is removed. On the other hand, by using Acropora cultured in controlled condition, with changing temperature on a range comprised between 23 and 29°C, the comparison of oxygen and carbon isotopic values revealed the role played by kinetic fractionation. This apparent paradox of two co-existing fractionations is explained by the isotopic analyzes of wild and cultured corals operated at micrometer size scale taking into account of microstructures of the skeleton. Two different crystals appear to be the growth units of the skeleton, each crystal corresponding to a specific deposition mechanism. Thus, the measurement performed with a conventional method is a "bulk" measurement, which depends upon two isotopic fractionations. Some investigations underlined the discrepancy of the meaning of the inter-annual and seasonal isotopic records, which could be illustrated by different isotopic calibrations assessed from seasonal or annual data. It has been also explained by micrometer analyses of Porites aragonite. A smoothing at around 400microns of isotopic measurements as well as Sr/Ca indicates that at seasonal time scale the growth unit is the month. This is in agreement with extensive studies conducted by biologists describing the mechanism governing the formation of Porites skeleton: every month is deposited a framework which is progressively filled in. By combining biologists and geochemists knowledge
Evaluating mallard adaptive management models with time series
Conn, P.B.; Kendall, W.L.
2004-01-01
Wildlife practitioners concerned with midcontinent mallard (Anas platyrhynchos) management in the United States have instituted a system of adaptive harvest management (AHM) as an objective format for setting harvest regulations. Under the AHM paradigm, predictions from a set of models that reflect key uncertainties about processes underlying population dynamics are used in coordination with optimization software to determine an optimal set of harvest decisions. Managers use comparisons of the predictive abilities of these models to gauge the relative truth of different hypotheses about density-dependent recruitment and survival, with better-predicting models giving more weight to the determination of harvest regulations. We tested the effectiveness of this strategy by examining convergence rates of 'predictor' models when the true model for population dynamics was known a priori. We generated time series for cases when the a priori model was 1 of the predictor models as well as for several cases when the a priori model was not in the model set. We further examined the addition of different levels of uncertainty into the variance structure of predictor models, reflecting different levels of confidence about estimated parameters. We showed that in certain situations, the model-selection process favors a predictor model that incorporates the hypotheses of additive harvest mortality and weakly density-dependent recruitment, even when the model is not used to generate data. Higher levels of predictor model variance led to decreased rates of convergence to the model that generated the data, but model weight trajectories were in general more stable. We suggest that predictive models should incorporate all sources of uncertainty about estimated parameters, that the variance structure should be similar for all predictor models, and that models with different functional forms for population dynamics should be considered for inclusion in predictor model! sets. All of these
Detection of cavity migration risks using radar interferometric time series
Chang, L.; Hanssen, R. F.
2012-12-01
, ERS-2, Envisat, and Radarsat-2, to investigate the dynamics (deformation) of the area. In particular we show, for the first time, shear-stress change distribution patterns within the structure of a building, over a period of close to 20 years. Time series analysis shows that deformation rates of ~4 mm/a could be detected for about 18 years, followed by a dramatic increase of up to 20 mm/a in the last period. These results imply that the driving mechanisms of the 2011 catastrophe have a very long lead time and are therefore likely due to a long-lasting gradual motion, such as the upward migration of a cavity. The analysis shows the collocation of the deformation location with relatively shallow near-horizontal mine shafts, suggesting that cavity migration has a high likelihood to be the driving mechanism of the collapse-sinkhole.
Factor Models in High-Dimensional Time Series: A Time-Domain Approach
Hallin, Marc; Lippi, Marco
2013-01-01
High-dimensional time series may well be the most common type of dataset in the socalled“big data” revolution, and have entered current practice in many areas, includingmeteorology, genomics, chemometrics, connectomics, complex physics simulations, biologicaland environmental research, finance and econometrics. The analysis of such datasetsposes significant challenges, both from a statistical as from a numerical point of view. Themost successful procedures so far have been based on dimension ...
Shen, Haipeng; HUANG, JIANHUA Z.
2008-01-01
We consider forecasting the latent rate profiles of a time series of inhomogeneous Poisson processes. The work is motivated by operations management of queueing systems, in particular, telephone call centers, where accurate forecasting of call arrival rates is a crucial primitive for efficient staffing of such centers. Our forecasting approach utilizes dimension reduction through a factor analysis of Poisson variables, followed by time series modeling of factor score series. Time series forec...
Zhao, Zoey Yi; Xie, Meng; West, Mike
2016-01-01
We discuss Bayesian forecasting of increasingly high-dimensional time series, a key area of application of stochastic dynamic models in the financial industry and allied areas of business. Novel state-space models characterizing sparse patterns of dependence among multiple time series extend existing multivariate volatility models to enable scaling to higher numbers of individual time series. The theory of these "dynamic dependence network" models shows how the individual series can be "decou...
HIGH ORDER FUZZY TIME SERIES MODEL AND ITS APLICATION TO IMKB
Directory of Open Access Journals (Sweden)
Çağdaş Hakan ALADAĞ
2010-12-01
Full Text Available The observations of some real time series such as temperature and stock market can take different values in a day. Instead of representing the observations of these time series by real numbers, employing linguistic values or fuzzy sets can be more appropriate. In recent years, many approaches have been introduced to analyze time series consisting of observations which are fuzzy sets and such time series are called fuzzy time series. In this study, a novel approach is proposed to analyze high order fuzzy time series model. The proposed method is applied to IMKB data and the obtained results are discussed. IMKB data is also analyzed by using some other fuzzy time series methods available in the literature and obtained results are compared to results obtained from the proposed method. As a result of the comparison, it is seen that the proposed method produce accurate forecasts.
