Time Series Spectroscopic and Photometric Observations of the Massive DAV BPM 37093
NASA Astrophysics Data System (ADS)
Nitta, Atsuko; Kepler, S. O.; Chene, Andre–Nicolas; Koester, D.; Provencal, J. L.; Sullivan, D. J.; Chote, Paul; Safeko, Ramotholo; Kanaan, Antonio; Romero, Alejandra; Corti, Mariela; Corti, Mariela; Kilic, Mukremin; Winget, D. E.
2015-06-01
BPM 37093 was the first of only a handful of massive (1.05+/-0.05 M⊙; Bergeron 2004;Koester & Allard 2000) white dwarf pulsators discovered (Kanaan et al. 1992). These stars are particularly interesting because the crystallized mass-fraction as a function of mass and temperature is poorly constrained by observation, yet this process adds 1-2 Gyr uncertainty in ages of the oldest white dwarf stars observed and hence, in the ages of associations that contain them (Abrikosov 1960; Kirzhnits 1960; Salpeter 1961). Last year, we discovered that ESO uses BPM 37093 as a standard star and extracted corresponding spectra from the public archive. The data suggested a large variation in the observed hydrogen line profiles that could potentially be due to pulsations, but the measurement did not reach a detection-quality threshold. To further explore this possibility, though, we obtained 4hrs of continuous time series spectroscopy of BPM 37093 with Gemini in the Northern Spring of 2014. We present our preliminary results from these data along with those from the accompanying time series photometric observations we gathered from Mt. John (New Zealand), South African Astronomical Observatory (SAAO), Panchromatic Robotic optical Monitoring and Polarimetry Telescopes (PROMPT) in Chile, and Complejo Astronomico El Leoncito (Argentina) to support the Gemini observations.
NASA Astrophysics Data System (ADS)
Pons, Xavier; Miquel, Ninyerola; Oscar, González-Guerrero; Cristina, Cea; Pere, Serra; Alaitz, Zabala; Lluís, Pesquer; Ivette, Serral; Joan, Masó; Cristina, Domingo; Maria, Serra Josep; Jordi, Cristóbal; Chris, Hain; Martha, Anderson; Juanjo, Vidal
2014-05-01
Combining climate dynamics and land cover at a relative coarse resolution allows a very interesting approach to global studies, because in many cases these studies are based on a quite high temporal resolution, but they may be limited in large areas like the Mediterranean. However, the current availability of long time series of Landsat imagery and spatially detailed surface climate models allow thinking on global databases improving the results of mapping in areas with a complex history of landscape dynamics, characterized by fragmentation, or areas where relief creates intricate climate patterns that can be hardly monitored or modeled at coarse spatial resolutions. DinaCliVe (supported by the Spanish Government and ERDF, and by the Catalan Government, under grants CGL2012-33927 and SGR2009-1511) is the name of the project that aims analyzing land cover and land use dynamics as well as vegetation stress, with a particular emphasis on droughts, and the role that climate variation may have had in such phenomena. To meet this objective is proposed to design a massive database from long time series of Landsat land cover products (grouped in quinquennia) and monthly climate records (in situ climate data) for the Iberian Peninsula (582,000 km2). The whole area encompasses 47 Landsat WRS2 scenes (Landsat 4 to 8 missions, from path 197 to 202 and from rows 30 to 34), and 52 Landsat WRS1 scenes (for the previous Landsat missions, 212 to 221 and 30 to 34). Therefore, a mean of 49.5 Landsat scenes, 8 quinquennia per scene and a about 6 dates per quinquennium , from 1975 to present, produces around 2376 sets resulting in 30 m x 30 m spatial resolution maps. Each set is composed by highly coherent geometric and radiometric multispectral and multitemporal (to account for phenology) imagery as well as vegetation and wetness indexes, and several derived topographic information (about 10 Tbyte of data). Furthermore, on the basis on a previous work: the Digital Climatic Atlas of
NASA Astrophysics Data System (ADS)
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
Pattern Recognition in Time Series
NASA Astrophysics Data System (ADS)
Lin, Jessica; Williamson, Sheri; Borne, Kirk D.; DeBarr, David
2012-03-01
Perhaps the most commonly encountered data types are time series, touching almost every aspect of human life, including astronomy. One obvious problem of handling time-series databases concerns with its typically massive size—gigabytes or even terabytes are common, with more and more databases reaching the petabyte scale. For example, in telecommunication, large companies like AT&T produce several hundred millions long-distance records per day [Cort00]. In astronomy, time-domain surveys are relatively new—these are surveys that cover a significant fraction of the sky with many repeat observations, thereby producing time series for millions or billions of objects. Several such time-domain sky surveys are now completed, such as the MACHO [Alco01],OGLE [Szym05], SDSS Stripe 82 [Bram08], SuperMACHO [Garg08], and Berkeley’s Transients Classification Pipeline (TCP) [Star08] projects. The Pan-STARRS project is an active sky survey—it began in 2010, a 3-year survey covering three-fourths of the sky with ˜60 observations of each field [Kais04]. The Large Synoptic Survey Telescope (LSST) project proposes to survey 50% of the visible sky repeatedly approximately 1000 times over a 10-year period, creating a 100-petabyte image archive and a 20-petabyte science database (http://www.lsst.org/). The LSST science database will include time series of over 100 scientific parameters for each of approximately 50 billion astronomical sources—this will be the largest data collection (and certainly the largest time series database) ever assembled in astronomy, and it rivals any other discipline’s massive data collections for sheer size and complexity. More common in astronomy are time series of flux measurements. As a consequence of many decades of observations (and in some cases, hundreds of years), a large variety of flux variations have been detected in astronomical objects, including periodic variations (e.g., pulsating stars, rotators, pulsars, eclipsing binaries
Energy Science and Technology Software Center (ESTSC)
2007-11-02
TSDB is a Python module for storing large volumes of time series data. TSDB stores data in binary files indexed by a timestamp. Aggregation functions (such as rate, sum, avg, etc.) can be performed on the data, but data is never discarded. TSDB is presently best suited for SNMP data but new data types are easily added.
GPS Position Time Series @ JPL
NASA Technical Reports Server (NTRS)
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
Network structure of multivariate time series
NASA Astrophysics Data System (ADS)
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.
Network structure of multivariate time series.
Lacasa, Lucas; Nicosia, Vincenzo; Latora, Vito
2015-01-01
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. PMID:26487040
Network structure of multivariate time series
Lacasa, Lucas; Nicosia, Vincenzo; Latora, Vito
2015-01-01
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. PMID:26487040
Permutations and time series analysis.
Cánovas, Jose S; Guillamón, Antonio
2009-12-01
The main aim of this paper is to show how the use of permutations can be useful in the study of time series analysis. In particular, we introduce a test for checking the independence of a time series which is based on the number of admissible permutations on it. The main improvement in our tests is that we are able to give a theoretical distribution for independent time series. PMID:20059199
NASA Astrophysics Data System (ADS)
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.
Time sharing massively parallel machines. Draft
Gorda, B.; Wolski, R.
1995-03-01
As part of the Massively Parallel Computing Initiative (MPCI) at the Lawrence Livermore National Laboratory, the authors have developed a simple, effective and portable time sharing mechanism by scheduling gangs of processes on tightly coupled parallel machines. By time-sharing the resources, the system interleaves production and interactive jobs. Immediate priority is given to interactive use, maintaining good response time. Production jobs are scheduled during idle periods, making use of the otherwise unused resources. In this paper the authors discuss their experience with gang scheduling over the 3 year life-time of the project. In section 2, they motivate the project and discuss some of its details. Section 3.0 describes the general scheduling problem and how gang scheduling addresses it. In section 4.0, they describe the implementation. Section 8.0 presents results culled over the lifetime of the project. They conclude this paper with some observations and possible future directions.
Linear Time Vertex Partitioning on Massive Graphs
Mell, Peter; Harang, Richard; Gueye, Assane
2016-01-01
The problem of optimally removing a set of vertices from a graph to minimize the size of the largest resultant component is known to be NP-complete. Prior work has provided near optimal heuristics with a high time complexity that function on up to hundreds of nodes and less optimal but faster techniques that function on up to thousands of nodes. In this work, we analyze how to perform vertex partitioning on massive graphs of tens of millions of nodes. We use a previously known and very simple heuristic technique: iteratively removing the node of largest degree and all of its edges. This approach has an apparent quadratic complexity since, upon removal of a node and adjoining set of edges, the node degree calculations must be updated prior to choosing the next node. However, we describe a linear time complexity solution using an array whose indices map to node degree and whose values are hash tables indicating the presence or absence of a node at that degree value. This approach also has a linear growth with respect to memory usage which is surprising since we lowered the time complexity from quadratic to linear. We empirically demonstrate linear scalability and linear memory usage on random graphs of up to 15000 nodes. We then demonstrate tractability on massive graphs through execution on a graph with 34 million nodes representing Internet wide router connectivity. PMID:27336059
Time series with tailored nonlinearities.
Räth, C; Laut, I
2015-10-01
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 uncorrelated 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. PMID:26565155
Time series with tailored nonlinearities
NASA Astrophysics Data System (ADS)
Räth, C.; Laut, I.
2015-10-01
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 uncorrelated 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.
ERIC Educational Resources Information Center
Bos, Theodore; Culver, Sarah E.
2000-01-01
Describes the Economagic Web site, a comprehensive site of free economic time-series data that can be used for research and instruction. Explains that it contains 100,000+ economic data series from sources such as the Federal Reserve Banking System, the Census Bureau, and the Department of Commerce. (CMK)
DETECTING MASSIVE GRAVITONS USING PULSAR TIMING ARRAYS
Lee, Kejia; Kramer, Michael; Jenet, Fredrick A.; Price, Richard H.; Wex, Norbert
2010-10-20
At the limit of weak static fields, general relativity becomes Newtonian gravity with a potential field that falls off as inverse distance rather than a theory of Yukawa-type fields with a finite range. General relativity also predicts that the speed of disturbances of its waves is c, the vacuum light speed, and is non-dispersive. For these reasons, the graviton, the boson for general relativity, can be considered to be massless. Massive gravitons, however, are features of some alternatives to general relativity. This has motivated experiments and observations that, so far, have been consistent with the zero-mass graviton of general relativity, but further tests will be valuable. A basis for new tests may be the high sensitivity gravitational wave (GW) experiments that are now being performed and the higher sensitivity experiments that are being planned. In these experiments, it should be feasible to detect low levels of dispersion due to non-zero graviton mass. One of the most promising techniques for such a detection may be the pulsar timing program that is sensitive to nano-Hertz GWs. Here, we present some details of such a detection scheme. The pulsar timing response to a GW background with the massive graviton is calculated, and the algorithm to detect the massive graviton is presented. We conclude that, with 90% probability, massless gravitons can be distinguished from gravitons heavier than 3 x 10{sup -22} eV (Compton wavelength {lambda}{sub g} = 4.1 x 10{sup 12} km), if bi-weekly observation of 60 pulsars is performed for 5 years with a pulsar rms timing accuracy of 100 ns. If 60 pulsars are observed for 10 years with the same accuracy, the detectable graviton mass is reduced to 5 x 10{sup -23} eV ({lambda}{sub g} = 2.5 x 10{sup 13} km); for 5 year observations of 100 or 300 pulsars, the sensitivity is respectively 2.5 x 10{sup -22} ({lambda}{sub g} = 5.0 x 10{sup 12} km) and 10{sup -22} eV ({lambda}{sub g} = 1.2 x 10{sup 13} km). Finally, a 10 year
Entropy of electromyography time series
NASA Astrophysics Data System (ADS)
Kaufman, Miron; Zurcher, Ulrich; Sung, Paul S.
