WorldWideScience

Sample records for cells time series

  1. Pseudotime estimation: deconfounding single cell time series

    Science.gov (United States)

    Reid, John E.; Wernisch, Lorenz

    2016-01-01

    Motivation: Repeated cross-sectional time series single cell data confound several sources of variation, with contributions from measurement noise, stochastic cell-to-cell variation and cell progression at different rates. Time series from single cell assays are particularly susceptible to confounding as the measurements are not averaged over populations of cells. When several genes are assayed in parallel these effects can be estimated and corrected for under certain smoothness assumptions on cell progression. Results: We present a principled probabilistic model with a Bayesian inference scheme to analyse such data. We demonstrate our method’s utility on public microarray, nCounter and RNA-seq datasets from three organisms. Our method almost perfectly recovers withheld capture times in an Arabidopsis dataset, it accurately estimates cell cycle peak times in a human prostate cancer cell line and it correctly identifies two precocious cells in a study of paracrine signalling in mouse dendritic cells. Furthermore, our method compares favourably with Monocle, a state-of-the-art technique. We also show using held-out data that uncertainty in the temporal dimension is a common confounder and should be accounted for in analyses of repeated cross-sectional time series. Availability and Implementation: Our method is available on CRAN in the DeLorean package. Contact: john.reid@mrc-bsu.cam.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27318198

  2. Reconstructing dynamic molecular states from single-cell time series.

    Science.gov (United States)

    Huang, Lirong; Pauleve, Loic; Zechner, Christoph; Unger, Michael; Hansen, Anders S; Koeppl, Heinz

    2016-09-01

    The notion of state for a system is prevalent in the quantitative sciences and refers to the minimal system summary sufficient to describe the time evolution of the system in a self-consistent manner. This is a prerequisite for a principled understanding of the inner workings of a system. Owing to the complexity of intracellular processes, experimental techniques that can retrieve a sufficient summary are beyond our reach. For the case of stochastic biomolecular reaction networks, we show how to convert the partial state information accessible by experimental techniques into a full system state using mathematical analysis together with a computational model. This is intimately related to the notion of conditional Markov processes and we introduce the posterior master equation and derive novel approximations to the corresponding infinite-dimensional posterior moment dynamics. We exemplify this state reconstruction approach using both in silico data and single-cell data from two gene expression systems in Saccharomyces cerevisiae, where we reconstruct the dynamic promoter and mRNA states from noisy protein abundance measurements. PMID:27605167

  3. Time series analysis.

    NARCIS (Netherlands)

    2013-01-01

    Time series analysis can be used to quantitatively monitor, describe, explain, and predict road safety developments. Time series analysis techniques offer the possibility of quantitatively modelling road safety developments in such a way that the dependencies between the observations of time series

  4. Time-series gene expression prof iles in AGS cells stimulated with Helicobacter pylori

    Institute of Scientific and Technical Information of China (English)

    2010-01-01

    AIM: To extend the knowledge of the dynamic interaction between Helicobacter pylori (H. pylori) and host mucosa. METHODS: A time-series cDNA microarray was performed in order to detect the temporal gene expression prof iles of human gastric epithelial adenocarcinoma cells infected with H. pylori. Six time points were selected to observe the changes in the model. A differential expression prof ile at each time point was obtained by comparing the microarray signal value with that of 0 h. Real-time polymerase ...

  5. Time Series Momentum

    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....

  6. Time Series Explorer

    Science.gov (United States)

    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

  7. Multivariate Time Series Search

    Data.gov (United States)

    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...

  8. Long time series

    DEFF Research Database (Denmark)

    Hisdal, H.; Holmqvist, E.; Hyvärinen, V.;

    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...

  9. Visual time series analysis

    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...

  10. Time series analysis

    CERN Document Server

    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

  11. Applied time series analysis

    CERN Document Server

    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)""…

  12. Causality between time series

    CERN Document Server

    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...

  13. GPS Position Time Series @ JPL

    Science.gov (United States)

    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

  14. Model-based deconvolution of cell cycle time-series data reveals gene expression details at high resolution.

    Directory of Open Access Journals (Sweden)

    Dan Siegal-Gaskins

    2009-08-01

    Full Text Available In both prokaryotic and eukaryotic cells, gene expression is regulated across the cell cycle to ensure "just-in-time" assembly of select cellular structures and molecular machines. However, present in all time-series gene expression measurements is variability that arises from both systematic error in the cell synchrony process and variance in the timing of cell division at the level of the single cell. Thus, gene or protein expression data collected from a population of synchronized cells is an inaccurate measure of what occurs in the average single-cell across a cell cycle. Here, we present a general computational method to extract "single-cell"-like information from population-level time-series expression data. This method removes the effects of 1 variance in growth rate and 2 variance in the physiological and developmental state of the cell. Moreover, this method represents an advance in the deconvolution of molecular expression data in its flexibility, minimal assumptions, and the use of a cross-validation analysis to determine the appropriate level of regularization. Applying our deconvolution algorithm to cell cycle gene expression data from the dimorphic bacterium Caulobacter crescentus, we recovered critical features of cell cycle regulation in essential genes, including ctrA and ftsZ, that were obscured in population-based measurements. In doing so, we highlight the problem with using population data alone to decipher cellular regulatory mechanisms and demonstrate how our deconvolution algorithm can be applied to produce a more realistic picture of temporal regulation in a cell.

  15. Bootstrapping High Dimensional Time Series

    OpenAIRE

    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...

  16. Autoencoding Time Series for Visualisation

    OpenAIRE

    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 ...

  17. FROG: Time-series analysis

    Science.gov (United States)

    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.

  18. Advances in time series forecasting

    CERN Document Server

    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.

  19. Fractal and Multifractal Time Series

    CERN Document Server

    Kantelhardt, Jan W

    2008-01-01

    Data series generated by complex systems exhibit fluctuations on many time scales and/or broad distributions of the values. In both equilibrium and non-equilibrium situations, the natural fluctuations are often found to follow a scaling relation over several orders of magnitude, allowing for a characterisation of the data and the generating complex system by fractal (or multifractal) scaling exponents. In addition, fractal and multifractal approaches can be used for modelling time series and deriving predictions regarding extreme events. This review article describes and exemplifies several methods originating from Statistical Physics and Applied Mathematics, which have been used for fractal and multifractal time series analysis.

  20. Time Series with Tailored Nonlinearities

    CERN Document Server

    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.

  1. Models for dependent time series

    CERN Document Server

    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

  2. Autoencoding Time Series for Visualisation

    CERN Document Server

    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.

  3. Time series analysis supporting the hypothesis that enhanced cosmic radiation during germ cell formation can increase breast cancer mortality in germ cell cohorts

    Science.gov (United States)

    Juckett, D. A.; Rosenberg, Barnett

    Techniques from cancer epidemiology and time series analysis were used to explore the hypothesis that cosmic radiation can induce germ cell changes leading to increases in future breast cancer mortality. A birth cohort time series for female breast cancer mortality was obtained using a model-independent, age-period-cohort analysis on age-specific mortality data for 1940-1990. The birth cohort series contained several oscillatory components, which were isolated and compared to the corresponding frequency components of a cosmic ray surrogate time series - Greenland ice-core 10Be concentrations. A technique, referred to as component wave-train alignment, was used to show that the breast cancer and cosmic ray oscillations were phase-locked approx. 25 years before the time of birth. This is consistent with the time of germ cell formation, which occurs during the fetal development stage of the preceding generation. Evidence is presented that the observable oscillations in the birth cohort series were residues of oscillations of much larger amplitude in the germ cell cohort, which were attenuated by the effect of the broad maternal age distribution. It is predicted that a minimum of 50% of breast cancer risk is associated with germ cell damage by cosmic radiation (priming event), which leads to the development of individuals with a higher risk of breast cancer. It is proposed that the priming event, by preceding other steps of carcinogenesis, works in concert with risk factor exposure during life. The priming event is consistent with epigenetic changes such as imprinting.

  4. Clustering of financial time series

    Science.gov (United States)

    D'Urso, Pierpaolo; Cappelli, Carmela; Di Lallo, Dario; Massari, Riccardo

    2013-05-01

    This paper addresses the topic of classifying financial time series in a fuzzy framework proposing two fuzzy clustering models both based on GARCH models. In general clustering of financial time series, due to their peculiar features, needs the definition of suitable distance measures. At this aim, the first fuzzy clustering model exploits the autoregressive representation of GARCH models and employs, in the framework of a partitioning around medoids algorithm, the classical autoregressive metric. The second fuzzy clustering model, also based on partitioning around medoids algorithm, uses the Caiado distance, a Mahalanobis-like distance, based on estimated GARCH parameters and covariances that takes into account the information about the volatility structure of time series. In order to illustrate the merits of the proposed fuzzy approaches an application to the problem of classifying 29 time series of Euro exchange rates against international currencies is presented and discussed, also comparing the fuzzy models with their crisp version.

  5. Multivariate Time Series Similarity Searching

    OpenAIRE

    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...

  6. Systematic identification of cell cycle regulated transcription factors from microarray time series data

    Directory of Open Access Journals (Sweden)

    Li Lei M

    2008-03-01

    Full Text Available Abstract Background The cell cycle has long been an important model to study the genome-wide transcriptional regulation. Although several methods have been introduced to identify cell cycle regulated genes from microarray data, they can not be directly used to investigate cell cycle regulated transcription factors (CCRTFs, because for many transcription factors (TFs it is their activities instead of expressions that are periodically regulated across the cell cycle. To overcome this problem, it is useful to infer TF activities across the cell cycle by integrating microarray expression data with ChIP-chip data, and then examine the periodicity of the inferred activities. For most species, however, large-scale ChIP-chip data are still not available. Results We propose a two-step method to identify the CCRTFs by integrating microarray cell cycle data with ChIP-chip data or motif discovery data. In S. cerevisiae, we identify 42 CCRTFs, among which 23 have been verified experimentally. The cell cycle related behaviors (e.g. at which cell cycle phase a TF achieves the highest activity predicted by our method are consistent with the well established knowledge about them. We also find that the periodical activity fluctuation of some TFs can be perturbed by the cell synchronization treatment. Moreover, by integrating expression data with in-silico motif discovery data, we identify 8 cell cycle associated regulatory motifs, among which 7 are binding sites for well-known cell cycle related TFs. Conclusion Our method is effective to identify CCRTFs by integrating microarray cell cycle data with TF-gene binding information. In S. cerevisiae, the TF-gene binding information is provided by the systematic ChIP-chip experiments. In other species where systematic ChIP-chip data is not available, in-silico motif discovery and analysis provide us with an alternative method. Therefore, our method is ready to be implemented to the microarray cell cycle data sets from

  7. Random time series in astronomy.

    Science.gov (United States)

    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

  8. Random time series in Astronomy

    CERN Document Server

    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 of stars in nearby galaxies; and persistent aperiodic variations (`noise') from powerful systems like 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 multivariate time series.

  9. Random time series in astronomy.

    Science.gov (United States)

    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.

  10. Stochastic Time-Series Spectroscopy

    CERN Document Server

    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...

  11. 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.

  12. A Course in Time Series Analysis

    CERN Document Server

    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

  13. Cell signaling review series

    Institute of Scientific and Technical Information of China (English)

    Aiming Lin; Zhenggang Liu

    2008-01-01

    @@ Signal transduction is pivotal for many, if not all, fundamental cellular functions including proliferation, differentiation, transformation and programmed cell death. Deregulation of cell signaling may result in certain types of cancers and other human diseases.

  14. Description of complex time series by multipoles

    DEFF Research Database (Denmark)

    Lewkowicz, M.; Levitan, J.; Puzanov, N.;

    2002-01-01

    We present a new method to describe time series with a highly complex time evolution. The time series is projected onto a two-dimensional phase-space plot which is quantified in terms of a multipole expansion where every data point is assigned a unit mass. The multipoles provide an efficient...... characterization of the original time series....

  15. Kolmogorov space in time series data

    Science.gov (United States)

    Kanjamapornkul, Kabin; Pinčák, Richard

    2016-10-01

    We provide the proof that the space of time series data is a Kolmogorov space with $T_{0}$-separation axiom using the loop space of time series data. In our approach we define a cyclic coordinate of intrinsic time scale of time series data after empirical mode decomposition. A spinor field of time series data comes from the rotation of data around price and time axis by defining a new extradimension to time series data. We show that there exist hidden eight dimensions in Kolmogorov space for time series data. Our concept is realized as the algorithm of empirical mode decomposition and intrinsic time scale decomposition and it is subsequently used for preliminary analysis on the real time series data.

  16. Time Series Analysis and Forecasting by Example

    CERN Document Server

    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

  17. A review of subsequence time series clustering.

    Science.gov (United States)

    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

  18. Data mining in time series databases

    CERN Document Server

    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.

  19. Outliers Mining in Time Series Data Sets

    Institute of Scientific and Technical Information of China (English)

    2002-01-01

    In this paper, we present a cluster-based algorithm for time series outlier mining.We use discrete Fourier transformation (DFT) to transform time series from time domain to frequency domain. Time series thus can be mapped as the points in k-dimensional space.For these points, a cluster-based algorithm is developed to mine the outliers from these points.The algorithm first partitions the input points into disjoint clusters and then prunes the clusters,through judgment that can not contain outliers.Our algorithm has been run in the electrical load time series of one steel enterprise and proved to be effective.

  20. Coupling between time series: a network view

    CERN Document Server

    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.

  1. International Work-Conference on Time Series

    CERN Document Server

    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.

  2. Random time series in Astronomy

    OpenAIRE

    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...

  3. Hurst Exponent Analysis of Financial Time Series

    Institute of Scientific and Technical Information of China (English)

    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.

  4. Statistical criteria for characterizing irradiance time series.

    Energy Technology Data Exchange (ETDEWEB)

    Stein, Joshua S.; Ellis, Abraham; Hansen, Clifford W.

    2010-10-01

    We propose and examine several statistical criteria for characterizing time series of solar irradiance. Time series of irradiance are used in analyses that seek to quantify the performance of photovoltaic (PV) power systems over time. Time series of irradiance are either measured or are simulated using models. Simulations of irradiance are often calibrated to or generated from statistics for observed irradiance and simulations are validated by comparing the simulation output to the observed irradiance. Criteria used in this comparison should derive from the context of the analyses in which the simulated irradiance is to be used. We examine three statistics that characterize time series and their use as criteria for comparing time series. We demonstrate these statistics using observed irradiance data recorded in August 2007 in Las Vegas, Nevada, and in June 2009 in Albuquerque, New Mexico.

  5. The Foundations of Modern Time Series Analysis

    CERN Document Server

    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.

  6. Reconstruction of time-delay systems from chaotic time series.

    Science.gov (United States)

    Bezruchko, B P; Karavaev, A S; Ponomarenko, V I; Prokhorov, M D

    2001-11-01

    We propose a method that allows one to estimate the parameters of model scalar time-delay differential equations from time series. The method is based on a statistical analysis of time intervals between extrema in the time series. We verify our method by using it for the reconstruction of time-delay differential equations from their chaotic solutions and for modeling experimental systems with delay-induced dynamics from their chaotic time series.

  7. Homogenising time series: beliefs, dogmas and facts

    Science.gov (United States)

    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.

  8. Network structure of multivariate time series

    Science.gov (United States)

    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.

  9. Time Series Analysis Using Composite Multiscale Entropy

    OpenAIRE

    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...

  10. A Simple Fuzzy Time Series Forecasting Model

    DEFF Research Database (Denmark)

    Ortiz-Arroyo, Daniel

    2016-01-01

    In this paper we describe a new first order fuzzy time series forecasting model. We show that our automatic fuzzy partitioning method provides an accurate approximation to the time series that when combined with rule forecasting and an OWA operator improves forecasting accuracy. Our model does...... not attempt to provide the best results in comparison with other forecasting methods but to show how to improve first order models using simple techniques. However, we show that our first order model is still capable of outperforming some more complex higher order fuzzy time series models....

  11. Time Series Analysis Forecasting and Control

    CERN Document Server

    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

  12. DATA MINING IN CANADIAN LYNX TIME SERIES

    Directory of Open Access Journals (Sweden)

    R.Karnaboopathy

    2012-01-01

    Full Text Available This paper sums up the applications of Statistical model such as ARIMA family timeseries models in Canadian lynx data time series analysis and introduces the method of datamining combined with Statistical knowledge to analysis Canadian lynx data series.

  13. 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.

  14. Evaluation of Harmonic Analysis of Time Series (HANTS): impact of gaps on time series reconstruction

    NARCIS (Netherlands)

    Zhou, J.Y.; Jia, L.; Hu, G.; Menenti, M.

    2012-01-01

    In recent decades, researchers have developed methods and models to reconstruct time series of irregularly spaced observations from satellite remote sensing, among which the widely used Harmonic Analysis of Time Series (HANTS) method. Many studies based on time series reconstructed with HANTS docume

  15. Forecasting Daily Time Series using Periodic Unobserved Components Time Series Models

    NARCIS (Netherlands)

    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

  16. Measuring nonlinear behavior in time series data

    Science.gov (United States)

    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.

  17. Complex network approach to fractional time series

    Science.gov (United States)

    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.

  18. Advanced spectral methods for climatic time series

    Science.gov (United States)

    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.

  19. Applied time series analysis and innovative computing

    CERN Document Server

    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.

  20. Nonlinear time series: semiparametric and nonparametric methods

    OpenAIRE

    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...

  1. 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.

  2. Bayes linear variance adjustment for time series

    CERN Document Server

    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.

  3. FATS: Feature Analysis for Time Series

    CERN Document Server

    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.

  4. Introduction to time series analysis and forecasting

    CERN Document Server

    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.

  5. Multiscale entropy analysis of electroseismic time series

    OpenAIRE

    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

  6. 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.

  7. Testing time symmetry in time series using data compression dictionaries

    OpenAIRE

    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...

  8. Feature Matching in Time Series Modelling

    CERN Document Server

    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...

  9. 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......, there is so far no systematic research to study and compare their performance. How to select effective techniques of feature preprocessing in a forecasting model remains a problem. In this paper, the authors conduct a comprehensive study of existing feature preprocessing techniques to evaluate their empirical...... performance in time series forecasting. It is demonstrated in our experiment that, effective feature preprocessing can significantly enhance forecasting accuracy. This research can be a useful guidance for researchers on effectively selecting feature preprocessing techniques and integrating them with time...

  10. Introduction to time series analysis and forecasting

    CERN Document Server

    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

  11. Layered Ensemble Architecture for Time Series Forecasting.

    Science.gov (United States)

    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

  12. 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.

  13. Climate Time Series Analysis and Forecasting

    Science.gov (United States)

    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.

  14. 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.