Time-series-analysis techniques applied to nuclear-material accounting
International Nuclear Information System (INIS)
This document is designed to introduce the reader to the applications of Time Series Analysis techniques to Nuclear Material Accountability data. Time series analysis techniques are designed to extract information from a collection of random variables ordered by time by seeking to identify any trends, patterns, or other structure in the series. Since nuclear material accountability data is a time series, one can extract more information using time series analysis techniques than by using other statistical techniques. Specifically, the objective of this document is to examine the applicability of time series analysis techniques to enhance loss detection of special nuclear materials. An introductory section examines the current industry approach which utilizes inventory differences. The error structure of inventory differences is presented. Time series analysis techniques discussed include the Shewhart Control Chart, the Cumulative Summation of Inventory Differences Statistics (CUSUM) and the Kalman Filter and Linear Smoother
SensL B-Series and C-Series silicon photomultipliers for time-of-flight positron emission tomography
Energy Technology Data Exchange (ETDEWEB)
O' Neill, K., E-mail: koneill@sensl.com; Jackson, C., E-mail: cjackson@sensl.com
2015-07-01
Silicon photomultipliers from SensL are designed for high performance, uniformity and low cost. They demonstrate peak photon detection efficiency of 41% at 420 nm, which is matched to the output spectrum of cerium doped lutetium orthosilicate. Coincidence resolving time of less than 220 ps is demonstrated. New process improvements have lead to the development of C-Series SiPM which reduces the dark noise by over an order of magnitude. In this paper we will show characterization test results which include photon detection efficiency, dark count rate, crosstalk probability, afterpulse probability and coincidence resolving time comparing B-Series to the newest pre-production C-Series. Additionally we will discuss the effect of silicon photomultiplier microcell size on coincidence resolving time allowing the optimal microcell size choice to be made for time of flight positron emission tomography systems.
Directory of Open Access Journals (Sweden)
Madeira Sara C
2009-06-01
Full Text Available Abstract Background The ability to monitor the change in expression patterns over time, and to observe the emergence of coherent temporal responses using gene expression time series, obtained from microarray experiments, is critical to advance our understanding of complex biological processes. In this context, biclustering algorithms have been recognized as an important tool for the discovery of local expression patterns, which are crucial to unravel potential regulatory mechanisms. Although most formulations of the biclustering problem are NP-hard, when working with time series expression data the interesting biclusters can be restricted to those with contiguous columns. This restriction leads to a tractable problem and enables the design of efficient biclustering algorithms able to identify all maximal contiguous column coherent biclusters. Methods In this work, we propose e-CCC-Biclustering, a biclustering algorithm that finds and reports all maximal contiguous column coherent biclusters with approximate expression patterns in time polynomial in the size of the time series gene expression matrix. This polynomial time complexity is achieved by manipulating a discretized version of the original matrix using efficient string processing techniques. We also propose extensions to deal with missing values, discover anticorrelated and scaled expression patterns, and different ways to compute the errors allowed in the expression patterns. We propose a scoring criterion combining the statistical significance of expression patterns with a similarity measure between overlapping biclusters. Results We present results in real data showing the effectiveness of e-CCC-Biclustering and its relevance in the discovery of regulatory modules describing the transcriptomic expression patterns occurring in Saccharomyces cerevisiae in response to heat stress. In particular, the results show the advantage of considering approximate patterns when compared to state of
Gómez-Extremera, Manuel; Carpena, Pedro; Ivanov, Plamen Ch.; Bernaola-Galván, Pedro A.
2016-04-01
We systematically study the scaling properties of the magnitude and sign of the fluctuations in correlated time series, which is a simple and useful approach to distinguish between systems with different dynamical properties but the same linear correlations. First, we decompose artificial long-range power-law linearly correlated time series into magnitude and sign series derived from the consecutive increments in the original series, and we study their correlation properties. We find analytical expressions for the correlation exponent of the sign series as a function of the exponent of the original series. Such expressions are necessary for modeling surrogate time series with desired scaling properties. Next, we study linear and nonlinear correlation properties of series composed as products of independent magnitude and sign series. These surrogate series can be considered as a zero-order approximation to the analysis of the coupling of magnitude and sign in real data, a problem still open in many fields. We find analytical results for the scaling behavior of the composed series as a function of the correlation exponents of the magnitude and sign series used in the composition, and we determine the ranges of magnitude and sign correlation exponents leading to either single scaling or to crossover behaviors. Finally, we obtain how the linear and nonlinear properties of the composed series depend on the correlation exponents of their magnitude and sign series. Based on this information we propose a method to generate surrogate series with controlled correlation exponent and multifractal spectrum.
Business Cycle Properties of Selected U.S. Economic Time Series, 1959-1988
James H. Stock; Mark W. Watson
1990-01-01
This paper catalogs the business cycle properties of 163 monthly U.S. economic time series over the three decades from 1959 through 1988. Two general sets of summary statistics are reported. The first set measures the comovement of each individual time series with a reference series representing real economic activity. These statistics focus on comovements at business cycle horizons. The second set of statistics examines the predictive content of each of the series for aggregate activity, rel...
Indirect inference with time series observed with error
ROSSI Eduardo; Santucci de Magistris, Paolo
2014-01-01
We analyze the properties of the indirect inference estimator when the observed series are contaminated by measurement error. We show that the indirect inference estimates are asymptotically biased when the nuisance parameters of the measurement error distribution are neglected in the indirect estimation. We propose to solve this inconsistency by jointly estimating the nuisance and the structural parameters. Under standard assumptions, this estimator is consistentand asymptotically normal. A ...