2007-12-01
A nonlinear analysis based on Renyi entropy is applied to electromyography (EMG) time series from back muscles. The time dependence of the entropy of the EMG signal exhibits a crossover from a subdiffusive regime at short times to a plateau at longer times. We argue that this behavior characterizes complex biological systems. The plateau value of the entropy can be used to differentiate between healthy and low back pain individuals.
The rationale for chemical time-series sampling has its roots in the same fundamental relationships as govern well hydraulics. Samples of ground water are collected as a function of increasing time of pumpage. The most efficient pattern of collection consists of logarithmically s...
Random time series in astronomy.
Vaughan, Simon
2013-02-13
Progress in astronomy comes from interpreting the signals encoded in the light received from distant objects: the distribution of light over the sky (images), over photon wavelength (spectrum), over polarization angle and over time (usually called light curves by astronomers). In the time domain, we see transient events such as supernovae, gamma-ray bursts and other powerful explosions; we see periodic phenomena such as the orbits of planets around nearby stars, radio pulsars and pulsations of stars in nearby galaxies; and we see persistent aperiodic variations ('noise') from powerful systems such as accreting black holes. I review just a few of the recent and future challenges in the burgeoning area of time domain astrophysics, with particular attention to persistently variable sources, the recovery of reliable noise power spectra from sparsely sampled time series, higher order properties of accreting black holes, and time delays and correlations in multi-variate time series. PMID:23277606
Inductive time series modeling program
Kirk, B.L.; Rust, B.W.
1985-10-01
A number of features that comprise environmental time series share a common mathematical behavior. Analysis of the Mauna Loa carbon dioxide record and other time series is aimed at constructing mathematical functions which describe as many major features of the data as possible. A trend function is fit to the data, removed, and the resulting residuals analyzed for any significant behavior. This is repeated until the residuals are driven to white noise. In the following discussion, the concept of trend will include cyclic components. The mathematical tools and program packages used are VARPRO (Golub and Pereyra 1973), for the least squares fit, and a modified version of our spectral analysis program (Kirk et al. 1979), for spectrum and noise analysis. The program is written in FORTRAN. All computations are done in double precision, except for the plotting calls where the DISSPLA package is used. The core requirement varies between 600 K and 700 K. The program is implemented on the IBM 360/370. Currently, the program can analyze up to five different time series where each series contains no more than 300 points. 12 refs.
Massive subchorionic thrombohematoma: a series of 10 cases.
Fung, Tak Yuen; To, Ka Fai; Sahota, Daljit Singh; Chan, Lin Wai; Leung, Tak Yeung; Lau, Tze Kin
2010-10-01
A retrospective audit identified 10 cases of massive idiopathic subchorionic thrombohematoma. The incidence was 1:3,133. Only six of these pregnancies resulted in a livebirth and only two reached term. In eight cases there were ultrasound abnormalities, including two cases of placentomegaly both of which resulted in a pregnancy loss. There was one placental abruption. Seven of the women were nulliparous. Massive subchorionic thrombohematoma is associated with poor pregnancy outcome. Ultrasound findings of placentomegaly might be a bad prognostic sign. PMID:20846069
High Performance Biomedical Time Series Indexes Using Salient Segmentation
Woodbridge, Jonathan; Mortazavi, Bobak; Bui, Alex A.T.; Sarrafzadeh, Majid
2016-01-01
The advent of remote and wearable medical sensing has created a dire need for efficient medical time series databases. Wearable medical sensing devices provide continuous patient monitoring by various types of sensors and have the potential to create massive amounts of data. Therefore, time series databases must utilize highly optimized indexes in order to efficiently search and analyze stored data. This paper presents a highly efficient technique for indexing medical time series signals using Locality Sensitive Hashing (LSH). Unlike previous work, only salient (or interesting) segments are inserted into the index. This technique reduces search times by up to 95% while yielding near identical search results. PMID:23367072
Introduction to Time Series Analysis
NASA Technical Reports Server (NTRS)
Hardin, J. C.
1986-01-01
The field of time series analysis is explored from its logical foundations to the most modern data analysis techniques. The presentation is developed, as far as possible, for continuous data, so that the inevitable use of discrete mathematics is postponed until the reader has gained some familiarity with the concepts. The monograph seeks to provide the reader with both the theoretical overview and the practical details necessary to correctly apply the full range of these powerful techniques. In addition, the last chapter introduces many specialized areas where research is currently in progress.
Hydrodynamic analysis of time series
NASA Astrophysics Data System (ADS)
Suciu, N.; Vamos, C.; Vereecken, H.; Vanderborght, J.
2003-04-01
It was proved that balance equations for systems with corpuscular structure can be derived if a kinematic description by piece-wise analytic functions is available [1]. For example, the hydrodynamic equations for one-dimensional systems of inelastic particles, derived in [2], were used to prove the inconsistency of the Fourier law of heat with the microscopic structure of the system. The hydrodynamic description is also possible for single particle systems. In this case, averages of physical quantities associated with the particle, over a space-time window, generalizing the usual ``moving averages'' which are performed on time intervals only, were shown to be almost everywhere continuous space-time functions. Moreover, they obey balance partial differential equations (continuity equation for the 'concentration', Navier-Stokes equation, a. s. o.) [3]. Time series can be interpreted as trajectories in the space of the recorded parameter. Their hydrodynamic interpretation is expected to enable deterministic predictions, when closure relations can be obtained for the balance equations. For the time being, a first result is the estimation of the probability density for the occurrence of a given parameter value, by the normalized concentration field from the hydrodynamic description. The method is illustrated by hydrodynamic analysis of three types of time series: white noise, stock prices from financial markets and groundwater levels recorded at Krauthausen experimental field of Forschungszentrum Jülich (Germany). [1] C. Vamoş, A. Georgescu, N. Suciu, I. Turcu, Physica A 227, 81-92, 1996. [2] C. Vamoş, N. Suciu, A. Georgescu, Phys. Rev E 55, 5, 6277-6280, 1997. [3] C. Vamoş, N. Suciu, W. Blaj, Physica A, 287, 461-467, 2000.
Multiple Indicator Stationary Time Series Models.
ERIC Educational Resources Information Center
Sivo, Stephen A.
2001-01-01
Discusses the propriety and practical advantages of specifying multivariate time series models in the context of structural equation modeling for time series and longitudinal panel data. For time series data, the multiple indicator model specification improves on classical time series analysis. For panel data, the multiple indicator model…
Analysis of time series from stochastic processes
Gradisek; Siegert; Friedrich; Grabec
2000-09-01
Analysis of time series from stochastic processes governed by a Langevin equation is discussed. Several applications for the analysis are proposed based on estimates of drift and diffusion coefficients of the Fokker-Planck equation. The coefficients are estimated directly from a time series. The applications are illustrated by examples employing various synthetic time series and experimental time series from metal cutting. PMID:11088809
Massive localized lymphedema: A case series and literature review.
Evans, Robin James; Scilley, Chris
2011-01-01
A large, deep, soft tissue mass is often malignant in nature; however, a recent study described a large soft tissue mass present in morbidly obese patients that was found to be benign. Massive localized lymphedema (MLL) is a large pedunculated lymphadematous mass found in the lower extremity of morbidly obese patients. MLL often enlarges over many years and may interfere with mobility. Although histologically similar to well-differentiated liposarcoma, MLL has recently emerged as a separate, benign clinical entity. The pathophysiology of MLL is yet to be understood. A literature review, and the authors' experiences are discussed to assist in clinical decision making. PMID:22942667
Multivariate Time Series Similarity Searching
Wang, Jimin; Zhu, Yuelong; Li, Shijin; Wan, Dingsheng; Zhang, Pengcheng
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 searching method. Several experiments, which used the classification accuracy as a measure, were performed on six datasets from the UCI KDD Archive to validate the method. The results show the advantage of the approach compared to the traditional similarity measures, such as Euclidean distance (ED), cynamic time warping (DTW), point distribution (PD), PCA similarity factor (SPCA), and extended Frobenius norm (Eros), for MTS datasets in some ways. Our experiments also demonstrate that no measure can fit all datasets, and the proposed measure is a choice for similarity searches. PMID:24895665
Multivariate time series similarity searching.
Wang, Jimin; Zhu, Yuelong; Li, Shijin; Wan, Dingsheng; Zhang, Pengcheng
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 searching method. Several experiments, which used the classification accuracy as a measure, were performed on six datasets from the UCI KDD Archive to validate the method. The results show the advantage of the approach compared to the traditional similarity measures, such as Euclidean distance (ED), cynamic time warping (DTW), point distribution (PD), PCA similarity factor (SPCA), and extended Frobenius norm (Eros), for MTS datasets in some ways. Our experiments also demonstrate that no measure can fit all datasets, and the proposed measure is a choice for similarity searches. PMID:24895665
A review of subsequence time series clustering.
Zolhavarieh, Seyedjamal; Aghabozorgi, Saeed; Teh, Ying Wah
2014-01-01
Clustering of subsequence time series remains an open issue in time series clustering. Subsequence time series clustering is used in different fields, such as e-commerce, outlier detection, speech recognition, biological systems, DNA recognition, and text mining. One of the useful fields in the domain of subsequence time series clustering is pattern recognition. To improve this field, a sequence of time series data is used. This paper reviews some definitions and backgrounds related to subsequence time series clustering. The categorization of the literature reviews is divided into three groups: preproof, interproof, and postproof period. Moreover, various state-of-the-art approaches in performing subsequence time series clustering are discussed under each of the following categories. The strengths and weaknesses of the employed methods are evaluated as potential issues for future studies. PMID:25140332
A Review of Subsequence Time Series Clustering
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
Translation invariant time-dependent solutions to massive gravity
Mourad, J.; Steer, D.A. E-mail: steer@apc.univ-paris7.fr
2013-12-01
Homogeneous time-dependent solutions of massive gravity generalise the plane wave solutions of the linearised Fierz-Pauli equations for a massive spin-two particle, as well as the Kasner solutions of General Relativity. We show that they also allow a clear counting of the degrees of freedom and represent a simplified framework to work out the constraints, the equations of motion and the initial value formulation. We work in the vielbein formulation of massive gravity, find the phase space resulting from the constraints and show that several disconnected sectors of solutions exist some of which are unstable. The initial values determine the sector to which a solution belongs. Classically, the theory is not pathological but quantum mechanically the theory may suffer from instabilities. The latter are not due to an extra ghost-like degree of freedom.
Nonparametric causal inference for bivariate time series
NASA Astrophysics Data System (ADS)
McCracken, James M.; Weigel, Robert S.
2016-02-01
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.
Forecasting Enrollments with Fuzzy Time Series.
ERIC Educational Resources Information Center
Song, Qiang; Chissom, Brad S.