  15. Fuzzy Information Granules in Time Series Data

    OpenAIRE

    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...

  16. 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 i...... in a neural network. We give a rough description of the problem, insist on the concept of generalisation, and propose a generalisation-based method. We compare it to a non-parametric test, and carry out experiments, both on the well-known Henon map, and on a real data set...

  17. Dynamical networks reconstructed from time series

    CERN Document Server

    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.

  18. On clustering fMRI time series

    DEFF Research Database (Denmark)

    Goutte, C; Toft, P; 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 indi......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...

  19. 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, ...

  20. Introduction to time series and forecasting

    CERN Document Server

    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...

  1. Modeling vector nonlinear time series using POLYMARS

    NARCIS (Netherlands)

    J.G. de Gooijer; B.K. Ray

    2003-01-01

    A modified multivariate adaptive regression splines method for modeling vector nonlinear time series is investigated. The method results in models that can capture certain types of vector self-exciting threshold autoregressive behavior, as well as provide good predictions for more general vector non

  2. Nonlinear time-series analysis revisited

    Science.gov (United States)

    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.

  3. Nonlinear Time Series Analysis via Neural Networks

    Science.gov (United States)

    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.

  4. Nonlinear time-series analysis revisited.

    Science.gov (United States)

    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

  5. Time series tapering for short data samples

    DEFF Research Database (Denmark)

    Kaimal, J.C.; Kristensen, L.

    1991-01-01

    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...

  6. Designer networks for time series processing

    DEFF Research Database (Denmark)

    Svarer, C; Hansen, Lars Kai; Larsen, Jan;

    1993-01-01

    The conventional tapped-delay neural net may be analyzed using statistical methods and the results of such analysis can be applied to model optimization. The authors review and extend efforts to demonstrate the power of this strategy within time series processing. They attempt to design compact...

  7. Useful Pattern Mining on Time Series

    DEFF Research Database (Denmark)

    Goumatianos, Nikitas; Christou, Ioannis T; Lindgren, Peter

    2013-01-01

    calculations as complex but efficient distributed SQL queries on the relational databases that store the time-series. We present initial results from mining all frequent candlestick sequences with the characteristic property that when they occur then, with an average at least 60% probability, they signal a 2...

  8. 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.

  9. 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.

  10. 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.

  11. Fractal Analysis On Internet Traffic Time Series

    CERN Document Server

    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.

  12. The Statistical Analysis of Time Series

    CERN Document Server

    Anderson, T W

    2011-01-01

    The Wiley Classics Library consists of selected books that have become recognized classics in their respective fields. With these new unabridged and inexpensive editions, Wiley hopes to extend the life of these important works by making them available to future generations of mathematicians and scientists. Currently available in the Series: T. W. Anderson Statistical Analysis of Time Series T. S. Arthanari & Yadolah Dodge Mathematical Programming in Statistics Emil Artin Geometric Algebra Norman T. J. Bailey The Elements of Stochastic Processes with Applications to the Natural Sciences George

  13. What marketing scholars should know about time series analysis : time series applications in marketing

    NARCIS (Netherlands)

    Horváth, Csilla; Kornelis, Marcel; Leeflang, Peter S.H.

    2002-01-01

    In this review, we give a comprehensive summary of time series techniques in marketing, and discuss a variety of time series analysis (TSA) techniques and models. We classify them in the sets (i) univariate TSA, (ii) multivariate TSA, and (iii) multiple TSA. We provide relevant marketing application

  14. 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.

  15. Time Series Analysis Using Geometric Template Matching.

    Science.gov (United States)

    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

  16. Visibility graphlet approach to chaotic time series.

    Science.gov (United States)

    Mutua, Stephen; Gu, Changgui; Yang, Huijie

    2016-05-01

    Many novel methods have been proposed for mapping time series into complex networks. Although some dynamical behaviors can be effectively captured by existing approaches, the preservation and tracking of the temporal behaviors of a chaotic system remains an open problem. In this work, we extended the visibility graphlet approach to investigate both discrete and continuous chaotic time series. We applied visibility graphlets to capture the reconstructed local states, so that each is treated as a node and tracked downstream to create a temporal chain link. Our empirical findings show that the approach accurately captures the dynamical properties of chaotic systems. Networks constructed from periodic dynamic phases all converge to regular networks and to unique network structures for each model in the chaotic zones. Furthermore, our results show that the characterization of chaotic and non-chaotic zones in the Lorenz system corresponds to the maximal Lyapunov exponent, thus providing a simple and straightforward way to analyze chaotic systems.

  17. Time-Series Analysis: A Cautionary Tale

    Science.gov (United States)

    Damadeo, Robert

    2015-01-01

    Time-series analysis has often been a useful tool in atmospheric science for deriving long-term trends in various atmospherically important parameters (e.g., temperature or the concentration of trace gas species). In particular, time-series analysis has been repeatedly applied to satellite datasets in order to derive the long-term trends in stratospheric ozone, which is a critical atmospheric constituent. However, many of the potential pitfalls relating to the non-uniform sampling of the datasets were often ignored and the results presented by the scientific community have been unknowingly biased. A newly developed and more robust application of this technique is applied to the Stratospheric Aerosol and Gas Experiment (SAGE) II version 7.0 ozone dataset and the previous biases and newly derived trends are presented.

  18. 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 indi......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 indicate whether sets of voxels are activated in a similar way or in different ways. Typically, delays between two activated signals are not identified. In this article, we use clustering methods to detect similarities in activation between voxels. We employ a novel metric that measures the similarity...

  19. Univariate time series forecasting algorithm validation

    Science.gov (United States)

    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.

  20. Multivariate Voronoi Outlier Detection for Time Series

    OpenAIRE

    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...

  1. Estimation and Forecasting in Time Series Models

    OpenAIRE

    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...

  2. Time-series models in marketing.

    OpenAIRE

    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 ...

  3. Time Series Forecasting with Missing Values

    OpenAIRE

    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...

  4. Nonparametric inference for unbalance time series data

    OpenAIRE

    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...

  5. Nonparametric inference for unbalanced time series data

    OpenAIRE

    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...

  6. Evolving time series forecasting ARMA models

    OpenAIRE

    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...

  7. Analysis of Polyphonic Musical Time Series

    Science.gov (United States)

    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.

  8. Interpretation of a compositional time series

    Science.gov (United States)

    Tolosana-Delgado, R.; van den Boogaart, K. G.

    2012-04-01

    Common methods for multivariate time series analysis use linear operations, from the definition of a time-lagged covariance/correlation to the prediction of new outcomes. However, when the time series response is a composition (a vector of positive components showing the relative importance of a set of parts in a total, like percentages and proportions), then linear operations are afflicted of several problems. For instance, it has been long recognised that (auto/cross-)correlations between raw percentages are spurious, more dependent on which other components are being considered than on any natural link between the components of interest. Also, a long-term forecast of a composition in models with a linear trend will ultimately predict negative components. In general terms, compositional data should not be treated in a raw scale, but after a log-ratio transformation (Aitchison, 1986: The statistical analysis of compositional data. Chapman and Hill). This is so because the information conveyed by a compositional data is relative, as stated in their definition. The principle of working in coordinates allows to apply any sort of multivariate analysis to a log-ratio transformed composition, as long as this transformation is invertible. This principle is of full application to time series analysis. We will discuss how results (both auto/cross-correlation functions and predictions) can be back-transformed, viewed and interpreted in a meaningful way. One view is to use the exhaustive set of all possible pairwise log-ratios, which allows to express the results into D(D - 1)/2 separate, interpretable sets of one-dimensional models showing the behaviour of each possible pairwise log-ratios. Another view is the interpretation of estimated coefficients or correlations back-transformed in terms of compositions. These two views are compatible and complementary. These issues are illustrated with time series of seasonal precipitation patterns at different rain gauges of the USA

  9. Homogenization of precipitation time series with ACMANT

    Science.gov (United States)

    Domonkos, Peter

    2015-10-01

    New method for the time series homogenization of observed precipitation (PP) totals is presented; this method is a unit of the ACMANT software package. ACMANT is a relative homogenization method; minimum four time series with adequate spatial correlations are necessary for its use. The detection of inhomogeneities (IHs) is performed with fitting optimal step function, while the calculation of adjustment terms is based on the minimization of the residual variance in homogenized datasets. Together with the presentation of PP homogenization with ACMANT, some peculiarities of PP homogenization as, for instance, the frequency and seasonal variation of IHs in observed PP data and their relation to the performance of homogenization methods are discussed. In climatic regions of snowy winters, ACMANT distinguishes two seasons, namely, rainy season and snowy season, and the seasonal IHs are searched with bivariate detection. ACMANT is a fully automatic method, is freely downloadable from internet and treats either daily or monthly input. Series of observed data in the input dataset may cover different periods, and the occurrence of data gaps is allowed. False zero values instead of missing data code or physical outliers should be corrected before running ACMANT. Efficiency tests indicate that ACMANT belongs to the best performing methods, although further comparative tests of automatic homogenization methods are needed to confirm or reject this finding.

  10. Normalizing the causality between time series

    CERN Document Server

    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 ...

  11. 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.

  12. Fractal fluctuations in cardiac time series

    Science.gov (United States)

    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.

  13. Time Series Forecasting A Nonlinear Dynamics Approach

    CERN Document Server

    Sello, S

    1999-01-01

    The problem of prediction of a given time series is examined on the basis of recent nonlinear dynamics theories. Particular attention is devoted to forecast the amplitude and phase of one of the most common solar indicator activity, the international monthly smoothed sunspot number. It is well known that the solar cycle is very difficult to predict due to the intrinsic complexity of the related time behaviour and to the lack of a succesful quantitative theoretical model of the Sun magnetic cycle. Starting from a previous recent work, we checked the reliability and accuracy of a forecasting model based on concepts of nonlinear dynamical systems applied to experimental time series, such as embedding phase space,Lyapunov spectrum,chaotic behaviour. The model is based on a locally hypothesis of the behaviour on the embedding space, utilizing an optimal number k of neighbour vectors to predict the future evolution of the current point with the set of characteristic parameters determined by several previous paramet...

  14. Directed networks with underlying time structures from multivariate time series

    CERN Document Server

    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.

  15. Fourier analysis of time series an introduction

    CERN Document Server

    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

  16. Forecasting with nonlinear time series models

    DEFF Research Database (Denmark)

    Kock, Anders Bredahl; Teräsvirta, Timo

    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...... applied to economic fore- casting problems, is briefly highlighted. A number of large published studies comparing macroeconomic forecasts obtained using different time series models are discussed, and the paper also contains a small simulation study comparing recursive and direct forecasts in a partic...

  17. Time Series Photometry of KZ Lacertae

    Science.gov (United States)

    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.

  18. Time series analysis of temporal networks

    Science.gov (United States)

    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

  19. Time series modelling of surface pressure data

    Science.gov (United States)

    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.

  20. Ensemble vs. time averages in financial time series analysis

    Science.gov (United States)

    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.

  1. Partial spectral analysis of hydrological time series

    Science.gov (United States)

    Jukić, D.; Denić-Jukić, V.

    2011-03-01

    SummaryHydrological time series comprise the influences of numerous processes involved in the transfer of water in hydrological cycle. It implies that an ambiguity with respect to the processes encoded in spectral and cross-spectral density functions exists. Previous studies have not paid attention adequately to this issue. Spectral and cross-spectral density functions represent the Fourier transforms of auto-covariance and cross-covariance functions. Using this basic property, the ambiguity is resolved by applying a novel approach based on the spectral representation of partial correlation. Mathematical background for partial spectral density, partial amplitude and partial phase functions is presented. The proposed functions yield the estimates of spectral density, amplitude and phase that are not affected by a controlling process. If an input-output relation is the subject of interest, antecedent and subsequent influences of the controlling process can be distinguished considering the input event as a referent point. The method is used for analyses of the relations between the rainfall, air temperature and relative humidity, as well as the influences of air temperature and relative humidity on the discharge from karst spring. Time series are collected in the catchment of the Jadro Spring located in the Dinaric karst area of Croatia.

  2. An introduction to state space time series analysis.

    NARCIS (Netherlands)

    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 wi

  3. 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.

  4. Trend prediction of chaotic time series

    Institute of Scientific and Technical Information of China (English)

    2007-01-01

    Trend prediction of chaotic ti me series is anin-teresting probleminti me series analysis andti me se-ries data mining(TSDM)fields[1].TSDM-basedmethods can successfully characterize and predictcomplex,irregular,and chaotic ti me series.Somemethods have been proposed to predict the trend ofchaotic ti me series.In our knowledge,these meth-ods can be classified into t wo categories as follows.The first category is based on the embeddedspace[2-3],where rawti me series data is mapped to areconstructed phase spac...

  5. Periodograms for Multiband Astronomical Time Series

    CERN Document Server

    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...

  6. Periodograms for multiband astronomical time series

    Science.gov (United States)

    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.

  7. Correlation filtering in financial time series

    CERN Document Server

    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).

  8. Normalizing the causality between time series

    Science.gov (United States)

    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.

  9. Highly comparative, feature-based time-series classification

    CERN Document Server

    Fulcher, Ben D

    2014-01-01

    A highly comparative, feature-based approach to time series classification is introduced that uses an extensive database of algorithms to extract thousands of interpretable features from time series. These features are derived from across the scientific time-series analysis literature, and include summaries of time series in terms of their correlation structure, distribution, entropy, stationarity, scaling properties, and fits to a range of time-series models. After computing thousands of features for each time series in a training set, those that are most informative of the class structure are selected using greedy forward feature selection with a linear classifier. The resulting feature-based classifiers automatically learn the differences between classes using a reduced number of time-series properties, and circumvent the need to calculate distances between time series. Representing time series in this way results in orders of magnitude of dimensionality reduction, allowing the method to perform well on ve...

  10. PERIODOGRAMS FOR MULTIBAND ASTRONOMICAL TIME SERIES

    Energy Technology Data Exchange (ETDEWEB)

    VanderPlas, Jacob T. [eScience Institute, University of Washington, Seattle, WA (United States); Ivezic, Željko [Department of Astronomy, University of Washington, Seattle, WA (United States)

    2015-10-10

    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. After a pedagogical development of the formalism of least-squares spectral analysis, which motivates the essential features of the multiband model, 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, a vast improvement over the years of data reported to be required by previous studies. A Python implementation of this method, along with code to fully reproduce the results reported here, is available on GitHub.

  11. Extracting Common Time Trends from Concurrent Time Series: Maximum Autocorrelation Factors with Application to Tree Ring Time Series Data

    OpenAIRE

    Haugen, Matz A.; Rajaratnam, Bala; Switzer, Paul

    2015-01-01

    Concurrent time series commonly arise in various applications, including when monitoring the environment such as in air quality measurement networks, weather stations, oceanographic buoys, or in paleo form such as lake sediments, tree rings, ice cores, or coral isotopes, with each monitoring or sampling site providing one of the time series. The goal in such applications is to extract a common time trend or signal in the observed data. Other examples where the goal is to extract a common time...

  12. AMTEC vapor-vapor series connected cells

    Science.gov (United States)

    Underwood, Mark L.; Williams, Roger M.; Ryan, Margaret A.; Nakamura, Barbara J.; Oconnor, Dennis E.

    1995-08-01

    An alkali metal thermoelectric converter (AMTEC) having a plurality of cells structurally connected in series to form a septum dividing a plenum into two chambers, and electrically connected in series, is provided with porous metal anodes and porous metal cathodes in the cells. The cells may be planar or annular, and in either case a metal alkali vapor at a high temperature is provided to the plenum through one chamber on one side of the wall and returned to a vapor boiler after condensation at a chamber on the other side of the wall in the plenum. If the cells are annular, a heating core may be placed along the axis of the stacked cells. This arrangement of series-connected cells allows efficient generation of power at high voltage and low current.

  13. Timing calibration and spectral cleaning of LOFAR time series data

    Science.gov (United States)

    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.

  14. 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

  15. Timing calibration and spectral cleaning of LOFAR time series data

    CERN Document Server

    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...

  16. 75 FR 55699 - Series LLCs and Cell Companies

    Science.gov (United States)

    2010-09-14

    ... Internal Revenue Service 26 CFR Part 301 RIN 1545-BI69 Series LLCs and Cell Companies AGENCY: Internal... limited liability company (LLC), a cell of a domestic cell company, or a foreign series or cell that... domestic series LLC, a cell of a domestic cell company, or a foreign series or cell that conducts...

  17. Series cell light extinction monitor

    Science.gov (United States)

    Novick, Vincent J.

    1990-01-01

    A method and apparatus for using the light extinction measurements from two or more light cells positioned along a gasflow chamber in which the gas volumetric rate is known to determine particle number concentration and mass concentration of an aerosol independent of extinction coefficient and to determine estimates for particle size and mass concentrations. The invention is independent of particle size. This invention has application to measurements made during a severe nuclear reactor fuel damage test.

  18. Time series models of symptoms in schizophrenia.

    Science.gov (United States)

    Tschacher, Wolfgang; Kupper, Zeno

    2002-12-15

    The symptom courses of 84 schizophrenia patients (mean age: 24.4 years; mean previous admissions: 1.3; 64% males) of a community-based acute ward were examined to identify dynamic patterns of symptoms and to investigate the relation between these patterns and treatment outcome. The symptoms were monitored by systematic daily staff ratings using a scale composed of three factors: psychoticity, excitement, and withdrawal. Patients showed moderate to high symptomatic improvement documented by effect size measures. Each of the 84 symptom trajectories was analyzed by time series methods using vector autoregression (VAR) that models the day-to-day interrelations between symptom factors. Multiple and stepwise regression analyses were then performed on the basis of the VAR models. Two VAR parameters were found to be associated significantly with favorable outcome in this exploratory study: 'withdrawal preceding a reduction of psychoticity' as well as 'excitement preceding an increase of withdrawal'. The findings were interpreted as generating hypotheses about how patients cope with psychotic episodes.

  19. Peat conditions mapping using MODIS time series

    Science.gov (United States)

    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.

  20. Climate Prediction Center (CPC) Global Temperature Time Series

    Data.gov (United States)

    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...

  1. Climate Prediction Center (CPC) Global Precipitation Time Series

    Data.gov (United States)

    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...

  2. Some results of analysis of source position time series

    CERN Document Server

    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.

  3. An introduction to state space time series analysis.

    OpenAIRE

    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...

  4. Seasonal Time Series Analysis Based on Genetic Algorithm

    Institute of Scientific and Technical Information of China (English)

    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.

  5. Time Series Observations in the North Indian Ocean

    Digital Repository Service at National Institute of Oceanography (India)

    Shenoy, D.M.; Naik, H.; Kurian, S.; Naqvi, S.W.A.; Khare, N.