The concept of fuzzy time series is introduced and used to forecast the enrollment of a university. Fuzzy time series, an aspect of fuzzy set theory, forecasts enrollment using a first-order time-invariant model. To evaluate the model, the conventional linear regression technique is applied and the predicted values obtained are compared to the…
Statistical criteria for characterizing irradiance time series.
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.
Generation of artificial helioseismic time-series
NASA Technical Reports Server (NTRS)
Schou, J.; Brown, T. M.
1993-01-01
We present an outline of an algorithm to generate artificial helioseismic time-series, taking into account as much as possible of the knowledge we have on solar oscillations. The hope is that it will be possible to find the causes of some of the systematic errors in analysis algorithms by testing them with such artificial time-series.
Salient Segmentation of Medical Time Series Signals
Woodbridge, Jonathan; Lan, Mars; Sarrafzadeh, Majid; Bui, Alex
2016-01-01
Searching and mining medical time series databases is extremely challenging due to large, high entropy, and multidimensional datasets. Traditional time series databases are populated using segments extracted by a sliding window. The resulting database index contains an abundance of redundant time series segments with little to no alignment. This paper presents the idea of “salient segmentation”. Salient segmentation is a probabilistic segmentation technique for populating medical time series databases. Segments with the lowest probabilities are considered salient and are inserted into the index. The resulting index has little redundancy and is composed of aligned segments. This approach reduces index sizes by more than 98% over conventional sliding window techniques. Furthermore, salient segmentation can reduce redundancy in motif discovery algorithms by more than 85%, yielding a more succinct representation of a time series signal.
Entropic Analysis of Electromyography Time Series
NASA Astrophysics Data System (ADS)
Kaufman, Miron; Sung, Paul
2005-03-01
We are in the process of assessing the effectiveness of fractal and entropic measures for the diagnostic of low back pain from surface electromyography (EMG) time series. Surface electromyography (EMG) is used to assess patients with low back pain. In a typical EMG measurement, the voltage is measured every millisecond. We observed back muscle fatiguing during one minute, which results in a time series with 60,000 entries. We characterize the complexity of time series by computing the Shannon entropy time dependence. The analysis of the time series from different relevant muscles from healthy and low back pain (LBP) individuals provides evidence that the level of variability of back muscle activities is much larger for healthy individuals than for individuals with LBP. In general the time dependence of the entropy shows a crossover from a diffusive regime to a regime characterized by long time correlations (self organization) at about 0.01s.
Biclustering of time series microarray data.
Meng, Jia; Huang, Yufei
2012-01-01
Clustering is a popular data exploration technique widely used in microarray data analysis. In this chapter, we review ideas and algorithms of bicluster and its applications in time series microarray analysis. We introduce first the concept and importance of biclustering and its different variations. We then focus our discussion on the popular iterative signature algorithm (ISA) for searching biclusters in microarray dataset. Next, we discuss in detail the enrichment constraint time-dependent ISA (ECTDISA) for identifying biologically meaningful temporal transcription modules from time series microarray dataset. In the end, we provide an example of ECTDISA application to time series microarray data of Kaposi's Sarcoma-associated Herpesvirus (KSHV) infection. PMID:22130875
Homogenising time series: beliefs, dogmas and facts
NASA Astrophysics Data System (ADS)
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.
Modeling Time Series Data for Supervised Learning
ERIC Educational Resources Information Center
Baydogan, Mustafa Gokce
2012-01-01
Temporal data are increasingly prevalent and important in analytics. Time series (TS) data are chronological sequences of observations and an important class of temporal data. Fields such as medicine, finance, learning science and multimedia naturally generate TS data. Each series provide a high-dimensional data vector that challenges the learning…
Developing consistent time series landsat data products
Technology Transfer Automated Retrieval System (TEKTRAN)
The Landsat series satellite has provided earth observation data record continuously since early 1970s. There are increasing demands on having a consistent time series of Landsat data products. In this presentation, I will summarize the work supported by the USGS Landsat Science Team project from 20...
Visibility Graph Based Time Series Analysis
Stephen, Mutua; Gu, Changgui; Yang, Huijie
2015-01-01
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. PMID:26571115
Measuring nonlinear behavior in time series data
NASA Astrophysics Data System (ADS)
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.
Advanced spectral methods for climatic time series
Ghil, M.; Allen, M.R.; Dettinger, M.D.; Ide, K.; Kondrashov, D.; Mann, M.E.; Robertson, A.W.; Saunders, A.; Tian, Y.; Varadi, F.; Yiou, P.
2002-01-01
The analysis of univariate or multivariate time series provides crucial information to describe, understand, and predict climatic variability. The discovery and implementation of a number of novel methods for extracting useful information from time series has recently revitalized this classical field of study. Considerable progress has also been made in interpreting the information so obtained in terms of dynamical systems theory. In this review we describe the connections between time series analysis and nonlinear dynamics, discuss signal- to-noise enhancement, and present some of the novel methods for spectral analysis. The various steps, as well as the advantages and disadvantages of these methods, are illustrated by their application to an important climatic time series, the Southern Oscillation Index. This index captures major features of interannual climate variability and is used extensively in its prediction. Regional and global sea surface temperature data sets are used to illustrate multivariate spectral methods. Open questions and further prospects conclude the review.
Complex network approach to fractional time series
NASA Astrophysics Data System (ADS)
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.
Detecting nonlinear structure in time series
Theiler, J.
1991-01-01
We describe an approach for evaluating the statistical significance of evidence for nonlinearity in a time series. The formal application of our method requires the careful statement of a null hypothesis which characterizes a candidate linear process, the generation of an ensemble of surrogate'' data sets which are similar to the original time series but consistent with the null hypothesis, and the computation of a discriminating statistic for the original and for each of the surrogate data sets. The idea is to test the original time series against the null hypothesis by checking whether the discriminating statistic computed for the original time series differs significantly from the statistics computed for each of the surrogate sets. While some data sets very cleanly exhibit low-dimensional chaos, there are many cases where the evidence is sketchy and difficult to evaluate. We hope to provide a framework within which such claims of nonlinearity can be evaluated. 5 refs., 4 figs.
Nonlinear Analysis of Surface EMG Time Series
NASA Astrophysics Data System (ADS)
Zurcher, Ulrich; Kaufman, Miron; Sung, Paul
2004-04-01
Applications of nonlinear analysis of surface electromyography time series of patients with and without low back pain are presented. Limitations of the standard methods based on the power spectrum are discussed.
Complex network approach to fractional time series
Manshour, Pouya
2015-10-15
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.
Homogenising time series: Beliefs, dogmas and facts
NASA Astrophysics Data System (ADS)
Domonkos, P.
2010-09-01
For obtaining reliable information about climate change and climate variability the use of high quality data series is essentially important, and one basic tool of quality improvements is the statistical homogenisation of observed time series. In the recent decades large number of homogenisation methods has been developed, but the real effects of their application on time series are still not known entirely. The ongoing COST HOME project (COST ES0601) is devoted to reveal the real impacts of homogenisation methods more detailed and with higher confidence than earlier. As 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 to test the wide variety of homogenisation methods, and analyse the real effects of selected theoretical recommendations. The author believes that several old theoretical rules have to be re-evaluated. Some examples of the hot questions, a) Statistically detected change-points can be accepted only with the confirmation of metadata information? b) Do semi-hierarchic algorithms for detecting multiple change-points in time series function effectively in practise? c) Is it good to limit the spatial comparison of candidate series with up to five other series in the neighbourhood? Empirical results - those from the COST benchmark, and other experiments too - show that real observed time series usually include several inhomogeneities of different sizes. Small inhomogeneities seem like part of the climatic variability, thus the pure application of 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. The developers and users of homogenisation methods have to bear in mind that
Translation invariant time-dependent solutions to massive gravity II
Mourad, J.; Steer, D.A. E-mail: steer@apc.univ-paris7.fr
2014-06-01
This paper is a sequel to JCAP 12 (2013) 004 and is also devoted to translation-invariant solutions of ghost-free massive gravity in its moving frame formulation. Here we consider a mass term which is linear in the vielbein (corresponding to a β{sub 3} term in the 4D metric formulation) in addition to the cosmological constant. We determine explicitly the constraints, and from the initial value formulation show that the time-dependent solutions can have singularities at a finite time. Although the constraints give, as in the β{sub 1} case, the correct number of degrees of freedom for a massive spin two field, we show that the lapse function can change sign at a finite time causing a singular time evolution. This is very different to the β{sub 1} case where time evolution is always well defined. We conclude that the β{sub 3} mass term can be pathological and should be treated with care.
Detecting chaos in irregularly sampled time series.
Kulp, C W
2013-09-01
Recently, Wiebe and Virgin [Chaos 22, 013136 (2012)] developed an algorithm which detects chaos by analyzing a time series' power spectrum which is computed using the Discrete Fourier Transform (DFT). Their algorithm, like other time series characterization algorithms, requires that the time series be regularly sampled. Real-world data, however, are often irregularly sampled, thus, making the detection of chaotic behavior difficult or impossible with those methods. In this paper, a characterization algorithm is presented, which effectively detects chaos in irregularly sampled time series. The work presented here is a modification of Wiebe and Virgin's algorithm and uses the Lomb-Scargle Periodogram (LSP) to compute a series' power spectrum instead of the DFT. The DFT is not appropriate for irregularly sampled time series. However, the LSP is capable of computing the frequency content of irregularly sampled data. Furthermore, a new method of analyzing the power spectrum is developed, which can be useful for differentiating between chaotic and non-chaotic behavior. The new characterization algorithm is successfully applied to irregularly sampled data generated by a model as well as data consisting of observations of variable stars. PMID:24089946
Heuristic segmentation of a nonstationary time series
NASA Astrophysics Data System (ADS)
Fukuda, Kensuke; Eugene Stanley, H.; Nunes Amaral, Luís A.
2004-02-01
Many phenomena, both natural and human influenced, give rise to signals whose statistical properties change under time translation, i.e., are nonstationary. For some practical purposes, a nonstationary time series can be seen as a concatenation of stationary segments. However, the exact segmentation of a nonstationary time series is a hard computational problem which cannot be solved exactly by existing methods. For this reason, heuristic methods have been proposed. Using one such method, it has been reported that for several cases of interest—e.g., heart beat data and Internet traffic fluctuations—the distribution of durations of these stationary segments decays with a power-law tail. A potential technical difficulty that has not been thoroughly investigated is that a nonstationary time series with a (scalefree) power-law distribution of stationary segments is harder to segment than other nonstationary time series because of the wider range of possible segment lengths. Here, we investigate the validity of a heuristic segmentation algorithm recently proposed by Bernaola-Galván et al. [Phys. Rev. Lett. 87, 168105 (2001)] by systematically analyzing surrogate time series with different statistical properties. We find that if a given nonstationary time series has stationary periods whose length is distributed as a power law, the algorithm can split the time series into a set of stationary segments with the correct statistical properties. We also find that the estimated power-law exponent of the distribution of stationary-segment lengths is affected by (i) the minimum segment length and (ii) the ratio R≡σɛ/σx¯, where σx¯ is the standard deviation of the mean values of the segments and σɛ is the standard deviation of the fluctuations within a segment. Furthermore, we determine that the performance of the algorithm is generally not affected by uncorrelated noise spikes or by weak long-range temporal correlations of the fluctuations within segments.
Forbidden patterns in financial time series.
Zanin, Massimiliano
2008-03-01
The existence of forbidden patterns, i.e., certain missing sequences in a given time series, is a recently proposed instrument of potential application in the study of time series. Forbidden patterns are related to the permutation entropy, which has the basic properties of classic chaos indicators, such as Lyapunov exponent or Kolmogorov entropy, thus allowing to separate deterministic (usually chaotic) from random series; however, it requires fewer values of the series to be calculated, and it is suitable for using with small datasets. In this paper, the appearance of forbidden patterns is studied in different economical indicators such as stock indices (Dow Jones Industrial Average and Nasdaq Composite), NYSE stocks (IBM and Boeing), and others (ten year Bond interest rate), to find evidence of deterministic behavior in their evolutions. Moreover, the rate of appearance of the forbidden patterns is calculated, and some considerations about the underlying dynamics are suggested. PMID:18377070
Development of an IUE Time Series Browser
NASA Technical Reports Server (NTRS)
Massa, Derck
2005-01-01
The International Ultraviolet Explorer (IUE) satellite operated successfully for more than 17 years. Its archive of more than 100,000 science exposures is widely acknowledged as an invaluable scientific resource that will not be duplicated in the foreseeable future. We have searched this archive for objects which were observed 10 or more times with the same spectral dispersion and wavelength coverage over the lifetime of IUE. Using this definition of a time series, we find that roughly half of the science exposures are members of such time series. This paper describes a WEB-based IUE time series browser which enables the user to visually inspect the repeated observations for variability and to examine each member spectrum individually. Further, if the researcher determines that a specific data set is worthy of further investigation, it can be easily downloaded for further, detailed analysis.
Learning time series for intelligent monitoring
NASA Technical Reports Server (NTRS)
Manganaris, Stefanos; Fisher, Doug
1994-01-01
We address the problem of classifying time series according to their morphological features in the time domain. In a supervised machine-learning framework, we induce a classification procedure from a set of preclassified examples. For each class, we infer a model that captures its morphological features using Bayesian model induction and the minimum message length approach to assign priors. In the performance task, we classify a time series in one of the learned classes when there is enough evidence to support that decision. Time series with sufficiently novel features, belonging to classes not present in the training set, are recognized as such. We report results from experiments in a monitoring domain of interest to NASA.
Predicting road accidents: Structural time series approach
NASA Astrophysics Data System (ADS)
Junus, Noor Wahida Md; Ismail, Mohd Tahir
2014-07-01
In this paper, the model for occurrence of road accidents in Malaysia between the years of 1970 to 2010 was developed and throughout this model the number of road accidents have been predicted by using the structural time series approach. The models are developed by using stepwise method and the residual of each step has been analyzed. The accuracy of the model is analyzed by using the mean absolute percentage error (MAPE) and the best model is chosen based on the smallest Akaike information criterion (AIC) value. A structural time series approach found that local linear trend model is the best model to represent the road accidents. This model allows level and slope component to be varied over time. In addition, this approach also provides useful information on improving the conventional time series method.
Integrated method for chaotic time series analysis
Hively, L.M.; Ng, E.G.
1998-09-29
Methods and apparatus for automatically detecting differences between similar but different states in a nonlinear process monitor nonlinear data are disclosed. Steps include: acquiring the data; digitizing the data; obtaining nonlinear measures of the data via chaotic time series analysis; obtaining time serial trends in the nonlinear measures; and determining by comparison whether differences between similar but different states are indicated. 8 figs.
Integrated method for chaotic time series analysis
Hively, Lee M.; Ng, Esmond G.
1998-01-01
Methods and apparatus for automatically detecting differences between similar but different states in a nonlinear process monitor nonlinear data. Steps include: acquiring the data; digitizing the data; obtaining nonlinear measures of the data via chaotic time series analysis; obtaining time serial trends in the nonlinear measures; and determining by comparison whether differences between similar but different states are indicated.
Building Chaotic Model From Incomplete Time Series
NASA Astrophysics Data System (ADS)
Siek, Michael; Solomatine, Dimitri
2010-05-01
This paper presents a number of novel techniques for building a predictive chaotic model from incomplete time series. A predictive chaotic model is built by reconstructing the time-delayed phase space from observed time series and the prediction is made by a global model or adaptive local models based on the dynamical neighbors found in the reconstructed phase space. In general, the building of any data-driven models depends on the completeness and quality of the data itself. However, the completeness of the data availability can not always be guaranteed since the measurement or data transmission is intermittently not working properly due to some reasons. We propose two main solutions dealing with incomplete time series: using imputing and non-imputing methods. For imputing methods, we utilized the interpolation methods (weighted sum of linear interpolations, Bayesian principle component analysis and cubic spline interpolation) and predictive models (neural network, kernel machine, chaotic model) for estimating the missing values. After imputing the missing values, the phase space reconstruction and chaotic model prediction are executed as a standard procedure. For non-imputing methods, we reconstructed the time-delayed phase space from observed time series with missing values. This reconstruction results in non-continuous trajectories. However, the local model prediction can still be made from the other dynamical neighbors reconstructed from non-missing values. We implemented and tested these methods to construct a chaotic model for predicting storm surges at Hoek van Holland as the entrance of Rotterdam Port. The hourly surge time series is available for duration of 1990-1996. For measuring the performance of the proposed methods, a synthetic time series with missing values generated by a particular random variable to the original (complete) time series is utilized. There exist two main performance measures used in this work: (1) error measures between the actual
Fractal and natural time analysis of geoelectrical time series
NASA Astrophysics Data System (ADS)
Ramirez Rojas, A.; Moreno-Torres, L. R.; Cervantes, F.
2013-05-01
In this work we show the analysis of geoelectric time series linked with two earthquakes of M=6.6 and M=7.4. That time series were monitored at the South Pacific Mexican coast, which is the most important active seismic subduction zone in México. The geolectric time series were analyzed by using two complementary methods: a fractal analysis, by means of the detrended fluctuation analysis (DFA) in the conventional time, and the power spectrum defined in natural time domain (NTD). In conventional time we found long-range correlations prior to the EQ-occurrences and simultaneously in NTD, the behavior of the power spectrum suggest the possible existence of seismo electric signals (SES) similar with the previously reported in equivalent time series monitored in Greece prior to earthquakes of relevant magnitude.
Layered Ensemble Architecture for Time Series Forecasting.
Rahman, Md Mustafizur; Islam, Md Monirul; Murase, Kazuyuki; Yao, Xin
2016-01-01
Time series forecasting (TSF) has been widely used in many application areas such as science, engineering, and finance. The phenomena generating time series are usually unknown and information available for forecasting is only limited to the past values of the series. It is, therefore, necessary to use an appropriate number of past values, termed lag, for forecasting. This paper proposes a layered ensemble architecture (LEA) for TSF problems. Our LEA consists of two layers, each of which uses an ensemble of multilayer perceptron (MLP) networks. While the first ensemble layer tries to find an appropriate lag, the second ensemble layer employs the obtained lag for forecasting. Unlike most previous work on TSF, the proposed architecture considers both accuracy and diversity of the individual networks in constructing an ensemble. LEA trains different networks in the ensemble by using different training sets with an aim of maintaining diversity among the networks. However, it uses the appropriate lag and combines the best trained networks to construct the ensemble. This indicates LEAs emphasis on accuracy of the networks. The proposed architecture has been tested extensively on time series data of neural network (NN)3 and NN5 competitions. It has also been tested on several standard benchmark time series data. In terms of forecasting accuracy, our experimental results have revealed clearly that LEA is better than other ensemble and nonensemble methods. PMID:25751882
Climate Time Series Analysis and Forecasting
NASA Astrophysics Data System (ADS)
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.
Intrinsic superstatistical components of financial time series
NASA Astrophysics Data System (ADS)
Vamoş, Călin; Crăciun, Maria
2014-12-01
Time series generated by a complex hierarchical system exhibit various types of dynamics at different time scales. A financial time series is an example of such a multiscale structure with time scales ranging from minutes to several years. In this paper we decompose the volatility of financial indices into five intrinsic components and we show that it has a heterogeneous scale structure. The small-scale components have a stochastic nature and they are independent 99% of the time, becoming synchronized during financial crashes and enhancing the heavy tails of the volatility distribution. The deterministic behavior of the large-scale components is related to the nonstationarity of the financial markets evolution. Our decomposition of the financial volatility is a superstatistical model more complex than those usually limited to a superposition of two independent statistics at well-separated time scales.
Characterization of Experimental Chaotic Time Series
NASA Astrophysics Data System (ADS)
Tomlin, Brett; Olsen, Thomas; Callan, Kristine; Wiener, Richard
2004-05-01
Correlation dimension and Lyapunov dimension are complementary measures of the strength of the chaotic dynamics of a nonlinear system. Long time series were obtained from experiment, both in a modified Taylor-Couette fluid flow apparatus and a non-linear electronic circuit. The irregular generation of Taylor Vortex Pairs in Taylor-Couette flow with hourglass geometry has previously demonstrated low dimensional chaos( T. Olsen, R. Bjorge, & R. Wiener, Bull. Am. Phys. Soc. 47-10), 76 (2002).. The non-linear circuit allows for the acquisition of very large time series and serves as test case for the numerical procedures. Details of the calculation and results are presented.
Clustering Short Time-Series Microarray
NASA Astrophysics Data System (ADS)
Ping, Loh Wei; Hasan, Yahya Abu
2008-01-01
Most microarray analyses are carried out on static gene expressions. However, the dynamical study of microarrays has lately gained more attention. Most researches on time-series microarray emphasize on the bioscience and medical aspects but few from the numerical aspect. This study attempts to analyze short time-series microarray mathematically using STEM clustering tool which formally preprocess data followed by clustering. We next introduce the Circular Mould Distance (CMD) algorithm with combinations of both preprocessing and clustering analysis. Both methods are subsequently compared in terms of efficiencies.
Detecting smoothness in noisy time series
Cawley, R.; Hsu, G.; Salvino, L.W.
1996-06-01
We describe the role of chaotic noise reduction in detecting an underlying smoothness in a dataset. We have described elsewhere a general method for assessing the presence of determinism in a time series, which is to test against the class of datasets producing smoothness (i.e., the null hypothesis is determinism). In order to reduce the likelihood of a false call, we recommend this kind of analysis be applied first to a time series whose deterministic origin is at question. We believe this step should be taken before implementing other methods of dynamical analysis and measurement, such as correlation dimension or Lyapounov spectrum. {copyright} {ital 1996 American Institute of Physics.}
TimeSeer: Scagnostics for high-dimensional time series.
Dang, Tuan Nhon; Anand, Anushka; Wilkinson, Leland
2013-03-01
We introduce a method (Scagnostic time series) and an application (TimeSeer) for organizing multivariate time series and for guiding interactive exploration through high-dimensional data. The method is based on nine characterizations of the 2D distributions of orthogonal pairwise projections on a set of points in multidimensional euclidean space. These characterizations include measures, such as, density, skewness, shape, outliers, and texture. Working directly with these Scagnostic measures, we can locate anomalous or interesting subseries for further analysis. Our application is designed to handle the types of doubly multivariate data series that are often found in security, financial, social, and other sectors. PMID:23307611
Multifractal analysis of polyalanines time series
NASA Astrophysics Data System (ADS)
Figueirêdo, P. H.; Nogueira, E.; Moret, M. A.; Coutinho, Sérgio
2010-05-01
Multifractal properties of the energy time series of short α-helix structures, specifically from a polyalanine family, are investigated through the MF-DFA technique ( multifractal detrended fluctuation analysis). Estimates for the generalized Hurst exponent h(q) and its associated multifractal exponents τ(q) are obtained for several series generated by numerical simulations of molecular dynamics in different systems from distinct initial conformations. All simulations were performed using the GROMOS force field, implemented in the program THOR. The main results have shown that all series exhibit multifractal behavior depending on the number of residues and temperature. Moreover, the multifractal spectra reveal important aspects of the time evolution of the system and suggest that the nucleation process of the secondary structures during the visits on the energy hyper-surface is an essential feature of the folding process.