    Ocean and the ongoing time series study (Candolim Time Series; CaTS) off Goa. In addition, this article also focuses on the new time series initiative in the Arabian Sea and the Bay of Bengal under Sustained Indian Ocean Biogeochemistry and Ecosystem...

  6. Statistical Inference Methods for Sparse Biological Time Series Data

    Directory of Open Access Journals (Sweden)

    Voit Eberhard O

    2011-04-01

    Full Text Available Abstract Background Comparing metabolic profiles under different biological perturbations has become a powerful approach to investigating the functioning of cells. The profiles can be taken as single snapshots of a system, but more information is gained if they are measured longitudinally over time. The results are short time series consisting of relatively sparse data that cannot be analyzed effectively with standard time series techniques, such as autocorrelation and frequency domain methods. In this work, we study longitudinal time series profiles of glucose consumption in the yeast Saccharomyces cerevisiae under different temperatures and preconditioning regimens, which we obtained with methods of in vivo nuclear magnetic resonance (NMR spectroscopy. For the statistical analysis we first fit several nonlinear mixed effect regression models to the longitudinal profiles and then used an ANOVA likelihood ratio method in order to test for significant differences between the profiles. Results The proposed methods are capable of distinguishing metabolic time trends resulting from different treatments and associate significance levels to these differences. Among several nonlinear mixed-effects regression models tested, a three-parameter logistic function represents the data with highest accuracy. ANOVA and likelihood ratio tests suggest that there are significant differences between the glucose consumption rate profiles for cells that had been--or had not been--preconditioned by heat during growth. Furthermore, pair-wise t-tests reveal significant differences in the longitudinal profiles for glucose consumption rates between optimal conditions and heat stress, optimal and recovery conditions, and heat stress and recovery conditions (p-values Conclusion We have developed a nonlinear mixed effects model that is appropriate for the analysis of sparse metabolic and physiological time profiles. The model permits sound statistical inference procedures

  7. 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.

  8. Time and ensemble averaging in time series analysis

    CERN Document Server

    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...

  9. Hidden Markov Models for Time Series An Introduction Using R

    CERN Document Server

    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.

  10. 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–specific approach to the detection of structural change, currently implemented in Autometrics via indicator saturation, has proven to be both practical and effective in the context of stationary dynamic regression models and unit–root autoregressions. By focusing on impulse– and step–indicator saturation, we...... and a stationary component. Further, we apply both kinds of indicator saturation to detect additive outliers and level shifts in the industrial production series in five European countries....

  11. Approximate Entropies for Stochastic Time Series and EKG Time Series of Patients with Epilepsy and Pseudoseizures

    Science.gov (United States)

    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.

  12. Learning restricted Boolean network model by time-series data.

    Science.gov (United States)

    Ouyang, Hongjia; Fang, Jie; Shen, Liangzhong; Dougherty, Edward R; Liu, Wenbin

    2014-01-01

    Restricted Boolean networks are simplified Boolean networks that are required for either negative or positive regulations between genes. Higa et al. (BMC Proc 5:S5, 2011) proposed a three-rule algorithm to infer a restricted Boolean network from time-series data. However, the algorithm suffers from a major drawback, namely, it is very sensitive to noise. In this paper, we systematically analyze the regulatory relationships between genes based on the state switch of the target gene and propose an algorithm with which restricted Boolean networks may be inferred from time-series data. We compare the proposed algorithm with the three-rule algorithm and the best-fit algorithm based on both synthetic networks and a well-studied budding yeast cell cycle network. The performance of the algorithms is evaluated by three distance metrics: the normalized-edge Hamming distance [Formula: see text], the normalized Hamming distance of state transition [Formula: see text], and the steady-state distribution distance μ (ssd). Results show that the proposed algorithm outperforms the others according to both [Formula: see text] and [Formula: see text], whereas its performance according to μ (ssd) is intermediate between best-fit and the three-rule algorithms. Thus, our new algorithm is more appropriate for inferring interactions between genes from time-series data.

  13. Scale-dependent intrinsic entropies of complex time series.

    Science.gov (United States)

    Yeh, Jia-Rong; Peng, Chung-Kang; Huang, Norden E

    2016-04-13

    Multi-scale entropy (MSE) was developed as a measure of complexity for complex time series, and it has been applied widely in recent years. The MSE algorithm is based on the assumption that biological systems possess the ability to adapt and function in an ever-changing environment, and these systems need to operate across multiple temporal and spatial scales, such that their complexity is also multi-scale and hierarchical. Here, we present a systematic approach to apply the empirical mode decomposition algorithm, which can detrend time series on various time scales, prior to analysing a signal's complexity by measuring the irregularity of its dynamics on multiple time scales. Simulated time series of fractal Gaussian noise and human heartbeat time series were used to study the performance of this new approach. We show that our method can successfully quantify the fractal properties of the simulated time series and can accurately distinguish modulations in human heartbeat time series in health and disease.

  14. Multiscale entropy to distinguish physiologic and synthetic RR time series.

    Science.gov (United States)

    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

  15. Distributed series resistance effects in solar cells

    DEFF Research Database (Denmark)

    Nielsen, Lars Drud

    1982-01-01

    A mathematical treatment is presented of the effects of one-dimensional distributed series resistance in solar cells. A general perturbation theory is developed, including consistently the induced spatial variation of diode current density and leading to a first-order equivalent lumped resistance...... to cause an effective doubling of the "diode quality factor."...

  16. Multifractal Analysis of Aging and Complexity in Heartbeat Time Series

    Science.gov (United States)

    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.

  17. 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.

  18. Estimating Time-varying Trends from Geodetic Time Series

    Science.gov (United States)

    Didova, O.; Gunter, B. C.; Riva, R.; Klees, R.; Roese-Koerner, L.

    2015-12-01

    Modeling signal and noise in geodetic time series is crucial for the proper interpretation of the data. Depending on how the functional and stochastic models are defined, the estimated trend and corresponding uncertainties can vary significantly, emphasizing the need for a robust tool for their estimation. In this study, instead of using the traditional deterministic approach where seasonal signals are estimated with fixed amplitudes and phases and the trend is assumed to be linear, an alternate approach is presented in which these signals are modeled stochastically. The benefit of this approach is that it allows for physically natural variations of the various signal constituents over time. To accomplish this, state space models are defined and solved through the use of a Kalman filter. Since the appropriate choice of the noise parameters is at the heart of the proposed approach, a robust method for their estimation is developed. The performance of the methodology is demonstrated using Gravity Recovery and Climate Experiment (GRACE) and the Global Positioning System (GPS) data at the CAS1 station located in East Antarctica and compared to commonly used least-squares adjustment techniques. The results show that the developed technique allows for a more reliable trend estimation as well as for more physically valuable interpretations while validating independent geodetic observing systems. Moreover, the results suggest that the pursued methodology should become the standard in particular when analyzing climatologic data.

  19. 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.

  20. Visibility graph network analysis of gold price time series

    Science.gov (United States)

    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.

  1. On correlations and fractal characteristics of time series

    CERN Document Server

    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 ...

  2. Non-parametric causal inference for bivariate time series

    CERN Document Server

    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.

  3. Predicting Chaotic Time Series Using Recurrent Neural Network

    Institute of Scientific and Technical Information of China (English)

    ZHANG Jia-Shu; XIAO Xian-Ci

    2000-01-01

    A new proposed method, i.e. the recurrent neural network (RNN), is introduced to predict chaotic time series. The effectiveness of using RNN for making one-step and multi-step predictions is tested based on remarkable few datum points by computer-generated chaotic time series. Numerical results show that the RNN proposed here is a very powerful tool for making prediction of chaotic time series.

  4. Information distance and its application in time series

    Directory of Open Access Journals (Sweden)

    B. Mirza

    2008-03-01

    Full Text Available   In this paper a new method is introduced for studying time series of complex systems. This method is based on using the concept of entropy and Jensen-Shannon divergence. In this paper this method is applied to time series of billiard system and heart signals. By this method, we can diagnose the healthy and unhealthy heart and also chaotic billiards from non chaotic systems . The method can also be applied to other time series.

  5. Power-weighted densities for time series data

    OpenAIRE

    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...

  6. 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.

  7. Interpretable Early Classification of Multivariate Time Series

    Science.gov (United States)

    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,…

  8. Time Series Properties of Expectation Biases

    OpenAIRE

    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, ...

  9. Volatility modeling of rainfall time series

    Science.gov (United States)

    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.

  10. Studies on time series applications in environmental sciences

    CERN Document Server

    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. .

  11. 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.

  12. Recovery of the Time-Evolution Equation of Time-Delay Systems from Time Series

    CERN Document Server

    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...

  13. Robust Forecasting of Non-Stationary Time Series

    NARCIS (Netherlands)

    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

  14. Stata: The language of choice for time series analysis?

    OpenAIRE

    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.

  15. Two Fractal Overlap Time Series: Earthquakes and Market Crashes

    OpenAIRE

    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.

  16. Metagenomics meets time series analysis: unraveling microbial community dynamics

    NARCIS (Netherlands)

    Faust, K.; Lahti, L.M.; Gonze, D.; Vos, de W.M.; Raes, J.

    2015-01-01

    The recent increase in the number of microbial time series studies offers new insights into the stability and dynamics of microbial communities, from the world's oceans to human microbiota. Dedicated time series analysis tools allow taking full advantage of these data. Such tools can reveal periodic

  17. Using Time-Series Regression to Predict Academic Library Circulations.

    Science.gov (United States)

    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…

  18. 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.

  19. Using wavelets for time series forecasting: Does it pay off?

    OpenAIRE

    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...

  20. Proteomic profiling of glucocorticoid-exposed myogenic cells: Time series assessment of protein translocation and transcription of inactive mRNAs

    Directory of Open Access Journals (Sweden)

    Hoffman Eric P

    2009-07-01

    Full Text Available Abstract Background Prednisone, one of the most highly prescribed drugs, has well characterized effects on gene transcription mediated by the glucocorticoid receptor. These effects are typically occurring on the scale of hours. Prednisone also has a number of non-transcriptional effects (occurring on minutes scale on protein signaling, yet these are less well studied. We sought to expand the understanding of acute effects of prednisone action on cell signaling using a combination of SILAC strategy and subcellular fractionations from C2C12 myotubes. Results De novo translation of proteins was inhibited in both SILAC labeled and unlabeled C2C12 myotubes. Unlabeled cells were exposed to prednisone while SILAC labeled cells remained untreated. After 0, 5, 15, and 30 minutes of prednisone exposure, labeled and unlabeled cells were mixed at 1:1 ratios and fractionated into cytosolic and nuclear fractions. A total of 534 proteins in the cytosol and 626 proteins in the nucleus were identified and quantitated, using 3 or more peptides per protein with peptide based probability ≤ 0.001. We identified significant increases (1.7- to 3.1- fold in cytoplasmic abundance of 11 ribosomal proteins within 5 minutes of exposure, all of which returned to baseline by 30 min. We hypothesized that these drug-induced acute changes in the subcellular localization of the cell's protein translational machinery could lead to altered translation of quiescent RNAs. To test this, de novo protein synthesis was assayed after 15 minutes of drug exposure. Quantitative fluorography identified 16 2D gel spots showing rapid changes in translation; five of these were identified by MS/MS (pyruvate kinase, annexin A6 isoform A and isoform B, nasopharyngeal epithelium specific protein 1, and isoform 2 of Replication factor C subunit 1, and all showed the 5' terminal oligopyrimidine motifs associated with mRNA sequestration to and from inactive mRNA pools. Conclusion We describe novel

  1. Interactive analysis of gappy bivariate time series using AGSS

    OpenAIRE

    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...

  2. Comparison of New and Old Sunspot Number Time Series

    Science.gov (United States)

    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.

  3. Testing time series reversibility using complex network methods

    CERN Document Server

    Donges, Jonathan F; Kurths, Jürgen

    2012-01-01

    The absence of time-reversal symmetry is a fundamental property of many nonlinear time series. Here, we propose a set of novel statistical tests for time series reversibility based on standard and horizontal visibility graphs. Specifically, we statistically compare the distributions of time-directed variants of the common graph-theoretical measures degree and local clustering coefficient. Unlike other tests for reversibility, our approach does not require constructing surrogate data and can be applied to relatively short time series. We demonstrate its performance for realisations of paradigmatic model systems with known time-reversal properties as well as pickling up signatures of nonlinearity in some well-studied real-world neuro-physiological time series.

  4. Application of p-adic analysis to time series

    OpenAIRE

    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.

  5. 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.

  6. Performance of multifractal detrended fluctuation analysis on short time series

    CERN Document Server

    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.

  7. Database for Hydrological Time Series of Inland Waters (DAHITI)

    Science.gov (United States)

    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.

  8. 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.

  9. Image-Based Learning Approach Applied to Time Series Forecasting

    OpenAIRE

    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...

  10. Forecasting Compositional Time Series with Exponential Smoothing Methods

    OpenAIRE

    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...

  11. Detecting temporal and spatial correlations in pseudoperiodic time series

    Science.gov (United States)

    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.

  12. 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.

  13. Investigating effects in GNSS station coordinate time series

    OpenAIRE

    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...

  14. On the detection of superdiffusive behaviour in time series

    CERN Document Server

    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.

  15. Multivariate time series analysis with R and financial applications

    CERN Document Server

    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

  16. A vector of quarters representation for bivariate time series

    NARCIS (Netherlands)

    Ph.H.B.F. Franses (Philip Hans)

    1995-01-01

    textabstractIn this paper it is shown that several models for a bivariate nonstationary quarterly time series are nested in a vector autoregression with cointegration restrictions for the eight annual series of quarterly observations. Or, the Granger Representation Theorem is extended to incorporate

  17. A multivariate approach to modeling univariate seasonal time series

    NARCIS (Netherlands)

    Ph.H.B.F. Franses (Philip Hans)

    1994-01-01

    textabstractA seasonal time series can be represented by a vector autoregressive model for the annual series containing the seasonal observations. This model allows for periodically varying coefficients. When the vector elements are integrated, the maximum likelihood cointegration method can be used

  18. 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 the time series under consideration is available. Therefore, a black-box optimization approach is our method of choice for detecting structural breaks. We describe a genetic algorithm framework which easily adapts to a large number of statistical settings. To evaluate the usefulness of different 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 precision...

  19. Multi-dimensional sparse time series: feature extraction

    CERN Document Server

    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.

  20. A Matlab Code for Univariate Time Series Forecasting

    OpenAIRE

    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.

  1. Lagrangian Time Series Models for Ocean Surface Drifter Trajectories

    CERN Document Server

    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.

  2. AFSC/ABL: Naknek sockeye salmon scale time series

    Data.gov (United States)

    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....

  3. AFSC/ABL: Ugashik sockeye salmon scale time series

    Data.gov (United States)

    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...

  4. A mixed time series model of binomial counts

    Science.gov (United States)

    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.

  5. Fast and Flexible Multivariate Time Series Subsequence Search

    Data.gov (United States)

    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...

  6. Review of English textbooks in time series analysis (in Russian)

    OpenAIRE

    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.

  7. The Ohio economy: using time series characteristics in forecasting

    OpenAIRE

    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.

  8. Residual diagnostics for cross-section time series regression models

    OpenAIRE

    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.

  9. Application of a Local Polynomial Approximation Chaotic Time Series Prediction

    OpenAIRE

    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...

  10. Time Series Estimates of the Italian Consumer Confidence Indicator

    OpenAIRE

    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.

  11. On the prediction of stationary functional time series

    OpenAIRE

    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...

  12. Trimmed Granger causality between two groups of time series

    OpenAIRE

    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...

  13. Model-Coupled Autoencoder for Time Series Visualisation

    OpenAIRE

    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...

  14. 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.

  15. 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

  16. Automated Feature Design for Time Series Classification by Genetic Programming

    OpenAIRE

    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...

  17. 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.

  18. Time series modelling and forecasting of Sarawak black pepper price

    OpenAIRE

    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...

  19. Time Series Analysis of Insar Data: Methods and Trends

    Science.gov (United States)

    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.

  20. Comparison of New and Old Sunspot Number Time Series

    Science.gov (United States)

    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.

  1. 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.

  2. Time-varying parameter auto-regressive models for autocovariance nonstationary time series

    Institute of Scientific and Technical Information of China (English)

    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.

  3. A method for detecting changes in long time series

    Energy Technology Data Exchange (ETDEWEB)

    Downing, D.J.; Lawkins, W.F.; Morris, M.D.; Ostrouchov, G.

    1995-09-01

    Modern scientific activities, both physical and computational, can result in time series of many thousands or even millions of data values. Here the authors describe a statistically motivated algorithm for quick screening of very long time series data for the presence of potentially interesting but arbitrary changes. The basic data model is a stationary Gaussian stochastic process, and the approach to detecting a change is the comparison of two predictions of the series at a time point or contiguous collection of time points. One prediction is a ``forecast``, i.e. based on data from earlier times, while the other a ``backcast``, i.e. based on data from later times. The statistic is the absolute value of the log-likelihood ratio for these two predictions, evaluated at the observed data. A conservative procedure is suggested for specifying critical values for the statistic under the null hypothesis of ``no change``.

  4. Symplectic geometry spectrum regression for prediction of noisy time series

    Science.gov (United States)

    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).

  5. Comparison of time series using entropy and mutual correlation

    Science.gov (United States)

    Madonna, Fabio; Rosoldi, Marco

    2015-04-01

    The potential for redundant time series to reduce uncertainty in atmospheric variables has not been investigated comprehensively for climate observations. Moreover, comparison among time series of in situ and ground based remote sensing measurements have been performed using several methods, but quite often relying on linear models. In this work, the concepts of entropy (H) and mutual correlation (MC), defined in the frame of the information theory, are applied to the study of essential climate variables with the aim of characterizing the uncertainty of a time series and the redundancy of collocated measurements provided by different surface-based techniques. In particular, integrated water vapor (IWV) and water vapour mixing ratio times series obtained at five highly instrumented GRUAN (GCOS, Global Climate Observing System, Reference Upper-Air Network) stations with several sensors (e.g radiosondes, GPS, microwave and infrared radiometers, Raman lidar), in the period from 2010-2012, are analyzed in terms of H and MC. The comparison between the probability density functions of the time series shows that caution in using linear assumptions is needed and the use of statistics, like entropy, that are robust to outliers, is recommended to investigate measurements time series. Results reveals that the random uncertainties on the IWV measured with radiosondes, global positioning system, microwave and infrared radiometers, and Raman lidar measurements differed by less than 8 % over the considered time period. Comparisons of the time series of IWV content from ground-based remote sensing instruments with in situ soundings showed that microwave radiometers have the highest redundancy with the IWV time series measured by radiosondes and therefore the highest potential to reduce the random uncertainty of the radiosondes time series. Moreover, the random uncertainty of a time series from one instrument can be reduced by 60% by constraining the measurements with those from

  6. 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

  7. Correlation measure to detect time series distances, whence economy globalization

    Science.gov (United States)

    Miśkiewicz, Janusz; Ausloos, Marcel

    2008-11-01

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

  8. Detection of flood events in hydrological discharge time series

    Science.gov (United States)

    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

  9. 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.