Directionality volatility in electroencephalogram time series
NASA Astrophysics Data System (ADS)
Mansor, Mahayaudin M.; Green, David A.; Metcalfe, Andrew V.
2016-06-01
We compare time series of electroencephalograms (EEGs) from healthy volunteers with EEGs from subjects diagnosed with epilepsy. The EEG time series from the healthy group are recorded during awake state with their eyes open and eyes closed, and the records from subjects with epilepsy are taken from three different recording regions of pre-surgical diagnosis: hippocampal, epileptogenic and seizure zone. The comparisons for these 5 categories are in terms of deviations from linear time series models with constant variance Gaussian white noise error inputs. One feature investigated is directionality, and how this can be modelled by either non-linear threshold autoregressive models or non-Gaussian errors. A second feature is volatility, which is modelled by Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) processes. Other features include the proportion of variability accounted for by time series models, and the skewness and the kurtosis of the residuals. The results suggest these comparisons may have diagnostic potential for epilepsy and provide early warning of seizures.
Topological analysis of chaotic time series
NASA Astrophysics Data System (ADS)
Gilmore, Robert
1997-10-01
Topological methods have recently been developed for the classification, analysis, and synthesis of chaotic time series. These methods can be applied to time series with a Lyapunov dimension less than three. The procedure determines the stretching and squeezing mechanisms which operate to create a strange attractor and organize all the unstable periodic orbits in the attractor in a unique way. Strange attractors are identified by a set of integers. These are topological invariants for a two dimensional branched manifold, which is the infinite dissipation limit of the strange attractor. It is remarkable that this topological information can be extracted from chaotic time series. The data required for this analysis need not be extensive or exceptionally clean. The topological invariants: (1) are subject to validation/invalidation tests; (2) describe how to model the data; and (3) do not change as control parameters change. Topological analysis is the first step in a doubly discrete classification scheme for strange attractors. The second discrete classification involves specification of a 'basis set' set of periodic orbits whose presence forces the existence of all other periodic orbits in the strange attractor. The basis set of orbits does change as control parameters change. Quantitative models developed to describe time series data are tested by the methods of entrainment. This analysis procedure has been applied to analyze a number of data sets. Several analyses are described.
Nonlinear time-series analysis revisited
NASA Astrophysics Data System (ADS)
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.
Nonlinear time-series analysis revisited.
Bradley, Elizabeth; Kantz, Holger
2015-09-01
In 1980 and 1981, two pioneering papers laid the foundation for what became known as nonlinear time-series analysis: the analysis of observed data-typically univariate-via dynamical systems theory. Based on the concept of state-space reconstruction, this set of methods allows us to compute characteristic quantities such as Lyapunov exponents and fractal dimensions, to predict the future course of the time series, and even to reconstruct the equations of motion in some cases. In practice, however, there are a number of issues that restrict the power of this approach: whether the signal accurately and thoroughly samples the dynamics, for instance, and whether it contains noise. Moreover, the numerical algorithms that we use to instantiate these ideas are not perfect; they involve approximations, scale parameters, and finite-precision arithmetic, among other things. Even so, nonlinear time-series analysis has been used to great advantage on thousands of real and synthetic data sets from a wide variety of systems ranging from roulette wheels to lasers to the human heart. Even in cases where the data do not meet the mathematical or algorithmic requirements to assure full topological conjugacy, the results of nonlinear time-series analysis can be helpful in understanding, characterizing, and predicting dynamical systems. PMID:26428563
SO2 EMISSIONS AND TIME SERIES MODELS
The paper describes a time series model that permits the estimation of the statistical properties of pounds of SO2 per million Btu in stack emissions. It uses measured values for this quantity provided by coal sampling and analysis (CSA), by a continuous emissions monitor (CEM), ...
Three Analysis Examples for Time Series Data
Technology Transfer Automated Retrieval System (TEKTRAN)
With improvements in instrumentation and the automation of data collection, plot level repeated measures and time series data are increasingly available to monitor and assess selected variables throughout the duration of an experiment or project. Records and metadata on variables of interest alone o...
Event Discovery in Astronomical Time Series
NASA Astrophysics Data System (ADS)
Preston, D.; Protopapas, P.; Brodley, C.
2009-09-01
The discovery of events in astronomical time series data is a non-trival problem. Existing methods address the problem by requiring a fixed-sized sliding window which, given the varying lengths of events and sampling rates, could overlook important events. In this work, we develop probability models for finding the significance of an arbitrary-sized sliding window, and use these probabilities to find areas of significance. In addition, we present our analyses of major surveys archived at the Time Series Center, part of the Initiative in Innovative Computing at Harvard University. We applied our method to the time series data in order to discover events such as microlensing or any non-periodic events in the MACHO, OGLE and TAOS surveys. The analysis shows that the method is an effective tool for filtering out nearly 99% of noisy and uninteresting time series from a large set of data, but still provides full recovery of all known variable events (microlensing, blue star events, supernovae etc.). Furthermore, due to its efficiency, this method can be performed on-the-fly and will be used to analyze upcoming surveys, such as Pan-STARRS.
Nonlinear Time Series Analysis via Neural Networks
NASA Astrophysics Data System (ADS)
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.
Classification of time series patterns from complex dynamic systems
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.
Delay Differential Analysis of Time Series
Lainscsek, Claudia; Sejnowski, Terrence J.
2015-01-01
Nonlinear dynamical system analysis based on embedding theory has been used for modeling and prediction, but it also has applications to signal detection and classification of time series. An embedding creates a multidimensional geometrical object from a single time series. Traditionally either delay or derivative embeddings have been used. The delay embedding is composed of delayed versions of the signal, and the derivative embedding is composed of successive derivatives of the signal. The delay embedding has been extended to nonuniform embeddings to take multiple timescales into account. Both embeddings provide information on the underlying dynamical system without having direct access to all the system variables. Delay differential analysis is based on functional embeddings, a combination of the derivative embedding with nonuniform delay embeddings. Small delay differential equation (DDE) models that best represent relevant dynamic features of time series data are selected from a pool of candidate models for detection or classification. We show that the properties of DDEs support spectral analysis in the time domain where nonlinear correlation functions are used to detect frequencies, frequency and phase couplings, and bispectra. These can be efficiently computed with short time windows and are robust to noise. For frequency analysis, this framework is a multivariate extension of discrete Fourier transform (DFT), and for higher-order spectra, it is a linear and multivariate alternative to multidimensional fast Fourier transform of multidimensional correlations. This method can be applied to short or sparse time series and can be extended to cross-trial and cross-channel spectra if multiple short data segments of the same experiment are available. Together, this time-domain toolbox provides higher temporal resolution, increased frequency and phase coupling information, and it allows an easy and straightforward implementation of higher-order spectra across time
Remote Sensing Time Series Product Tool
NASA Technical Reports Server (NTRS)
Predos, Don; Ryan, Robert E.; Ross, Kenton W.
2006-01-01
The TSPT (Time Series Product Tool) software was custom-designed for NASA to rapidly create and display single-band and band-combination time series, such as NDVI (Normalized Difference Vegetation Index) images, for wide-area crop surveillance and for other time-critical applications. The TSPT, developed in MATLAB, allows users to create and display various MODIS (Moderate Resolution Imaging Spectroradiometer) or simulated VIIRS (Visible/Infrared Imager Radiometer Suite) products as single images, as time series plots at a selected location, or as temporally processed image videos. Manually creating these types of products is extremely labor intensive; however, the TSPT development tool makes the process simplified and efficient. MODIS is ideal for monitoring large crop areas because of its wide swath (2330 km), its relatively small ground sample distance (250 m), and its high temporal revisit time (twice daily). Furthermore, because MODIS imagery is acquired daily, rapid changes in vegetative health can potentially be detected. The new TSPT technology provides users with the ability to temporally process high-revisit-rate satellite imagery, such as that acquired from MODIS and from its successor, the VIIRS. The TSPT features the important capability of fusing data from both MODIS instruments onboard the Terra and Aqua satellites, which drastically improves cloud statistics. With the TSPT, MODIS metadata is used to find and optionally remove bad and suspect data. Noise removal and temporal processing techniques allow users to create low-noise time series plots and image videos and to select settings and thresholds that tailor particular output products. The TSPT GUI (graphical user interface) provides an interactive environment for crafting what-if scenarios by enabling a user to repeat product generation using different settings and thresholds. The TSPT Application Programming Interface provides more fine-tuned control of product generation, allowing experienced
Algorithm for Compressing Time-Series Data
NASA Technical Reports Server (NTRS)
Hawkins, S. Edward, III; Darlington, Edward Hugo
2012-01-01
An algorithm based on Chebyshev polynomials effects lossy compression of time-series data or other one-dimensional data streams (e.g., spectral data) that are arranged in blocks for sequential transmission. The algorithm was developed for use in transmitting data from spacecraft scientific instruments to Earth stations. In spite of its lossy nature, the algorithm preserves the information needed for scientific analysis. The algorithm is computationally simple, yet compresses data streams by factors much greater than two. The algorithm is not restricted to spacecraft or scientific uses: it is applicable to time-series data in general. The algorithm can also be applied to general multidimensional data that have been converted to time-series data, a typical example being image data acquired by raster scanning. However, unlike most prior image-data-compression algorithms, this algorithm neither depends on nor exploits the two-dimensional spatial correlations that are generally present in images. In order to understand the essence of this compression algorithm, it is necessary to understand that the net effect of this algorithm and the associated decompression algorithm is to approximate the original stream of data as a sequence of finite series of Chebyshev polynomials. For the purpose of this algorithm, a block of data or interval of time for which a Chebyshev polynomial series is fitted to the original data is denoted a fitting interval. Chebyshev approximation has two properties that make it particularly effective for compressing serial data streams with minimal loss of scientific information: The errors associated with a Chebyshev approximation are nearly uniformly distributed over the fitting interval (this is known in the art as the "equal error property"); and the maximum deviations of the fitted Chebyshev polynomial from the original data have the smallest possible values (this is known in the art as the "min-max property").
Modelling population change from time series data
Barker, R.J.; Sauer, J.R.
1992-01-01
Information on change in population size over time is among the most basic inputs for population management. Unfortunately, population changes are generally difficult to identify, and once identified difficult to explain. Sources of variald (patterns) in population data include: changes in environment that affect carrying capaciyy and produce trend, autocorrelative processes, irregular environmentally induced perturbations, and stochasticity arising from population processes. In addition. populations are almost never censused and many surveys (e.g., the North American Breeding Bird Survey) produce multiple, incomplete time series of population indices, providing further sampling complications. We suggest that each source of pattern should be used to address specific hypotheses regarding population change, but that failure to correctly model each source can lead to false conclusions about the dynamics of populations. We consider hypothesis tests based on each source of pattern, and the effects of autocorrelated observations and sampling error. We identify important constraints on analyses of time series that limit their use in identifying underlying relationships.