  10. Discovering shared and individual latent structure in multiple time series

    CERN Document Server

    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.

  11. Forecasting Compositional Time Series: A State Space Approach

    OpenAIRE

    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...

  12. Arbitrage, market definition and monitoring a time series approach

    OpenAIRE

    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...

  13. A refined fuzzy time series model for stock market forecasting

    Science.gov (United States)

    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.

  14. Weighted statistical parameters for irregularly sampled time series

    CERN Document Server

    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...

  15. Time series analysis of the response of measurement instruments

    CERN Document Server

    Georgakaki, Dimitra; Polatoglou, Hariton

    2012-01-01

    In this work the significance of treating a set of measurements as a time series is being explored. Time Series Analysis (TSA) techniques, part of the Exploratory Data Analysis (EDA) approach, can provide much insight regarding the stochastic correlations that are induced on the outcome of an experiment by the measurement system and can provide criteria for the limited use of the classical variance in metrology. Specifically, techniques such as the Lag Plots, Autocorrelation Function, Power Spectral Density and Allan Variance are used to analyze series of sequential measurements, collected at equal time intervals from an electromechanical transducer. These techniques are used in conjunction with power law models of stochastic noise in order to characterize time or frequency regimes for which the usually assumed white noise model is adequate for the description of the measurement system response. However, through the detection of colored noise, usually referred to as flicker noise, which is expected to appear ...

  16. Image-Based Learning Approach Applied to Time Series Forecasting

    Directory of Open Access Journals (Sweden)

    J. C. Chimal-Eguía

    2012-06-01

    Full Text Available 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 datarepresentation is based on information obtained by image axis division into boxes. The difference between this newinput data representation and the classical is that this technique is not time-dependent. This new information isimplemented in the new Image-Based Learning Approach (IBLA and by means of a probabilistic mechanism thislearning technique is applied to the interesting problem of time series forecasting. The experimental results indicatethat by using the methodology proposed in this article, it is possible to obtain better results than with the classicaltechniques such as artificial neuronal networks and support vector machines.

  17. Minimum entropy density method for the time series analysis

    Science.gov (United States)

    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.

  18. Multiscale entropy analysis of complex physiologic time series.

    Science.gov (United States)

    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

  19. Time Series Analysis of Wheat Futures Reward in China

    Institute of Scientific and Technical Information of China (English)

    2005-01-01

    Different from the fact that the main researches are focused on single futures contract and lack of the comparison of different periods, this paper described the statistical characteristics of wheat futures reward time series of Zhengzhou Commodity Exchange in recent three years. Besides the basic statistic analysis, the paper used the GARCH and EGARCH model to describe the time series which had the ARCH effect and analyzed the persistence of volatility shocks and the leverage effect. The results showed that compared with that of normal one,wheat futures reward series were abnormality, leptokurtic and thick tail distribution. The study also found that two-part of the reward series had no autocorrelation. Among the six correlative series, three ones presented the ARCH effect. By using of the Auto-regressive Distributed Lag Model, GARCH model and EGARCH model, the paper demonstrates the persistence of volatility shocks and the leverage effect on the wheat futures reward time series. The results reveal that on the one hand, the statistical characteristics of the wheat futures reward are similar to the aboard mature futures market as a whole. But on the other hand, the results reflect some shortages such as the immatureness and the over-control by the government in the Chinese future market.

  20. Wavelet analysis for non-stationary, nonlinear time series

    Science.gov (United States)

    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.

  1. Sparse time series chain graphical models for reconstructing genetic networks

    NARCIS (Netherlands)

    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

  2. Optimization of recurrent neural networks for time series modeling

    DEFF Research Database (Denmark)

    Pedersen, Morten With

    1997-01-01

    The present thesis is about optimization of recurrent neural networks applied to time series modeling. In particular is considered fully recurrent networks working from only a single external input, one layer of nonlinear hidden units and a li near output unit applied to prediction of discrete time...

  3. 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.

  4. AMP: a new time-frequency feature extraction method for intermittent time-series data

    OpenAIRE

    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...

  5. 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.

  6. Time series analysis by the Maximum Entropy method

    Energy Technology Data Exchange (ETDEWEB)

    Kirk, B.L.; Rust, B.W.; Van Winkle, W.

    1979-01-01

    The principal subject of this report is the use of the Maximum Entropy method for spectral analysis of time series. The classical Fourier method is also discussed, mainly as a standard for comparison with the Maximum Entropy method. Examples are given which clearly demonstrate the superiority of the latter method over the former when the time series is short. The report also includes a chapter outlining the theory of the method, a discussion of the effects of noise in the data, a chapter on significance tests, a discussion of the problem of choosing the prediction filter length, and, most importantly, a description of a package of FORTRAN subroutines for making the various calculations. Cross-referenced program listings are given in the appendices. The report also includes a chapter demonstrating the use of the programs by means of an example. Real time series like the lynx data and sunspot numbers are also analyzed. 22 figures, 21 tables, 53 references.

  7. Increment entropy as a measure of complexity for time series

    CERN Document Server

    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.

  8. Parameter-Free Search of Time-Series Discord

    Institute of Scientific and Technical Information of China (English)

    Wei Luo; Marcus Gallagher; Janet Wiles

    2013-01-01

    Time-series discord is widely used in data mining applications to characterize anomalous subsequences in time series.Compared to some other discord search algorithms,the direct search algorithm based on the recurrence plot shows the advantage of being fast and parameter free.The direct search algorithm,however,relies on quasi-periodicity in input time series,an assumption that limits the algorithm's applicability.In this paper,we eliminate the periodicity assumption from the direct search algorithm by proposing a reference function for subsequences and a new sampling strategy based on the reference function.These measures result in a new algorithm with improved efficiency and robustness,as evidenced by our empirical evaluation.

  9. 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

  10. General expression for linear and nonlinear time series models

    Institute of Scientific and Technical Information of China (English)

    Ren HUANG; Feiyun XU; Ruwen CHEN

    2009-01-01

    The typical time series models such as ARMA, AR, and MA are founded on the normality and stationarity of a system and expressed by a linear difference equation; therefore, they are strictly limited to the linear system. However, some nonlinear factors are within the practical system; thus, it is difficult to fit the model for real systems with the above models. This paper proposes a general expression for linear and nonlinear auto-regressive time series models (GNAR). With the gradient optimization method and modified AIC information criteria integrated with the prediction error, the parameter estimation and order determination are achieved. The model simulation and experiments show that the GNAR model can accurately approximate to the dynamic characteristics of the most nonlinear models applied in academics and engineering. The modeling and prediction accuracy of the GNAR model is superior to the classical time series models. The proposed GNAR model is flexible and effective.

  11. Feature-preserving interpolation and filtering of environmental time series

    CERN Document Server

    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.

  12. Asymptotics for Nonlinear Transformations of Fractionally Integrated Time Series

    Institute of Scientific and Technical Information of China (English)

    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.

  13. Grammar-based feature generation for time-series prediction

    CERN Document Server

    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 ...

  14. Time series, correlation matrices and random matrix models

    Energy Technology Data Exchange (ETDEWEB)

    Vinayak [Instituto de Ciencias Físicas, Universidad Nacional Autónoma de México, C.P. 62210 Cuernavaca (Mexico); Seligman, Thomas H. [Instituto de Ciencias Físicas, Universidad Nacional Autónoma de México, C.P. 62210 Cuernavaca, México and Centro Internacional de Ciencias, C.P. 62210 Cuernavaca (Mexico)

    2014-01-08

    In this set of five lectures the authors have presented techniques to analyze open classical and quantum systems using correlation matrices. For diverse reasons we shall see that random matrices play an important role to describe a null hypothesis or a minimum information hypothesis for the description of a quantum system or subsystem. In the former case various forms of correlation matrices of time series associated with the classical observables of some system. The fact that such series are necessarily finite, inevitably introduces noise and this finite time influence lead to a random or stochastic component in these time series. By consequence random correlation matrices have a random component, and corresponding ensembles are used. In the latter we use random matrices to describe high temperature environment or uncontrolled perturbations, ensembles of differing chaotic systems etc. The common theme of the lectures is thus the importance of random matrix theory in a wide range of fields in and around physics.

  15. Detection of "noisy" chaos in a time series

    DEFF Research Database (Denmark)

    Chon, K H; Kanters, J K; Cohen, R J;

    1997-01-01

    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 simulations...

  16. Complex Network Approach to the Fractional Time Series

    CERN Document Server

    Manshour, Pouya

    2015-01-01

    In order to extract the correlation information inherited in a 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 the fractional processes onto complex networks. The parabolic exponential functions are found to ?fit with the corresponding degree distributions, with Hurst dependent ?fitting parameter. Further, we take into account other topological properties such as the 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 the antipersistent fractional Gaussian noises. To solve this problem, we take into account the Spearman correlation coefficient between the node's degree and its corresp...

  17. Detection of "noisy" chaos in a time series

    Science.gov (United States)

    Chon, K. H.; Kanters, J. K.; Cohen, R. J.; Holstein-Rathlou, N. H.

    1997-01-01

    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 simulations, and applied to heart rate variability data.

  18. 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.

  19. The time series forecasting: from the aspect of network

    CERN Document Server

    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.

  20. Detecting multiple breaks in geodetic time series using indicator saturation.

    Science.gov (United States)

    Jackson, Luke; Pretis, Felix

    2016-04-01

    Identifying the timing and magnitude of breaks in geodetic time series has been the source of much discussion. Instruments recording different geophysical phenomena may record long term trends, quasi-periodic signals at a variety of time scales from days to decades, and sudden breaks due to natural or anthropogenic causes, ranging from instrument replacement to earthquakes. Records can not always be relied upon to be continuous in time, yet one may desire to accurately bridge gaps without performing interpolation. We apply the novel Indicator Saturation (IS) method to identify breaks in a synthetic GPS time series used for the Detection of Offsets in GPS Experiments (DOGEX). The IS approach differs from alternative break detection methods by considering every point in the time series as a break, until it is demonstrated statistically that it is not. Saturating a model with a full set of break functions and removing all but significant ones, formulates the detection of breaks as a problem of model selection. This allows multiple breaks of different forms (from impulses, to shifts in the mean, and changing trends) without requiring a minimum break-length to be detected, while simultaneously modelling any underlying variation driven by additional covariates. To address selection bias in the coefficients, we demonstrate the bias-corrected estimates of break coefficients when using step-shifts in the mean of the modelled time-series. The regimes of the time-varying mean of the time-series (the `coefficient path' of the intercept determined by the detected breaks) can be used to conduct hypothesis tests on whether subsequent shifts offset each other - for example whether a measurement change induces a temporary bias rather than a permanent one. We explore this non-classical analysis method to see if it can bring about the sub millimetre errors in long term rates of land motion currently required by the GPS community.

  1. A multidisciplinary database for geophysical time series management

    Science.gov (United States)

    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.

  2. Visual analytics techniques for large multi-attribute time series data

    Science.gov (United States)

    Hao, Ming C.; Dayal, Umeshwar; Keim, Daniel A.

    2008-01-01

    Time series data commonly occur when variables are monitored over time. Many real-world applications involve the comparison of long time series across multiple variables (multi-attributes). Often business people want to compare this year's monthly sales with last year's sales to make decisions. Data warehouse administrators (DBAs) want to know their daily data loading job performance. DBAs need to detect the outliers early enough to act upon them. In this paper, two new visual analytic techniques are introduced: The color cell-based Visual Time Series Line Charts and Maps highlight significant changes over time in a long time series data and the new Visual Content Query facilitates finding the contents and histories of interesting patterns and anomalies, which leads to root cause identification. We have applied both methods to two real-world applications to mine enterprise data warehouse and customer credit card fraud data to illustrate the wide applicability and usefulness of these techniques.

  3. 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.

  4. Scaling analysis of multi-variate intermittent time series

    Science.gov (United States)

    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.

  5. 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...... unconditional skewness. We consider modelling the unconditional mean and variance using models that respond nonlinearly or asymmetrically to shocks. We investigate the implications of these models on the third-moment structure of the marginal distribution as well as conditions under which the unconditional...

  6. 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.

  7. 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...

  8. Mining Rules from Electrical Load Time Series Data Set

    Institute of Scientific and Technical Information of China (English)

    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.

  9. Multiscaling comparative analysis of time series and geophysical phenomena

    CERN Document Server

    Scafetta, N; Scafetta, Nicola; West, Bruce J.

    2005-01-01

    Different methods are used to determine the scaling exponents associated with a time series describing a complex dynamical process, such as those observed in geophysical systems. Many of these methods are based on the numerical evaluation of the variance of a diffusion process whose step increments are generated by the data. An alternative method focuses on the direct evaluation of the scaling coefficient of the Shannon entropy of the same diffusion distribution. The combined use of these methods can efficiently distinguish between fractal Gaussian and L\\'{e}vy-walk time series and help to discern between alternative underling complex dynamics.

  10. 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...

  11. Estimation of time series noise covariance using correlation technology

    Institute of Scientific and Technical Information of China (English)

    2011-01-01

    Covariance of clean signal and observed noise is necessary for extracting clean signal from a time series.This is transferred to calculate the covariance of observed noise and clean signal's MA process,when the clean signal is described by an autoregressive moving average (ARMA) model.Using the correlations of the innovations data from observed time series to form a least-squares problem,a concisely autocovariance least-square (CALS) method has been proposed to estimate the covariance.We also extended our w...

  12. Characterizing Weak Chaos using Time Series of Lyapunov Exponents

    OpenAIRE

    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 ...

  13. Kālī: Time series data modeler

    Science.gov (United States)

    Kasliwal, Vishal P.

    2016-07-01

    The fully parallelized and vectorized software package Kālī models time series data using various stochastic processes such as continuous-time ARMA (C-ARMA) processes and uses Bayesian Markov Chain Monte-Carlo (MCMC) for inferencing a stochastic light curve. Kālimacr; is written in c++ with Python language bindings for ease of use. K¯lī is named jointly after the Hindu goddess of time, change, and power and also as an acronym for KArma LIbrary.

  14. Chaotic time series analysis of vision evoked EEG

    Science.gov (United States)

    Zhang, Ningning; Wang, Hong

    2010-01-01

    To investigate the human brain activities for aesthetic processing, beautiful woman face picture and ugly buffoon face picture were applied. Twelve subjects were assigned the aesthetic processing task while the electroencephalogram (EEG) was recorded. Event-related brain potential (ERP) was required from the 32 scalp electrodes and the ugly buffoon picture produced larger amplitudes for the N1, P2, N2, and late slow wave components. Average ERP from the ugly buffoon picture were larger than that from the beautiful woman picture. The ERP signals shows that the ugly buffoon elite higher emotion waves than the beautiful woman face, because some expression is on the face of the buffoon. Then, chaos time series analysis was carried out to calculate the largest Lyapunov exponent using small data set method and the correlation dimension using G-P algorithm. The results show that the largest Lyapunov exponents of the ERP signals are greater than zero, which indicate that the ERP signals may be chaotic. The correlations dimensions coming from the beautiful woman picture are larger than that from the ugly buffoon picture. The comparison of the correlations dimensions shows that the beautiful face can excite the brain nerve cells. The research in the paper is a persuasive proof to the opinion that cerebrum's work is chaotic under some picture stimuli.

  15. FTSPlot: fast time series visualization for large datasets.

    Science.gov (United States)

    Riss, Michael

    2014-01-01

    The analysis of electrophysiological recordings often involves visual inspection of time series data to locate specific experiment epochs, mask artifacts, and verify the results of signal processing steps, such as filtering or spike detection. Long-term experiments with continuous data acquisition generate large amounts of data. Rapid browsing through these massive datasets poses a challenge to conventional data plotting software because the plotting time increases proportionately to the increase in the volume of data. This paper presents FTSPlot, which is a visualization concept for large-scale time series datasets using techniques from the field of high performance computer graphics, such as hierarchic level of detail and out-of-core data handling. In a preprocessing step, time series data, event, and interval annotations are converted into an optimized data format, which then permits fast, interactive visualization. The preprocessing step has a computational complexity of O(n x log(N)); the visualization itself can be done with a complexity of O(1) and is therefore independent of the amount of data. A demonstration prototype has been implemented and benchmarks show that the technology is capable of displaying large amounts of time series data, event, and interval annotations lag-free with visualization method for long-term electrophysiological experiments.

  16. Studies in Astronomical Time Series Analysis. VI. Bayesian Block Representations

    CERN Document Server

    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...

  17. A multiscale statistical model for time series forecasting

    Science.gov (United States)

    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.

  18. Segmentation of time series with long-range fractal correlations

    Science.gov (United States)

    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

  19. Recovery of delay time from time series based on the nearest neighbor method

    Science.gov (United States)

    Prokhorov, M. D.; Ponomarenko, V. I.; Khorev, V. S.

    2013-12-01

    We propose a method for the recovery of delay time from time series of time-delay systems. The method is based on the nearest neighbor analysis. The method allows one to reconstruct delays in various classes of time-delay systems including systems of high order, systems with several coexisting delays, and nonscalar time-delay systems. It can be applied to time series heavily corrupted by additive and dynamical noise.

  20. Recovery of delay time from time series based on the nearest neighbor method

    Energy Technology Data Exchange (ETDEWEB)

    Prokhorov, M.D., E-mail: mdprokhorov@yandex.ru [Saratov Branch of Kotel' nikov Institute of Radio Engineering and Electronics of Russian Academy of Sciences, Zelyonaya Street, 38, Saratov 410019 (Russian Federation); Ponomarenko, V.I. [Saratov Branch of Kotel' nikov Institute of Radio Engineering and Electronics of Russian Academy of Sciences, Zelyonaya Street, 38, Saratov 410019 (Russian Federation); Department of Nano- and Biomedical Technologies, Saratov State University, Astrakhanskaya Street, 83, Saratov 410012 (Russian Federation); Khorev, V.S. [Department of Nano- and Biomedical Technologies, Saratov State University, Astrakhanskaya Street, 83, Saratov 410012 (Russian Federation)

    2013-12-09

    We propose a method for the recovery of delay time from time series of time-delay systems. The method is based on the nearest neighbor analysis. The method allows one to reconstruct delays in various classes of time-delay systems including systems of high order, systems with several coexisting delays, and nonscalar time-delay systems. It can be applied to time series heavily corrupted by additive and dynamical noise.

  1. 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.

  2. Bayes model averaging of cyclical decompositions in economic time series

    NARCIS (Netherlands)

    R.H. Kleijn (Richard); H.K. van Dijk (Herman)

    2003-01-01

    textabstractA flexible decomposition of a time series into stochastic cycles under possible non-stationarity is specified, providing both a useful data analysis tool and a very wide model class. A Bayes procedure using Markov Chain Monte Carlo (MCMC) is introduced with a model averaging approach whi

  3. On the Identifiability Conditions in Some Nonlinear Time Series Models

    OpenAIRE

    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.

  4. Notes on economic time series analysis system theoretic perspectives

    CERN Document Server

    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...

  5. Long-memory time series theory and methods

    CERN Document Server

    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.

  6. Extracting the relevant delays in time series modelling

    DEFF Research Database (Denmark)

    Goutte, Cyril

    1997-01-01

    selection, and more precisely stepwise forward selection. The method is compared to other forward selection schemes, as well as to a nonparametric tests aimed at estimating the embedding dimension of time series. The final application extends these results to the efficient estimation of FIR filters on some...... real data...

  7. 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...

  8. Testing for asymmetry in economic time series using bootstrap methods

    OpenAIRE

    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.

  9. Wavelet methods in (financial) time-series processing

    NARCIS (Netherlands)

    Struzik, Z.R.

    2000-01-01

    We briefly describe the major advantages of using the wavelet transform for the processing of financial time series on the example of the S&P index. In particular, we show how to uncover local the scaling (correlation) characteristics of the S&P index with the wavelet based effective H'older expone

  10. 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.

  11. Time Series Data Visualization in World Wide Telescope

    Science.gov (United States)

    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.

  12. Deriving dynamic marketing effectiveness from econometric time series models

    NARCIS (Netherlands)

    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

  13. Practical implementation of nonlinear time series methods The TISEAN package

    CERN Document Server

    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 ...

  14. FIXED-DESIGN SEMIPARAMETRIC REGRESSION FOR LINEAR TIME SERIES

    Institute of Scientific and Technical Information of China (English)

    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.

  15. 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......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 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 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...

  16. Multi-Scale Dissemination of Time Series Data

    DEFF Research Database (Denmark)

    Guo, Qingsong; Zhou, Yongluan; Su, Li

    2013-01-01

    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...

  17. Structured Time Series Analysis for Human Action Segmentation and Recognition.

    Science.gov (United States)

    Dian Gong; Medioni, Gerard; Xuemei Zhao

    2014-07-01

    We address the problem of structure learning of human motion in order to recognize actions from a continuous monocular motion sequence of an arbitrary person from an arbitrary viewpoint. Human motion sequences are represented by multivariate time series in the joint-trajectories space. Under this structured time series framework, we first propose Kernelized Temporal Cut (KTC), an extension of previous works on change-point detection by incorporating Hilbert space embedding of distributions, to handle the nonparametric and high dimensionality issues of human motions. Experimental results demonstrate the effectiveness of our approach, which yields realtime segmentation, and produces high action segmentation accuracy. Second, a spatio-temporal manifold framework is proposed to model the latent structure of time series data. Then an efficient spatio-temporal alignment algorithm Dynamic Manifold Warping (DMW) is proposed for multivariate time series to calculate motion similarity between action sequences (segments). Furthermore, by combining the temporal segmentation algorithm and the alignment algorithm, online human action recognition can be performed by associating a few labeled examples from motion capture data. The results on human motion capture data and 3D depth sensor data demonstrate the effectiveness of the proposed approach in automatically segmenting and recognizing motion sequences, and its ability to handle noisy and partially occluded data, in the transfer learning module. PMID:26353312

  18. Time Series Analysis for the Drac River Basin (france)

    Science.gov (United States)

    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

  19. Irreversibility of financial time series: A graph-theoretical approach

    Science.gov (United States)

    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.

  20. Metagenomics meets time series analysis: unraveling microbial community dynamics.

    Science.gov (United States)

    Faust, Karoline; Lahti, Leo; Gonze, Didier; de Vos, Willem M; Raes, Jeroen

    2015-06-01

    The recent increase in the number of microbial time series studies offers new insights into the stability and dynamics of microbial communities, from the world's oceans to human microbiota. Dedicated time series analysis tools allow taking full advantage of these data. Such tools can reveal periodic patterns, help to build predictive models or, on the contrary, quantify irregularities that make community behavior unpredictable. Microbial communities can change abruptly in response to small perturbations, linked to changing conditions or the presence of multiple stable states. With sufficient samples or time points, such alternative states can be detected. In addition, temporal variation of microbial interactions can be captured with time-varying networks. Here, we apply these techniques on multiple longitudinal datasets to illustrate their potential for microbiome research.

  1. Multiple imputation for time series data with Amelia package.

    Science.gov (United States)

    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

  2. Mixed Spectrum Analysis on fMRI Time-Series.

    Science.gov (United States)

    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

  3. 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.

  4. Financial Time Series Forecasting Using Directed-Weighted Chunking SVMs

    OpenAIRE

    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, ...

  5. Forecasting Framework for Open Access Time Series in Energy

    OpenAIRE

    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...

  6. Autoregression of Quasi-Stationary Time Series (Invited)

    Science.gov (United States)

    Meier, T. M.; Küperkoch, L.

    2009-12-01

    Autoregression is a model based tool for spectral analysis and prediction of time series. It has the potential to increase the resolution of spectral estimates. However, the validity of the assumed model has to be tested. Here we review shortly methods for the determination of the parameters of autoregression and summarize properties of autoregressive prediction and autoregressive spectral analysis. Time series with a limited number of dominant frequencies varying slowly in time (quasi-stationary time series) may well be described by a time-dependent autoregressive model of low order. An algorithm for the estimation of the autoregression parameters in a moving window is presented. Time-varying dominant frequencies are estimated. The comparison to results obtained by Fourier transform based methods and the visualization of the time dependent normalized prediction error are essential for quality assessment of the results. The algorithm is applied to synthetic examples as well as to mircoseism and tremor. The sensitivity of the results to the choice of model and filter parameters is discussed. Autoregressive forward prediction offers the opportunity to detect body wave phases in seismograms and to determine arrival times automatically. Examples are shown for P- and S-phases at local and regional distances. In order to determine S-wave arrival times the autoregressive model is extended to multi-component recordings. For the detection of significant temporal changes in waveforms, the choice of the model appears to be less crucial compared to spectral analysis. Temporal changes in frequency, amplitude, phase, and polarisation are detectable by autoregressive prediction. Quality estimates of automatically determined onset times may be obtained from the slope of the absolute prediction error as a function of time and the signal-to-noise ratio. Results are compared to manual readings.

  7. Minimum Entropy Density Method for the Time Series Analysis

    CERN Document Server

    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.

  8. Adaptively Sharing Time-Series with Differential Privacy

    CERN Document Server

    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...

  9. A comprehensive characterization of recurrences in time series

    CERN Document Server

    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.

  10. Cross Recurrence Plot Based Synchronization of Time Series

    CERN Document Server

    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.

  11. 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.

  12. Time series segmentation with shifting means hidden markov models

    Science.gov (United States)

    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.

  13. Time Series Models for Exchange Rate and Agricultural Price Forecasts Time Series Models for Exchange Rate and Agricultural Price Forecasts

    Directory of Open Access Journals (Sweden)

    David Orden

    1988-03-01

    Full Text Available Time Series Models for Exchange Rate and Agricultural Price Forecasts In this study, we focus on the role of the exchange rate in explaining variation in agricultural commodity prices. Particular attention is paid to stationary and models in levels versus differences and we find differencing useful in making agricultural prices forecasts.

  14. Measures of Analysis of Time Series (MATS: A MATLAB Toolkit for Computation of Multiple Measures on Time Series Data Bases

    Directory of Open Access Journals (Sweden)

    Dimitris Kugiumtzis

    2010-02-01

    Full Text Available In many applications, such as physiology and finance, large time series data bases are to be analyzed requiring the computation of linear, nonlinear and other measures. Such measures have been developed and implemented in commercial and freeware softwares rather selectively and independently. The Measures of Analysis of Time Series (MATS MATLAB toolkit is designed to handle an arbitrary large set of scalar time series and compute a large variety of measures on them, allowing for the specification of varying measure parameters as well. The variety of options with added facilities for visualization of the results support different settings of time series analysis, such as the detection of dynamics changes in long data records, resampling (surrogate or bootstrap tests for independence and linearity with various test statistics, and discrimination power of different measures and for different combinations of their parameters. The basic features of MATS are presented and the implemented measures are briefly described. The usefulness of MATS is illustrated on some empirical examples along with screenshots.

  15. Exploring large scale time-series data using nested timelines

    Science.gov (United States)

    Xie, Zaixian; Ward, Matthew O.; Rundensteiner, Elke A.

    2013-01-01

    When data analysts study time-series data, an important task is to discover how data patterns change over time. If the dataset is very large, this task becomes challenging. Researchers have developed many visualization techniques to help address this problem. However, little work has been done regarding the changes of multivariate patterns, such as linear trends and clusters, on time-series data. In this paper, we describe a set of history views to fill this gap. This technique works under two modes: merge and non-merge. For the merge mode, merge algorithms were applied to selected time windows to generate a change-based hierarchy. Contiguous time windows having similar patterns are merged first. Users can choose different levels of merging with the tradeoff between more details in the data and less visual clutter in the visualizations. In the non-merge mode, the framework can use natural hierarchical time units or one defined by domain experts to represent timelines. This can help users navigate across long time periods. Gridbased views were designed to provide a compact overview for the history data. In addition, MDS pattern starfields and distance maps were developed to enable users to quickly investigate the degree of pattern similarity among different time periods. The usability evaluation demonstrated that most participants could understand the concepts of the history views correctly and finished assigned tasks with a high accuracy and relatively fast response time.

  16. Reconstruction of ensembles of coupled time-delay systems from time series

    Science.gov (United States)

    Sysoev, I. V.; Prokhorov, M. D.; Ponomarenko, V. I.; Bezruchko, B. P.

    2014-06-01

    We propose a method to recover from time series the parameters of coupled time-delay systems and the architecture of couplings between them. The method is based on a reconstruction of model delay-differential equations and estimation of statistical significance of couplings. It can be applied to networks composed of nonidentical nodes with an arbitrary number of unidirectional and bidirectional couplings. We test our method on chaotic and periodic time series produced by model equations of ensembles of diffusively coupled time-delay systems in the presence of noise, and apply it to experimental time series obtained from electronic oscillators with delayed feedback coupled by resistors.

  17. Building Real-Time Network Intrusion Detection System Based on Parallel Time-Series Mining Techniques

    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.

  18. TimeSeriesStreaming.vi: LabVIEW program for reliable data streaming of large analog time series

    CERN Document Server

    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.

  19. Copulas and time series with long-ranged dependences

    CERN Document Server

    Chicheportiche, Rémy

    2013-01-01

    We review ideas on temporal dependences and recurrences in discrete time series from several areas of natural and social sciences. We revisit existing studies and redefine the relevant observables in the language of copulas (joint laws of the ranks). We propose that copulas provide an appropriate mathematical framework to study non-linear time dependences and related concepts - like aftershocks, Omori law, recurrences, waiting times. We also critically argue using this global approach that previous phenomenological attempts involving only a long-ranged autocorrelation function lacked complexity in that they were essentially mono-scale.

  20. Assessing spatial covariance among time series of abundance.

    Science.gov (United States)

    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

  1. Assessing spatial covariance among time series of abundance.

    Science.gov (United States)

    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

  2. FTSPlot: fast time series visualization for large datasets.

    Directory of Open Access Journals (Sweden)

    Michael Riss

    Full Text Available The analysis of electrophysiological recordings often involves visual inspection of time series data to locate specific experiment epochs, mask artifacts, and verify the results of signal processing steps, such as filtering or spike detection. Long-term experiments with continuous data acquisition generate large amounts of data. Rapid browsing through these massive datasets poses a challenge to conventional data plotting software because the plotting time increases proportionately to the increase in the volume of data. This paper presents FTSPlot, which is a visualization concept for large-scale time series datasets using techniques from the field of high performance computer graphics, such as hierarchic level of detail and out-of-core data handling. In a preprocessing step, time series data, event, and interval annotations are converted into an optimized data format, which then permits fast, interactive visualization. The preprocessing step has a computational complexity of O(n x log(N; the visualization itself can be done with a complexity of O(1 and is therefore independent of the amount of data. A demonstration prototype has been implemented and benchmarks show that the technology is capable of displaying large amounts of time series data, event, and interval annotations lag-free with < 20 ms ms. The current 64-bit implementation theoretically supports datasets with up to 2(64 bytes, on the x86_64 architecture currently up to 2(48 bytes are supported, and benchmarks have been conducted with 2(40 bytes/1 TiB or 1.3 x 10(11 double precision samples. The presented software is freely available and can be included as a Qt GUI component in future software projects, providing a standard visualization method for long-term electrophysiological experiments.

  3. 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.

  4. Dynamical analysis and visualization of tornadoes time series.

    Science.gov (United States)

    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

  5. Times series averaging from a probabilistic interpretation of time-elastic kernel

    OpenAIRE

    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 ...

  6. Learning time series evolution by unsupervised extraction of correlations

    Science.gov (United States)

    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

  7. Fully automated period detection from variable stars' time series data

    CERN Document Server

    Shaju, K Y; Thayyullathil, Ramesh Babu

    2010-01-01

    We propose a fully automated method of period determination for the time series data of variable stars. For convenience the discussions in this paper are done in terms of frequency instead of period. Relying on the SigSpec technique (Reegen 2007), it employs a statistically unbiased treatment of frequency-domain noise and avoids spurious (i. e. noise induced) and alias peaks to the highest possible extent without any human intervention. From the output file produced by SigSpec, the frequency with maximum significance is chosen as the genuine frequency. We present tests on ASAS data and the results show that SigSpec can be effectively used for fully automated frequency detection from variable stars' time series data.

  8. Model-Coupled Autoencoder for Time Series Visualisation

    CERN Document Server

    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...

  9. 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.

  10. Radial basis function network design for chaotic time series prediction

    Energy Technology Data Exchange (ETDEWEB)

    Shin, Chang Yong; Kim, Taek Soo; Park, Sang Hui [Yonsei University, Seoul (Korea, Republic of); Choi, Yoon Ho [Kyonggi University, Suwon (Korea, Republic of)

    1996-04-01

    In this paper, radial basis function networks with two hidden layers, which employ the K-means clustering method and the hierarchical training, are proposed for improving the short-term predictability of chaotic time series. Furthermore the recursive training method of radial basis function network using the recursive modified Gram-Schmidt algorithm is proposed for the purpose. In addition, the radial basis function networks trained by the proposed training methods are compared with the X.D. He A Lapedes`s model and the radial basis function network by non-recursive training method. Through this comparison, an improved radial basis function network for predicting chaotic time series is presented. (author). 17 refs., 8 figs., 3 tabs.

  11. Simple Patterns in Fluctuations of Time Series of Economic Interest

    Science.gov (United States)

    Fanchiotti, H.; García Canal, C. A.; García Zúñiga, H.

    Time series corresponding to nominal exchange rates between the US dollar and Argentina, Brazil and European Economic Community currencies; different financial indexes as the Industrial Dow Jones, the British Footsie, the German DAX Composite, the Australian Share Price and the Nikkei Cash and also different Argentine local tax revenues, are analyzed looking for the appearance of simple patterns and the possible definition of forecast evaluators. In every case, the statistical fractal dimensions are obtained from the behavior of the corresponding variance of increments at a given lag. The detrended fluctuation analysis of the data in terms of the corresponding exponent in the resulting power law is carried out. Finally, the frequency power spectra of all the time series considered are computed and compared

  12. Fast Nonparametric Clustering of Structured Time-Series.

    Science.gov (United States)

    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

  13. 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

  14. Deviations from uniform power law scaling in nonstationary time series

    Science.gov (United States)

    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.

  15. 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.

  16. The multiscale analysis between stock market time series

    Science.gov (United States)

    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.

  17. Time Series Analysis, Modeling and Applications A Computational Intelligence Perspective

    CERN Document Server

    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...

  18. Modeling Philippine Stock Exchange Composite Index Using Time Series Analysis

    Science.gov (United States)

    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.

  19. Using Artificial Neural Networks To Forecast Financial Time Series

    OpenAIRE

    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...

  20. Forecasting Stock Prices by Using Alternative Time Series Models

    OpenAIRE

    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...

  1. 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.

  2. 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.

  3. Clustering Time-Series Energy Data from Smart Meters

    OpenAIRE

    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...

  4. Time-series properties of state-level public expenditure.

    OpenAIRE

    Rajaraman, Indira; Mukhopadhyaya, Hiranya; Rao, Kavita R.

    2001-01-01

    Public expenditure reform must be underpinned by some understanding of the time-series properties of public expenditure. This paper examines the univariate properties of aggregate revenue expenditure at the level of State governments in India over the period 1974-98 for three states: Punjab, Haryana and Maharashtra. The empirical exercise is performed on the logarithmic transformation of aggregate revenue expenditure in terms of nominal (rather than ex post real) expenditure, not normalised t...

  5. 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

  6. Time series clustering based on nonparametric multidimensional forecast densities

    OpenAIRE

    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 ...

  7. Surrogate data method applied to nonlinear time series

    OpenAIRE

    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...

  8. Seasonal modulation mixed models for time series forecasting

    OpenAIRE

    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...

  9. Mode Analysis with Autocorrelation Method (Single Time Series) in Tokamak

    Science.gov (United States)

    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.

  10. Automated analysis of protein subcellular location in time series images

    OpenAIRE

    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...

  11. 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.

  12. Nonparametric risk bounds for time-series forecasting

    OpenAIRE

    Daniel McDonald; Cosma Shalizi; Mark Schervish

    2012-01-01

    We derive generalization error bounds -- bounds on the expected inaccuracy of the predictions -- for traditional time series forecasting models. Our results hold for many standard forecasting tools including autoregressive models, moving average models, and, more generally, linear state-space models. These bounds allow forecasters to select among competing models and to guarantee that with high probability, their chosen model will perform well without making strong assumptions about the data ...

  13. DEM error retrieval by analyzing time series of differential interferograms

    OpenAIRE

    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...

  14. Data-driven simulation of complex multidimensional time series

    OpenAIRE

    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...