Time series regression studies in environmental epidemiology
Bhaskaran, Krishnan; Gasparrini, Antonio; Hajat, Shakoor; Smeeth, Liam; Armstrong, Ben
2013-01-01
Time series regression studies have been widely used in environmental epidemiology, notably in investigating the short-term associations between exposures such as air pollution, weather variables or pollen, and health outcomes such as mortality, myocardial infarction or disease-specific hospital admissions. Typically, for both exposure and outcome, data are available at regular time intervals (e.g. daily pollution levels and daily mortality counts) and the aim is to explore short-term associations between them. In this article, we describe the general features of time series data, and we outline the analysis process, beginning with descriptive analysis, then focusing on issues in time series regression that differ from other regression methods: modelling short-term fluctuations in the presence of seasonal and long-term patterns, dealing with time varying confounding factors and modelling delayed (‘lagged’) associations between exposure and outcome. We finish with advice on model checking and sensitivity analysis, and some common extensions to the basic model. PMID:23760528
Time series regression studies in environmental epidemiology.
Bhaskaran, Krishnan; Gasparrini, Antonio; Hajat, Shakoor; Smeeth, Liam; Armstrong, Ben
2013-08-01
Time series regression studies have been widely used in environmental epidemiology, notably in investigating the short-term associations between exposures such as air pollution, weather variables or pollen, and health outcomes such as mortality, myocardial infarction or disease-specific hospital admissions. Typically, for both exposure and outcome, data are available at regular time intervals (e.g. daily pollution levels and daily mortality counts) and the aim is to explore short-term associations between them. In this article, we describe the general features of time series data, and we outline the analysis process, beginning with descriptive analysis, then focusing on issues in time series regression that differ from other regression methods: modelling short-term fluctuations in the presence of seasonal and long-term patterns, dealing with time varying confounding factors and modelling delayed ('lagged') associations between exposure and outcome. We finish with advice on model checking and sensitivity analysis, and some common extensions to the basic model. PMID:23760528
Sliced Inverse Regression for Time Series Analysis
NASA Astrophysics Data System (ADS)
Chen, Li-Sue
1995-11-01
In this thesis, general nonlinear models for time series data are considered. A basic form is x _{t} = f(beta_sp{1} {T}X_{t-1},beta_sp {2}{T}X_{t-1},... , beta_sp{k}{T}X_ {t-1},varepsilon_{t}), where x_{t} is an observed time series data, X_{t } is the first d time lag vector, (x _{t},x_{t-1},... ,x _{t-d-1}), f is an unknown function, beta_{i}'s are unknown vectors, varepsilon_{t }'s are independent distributed. Special cases include AR and TAR models. We investigate the feasibility applying SIR/PHD (Li 1990, 1991) (the sliced inverse regression and principal Hessian methods) in estimating beta _{i}'s. PCA (Principal component analysis) is brought in to check one critical condition for SIR/PHD. Through simulation and a study on 3 well -known data sets of Canadian lynx, U.S. unemployment rate and sunspot numbers, we demonstrate how SIR/PHD can effectively retrieve the interesting low-dimension structures for time series data.
Univariate time series forecasting algorithm validation
NASA Astrophysics Data System (ADS)
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.
Multifractal Analysis of Sunspot Number Time Series
NASA Astrophysics Data System (ADS)
Kasde, Satish Kumar; Gwal, Ashok Kumar; Sondhiya, Deepak Kumar
2016-07-01
Multifractal analysis based approaches have been recently developed as an alternative framework to study the complex dynamical fluctuations in sunspot numbers data including solar cycles 20 to 23 and ascending phase of current solar cycle 24.To reveal the multifractal nature, the time series data of monthly sunspot number are analyzed by singularity spectrum and multi resolution wavelet analysis. Generally, the multifractility in sunspot number generate turbulence with the typical characteristics of the anomalous process governing the magnetosphere and interior of Sun. our analysis shows that singularities spectrum of sunspot data shows well Gaussian shape spectrum, which clearly establishes the fact that monthly sunspot number has multifractal character. The multifractal analysis is able to provide a local and adaptive description of the cyclic components of sunspot number time series, which are non-stationary and result of nonlinear processes. Keywords: Sunspot Numbers, Magnetic field, Multifractal analysis and wavelet Transform Techniques.
Time-Series Analysis: A Cautionary Tale
NASA Technical Reports Server (NTRS)
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.
Time Series Analysis Using Geometric Template Matching.
Frank, Jordan; Mannor, Shie; Pineau, Joelle; Precup, Doina
2013-03-01
We present a novel framework for analyzing univariate time series data. At the heart of the approach is a versatile algorithm for measuring the similarity of two segments of time series called geometric template matching (GeTeM). First, we use GeTeM to compute a similarity measure for clustering and nearest-neighbor classification. Next, we present a semi-supervised learning algorithm that uses the similarity measure with hierarchical clustering in order to improve classification performance when unlabeled training data are available. Finally, we present a boosting framework called TDEBOOST, which uses an ensemble of GeTeM classifiers. TDEBOOST augments the traditional boosting approach with an additional step in which the features used as inputs to the classifier are adapted at each step to improve the training error. We empirically evaluate the proposed approaches on several datasets, such as accelerometer data collected from wearable sensors and ECG data. PMID:22641699
FTSPlot: Fast Time Series Visualization for Large Datasets
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 ; the visualization itself can be done with a complexity of 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 ms. The current 64-bit implementation theoretically supports datasets with up to bytes, on the x86_64 architecture currently up to bytes are supported, and benchmarks have been conducted with bytes/1 TiB or 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. PMID:24732865
Aggregated Indexing of Biomedical Time Series Data
Woodbridge, Jonathan; Mortazavi, Bobak; Sarrafzadeh, Majid; Bui, Alex A.T.
2016-01-01
Remote and wearable medical sensing has the potential to create very large and high dimensional datasets. Medical time series databases must be able to efficiently store, index, and mine these datasets to enable medical professionals to effectively analyze data collected from their patients. Conventional high dimensional indexing methods are a two stage process. First, a superset of the true matches is efficiently extracted from the database. Second, supersets are pruned by comparing each of their objects to the query object and rejecting any objects falling outside a predetermined radius. This pruning stage heavily dominates the computational complexity of most conventional search algorithms. Therefore, indexing algorithms can be significantly improved by reducing the amount of pruning. This paper presents an online algorithm to aggregate biomedical times series data to significantly reduce the search space (index size) without compromising the quality of search results. This algorithm is built on the observation that biomedical time series signals are composed of cyclical and often similar patterns. This algorithm takes in a stream of segments and groups them to highly concentrated collections. Locality Sensitive Hashing (LSH) is used to reduce the overall complexity of the algorithm, allowing it to run online. The output of this aggregation is used to populate an index. The proposed algorithm yields logarithmic growth of the index (with respect to the total number of objects) while keeping sensitivity and specificity simultaneously above 98%. Both memory and runtime complexities of time series search are improved when using aggregated indexes. In addition, data mining tasks, such as clustering, exhibit runtimes that are orders of magnitudes faster when run on aggregated indexes.
Analysis of Polyphonic Musical Time Series
NASA Astrophysics Data System (ADS)
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.
Characterization of noisy symbolic time series.
Kulp, Christopher W; Smith, Suzanne
2011-02-01
The 0-1 test for chaos is a recently developed time series characterization algorithm that can determine whether a system is chaotic or nonchaotic. While the 0-1 test was designed for deterministic series, in real-world measurement situations, noise levels may not be known and the 0-1 test may have difficulty distinguishing between chaos and randomness. In this paper, we couple the 0-1 test for chaos with a test for determinism and apply these tests to noisy symbolic series generated from various model systems. We find that the pairing of the 0-1 test with a test for determinism improves the ability to correctly distinguish between chaos and randomness from a noisy series. Furthermore, we explore the modes of failure for the 0-1 test and the test for determinism so that we can better understand the effectiveness of the two tests to handle various levels of noise. We find that while the tests can handle low noise and high noise situations, moderate levels of noise can lead to inconclusive results from the two tests. PMID:21405890
Spectrophotometric Time Series of η Carinae's Great Eruption
NASA Astrophysics Data System (ADS)
Rest, Armin; Bianco, Federica; Chornock, Ryan; Clocchiatti, Alejandro; James, David; Margheim, Steve; Matheson, Thomas; Prieto, Jose Luis; Smith, Chris; Smith, Nathan; Walborn, Nolan; Welch, Doug; Zenteno, Alfredo
2014-08-01
η Car serves as our most important template for understanding non-SN transients from massive stars in external galaxies. However, until recently, no spectra were available because its historic ``Great Eruption'' (GE) occurred from 1838-1858, before the invention of the astronomical spectrograph, and only visual estimates of its brightness were recorded teSF11. Now we can also obtain a spectral sequence of the eruption through its light echoes we discovered, which will be of great value since spectra are our most important tool for inferring physical properties of extragalactic transients. Subsequent spectroscopic follow-up revealed that its outburst was most similar to those of G-type supergiants, rather than reported LBV outburst spectral types of F-type (or earlier) teRest12_eta. These differences between the GE and the extragalactic transients presumed to be its analogues raise questions about traditional scenarios for the outburst. We propose to obtain a spectrophotometric time series of the GE from different directions, allowing the original eruption of η Car to be studied as a function of time as well as latitude, something only possible with light echoes. This unique detailed spectroscopic study of the light echoes of η Car will help us understand (episodic) mass- loss in the most massive evolved stars and their connection to the most energetic core-collapse SNe.
Evolutionary factor analysis of replicated time series.
Motta, Giovanni; Ombao, Hernando
2012-09-01
In this article, we develop a novel method that explains the dynamic structure of multi-channel electroencephalograms (EEGs) recorded from several trials in a motor-visual task experiment. Preliminary analyses of our data suggest two statistical challenges. First, the variance at each channel and cross-covariance between each pair of channels evolve over time. Moreover, the cross-covariance profiles display a common structure across all pairs, and these features consistently appear across all trials. In the light of these features, we develop a novel evolutionary factor model (EFM) for multi-channel EEG data that systematically integrates information across replicated trials and allows for smoothly time-varying factor loadings. The individual EEGs series share common features across trials, thus, suggesting the need to pool information across trials, which motivates the use of the EFM for replicated time series. We explain the common co-movements of EEG signals through the existence of a small number of common factors. These latent factors are primarily responsible for processing the visual-motor task which, through the loadings, drive the behavior of the signals observed at different channels. The estimation of the time-varying loadings is based on the spectral decomposition of the estimated time-varying covariance matrix. PMID:22364516
Homogenization of precipitation time series with ACMANT
NASA Astrophysics Data System (ADS)
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.