  15. A time series analysis system using visual operations

    OpenAIRE

    Yamamoto, Yoshikazu; Nakano, Junji

    2000-01-01

    We design and implement a prototype time series analysis system named TISAS for fully using modern graphical user interface technologies. An object oriented approach is adopted to represent data, statistics and models as instance objects and to visualize them by icons on the screen arranged as a tree for recording the analysis process clearly. When we point an icon which represents an object we want to handle, a pop-up menu, whose items are statistical procedures available for the object, app...

  16. Time series regression model for infectious disease and weather.

    Science.gov (United States)

    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

  17. Comparison of correlation analysis techniques for irregularly sampled time series

    Directory of Open Access Journals (Sweden)

    K. Rehfeld

    2011-06-01

    Full Text Available Geoscientific measurements often provide time series with irregular time sampling, requiring either data reconstruction (interpolation or sophisticated methods to handle irregular sampling. We compare the linear interpolation technique and different approaches for analyzing the correlation functions and persistence of irregularly sampled time series, as Lomb-Scargle Fourier transformation and kernel-based methods. In a thorough benchmark test we investigate the performance of these techniques.

    All methods have comparable root mean square errors (RMSEs for low skewness of the inter-observation time distribution. For high skewness, very irregular data, interpolation bias and RMSE increase strongly. We find a 40 % lower RMSE for the lag-1 autocorrelation function (ACF for the Gaussian kernel method vs. the linear interpolation scheme,in the analysis of highly irregular time series. For the cross correlation function (CCF the RMSE is then lower by 60 %. The application of the Lomb-Scargle technique gave results comparable to the kernel methods for the univariate, but poorer results in the bivariate case. Especially the high-frequency components of the signal, where classical methods show a strong bias in ACF and CCF magnitude, are preserved when using the kernel methods.

    We illustrate the performances of interpolation vs. Gaussian kernel method by applying both to paleo-data from four locations, reflecting late Holocene Asian monsoon variability as derived from speleothem δ18O measurements. Cross correlation results are similar for both methods, which we attribute to the long time scales of the common variability. The persistence time (memory is strongly overestimated when using the standard, interpolation-based, approach. Hence, the Gaussian kernel is a reliable and more robust estimator with significant advantages compared to other techniques and suitable for large scale application to paleo-data.

  18. 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.

  19. Genetic programming and serial processing for time series classification.

    Science.gov (United States)

    Alfaro-Cid, Eva; Sharman, Ken; Esparcia-Alcázar, Anna I

    2014-01-01

    This work describes an approach devised by the authors for time series classification. In our approach genetic programming is used in combination with a serial processing of data, where the last output is the result of the classification. The use of genetic programming for classification, although still a field where more research in needed, is not new. However, the application of genetic programming to classification tasks is normally done by considering the input data as a feature vector. That is, to the best of our knowledge, there are not examples in the genetic programming literature of approaches where the time series data are processed serially and the last output is considered as the classification result. The serial processing approach presented here fills a gap in the existing literature. This approach was tested in three different problems. Two of them are real world problems whose data were gathered for online or conference competitions. As there are published results of these two problems this gives us the chance to compare the performance of our approach against top performing methods. The serial processing of data in combination with genetic programming obtained competitive results in both competitions, showing its potential for solving time series classification problems. The main advantage of our serial processing approach is that it can easily handle very large datasets.

  20. Modeling financial time series with S-plus

    CERN Document Server

    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...

  1. 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.

  2. Complexity analysis of the UV radiation dose time series

    CERN Document Server

    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...

  3. Scaling detection in time series: diffusion entropy analysis.

    Science.gov (United States)

    Scafetta, Nicola; Grigolini, Paolo

    2002-09-01

    The methods currently used to determine the scaling exponent of a complex dynamic process described by a time series are based on the numerical evaluation of variance. This means that all of them can be safely applied only to the case where ordinary statistical properties hold true even if strange kinetics are involved. We illustrate a method of statistical analysis based on the Shannon entropy of the diffusion process generated by the time series, called diffusion entropy analysis (DEA). We adopt artificial Gauss and Lévy time series, as prototypes of ordinary and anomalous statistics, respectively, and we analyze them with the DEA and four ordinary methods of analysis, some of which are very popular. We show that the DEA determines the correct scaling exponent even when the statistical properties, as well as the dynamic properties, are anomalous. The other four methods produce correct results in the Gauss case but fail to detect the correct scaling in the case of Lévy statistics. PMID:12366207

  4. LS-SVR and AGO Based Time Series Prediction Method

    Institute of Scientific and Technical Information of China (English)

    ZHANG Shou-peng; LIU Shan; CHAI Wang-xu; ZHANG Jia-qi; GUO Yang-ming

    2016-01-01

    Recently , fault or health condition prediction of complex systems becomes an interesting research topic.However, it is difficult to establish precise physical model for complex systems , and the time series properties are often necessary to be incorporated for the prediction in practice .Currently ,the LS -SVR is widely adopted for prediction of systems with time series data .In this paper , in order to improve the prediction accuracy, accumulated generating operation (AGO) is carried out to improve the data quality and regularity of raw time series data based on grey system theory;then, the inverse accumulated generating operation ( IAGO) is performed to obtain the prediction results .In addition , due to the reason that appropriate kernel function plays an important role in improving the accuracy of prediction through LS-SVR, a modified Gaussian radial basis function (RBF) is proposed.The requirements of distance functions-based kernel functions are satisfied , which ensure fast damping at the place adjacent to the test point and a moderate damping at infinity .The presented model is applied to the analysis of benchmarks .As indicated by the results , the proposed method is an effective prediction one with good precision .

  5. Estimating the Lyapunov spectrum of time delay feedback systems from scalar time series.

    Science.gov (United States)

    Hegger, R

    1999-08-01

    On the basis of a recently developed method for modeling time delay systems, we propose a procedure to estimate the spectrum of Lyapunov exponents from a scalar time series. It turns out that the spectrum is approximated very well and allows for good estimates of the Lyapunov dimension even if the sampling rate of the time series is so low that the infinite dimensional tangent space is spanned quite sparsely.

  6. 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.

  7. 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.

  8. Time-series animation techniques for visualizing urban growth

    Science.gov (United States)

    Acevedo, W.; Masuoka, P.

    1997-01-01

    Time-series animation is a visually intuitive way to display urban growth. Animations of landuse change for the Baltimore-Washington region were generated by showing a series of images one after the other in sequential order. Before creating an animation, various issues which will affect the appearance of the animation should be considered, including the number of original data frames to use, the optimal animation display speed, the number of intermediate frames to create between the known frames, and the output media on which the animations will be displayed. To create new frames between the known years of data, the change in each theme (i.e. urban development, water bodies, transportation routes) must be characterized and an algorithm developed to create the in-between frames. Example time-series animations were created using a temporal GIS database of the Baltimore-Washington area. Creating the animations involved generating raster images of the urban development, water bodies, and principal transportation routes; overlaying the raster images on a background image; and importing the frames to a movie file. Three-dimensional perspective animations were created by draping each image over digital elevation data prior to importing the frames to a movie file. ?? 1997 Elsevier Science Ltd.

  9. 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.

  10. Nonlinear time-series-based adaptive control applications

    Science.gov (United States)

    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.

  11. Time-Series Analysis of Supergranule Characterstics at Solar Minimum

    Science.gov (United States)

    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.

  12. FAULT IDENTIFICATION IN HETEROGENEOUS NETWORKS USING TIME SERIES ANALYSIS

    Institute of Scientific and Technical Information of China (English)

    孙钦东; 张德运; 孙朝晖

    2004-01-01

    Fault management is crucial to provide quality of service grantees for the future networks, and fault identification is an essential part of it. A novel fault identification algorithm is proposed in this paper, which focuses on the anomaly detection of network traffic. Since the fault identification has been achieved using statistical information in management information base, the algorithm is compatible with the existing simple network management protocol framework. The network traffic time series is verified to be non-stationary. By fitting the adaptive autoregressive model, the series is transformed into a multidimensional vector. The training samples and identifiers are acquired from the network simulation. A k-nearest neighbor classifier identifies the system faults after being trained. The experiment results are consistent with the given fault scenarios, which prove the accuracy of the algorithm. The identification errors are discussed to illustrate that the novel fault identification algorithm is adaptive in the fault scenarios with network traffic change.

  13. 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.

  14. Removing atmosphere loading effect from GPS time series

    Science.gov (United States)

    Tiampo, K. F.; Samadi Alinia, H.; Samsonov, S. V.; Gonzalez, P. J.

    2015-12-01

    The GPS time series of site position are contaminated by various sources of noise; in particular, the ionospheric and tropospheric path delays are significant [Gray et al., 2000; Meyer et al., 2006]. The GPS path delay in the ionosphere is largely dependent on the wave frequency whereas the delay in troposphere is dependent on the length of the travel path and therefore site elevation. Various approaches available for compensating ionosphere path delay cannot be used for removal of the tropospheric component. Quantifying the tropospheric delay plays an important role for determination of the vertical GPS component precision, as tropospheric parameters over a large distance have very little correlation with each other. Several methods have been proposed for tropospheric signal elimination from GPS vertical time series. Here we utilize surface temperature fluctuations and seasonal variations in water vapour and air pressure data for various spatial and temporal profiles in order to more accurately remove the atmospheric path delay [Samsonov et al., 2014]. In this paper, we model the atmospheric path delay of vertical position time series by analyzing the signal in the frequency domain and study its dependency on topography in eastern Ontario for the time period from January 2008 to December 2012. Systematic dependency of amplitude of atmospheric path delay as a function of height and its temporal variations based on the development of a new, physics-based model relating tropospheric/atmospheric effects with topography and can help in determining the most accurate GPS position.The GPS time series of site position are contaminated by various sources of noise; in particular, the ionospheric and tropospheric path delays are significant [Gray et al., 2000; Meyer et al., 2006]. The GPS path delay in the ionosphere is largely dependent on the wave frequency whereas the delay in troposphere is dependent on the length of the travel path and therefore site elevation. Various

  15. Monitoring Forest Regrowth Using a Multi-Platform Time Series

    Science.gov (United States)

    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

  16. 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.

  17. Identifying multiple periodicities in sparse photon event time series

    Science.gov (United States)

    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.

  18. Improvement in global forecast for chaotic time series

    Science.gov (United States)

    Alves, P. R. L.; Duarte, L. G. S.; da Mota, L. A. C. P.

    2016-10-01

    In the Polynomial Global Approach to Time Series Analysis, the most costly (computationally speaking) step is the finding of the fitting polynomial. Here we present two routines that improve the forecasting. In the first, an algorithm that greatly improves this situation is introduced and implemented. The heart of this procedure is implemented on the specific routine which performs a mapping with great efficiency. In comparison with the similar procedure of the TimeS package developed by Carli et al. (2014), an enormous gain in efficiency and an increasing in accuracy are obtained. Another development in this work is the establishment of a level of confidence in global prediction with a statistical test for evaluating if the minimization performed is suitable or not. The other program presented in this article applies the Shapiro-Wilk test for checking the normality of the distribution of errors and calculates the expected deviation. The development is employed in observed and simulated time series to illustrate the performance obtained.

  19. Synthesis of rainfall time series in a high temporal resolution

    Science.gov (United States)

    Callau Poduje, Ana Claudia; Haberlandt, Uwe

    2014-05-01

    In order to optimize the design and operation of urban drainage systems, long and continuous rain series in a high temporal resolution are essential. As the length of the rainfall records is often short, particularly the data available with the temporal and regional resolutions required for urban hydrology, it is necessary to find some numerical representation of the precipitation phenomenon to generate long synthetic rainfall series. An Alternating Renewal Model (ARM) is applied for this purpose, which consists of two structures: external and internal. The former is the sequence of wet and dry spells, described by their durations which are simulated stochastically. The internal structure is characterized by the amount of rain corresponding to each wet spell and its distribution within the spell. A multivariate frequency analysis is applied to analyze the internal structure of the wet spells and to generate synthetic events. The stochastic time series must reproduce the statistical characteristics of observed high resolution precipitation measurements used to generate them. The spatio-temporal interdependencies between stations are addressed by resampling the continuous synthetic series based on the Simulated Annealing (SA) procedure. The state of Lower-Saxony and surrounding areas, located in the north-west of Germany is used to develop the ARM. A total of 26 rainfall stations with high temporal resolution records, i.e. rainfall data every 5 minutes, are used to define the events, find the most suitable probability distributions, calibrate the corresponding parameters, simulate long synthetic series and evaluate the results. The length of the available data ranges from 10 to 20 years. The rainfall series involved in the different steps of calculation are compared using a rainfall-runoff model to simulate the runoff behavior in urban areas. The EPA Storm Water Management Model (SWMM) is applied for this evaluation. The results show a good representation of the

  20. Mapping Brazilian savanna vegetation gradients with Landsat time series

    Science.gov (United States)

    Schwieder, Marcel; Leitão, Pedro J.; da Cunha Bustamante, Mercedes Maria; Ferreira, Laerte Guimarães; Rabe, Andreas; Hostert, Patrick

    2016-10-01

    Global change has tremendous impacts on savanna systems around the world. Processes related to climate change or agricultural expansion threaten the ecosystem's state, function and the services it provides. A prominent example is the Brazilian Cerrado that has an extent of around 2 million km2 and features high biodiversity with many endemic species. It is characterized by landscape patterns from open grasslands to dense forests, defining a heterogeneous gradient in vegetation structure throughout the biome. While it is undisputed that the Cerrado provides a multitude of valuable ecosystem services, it is exposed to changes, e.g. through large scale land conversions or climatic changes. Monitoring of the Cerrado is thus urgently needed to assess the state of the system as well as to analyze and further understand ecosystem responses and adaptations to ongoing changes. Therefore we explored the potential of dense Landsat time series to derive phenological information for mapping vegetation gradients in the Cerrado. Frequent data gaps, e.g. due to cloud contamination, impose a serious challenge for such time series analyses. We synthetically filled data gaps based on Radial Basis Function convolution filters to derive continuous pixel-wise temporal profiles capable of representing Land Surface Phenology (LSP). Derived phenological parameters revealed differences in the seasonal cycle between the main Cerrado physiognomies and could thus be used to calibrate a Support Vector Classification model to map their spatial distribution. Our results show that it is possible to map the main spatial patterns of the observed physiognomies based on their phenological differences, whereat inaccuracies occurred especially between similar classes and data-scarce areas. The outcome emphasizes the need for remote sensing based time series analyses at fine scales. Mapping heterogeneous ecosystems such as savannas requires spatial detail, as well as the ability to derive important

  1. Analysing time-varying trends in stratospheric ozone time series using the state space approach

    OpenAIRE

    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...

  2. Financial Time Series Prediction Using Elman Recurrent Random Neural Networks

    Science.gov (United States)

    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

  3. Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.

    Science.gov (United States)

    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

  4. VARTOOLS: A Program for Analyzing Astronomical Time-Series Data

    CERN Document Server

    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...

  5. Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.

    Science.gov (United States)

    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.

  6. Modeling Large Time Series for Efficient Approximate Query Processing

    DEFF Research Database (Denmark)

    Perera, Kasun S; Hahmann, Martin; Lehner, Wolfgang;

    2015-01-01

    these issues, compression techniques have been introduced in many areas of data processing. In this paper, we outline a new system that does not query complete datasets but instead utilizes models to extract the requested information. For time series data we use Fourier and Cosine transformations and piece......-wise aggregation to derive the models. These models are initially created from the original data and are kept in the database along with it. Subsequent queries are answered using the stored models rather than scanning and processing the original datasets. In order to support model query processing, we maintain......Evolving customer requirements and increasing competition force business organizations to store increasing amounts of data and query them for information at any given time. Due to the current growth of data volumes, timely extraction of relevant information becomes more and more difficult...

  7. Studying Dynamic Features in Myocardial Infarction Progression by Integrating miRNA-Transcription Factor Co-Regulatory Networks and Time-Series RNA Expression Data from Peripheral Blood Mononuclear Cells.

    Directory of Open Access Journals (Sweden)

    Hongbo Shi

    Full Text Available Myocardial infarction (MI is a serious heart disease and a leading cause of mortality and morbidity worldwide. Although some molecules (genes, miRNAs and transcription factors (TFs associated with MI have been studied in a specific pathological context, their dynamic characteristics in gene expressions, biological functions and regulatory interactions in MI progression have not been fully elucidated to date. In the current study, we analyzed time-series RNA expression data from peripheral blood mononuclear cells. We observed that significantly differentially expressed genes were sharply up- or down-regulated in the acute phase of MI, and then changed slowly until the chronic phase. Biological functions involved at each stage of MI were identified. Additionally, dynamic miRNA-TF co-regulatory networks were constructed based on the significantly differentially expressed genes and miRNA-TF co-regulatory motifs, and the dynamic interplay of miRNAs, TFs and target genes were investigated. Finally, a new panel of candidate diagnostic biomarkers (STAT3 and ICAM1 was identified to have discriminatory capability for patients with or without MI, especially the patients with or without recurrent events. The results of the present study not only shed new light on the understanding underlying regulatory mechanisms involved in MI progression, but also contribute to the discovery of true diagnostic biomarkers for MI.

  8. Estimation of coupling between time-delay systems from time series.

    Science.gov (United States)

    Prokhorov, M D; Ponomarenko, V I

    2005-07-01

    We propose a method for estimation of coupling between the systems governed by scalar time-delay differential equations of the Mackey-Glass type from the observed time series data. The method allows one to detect the presence of certain types of linear coupling between two time-delay systems, to define the type, strength, and direction of coupling, and to recover the model equations of coupled time-delay systems from chaotic time series corrupted by noise. We verify our method using both numerical and experimental data.

  9. A Tool to Recover Scalar Time-Delay Systems from Experimental Time Series

    CERN Document Server

    Bünner, M J; Meyer, T; Kittel, A; Parisi, J; Meyer, Th.

    1996-01-01

    We propose a method that is able to analyze chaotic time series, gained from exp erimental data. The method allows to identify scalar time-delay systems. If the dynamics of the system under investigation is governed by a scalar time-delay differential equation of the form $dy(t)/dt = h(y(t),y(t-\\tau_0))$, the delay time $\\tau_0$ and the functi on $h$ can be recovered. There are no restrictions to the dimensionality of the chaotic attractor. The method turns out to be insensitive to noise. We successfully apply the method to various time series taken from a computer experiment and two different electronic oscillators.

  10. 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.

  11. Quantifying evolutionary dynamics from variant-frequency time series.

    Science.gov (United States)

    Khatri, Bhavin S

    2016-01-01

    From Kimura's neutral theory of protein evolution to Hubbell's neutral theory of biodiversity, quantifying the relative importance of neutrality versus selection has long been a basic question in evolutionary biology and ecology. With deep sequencing technologies, this question is taking on a new form: given a time-series of the frequency of different variants in a population, what is the likelihood that the observation has arisen due to selection or neutrality? To tackle the 2-variant case, we exploit Fisher's angular transformation, which despite being discovered by Ronald Fisher a century ago, has remained an intellectual curiosity. We show together with a heuristic approach it provides a simple solution for the transition probability density at short times, including drift, selection and mutation. Our results show under that under strong selection and sufficiently frequent sampling these evolutionary parameters can be accurately determined from simulation data and so they provide a theoretical basis for techniques to detect selection from variant or polymorphism frequency time-series. PMID:27616332

  12. Reconstruction of Ordinary Differential Equations From Time Series Data

    CERN Document Server

    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...

  13. 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.

  14. Monthly hail time series analysis related to agricultural insurance

    Science.gov (United States)

    Tarquis, Ana M.; Saa, Antonio; Gascó, Gabriel; Díaz, M. C.; Garcia Moreno, M. R.; Burgaz, F.

    2010-05-01

    Hail is one of the mos important crop insurance in Spain being more than the 50% of the total insurance in cereal crops. The purpose of the present study is to carry out a study about the hail in cereals. Four provinces have been chosen, those with the values of production are higher: Burgos and Zaragoza for the wheat and Cuenca and Valladolid for the barley. The data that we had available for the study of the evolution and intensity of the damages for hail includes an analysis of the correlation between the ratios of agricultural insurances provided by ENESA and the number of days of annual hail (from 1981 to 2007). At the same time, several weather station per province were selected by the longest more complete data recorded (from 1963 to 2007) to perform an analysis of monthly time series of the number of hail days (HD). The results of the study show us that relation between the ratio of the agricultural insurances and the number of hail days is not clear. Several observations are discussed to explain these results as well as if it is possible to determinte a change in tendency in the HD time series.

  15. Ensemble Deep Learning for Biomedical Time Series Classification

    Directory of Open Access Journals (Sweden)

    Lin-peng Jin

    2016-01-01

    Full Text Available Ensemble learning has been proved to improve the generalization ability effectively in both theory and practice. In this paper, we briefly outline the current status of research on it first. Then, a new deep neural network-based ensemble method that integrates filtering views, local views, distorted views, explicit training, implicit training, subview prediction, and Simple Average is proposed for biomedical time series classification. Finally, we validate its effectiveness on the Chinese Cardiovascular Disease Database containing a large number of electrocardiogram recordings. The experimental results show that the proposed method has certain advantages compared to some well-known ensemble methods, such as Bagging and AdaBoost.

  16. Multifractal Time Series Analysis Based on Detrended Fluctuation Analysis

    Science.gov (United States)

    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.

  17. Real Rainfall Time Series for Storm Sewer Design

    DEFF Research Database (Denmark)

    Larsen, Torben

    ) as the model of the storm sewer system. The output of the simulation is the frequency distribution of the peak flow, overflow volume etc. from the overflow or retention storage. The parameters in the transfer model is found either from rainfall/runoff measurements in the catchment or from one or a few......The paper describes a simulation method for the design of retention storages, overflows etc. in storm sewer systems. The method is based on computer simulation with real rainfall time series as input ans with the aply of a simple transfer model of the ARMA-type (autoregressiv moving average model...

  18. Real Rainfall Time Series for Storm Sewer Design

    DEFF Research Database (Denmark)

    Larsen, Torben

    1981-01-01

    to a storm sewer system. The output of the simulation is the frequency distribution of the peak flow, overflow volume etc. from the overflow or the retention storage. The parameters in the transfer model are found either from rainfall/runoff measurements in the catchment or from one or more simulations......This paper describes a simulation method for the design of retention storages, overflows etc. in storm sewer systems. The method is based on computer simulation with real real rainfall time series as input and with a simple transfer model of the ARMA-type (Autoregressive moving average) applied...

  19. 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.

  20. 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.

  1. Time series analysis using semiparametric regression on oil palm production

    Science.gov (United States)

    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).

  2. 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.

  3. Kernel canonical-correlation Granger causality for multiple time series

    Science.gov (United States)

    Wu, Guorong; Duan, Xujun; Liao, Wei; Gao, Qing; Chen, Huafu

    2011-04-01

    Canonical-correlation analysis as a multivariate statistical technique has been applied to multivariate Granger causality analysis to infer information flow in complex systems. It shows unique appeal and great superiority over the traditional vector autoregressive method, due to the simplified procedure that detects causal interaction between multiple time series, and the avoidance of potential model estimation problems. However, it is limited to the linear case. Here, we extend the framework of canonical correlation to include the estimation of multivariate nonlinear Granger causality for drawing inference about directed interaction. Its feasibility and effectiveness are verified on simulated data.

  4. Quality Quandaries- Time Series Model Selection and Parsimony

    DEFF Research Database (Denmark)

    Bisgaard, Søren; Kulahci, Murat

    2009-01-01

    consideration in model selection should be parameter parsimony. They favor the use of parsimonious mixed ARMA models, noting that research has shown that a model building strategy that considers only autoregressive representations will lead to non-parsimonious models and to loss of forecasting accuracy.......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...

  5. Almost Periodically Correlated Time Series in Business Fluctuations Analysis

    CERN Document Server

    Lenart, Lukasz

    2012-01-01

    We propose a non-standard subsampling procedure to make formal statistical inference about the business cycle, one of the most important unobserved feature characterising fluctuations of economic growth. We show that some characteristics of business cycle can be modelled in a non-parametric way by discrete spectrum of the Almost Periodically Correlated (APC) time series. On the basis of estimated characteristics of this spectrum business cycle is extracted by filtering. As an illustration we characterise the man properties of business cycles in industrial production index for Polish economy.

  6. A series expansion for the time autocorrelation of dynamical variables

    CERN Document Server

    Maiocchi, A M; Giorgilli, A

    2011-01-01

    We present here a general iterative formula which gives a (formal) series expansion for the time autocorrelation of smooth dynamical variables, for all Hamiltonian systems endowed with an invariant measure. We add some criteria, theoretical in nature, which enable one to decide whether the decay of the correlations is exponentially fast or not. One of these criteria is implemented numerically for the case of the Fermi-Pasta-Ulam system, and we find indications which might suggest a sub-exponentially decay for such a system.

  7. Albedo Pattern Recognition and Time-Series Analyses in Malaysia

    Science.gov (United States)

    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

  8. Signatures of discrete scale invariance in Dst time series

    Science.gov (United States)

    Balasis, Georgios; Papadimitriou, Constantinos; Daglis, Ioannis A.; Anastasiadis, Anastasios; Athanasopoulou, Labrini; Eftaxias, Konstantinos

    2011-07-01

    Self-similar systems are characterized by continuous scale invariance and, in response, the existence of power laws. However, a significant number of systems exhibits discrete scale invariance (DSI) which in turn leads to log-periodic corrections to scaling that decorate the pure power law. Here, we present the results of a search of log-periodic corrections to scaling in the squares of Dst index increments which are taken as proxies of the energy dissipation rate in the magnetosphere. We show that Dst time series exhibit DSI and discuss the consequence of this feature, as well as the possible implications of Dst DSI on space weather forecasting efforts.

  9. A New Correlation Coefficient for Bivariate Time-Series Data

    OpenAIRE

    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. ...

  10. Nonlinear Time Series Prediction Using Chaotic Neural Networks

    Institute of Scientific and Technical Information of China (English)

    LI KePing; CHEN TianLun

    2001-01-01

    A nonlinear feedback term is introduced into the evaluation equation of weights of the backpropagation algorithm for neural network, the network becomes a chaotic one. For the purpose of that we can investigate how the different feedback terms affect the process of learning and forecasting, we use the model to forecast the nonlinear time series which is produced by Makey-Glass equation. By selecting the suitable feedback term, the system can escape from the local minima and converge to the global minimum or its approximate solutions, and the forecasting results are better than those of backpropagation algorithm.``

  11. 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.

  12. Ensemble Deep Learning for Biomedical Time Series Classification

    Science.gov (United States)

    2016-01-01

    Ensemble learning has been proved to improve the generalization ability effectively in both theory and practice. In this paper, we briefly outline the current status of research on it first. Then, a new deep neural network-based ensemble method that integrates filtering views, local views, distorted views, explicit training, implicit training, subview prediction, and Simple Average is proposed for biomedical time series classification. Finally, we validate its effectiveness on the Chinese Cardiovascular Disease Database containing a large number of electrocardiogram recordings. The experimental results show that the proposed method has certain advantages compared to some well-known ensemble methods, such as Bagging and AdaBoost.

  13. 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

  14. Time series analysis for minority game simulations of financial markets

    CERN Document Server

    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.

  15. 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.

  16. Univariate time series in geosciences theory and examples

    CERN Document Server

    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

  17. Time series ARIMA models for daily price of palm oil

    Science.gov (United States)

    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.

  18. Visualizing trends and clusters in ranked time-series data

    Science.gov (United States)

    Gousie, Michael B.; Grady, John; Branagan, Melissa

    2013-12-01

    There are many systems that provide visualizations for time-oriented data. Of those, few provide the means of finding patterns in time-series data in which rankings are also important. Fewer still have the fine granularity necessary to visually follow individual data points through time. We propose the Ranking Timeline, a novel visualization method for modestly-sized multivariate data sets that include the top ten rankings over time. The system includes two main visualization components: a ranking over time and a cluster analysis. The ranking visualization, loosely based on line plots, allows the user to track individual data points so as to facilitate comparisons within a given time frame. Glyphs represent additional attributes within the framework of the overall system. The user has control over many aspects of the visualization, including viewing a subset of the data and/or focusing on a desired time frame. The cluster analysis tool shows the relative importance of individual items in conjunction with a visualization showing the connection(s) to other, similar items, while maintaining the aforementioned glyphs and user interaction. The user controls the clustering according to a similarity threshold. The system has been implemented as a Web application, and has been tested with data showing the top ten actors/actresses from 1929-2010. The experiments have revealed patterns in the data heretofore not explored.

  19. Feasibility of real-time calculation of correlation integral derived statistics applied to EGG time series

    NARCIS (Netherlands)

    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

  20. Feasibility of real-time calculation of correlation integral derived statistics applied to EEG time series

    NARCIS (Netherlands)

    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

  1. Local polynomial method for ensemble forecast of time series

    Directory of Open Access Journals (Sweden)

    S. Regonda

    2005-01-01

    Full Text Available We present a nonparametric approach based on local polynomial regression for ensemble forecast of time series. The state space is first reconstructed by embedding the univariate time series of the response variable in a space of dimension (D with a delay time (τ. To obtain a forecast from a given time point t, three steps are involved: (i the current state of the system is mapped on to the state space, known as the feature vector, (ii a small number (K=α*n, α=fraction (0,1] of the data, n=data length of neighbors (and their future evolution to the feature vector are identified in the state space, and (iii a polynomial of order p is fitted to the identified neighbors, which is then used for prediction. A suite of parameter combinations (D, τ, α, p is selected based on an objective criterion, called the Generalized Cross Validation (GCV. All of the selected parameter combinations are then used to issue a T-step iterated forecast starting from the current time t, thus generating an ensemble forecast which can be used to obtain the forecast probability density function (PDF. The ensemble approach improves upon the traditional method of providing a single mean forecast by providing the forecast uncertainty. Further, for short noisy data it can provide better forecasts. We demonstrate the utility of this approach on two synthetic (Henon and Lorenz attractors and two real data sets (Great Salt Lake bi-weekly volume and NINO3 index. This framework can also be used to forecast a vector of response variables based on a vector of predictors.

  2. Hybrid perturbation methods based on statistical time series models

    Science.gov (United States)

    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.

  3. Financial time series prediction using spiking neural networks.

    Science.gov (United States)

    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

  4. A new complexity measure for time series analysis and classification

    Science.gov (United States)

    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).

  5. Financial time series prediction using spiking neural networks.

    Science.gov (United States)

    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.

  6. 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.

  7. Financial time series prediction using spiking neural networks.

    Directory of Open Access Journals (Sweden)

    David Reid

    Full Text Available 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.

  8. 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.

  9. 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.

  10. A Markov switching model for annual hydrologic time series

    Science.gov (United States)

    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.

  11. Time series analysis of gold production in Malaysia

    Science.gov (United States)

    Muda, Nora; Hoon, Lee Yuen

    2012-05-01

    Gold is a soft, malleable, bright yellow metallic element and unaffected by air or most reagents. It is highly valued as an asset or investment commodity and is extensively used in jewellery, industrial application, dentistry and medical applications. In Malaysia, gold mining is limited in several areas such as Pahang, Kelantan, Terengganu, Johor and Sarawak. The main purpose of this case study is to obtain a suitable model for the production of gold in Malaysia. The model can also be used to predict the data of Malaysia's gold production in the future. Box-Jenkins time series method was used to perform time series analysis with the following steps: identification, estimation, diagnostic checking and forecasting. In addition, the accuracy of prediction is tested using mean absolute percentage error (MAPE). From the analysis, the ARIMA (3,1,1) model was found to be the best fitted model with MAPE equals to 3.704%, indicating the prediction is very accurate. Hence, this model can be used for forecasting. This study is expected to help the private and public sectors to understand the gold production scenario and later plan the gold mining activities in Malaysia.

  12. Bayesian methods for outliers detection in GNSS time series

    Science.gov (United States)

    Qianqian, Zhang; Qingming, Gui

    2013-07-01

    This article is concerned with the problem of detecting outliers in GNSS time series based on Bayesian statistical theory. Firstly, a new model is proposed to simultaneously detect different types of outliers based on the conception of introducing different types of classification variables corresponding to the different types of outliers; the problem of outlier detection is converted into the computation of the corresponding posterior probabilities, and the algorithm for computing the posterior probabilities based on standard Gibbs sampler is designed. Secondly, we analyze the reasons of masking and swamping about detecting patches of additive outliers intensively; an unmasking Bayesian method for detecting additive outlier patches is proposed based on an adaptive Gibbs sampler. Thirdly, the correctness of the theories and methods proposed above is illustrated by simulated data and then by analyzing real GNSS observations, such as cycle slips detection in carrier phase data. Examples illustrate that the Bayesian methods for outliers detection in GNSS time series proposed by this paper are not only capable of detecting isolated outliers but also capable of detecting additive outlier patches. Furthermore, it can be successfully used to process cycle slips in phase data, which solves the problem of small cycle slips.

  13. 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.

  14. Time series clustering analysis of health-promoting behavior

    Science.gov (United States)

    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.

  15. Blind source separation problem in GPS time series

    Science.gov (United States)

    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

  16. 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.

  17. 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.

  18. Estimation of Hurst Exponent for the Financial Time Series

    Science.gov (United States)

    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.

  19. Time series analysis of the interdependence among air pollutants

    Energy Technology Data Exchange (ETDEWEB)

    Hsu, K.-J. (National Taiwan University, Taipei (Taiwan). Dept. of Atmospheric Sciences)

    1992-12-01

    A statistical time series analysis was applied to study the interdependence between the primary and secondary pollutants in the Taipei area. Estimations using the vector autoregression model (VAR) indicate that 2 and 4 h time lags are sufficient to represent the observed values at two stations studied. The impulse response functions and variance decompositions of NO, NO[sub 2] and O[sub 3] were derived using the vector moving average representations to examine the significance of one species on others. Influences of photochemistry and transport processes on these air pollutants at different locations were evaluated from the results. This technique may provide a simple tool for preliminary assessment of pollution problems. 14 refs., 6 figs., 6 tabs.

  20. A quasi-global precipitation time series for drought monitoring

    Science.gov (United States)

    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.

  1. Vegetation Dynamics of NW Mexico using MODIS time series data

    Science.gov (United States)

    Valdes, M.; Bonifaz, R.; Pelaez, G.; Leyva Contreras, A.

    2010-12-01

    Northwestern Mexico is an area subjected to a combination of marine and continental climatic influences which produce a highly variable vegetation dynamics throughout time. Using Moderate Resolution Imaging Spectroradiometer (MODIS) vegetation indices data (NDVI and EVI) from 2001 to 2008, mean and standard deviation image values of the time series were calculated. Using this data, annual vegetation dynamics was characterized based on the different values for the different vegetation types. Annual mean values were compared and inter annual variations or anomalies were analyzed calculating departures of de mean. An anomaly was considered if the value was over or under two standard deviations. Using this procedure it was possible determine spatio-temporal patterns over the study area and relate them to climatic conditions.

  2. 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)

  3. 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.; Smith, Jeff; Dugan, Roger

    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

  4. Seasonal signals in the reprocessed GPS coordinate time series

    Science.gov (United States)

    Kenyeres, A.; van Dam, T.; Figurski, M.; Szafranek, K.

    2008-12-01

    The global (IGS) and regional (EPN) CGPS time series have already been studied in detail by several authors to analyze the periodic signals and noise present in the long term displacement series. The comparisons indicated that the amplitude and phase of the CGPS derived seasonal signals mostly disagree with the surface mass redistribution models. The CGPS results are highly overestimating the seasonal term, only about 40% of the observed annual amplitude can be explained with the joint contribution of the geophysical models (Dong et al. 2002). Additionally the estimated amplitudes or phases are poorly coherent with the models, especially at sites close to coastal areas (van Dam et al, 2007). The conclusion of the studies was that the GPS results are distorted by analysis artifacts (e.g. ocean tide loading, aliasing of unmodeled short periodic tidal signals, antenna PCV models), monument thermal effects and multipath. Additionally, the GPS series available so far are inhomogeneous in terms of processing strategy, applied models and reference frames. The introduction of the absolute phase center variation (PCV) models for the satellite and ground antennae in 2006 and the related reprocessing of the GPS precise orbits made a perfect ground and strong argument for the complete re-analysis of the GPS observations from global to local level of networks. This enormous work is in progress within the IGS and a pilot analysis was already done for the complete EPN observations from 1996 to 2007 by the MUT group (Military University of Warsaw). The quick analysis of the results proved the expectations and the superiority of the reprocessed data. The noise level (weekly coordinate repeatability) was highly reduced making ground for the later analysis on the daily solution level. We also observed the significant decrease of the seasonal term in the residual coordinate time series, which called our attention to perform a repeated comparison of the GPS derived annual periodicity

  5. Time dependent intrinsic correlation analysis of temperature and dissolved oxygen time series using empirical mode decomposition

    CERN Document Server

    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...

  6. Adaptive Sampling of Time Series During Remote Exploration

    Science.gov (United States)

    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

  7. United States Forest Disturbance Trends Observed Using Landsat Time Series

    Science.gov (United States)

    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.

  8. Established time series measure occurrence and frequency of episodic events.

    Science.gov (United States)

    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

  9. Aerosol Climate Time Series in ESA Aerosol_cci

    Science.gov (United States)

    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

  10. VARTOOLS: A program for analyzing astronomical time-series data

    Science.gov (United States)

    Hartman, J. D.; Bakos, G. Á.