Fractal fluctuations in cardiac time series
NASA Technical Reports Server (NTRS)
West, B. J.; Zhang, R.; Sanders, A. W.; Miniyar, S.; Zuckerman, J. H.; Levine, B. D.; Blomqvist, C. G. (Principal Investigator)
1999-01-01
Human heart rate, controlled by complex feedback mechanisms, is a vital index of systematic circulation. However, it has been shown that beat-to-beat values of heart rate fluctuate continually over a wide range of time scales. Herein we use the relative dispersion, the ratio of the standard deviation to the mean, to show, by systematically aggregating the data, that the correlation in the beat-to-beat cardiac time series is a modulated inverse power law. This scaling property indicates the existence of long-time memory in the underlying cardiac control process and supports the conclusion that heart rate variability is a temporal fractal. We argue that the cardiac control system has allometric properties that enable it to respond to a dynamical environment through scaling.
Time Series Photometry of KZ Lacertae
NASA Astrophysics Data System (ADS)
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.
Time series analyses of global change data.
Lane, L J; Nichols, M H; Osborn, H B
1994-01-01
The hypothesis that statistical analyses of historical time series data can be used to separate the influences of natural variations from anthropogenic sources on global climate change is tested. Point, regional, national, and global temperature data are analyzed. Trend analyses for the period 1901-1987 suggest mean annual temperatures increased (in degrees C per century) globally at the rate of about 0.5, in the USA at about 0.3, in the south-western USA desert region at about 1.2, and at the Walnut Gulch Experimental Watershed in south-eastern Arizona at about 0.8. However, the rates of temperature change are not constant but vary within the 87-year period. Serial correlation and spectral density analysis of the temperature time series showed weak periodicities at various frequencies. The only common periodicity among the temperature series is an apparent cycle of about 43 years. The temperature time series were correlated with the Wolf sunspot index, atmospheric CO(2) concentrations interpolated from the Siple ice core data, and atmospheric CO(2) concentration data from Mauna Loa measurements. Correlation analysis of temperature data with concurrent data on atmospheric CO(2) concentrations and the Wolf sunspot index support previously reported significant correlation over the 1901-1987 period. Correlation analysis between temperature, atmospheric CO(2) concentration, and the Wolf sunspot index for the shorter period, 1958-1987, when continuous Mauna Loa CO(2) data are available, suggest significant correlation between global warming and atmospheric CO(2) concentrations but no significant correlation between global warming and the Wolf sunspot index. This may be because the Wolf sunspot index apparently increased from 1901 until about 1960 and then decreased thereafter, while global warming apparently continued to increase through 1987. Correlation of sunspot activity with global warming may be spurious but additional analyses are required to test this hypothesis
Time series analysis of temporal networks
NASA Astrophysics Data System (ADS)
Sikdar, Sandipan; Ganguly, Niloy; Mukherjee, Animesh
2016-01-01
A common but an important feature of all real-world networks is that they are temporal in nature, i.e., the network structure changes over time. Due to this dynamic nature, it becomes difficult to propose suitable growth models that can explain the various important characteristic properties of these networks. In fact, in many application oriented studies only knowing these properties is sufficient. For instance, if one wishes to launch a targeted attack on a network, this can be done even without the knowledge of the full network structure; rather an estimate of some of the properties is sufficient enough to launch the attack. We, in this paper show that even if the network structure at a future time point is not available one can still manage to estimate its properties. We propose a novel method to map a temporal network to a set of time series instances, analyze them and using a standard forecast model of time series, try to predict the properties of a temporal network at a later time instance. To our aim, we consider eight properties such as number of active nodes, average degree, clustering coefficient etc. and apply our prediction framework on them. We mainly focus on the temporal network of human face-to-face contacts and observe that it represents a stochastic process with memory that can be modeled as Auto-Regressive-Integrated-Moving-Average (ARIMA). We use cross validation techniques to find the percentage accuracy of our predictions. An important observation is that the frequency domain properties of the time series obtained from spectrogram analysis could be used to refine the prediction framework by identifying beforehand the cases where the error in prediction is likely to be high. This leads to an improvement of 7.96% (for error level ≤20%) in prediction accuracy on an average across all datasets. As an application we show how such prediction scheme can be used to launch targeted attacks on temporal networks. Contribution to the Topical Issue
Time series modelling of surface pressure data
NASA Astrophysics Data System (ADS)
Al-Awadhi, Shafeeqah; Jolliffe, Ian
1998-03-01
In this paper we examine time series modelling of surface pressure data, as measured by a barograph, at Herne Bay, England, during the years 1981-1989. Autoregressive moving average (ARMA) models have been popular in many fields over the past 20 years, although applications in climatology have been rather less widespread than in some disciplines. Some recent examples are Milionis and Davies (Int. J. Climatol., 14, 569-579) and Seleshi et al. (Int. J. Climatol., 14, 911-923). We fit standard ARMA models to the pressure data separately for each of six 2-month natural seasons. Differences between the best fitting models for different seasons are discussed. Barograph data are recorded continuously, whereas ARMA models are fitted to discretely recorded data. The effect of different spacings between the fitted data on the models chosen is discussed briefly.Often, ARMA models can give a parsimonious and interpretable representation of a time series, but for many series the assumptions underlying such models are not fully satisfied, and more complex models may be considered. A specific feature of surface pressure data in the UK is that its behaviour is different at high and at low pressures: day-to-day changes are typically larger at low pressure levels than at higher levels. This means that standard assumptions used in fitting ARMA models are not valid, and two ways of overcoming this problem are investigated. Transformation of the data to better satisfy the usual assumptions is considered, as is the use of non-linear, specifically threshold autoregressive (TAR), models.
Ensemble vs. time averages in financial time series analysis
NASA Astrophysics Data System (ADS)
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.
Singular spectrum analysis for time series with missing data
Schoellhamer, D.H.
2001-01-01
Geophysical time series often contain missing data, which prevents analysis with many signal processing and multivariate tools. A modification of singular spectrum analysis for time series with missing data is developed and successfully tested with synthetic and actual incomplete time series of suspended-sediment concentration from San Francisco Bay. This method also can be used to low pass filter incomplete time series.
Nonparametric, nonnegative deconvolution of large time series
NASA Astrophysics Data System (ADS)
Cirpka, O. A.
2006-12-01
There is a long tradition of characterizing hydrologic systems by linear models, in which the response of the system to a time-varying stimulus is computed by convolution of a system-specific transfer function with the input signal. Despite its limitations, the transfer-function concept has been shown valuable for many situations such as the precipitation/run-off relationships of catchments and solute transport in agricultural soils and aquifers. A practical difficulty lies in the identification of the transfer function. A common approach is to fit a parametric function, enforcing a particular shape of the transfer function, which may be in contradiction to the real behavior (e.g., multimodal transfer functions, long tails, etc.). In our nonparametric deconvolution, the transfer function is assumed an auto-correlated random time function, which is conditioned on the data by a Bayesian approach. Nonnegativity, which is a vital constraint for solute-transport applications, is enforced by the method of Lagrange multipliers. This makes the inverse problem nonlinear. In nonparametric deconvolution, identifying the auto-correlation parameters is crucial. Enforcing too much smoothness prohibits the identification of important features, whereas insufficient smoothing leads to physically meaningless transfer functions, mapping noise components in the two data series onto each other. We identify optimal smoothness parameters by the expectation-maximization method, which requires the repeated generation of many conditional realizations. The overall approach, however, is still significantly faster than Markov-Chain Monte-Carlo methods presented recently. We apply our approach to electric-conductivity time series measured in a river and monitoring wells in the adjacent aquifer. The data cover 1.5 years with a temporal resolution of 1h. The identified transfer functions have lengths of up to 60 days, making up 1440 parameters. We believe that nonparametric deconvolution is an
Assessing burn severity using satellite time series
NASA Astrophysics Data System (ADS)
Veraverbeke, Sander; Lhermitte, Stefaan; Verstraeten, Willem; Goossens, Rudi
2010-05-01
In this study a multi-temporal differenced Normalized Burn Ratio (dNBRMT) is presented to assess burn severity of the 2007 Peloponnese (Greece) wildfires. 8-day composites were created using the daily near infrared (NIR) and mid infrared (MIR) reflectance products of the Moderate Resolution Imaging Spectroradiometer (MODIS). Prior to the calculation of the dNBRMT a pixel-based control plot selection procedure was initiated for each burned pixel based on time series similarity of the pre-fire year 2006 to estimate the spatio-temporal NBR dynamics in the case that no fire event would have occurred. The dNBRMT is defined as the one-year post-fire integrated difference between the NBR values of the control and focal pixels. Results reveal the temporal dependency of the absolute values of bi-temporal dNBR maps as the mean temporal standard deviation of the one-year post-fire bi-temporal dNBR time series equaled 0.14 (standard deviation of 0.04). The dNBRMT's integration of temporal variability into one value potentially enhances the comparability of fires across space and time. In addition, the dNBRMT is robust to random noise thanks to the averaging effect. The dNBRMT, based on coarse resolution imagery with high temporal frequency, has the potential to become either a valuable complement to fine resolution Landsat dNBR mapping or an imperative option for assessing burn severity at a continental to global scale.
Time Series Analysis of the Blazar OJ 287
NASA Astrophysics Data System (ADS)
Gamel, Ellen; Ryle, W. T.; Carini, M. T.
2013-06-01
Blazars are a subset of active galactic nuclei (AGN) where the light is viewed along the jet of radiation produced by the central supermassive black hole. These very luminous objects vary in brightness and are associated with the cores of distant galaxies. The blazar, OJ 287, has been monitored and its brightness tracked over time. From these light curves the relationship between the characteristic “break frequency” and black hole mass can be determined through the use of power density spectra. In order to obtain a well-sampled light curve, this blazar will be observed at a wide range of timescales. Long time scales will be obtained using archived light curves from published literature. Medium time scales were obtained through a combination of data provided by Western Kentucky University and data collected at The Bank of Kentucky Observatory. Short time scales were achieved via a single night of observation at the 72” Perkins Telescope at Lowell Observatory in Flagstaff, AZ. Using time series analysis, we present a revised mass estimate for the super massive black hole of OJ 287. This object is of particular interest because it may harbor a binary black hole at its center.
Periodograms for multiband astronomical time series
NASA Astrophysics Data System (ADS)
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.
A New SBUV Ozone Profile Time Series
NASA Technical Reports Server (NTRS)
McPeters, Richard
2011-01-01
Under NASA's MEaSUREs program for creating long term multi-instrument data sets, our group at Goddard has re-processed ozone profile data from a series of SBUV instruments. We have processed data from the Nimbus 7 SBUV instrument (1979-1990) and data from SBUV/2 instruments on NOAA-9 (1985-1998), NOAA-11 (1989-1995), NOAA-16 (2001-2010), NOAA-17 (2002-2010), and NOAA-18 (2005-2010). This reprocessing uses the version 8 ozone profile algorithm but now uses the Brion, Daumont, and Malicet (BMD) ozone cross sections instead of the Bass and Paur cross sections. The new cross sections have much better resolution, and extended wavelength range, and a more consistent temperature dependence. The re-processing also uses an improved cloud height climatology based on the Raman cloud retrievals of OMI. Finally, the instrument-to-instrument calibration is set using matched scenes so that ozone diurnal variation in the upper stratosphere does not alias into the ozone trands. Where there is no instrument overlap, SAGE and MLS are used to estimate calibration offsets. Preliminary analysis shows a more coherent time series as a function of altitude. The net effect on profile total column ozone is on average an absolute reduction of about one percent. Comparisons with ground-based systems are significantly better at high latitudes.