    2016-10-01

    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 the program. VARTOOLS is designed especially for batch processing of light curves, including built-in support for parallel processing, making it useful for large time-domain surveys such as searches for transiting planets. Several examples are provided to illustrate the use of the program.

  11. 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.

  12. Hybrid Perturbation methods based on Statistical Time Series models

    CERN Document Server

    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...

  13. 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.

  14. Single-Index Additive Vector Autoregressive Time Series Models

    KAUST Repository

    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.

  15. Detecting Dynamical States from Noisy Time Series using Bicoherence

    CERN Document Server

    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...

  16. Incorporating Satellite Time-Series Data into Modeling

    Science.gov (United States)

    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.

  17. 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.

  18. Correlation filtering in financial time series (Invited Paper)

    Science.gov (United States)

    Aste, T.; Di Matteo, Tiziana; Tumminello, M.; Mantegna, R. N.

    2005-05-01

    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.,1 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).

  19. The Abysmal State of Abyssal Time Series: An Acoustic Challenge

    Science.gov (United States)

    Munk, W. H.; Worcester, P. F.; Dushaw, B. D.; Howe, B. M.; Spindel, R. C.

    2001-12-01

    The 20th century rise in global sea level by 18 cm has not been explained. The rise has been continuous and linear since the previous century. It cannot be predominantly the result of thermal expansion. Global ocean warming (as recently compiled by Levitus and his collaborators) started too late, is too non-linear and too weak to account for the recorded rise. It is not impossible that the global warming has been underestimated for lack of adequate observations in the southern hemisphere, and at abyssal depths. Time series of abyssal temperatures are badly lacking. Tomographic methods have the required precision, vertical resolution and horizontal integration to accomplish this task. A more likely explanation is to attribute most of the sea level rise to melting of polar ice sheets. There are two difficulties: the required melting is considerably larger than has generally been estimated, and there are serious restrictions imposed by astronomic measurements of the Earth?s rotation.

  20. 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.

  1. On The Fourier And Wavelet Analysis Of Coronal Time Series

    CERN Document Server

    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...

  2. Multivariate time series with linear state space structure

    CERN Document Server

    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...

  3. Time series analysis for minority game simulations of financial markets

    Science.gov (United States)

    Ferreira, Fernando F.; Francisco, Gerson; Machado, Birajara S.; Muruganandam, Paulsamy

    2003-04-01

    The minority game (MG) 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, several conclusions are obtained about the generating mechanism for this kind of evolution. The motion is deterministic, driven by occasional random external perturbation. When the interval between two successive perturbations is sufficiently large, one can find low dimensional chaos in this regime. However, the full motion of the MG model is found to be similar to that of the first differences of the SP500 index: stochastic, nonlinear and (unit root) stationary.

  4. 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.

  5. Optimal estimation of recurrence structures from time series

    Science.gov (United States)

    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.

  6. 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.

  7. Controlled, distributed data management of an Antarctic time series

    Science.gov (United States)

    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.

  8. Assessment of Time Series Complexity Using Improved Approximate Entropy

    Institute of Scientific and Technical Information of China (English)

    KONG De-Ren; XIE Hong-Bo

    2011-01-01

    @@ Approximate entropy(ApEn),a measure quantifying complexity and/or regularity,is believed to be an effective method of analyzing diverse settings.However,the similarity definition of vectors based on Heaviside function may cause some problems in the validity and accuracy of ApEn.To overcome the problems,an improved approximate entropy(iApEn)based on the sigmoid function is proposed.The performance of iApEn is tested on the independent identically distributed(IID)Gaussian noise,the MIX stochastic model,the Rossler map,the logistic map,and the high-dimensional Mackey-Glass oscillator.The results show that iApEn is superior to ApEn in several aspects,including better relative consistency,freedom of parameter selection,robust to noise,and more independence on record length when characterizing time series with different complexities.%Approximate entropy (ApEn), a measure quantifying complexity and/or regularity, is believed to be an effective method of analyzing diverse settings. However, the similarity definition of vectors based on Heaviside function may cause some problems in the validity and accuracy of ApEn. To overcome the problems, an improved approximate entropy (iApEn) based on the sigmoid function is proposed. The performance of iApEn is tested on the independent identically distributed (HD) Gaussian noise, the MIX stochastic model, the Rossler map, the logistic map, and the high-dimensional Mackey-Glass oscillator. The results show that iApEn is superior to ApEn in several aspects, including better relative consistency, freedom of parameter selection, robust to noise, and more independence on record length when characterizing time series with different complexities.

  9. Automated Bayesian model development for frequency detection in biological time series

    Directory of Open Access Journals (Sweden)

    Oldroyd Giles ED

    2011-06-01

    Full Text Available Abstract Background A first step in building a mathematical model of a biological system is often the analysis of the temporal behaviour of key quantities. Mathematical relationships between the time and frequency domain, such as Fourier Transforms and wavelets, are commonly used to extract information about the underlying signal from a given time series. This one-to-one mapping from time points to frequencies inherently assumes that both domains contain the complete knowledge of the system. However, for truncated, noisy time series with background trends this unique mapping breaks down and the question reduces to an inference problem of identifying the most probable frequencies. Results In this paper we build on the method of Bayesian Spectrum Analysis and demonstrate its advantages over conventional methods by applying it to a number of test cases, including two types of biological time series. Firstly, oscillations of calcium in plant root cells in response to microbial symbionts are non-stationary and noisy, posing challenges to data analysis. Secondly, circadian rhythms in gene expression measured over only two cycles highlights the problem of time series with limited length. The results show that the Bayesian frequency detection approach can provide useful results in specific areas where Fourier analysis can be uninformative or misleading. We demonstrate further benefits of the Bayesian approach for time series analysis, such as direct comparison of different hypotheses, inherent estimation of noise levels and parameter precision, and a flexible framework for modelling the data without pre-processing. Conclusions Modelling in systems biology often builds on the study of time-dependent phenomena. Fourier Transforms are a convenient tool for analysing the frequency domain of time series. However, there are well-known limitations of this method, such as the introduction of spurious frequencies when handling short and noisy time series, and

  10. Traffic time series analysis by using multiscale time irreversibility and entropy

    Science.gov (United States)

    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.

  11. Markov chain modeling of precipitation time series: Modeling waiting times between tipping bucket rain gauge tips

    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...

  12. Interglacial climate dynamics and advanced time series analysis

    Science.gov (United States)

    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

  13. Nonparametric directionality measures for time series and point process data.

    Science.gov (United States)

    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

  14. Time-series models for border inspection data.

    Science.gov (United States)

    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

  15. Visual analytics of phosphorylation time-series data on insulin response

    Science.gov (United States)

    Ma, David K. G.; Stolte, Christian; Kaur, Sandeep; Bain, Michael; O'Donoghue, Seán I.

    2013-10-01

    Visual analysis of time-series data on protein phosphorylation presents a particular challenge: bioinformatics tools currently available for visualising 'omics' data in time series have been developed primarily to study gene expression, and cannot easily be adopted to phosphorylation data, where a single protein typically has multiple phosphosites. In this study, we worked with an experimental research group that is applying very recent methods in high-throughput experimental proteomics to study the time course of protein phosphorylation events in human cells in vitro following stimulation by insulin, as part of a broader study of diabetes and obesity. We applied several existing visual analytics approaches with the goal of organising the data to facilitate new insight into underlying molecular processes. We developed a novel layout strategy called 'Minardo' that is loosely based on cell topology and ordered by time and causality. This layout utilises a frame of reference familiar to life scientists and helpful for organising and interpreting time-series data. This strategy proved to be useful, leading to new insights into the insulin response pathway. We are working on generalising the Minardo layout to accommodate similar datasets related to other signalling pathways, which should be straightforward.

  16. Mackenzie River Delta morphological change based on Landsat time series

    Science.gov (United States)

    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

  17. Auto-Regressive Models of Non-Stationary Time Series with Finite Length

    Institute of Scientific and Technical Information of China (English)

    FEI Wanchun; BAI Lun

    2005-01-01

    To analyze and simulate non-stationary time series with finite length, the statistical characteristics and auto-regressive (AR) models of non-stationary time series with finite length are discussed and studied. A new AR model called the time varying parameter AR model is proposed for solution of non-stationary time series with finite length. The auto-covariances of time series simulated by means of several AR models are analyzed. The result shows that the new AR model can be used to simulate and generate a new time series with the auto-covariance same as the original time series. The size curves of cocoon filaments regarded as non-stationary time series with finite length are experimentally simulated. The simulation results are significantly better than those obtained so far, and illustrate the availability of the time varying parameter AR model. The results are useful for analyzing and simulating non-stationary time series with finite length.

  18. 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

  19. 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

  20. Network-based estimation of time-dependent noise in GPS position time series

    Science.gov (United States)

    Dmitrieva, Ksenia; Segall, Paul; DeMets, Charles

    2015-06-01

    Some estimates of GPS velocity uncertainties are very low, 0.1 mm/year with 10 years of data. Yet, residual velocities relative to rigid plate models in nominally stable plate interiors can be an order of magnitude larger. This discrepancy could be caused by underestimating low-frequency time-dependent noise in position time series, such as random walk. We show that traditional estimators, based on individual time series, are insensitive to low-amplitude random walk, yet such noise significantly increases GPS velocity uncertainties. Here, we develop a method for determining representative noise parameters in GPS position time series, by analyzing an entire network simultaneously, which we refer to as the network noise estimator (NNE). We analyze data from the aseismic central-eastern USA, assuming that residual motions relative to North America, corrected for glacial isostatic adjustment (GIA), represent noise. The position time series are decomposed into signal (plate rotation and GIA) and noise components. NNE simultaneously processes multiple stations with a Kalman filter and solves for average noise components for the network by maximum likelihood estimation. Synthetic tests show that NNE correctly estimates even low-level random walk, thus providing better estimates of velocity uncertainties than conventional, single station methods. To test NNE on actual data, we analyze a heterogeneous 15 station GPS network from the central-eastern USA, assuming the noise is a sum of random walk, flicker and white noise. For the horizontal time series, NNE finds higher average random walk than the standard individual station-based method, leading to velocity uncertainties a factor of 2 higher than traditional methods.

  1. Academic Workload and Working Time: Retrospective Perceptions versus Time-Series Data

    Science.gov (United States)

    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…

  2. Detrended fluctuation analysis of laser Doppler flowmetry time series.

    Science.gov (United States)

    Esen, Ferhan; Aydin, Gülsün Sönmez; Esen, Hamza

    2009-12-01

    Detrended fluctuation analysis (DFA) of laser Doppler flow (LDF) time series appears to yield improved prognostic power in microvascular dysfunction, through calculation of the scaling exponent, alpha. In the present study the long lasting strenuous activity-induced change in microvascular function was evaluated by DFA in basketball players compared with sedentary control. Forearm skin blood flow was measured at rest and during local heating. Three scaling exponents, the slopes of the three regression lines, were identified corresponding to cardiac, cardio-respiratory and local factors. Local scaling exponent was always approximately one, alpha=1.01+/-0.15, in the control group and did not change with local heating. However, we found a broken line with two scaling exponents (alpha(1)=1.06+/-0.01 and alpha(2)=0.75+/-0.01) in basketball players. The broken line became a single line having one scaling exponent (alpha(T)=0.94+/-0.01) with local heating. The scaling exponents, alpha(2) and alpha(T), smaller than 1 indicate reduced long-range correlation in blood flow due to a loss of integration in local mechanisms and suggest endothelial dysfunction as the most likely candidate. Evaluation of microvascular function from a baseline LDF signal at rest is the superiority of DFA to other methods, spectral or not, that use the amplitude changes of evoked relative signal. PMID:19660479

  3. River flow time series using least squares support vector machines

    Science.gov (United States)

    Samsudin, R.; Saad, P.; Shabri, A.

    2011-06-01

    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 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.

  4. Forecasting Financial Time-Series using Artificial Market Models

    CERN Document Server

    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...

  5. Linear Detrending Subsequence Matching in Time-Series Databases

    CERN Document Server

    Gil, Myeong-Seon; Kim, Bum-Soo

    2010-01-01

    Each time-series has its own linear trend, the directionality of a timeseries, and removing the linear trend is crucial to get the more intuitive matching results. Supporting the linear detrending in subsequence matching is a challenging problem due to a huge number of possible subsequences. In this paper we define this problem the linear detrending subsequence matching and propose its efficient index-based solution. To this end, we first present a notion of LD-windows (LD means linear detrending), which is obtained as follows: we eliminate the linear trend from a subsequence rather than each window itself and obtain LD-windows by dividing the subsequence into windows. Using the LD-windows we then present a lower bounding theorem for the index-based matching solution and formally prove its correctness. Based on the lower bounding theorem, we next propose the index building and subsequence matching algorithms for linear detrending subsequence matching.We finally show the superiority of our index-based solution...

  6. Scene Context Dependency of Pattern Constancy of Time Series Imagery

    Science.gov (United States)

    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.

  7. Optimizing the search for transiting planets in long time series

    CERN Document Server

    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...

  8. 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.

  9. Modeling Tourist Arrivals Using Time Series Analysis: Evidence From Australia

    Directory of Open Access Journals (Sweden)

    Seyed AbdelhamidShobeiriNejad

    2012-01-01

    Full Text Available Australian tourism has a logistic trend as Butler’s model shows. The stagnation has not been reached so opportunities exist to increase tourism. The logistic model predicts 7.2 million tourists in 2015 but time series models of ARIMA and VAR improve the prediction and explain the data. The ARIMA (2, 2, 2 fits well while the VAR lead to Granger causalities between the three data sets. A regression model (R2 = 0.99 using Australian tourist arrival as a function of Europe and World arrivals allowed to further understand the Granger causality. The ARIMA model predicts tourist numbers to be approximately 6 million in 2015. The VAR technique allowed impulse response analysis as well. A two-way causality between the tourist in Australia, Europe and World exists, while impulse response indicated different effect patterns, where tourist arrivals increase in the first period and declines in the second period but experience seasonal fluctuations in the third period. The strongest causalities in were period 1 between World and Europe; period 2-a one-way causality from Australia to World and period 3-a two-way causalities between Australia, Europe and World. The impulse responses results were aligned with the Butler theory.

  10. 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.

  11. Landslide monitoring using airphotos time series and GIS

    Science.gov (United States)

    Kavoura, Katerina; Nikolakopoulos, Konstantinos G.; Sabatakakis, Nikolaos

    2014-10-01

    Western Greece is suffering by landslides. The term landslide includes a wide range of ground movement, such as slides, falls, flows etc. mainly based on gravity with the aid of many conditioning and triggering factors. Landslides provoke enormous changes to the natural and artificial relief. The annual cost of repairing the damage amounts to millions of euros. In this paper a combined use of airphotos time series, high resolution remote sensing data and GIS for the landslide monitoring is presented. Analog and digital air-photos used covered a period of almost 70 years from 1945 until 2012. Classical analog airphotos covered the period from 1945 to 2000, while digital airphotos and satellite images covered the 2008-2012 period. The air photos have been orthorectified using the Leica Photogrammetry Suite. Ground control points and a high accuracy DSM were used for the orthorectification of the air photos. The 2008 digital air photo mosaic from the Greek Cadastral with a spatial resolution of 25 cm and the respective DSM was used as the base map for all the others data sets. The RMS error was less than 0.5 pixel. Changes to the artificial constructions provoked by the landslideswere digitized and then implemented in an ARCGIS database. The results are presented in this paper.

  12. Task-Driven Evaluation of Aggregation in Time Series Visualization.

    Science.gov (United States)

    Albers, Danielle; Correll, Michael; Gleicher, Michael

    2014-01-01

    Many visualization tasks require the viewer to make judgments about aggregate properties of data. Recent work has shown that viewers can perform such tasks effectively, for example to efficiently compare the maximums or means over ranges of data. However, this work also shows that such effectiveness depends on the designs of the displays. In this paper, we explore this relationship between aggregation task and visualization design to provide guidance on matching tasks with designs. We combine prior results from perceptual science and graphical perception to suggest a set of design variables that influence performance on various aggregate comparison tasks. We describe how choices in these variables can lead to designs that are matched to particular tasks. We use these variables to assess a set of eight different designs, predicting how they will support a set of six aggregate time series comparison tasks. A crowd-sourced evaluation confirms these predictions. These results not only provide evidence for how the specific visualizations support various tasks, but also suggest using the identified design variables as a tool for designing visualizations well suited for various types of tasks.

  13. Innovative techniques to analyze time series of geomagnetic activity indices

    Science.gov (United States)

    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.

  14. 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.

  15. Presentations to Emergency Departments for COPD: A Time Series Analysis.

    Science.gov (United States)

    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

  16. A polynomial time biclustering algorithm for finding approximate expression patterns in gene expression time series

    OpenAIRE

    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 ...

  17. A Nonstationary Negative Binomial Time Series with Time-Dependent Covariates: Enterococcus Counts in Boston Harbor

    OpenAIRE

    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...

  18. 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.

  19. Nonlinear Time Series Analysis of White Dwarf Light Curves

    Science.gov (United States)

    Jevtic, N.; Zelechoski, S.; Feldman, H.; Peterson, C.; Schweitzer, J.

    2001-12-01

    We use nonlinear time series analysis methods to examine the light intensity curves of white dwarf PG1351+489 obtained by the Whole Earth Telescope (WET). Though these methods were originally introduced to study chaotic systems, when a clear signature of determinism is found for the process generating an observable and it couples the active degrees of freedom of the system, then the notion of phase space provides a framework for exploring the system dynamics of nonlinear systems in general. With a pronounced single frequency, its harmonics and other frequencies of lower amplitude on a broadband background, the PG1351 light curve lends itself to the use of time delay coordinates. Our phase space reconstruction yields a triangular, toroidal three-dimensional shape. This differs from earlier results of a circular toroidal representation. We find a morphological similarity to a magnetic dynamo model developed for fast rotators that yields a union of both results: the circular phase space structure for the ascending portion of the cycle, and the triangular structure for the declining portion. The rise and fall of the dynamo cycle yield both different phase space representations and different correlation dimensions. Since PG1351 is known to have no significant fields, these results may stimulate the observation of light curves of known magnetic white dwarfs for comparison. Using other data obtained by the WET, we compare the phase space reconstruction of DB white dwarf PG1351 with that of GD 358 which has a more complex power spectrum. We also compare these results with those for PG1159. There is some general similarity between the results of the phase space reconstruction for the DB white dwarfs. As expected, the difference between the results for the DB white dwarfs and PG1159 is great.

  20. Optimizing the search for transiting planets in long time series

    Science.gov (United States)

    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