Scaling laws from geomagnetic time series
Voros, Z.; Kovacs, P.; Juhasz, A.; Kormendi, A.; Green, A.W.
1998-01-01
The notion of extended self-similarity (ESS) is applied here for the X - component time series of geomagnetic field fluctuations. Plotting nth order structure functions against the fourth order structure function we show that low-frequency geomagnetic fluctuations up to the order n = 10 follow the same scaling laws as MHD fluctuations in solar wind, however, for higher frequencies (f > l/5[h]) a clear departure from the expected universality is observed for n > 6. ESS does not allow to make an unambiguous statement about the non triviality of scaling laws in "geomagnetic" turbulence. However, we suggest to use higher order moments as promising diagnostic tools for mapping the contributions of various remote magnetospheric sources to local observatory data. Copyright 1998 by the American Geophysical Union.
Normalizing the causality between time series.
Liang, X San
2015-08-01
Recently, a rigorous yet concise formula was derived to evaluate information flow, and hence the causality in a quantitative sense, between time series. To assess the importance of a resulting causality, it needs to be normalized. The normalization is achieved through distinguishing a Lyapunov exponent-like, one-dimensional phase-space stretching rate and a noise-to-signal ratio from the rate of information flow in the balance of the marginal entropy evolution of the flow recipient. It is verified with autoregressive models and applied to a real financial analysis problem. An unusually strong one-way causality is identified from IBM (International Business Machines Corporation) to GE (General Electric Company) in their early era, revealing to us an old story, which has almost faded into oblivion, about "Seven Dwarfs" competing with a giant for the mainframe computer market. PMID:26382363
Normalizing the causality between time series
NASA Astrophysics Data System (ADS)
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.
Using entropy to cut complex time series
NASA Astrophysics Data System (ADS)
Mertens, David; Poncela Casasnovas, Julia; Spring, Bonnie; Amaral, L. A. N.
2013-03-01
Using techniques from statistical physics, physicists have modeled and analyzed human phenomena varying from academic citation rates to disease spreading to vehicular traffic jams. The last decade's explosion of digital information and the growing ubiquity of smartphones has led to a wealth of human self-reported data. This wealth of data comes at a cost, including non-uniform sampling and statistically significant but physically insignificant correlations. In this talk I present our work using entropy to identify stationary sub-sequences of self-reported human weight from a weight management web site. Our entropic approach-inspired by the infomap network community detection algorithm-is far less biased by rare fluctuations than more traditional time series segmentation techniques. Supported by the Howard Hughes Medical Institute
Spectrophotometric Time Series of η Carinae's Great Eruption
NASA Astrophysics Data System (ADS)
Rest, Armin; Bianco, Federica; Chornock, Ryan; Matheson, Thomas; Prieto, Jose Luis; Smith, Chris; Smith, Nathan; Walborn, Nolan; Welch, Doug
2014-02-01
η Carinae (η Car) serves as our most important template for understanding non-SN transients from massive stars in external galaxies. However, until recently, no spectra were available because its historic ``Great Eruption'' (GE) occurred before the invention of the astronomical spectrograph. Now we can also obtain a spectral sequence of the eruption through echoes, which will be of great value since spectra are our most important tool for inferring physical properties of extragalactic transients. η Car was seen as the second brightest star in the sky during its 1800s GE, but only visual estimates of its brightness were recorded teSF11. In 2011 we discovered several light echoes (LEs) which appear to be from the 1838- 1858 η Car eruptions teRest12_eta. Subsequent spectroscopic follow-up revealed that its outburst spectral type was most similar to those of G-type supergiants, rather than reported LBV outburst spectral types of F-type (or earlier) teRest12_eta. These differences between the GE and the extragalactic transients presumed to be its analogues raise questions about traditional scenarios for the outburst. We propose to obtain a spectrophotometric time series of the GE from different directions, allowing the original eruption of η Car to be studied as a function of time as well as latitude. A detailed spectroscopic study of the LEs of η Car would help us understand (episodic) mass-loss in the most massive evolved stars and their connection to the most energetic core-collapse SNe.
Periodograms for Multiband Astronomical Time Series
NASA Astrophysics Data System (ADS)
VanderPlas, Jacob T.; Iv´, Željko
2015-10-01
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. 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.
Fast and Flexible Multivariate Time Series Subsequence Search
NASA Technical Reports Server (NTRS)
Bhaduri, Kanishka; Oza, Nikunj C.; Zhu, Qiang; Srivastava, Ashok N.
2010-01-01
Multivariate Time-Series (MTS) are ubiquitous, and are generated in areas as disparate as sensor recordings in aerospace systems, music and video streams, medical monitoring, and financial systems. Domain experts are often interested in searching for interesting multivariate patterns from these MTS databases which often contain several gigabytes of data. Surprisingly, research on MTS search is very limited. Most of the existing work only supports queries with the same length of data, or queries on a fixed set of variables. In this paper, we propose an efficient and flexible subsequence search framework for massive MTS databases, that, for the first time, enables querying on any subset of variables with arbitrary time delays between them. We propose two algorithms to solve this problem (1) a List Based Search (LBS) algorithm which uses sorted lists for indexing, and (2) a R*-tree Based Search (RBS) which uses Minimum Bounding Rectangles (MBR) to organize the subsequences. Both algorithms guarantee that all matching patterns within the specified thresholds will be returned (no false dismissals). The very few false alarms can be removed by a post-processing step. Since our framework is also capable of Univariate Time-Series (UTS) subsequence search, we first demonstrate the efficiency of our algorithms on several UTS datasets previously used in the literature. We follow this up with experiments using two large MTS databases from the aviation domain, each containing several millions of observations. Both these tests show that our algorithms have very high prune rates (>99%) thus needing actual disk access for only less than 1% of the observations. To the best of our knowledge, MTS subsequence search has never been attempted on datasets of the size we have used in this paper.
Timing calibration and spectral cleaning of LOFAR time series data
NASA Astrophysics Data System (ADS)
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.
`Geologic time series' of earth surface deformation
NASA Astrophysics Data System (ADS)
Friedrich, A. M.
2004-12-01
The debate of whether the earth has evolved gradually or by catastrophic change has dominated the geological sciences for many centuries. On a human timescale, the earth appears to be changing slowly except for a few sudden events (singularities) such as earthquakes, floods, or landslides. While these singularities dramatically affect the loss of life or the destruction of habitat locally, they have little effect on the global population growth rate or evolution of the earth's surface. It is also unclear to what degree such events leave their traces in the geologic record. Yet, the earth's surface is changing! For example, rocks that equilibrated at depths of > 30 km below the surface are exposed at high elevations in mountains belts indicating vertical motion (uplift) of tens of kilometers; and rocks that acquired a signature of the earth's magnetic field are found up to hundreds of kilometers from their origin indicating significant horizontal transport along great faults. Whether such long-term motion occurs at the rate indicated by the recurrence interval of singular events, or whether singularities also operate at a higher-order scale ("mega-singularities") are open questions. Attempts to address these questions require time series significantly longer than several recurrence intervals of singularities. For example, for surface rupturing earthquakes (Magnitude > 7) with recurrence intervals ranging from tens to tens of thousands of years, observation periods on the order of thousands of years to a million years would be needed. However, few if any of the presently available measurement methods provide both the necessary resolution and "recording duration." While paleoseismic methods have the appropriate spatial and temporal resolution, data collection along most faults has been limited to the last one or two earthquakes. Geologic and geomorphic measurements may record long-term changes in fault slip, but only provide rates averaged over many recurrence
Peat conditions mapping using MODIS time series
NASA Astrophysics Data System (ADS)
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.
NASA Astrophysics Data System (ADS)
Gao, Xiangyun; An, Haizhong; Fang, Wei; Huang, Xuan; Li, Huajiao; Zhong, Weiqiong; Ding, Yinghui
2014-07-01
The linear regression parameters between two time series can be different under different lengths of observation period. If we study the whole period by the sliding window of a short period, the change of the linear regression parameters is a process of dynamic transmission over time. We tackle fundamental research that presents a simple and efficient computational scheme: a linear regression patterns transmission algorithm, which transforms linear regression patterns into directed and weighted networks. The linear regression patterns (nodes) are defined by the combination of intervals of the linear regression parameters and the results of the significance testing under different sizes of the sliding window. The transmissions between adjacent patterns are defined as edges, and the weights of the edges are the frequency of the transmissions. The major patterns, the distance, and the medium in the process of the transmission can be captured. The statistical results of weighted out-degree and betweenness centrality are mapped on timelines, which shows the features of the distribution of the results. Many measurements in different areas that involve two related time series variables could take advantage of this algorithm to characterize the dynamic relationships between the time series from a new perspective.
Singular spectrum analysis and forecasting of hydrological time series
NASA Astrophysics Data System (ADS)
Marques, C. A. F.; Ferreira, J. A.; Rocha, A.; Castanheira, J. M.; Melo-Gonçalves, P.; Vaz, N.; Dias, J. M.
The singular spectrum analysis (SSA) technique is applied to some hydrological univariate time series to assess its ability to uncover important information from those series, and also its forecast skill. The SSA is carried out on annual precipitation, monthly runoff, and hourly water temperature time series. Information is obtained by extracting important components or, when possible, the whole signal from the time series. The extracted components are then subject to forecast by the SSA algorithm. It is illustrated the SSA ability to extract a slowly varying component (i.e. the trend) from the precipitation time series, the trend and oscillatory components from the runoff time series, and the whole signal from the water temperature time series. The SSA was also able to accurately forecast the extracted components of these time series.
Intercomparison of six Mediterranean zooplankton time series
NASA Astrophysics Data System (ADS)
Berline, Léo; Siokou-Frangou, Ioanna; Marasović, Ivona; Vidjak, Olja; Fernández de Puelles, M.^{a.} Luz; Mazzocchi, Maria Grazia; Assimakopoulou, Georgia; Zervoudaki, Soultana; Fonda-Umani, Serena; Conversi, Alessandra; Garcia-Comas, Carmen; Ibanez, Frédéric; Gasparini, Stéphane; Stemmann, Lars; Gorsky, Gabriel
2012-05-01
We analyzed and compared Mediterranean mesozooplankton time series spanning 1957-2006 from six coastal stations in the Balearic, Ligurian, Tyrrhenian, North and Middle Adriatic and Aegean Sea. Our analysis focused on fluctuations of major zooplankton taxonomic groups and their relation with environmental and climatic variability. Average seasonal cycles and interannual trends were derived. Stations spanned a large range of trophic status from oligotrophic to moderately eutrophic. Intra-station analyses showed (1) coherent multi-taxa trends off Villefranche sur mer that diverge from the previous results found at species level, (2) in Baleares, covariation of zooplankton and water masses as a consequence of the boundary hydrographic regime in the middle Western Mediterranean, (3) decrease in trophic status and abundance of some taxonomic groups off Naples, and (4) off Athens, an increase of zooplankton abundance and decrease in chlorophyll possibly caused by reduction of anthropogenic nutrient input, increase of microbial components, and more efficient grazing control on phytoplankton. (5) At basin scale, the analysis of temperature revealed significant positive correlations between Villefranche, Trieste and Naples for annual and/or winter average, and synchronous abrupt cooling and warming events centered in 1987 at the same three sites. After correction for multiple comparisons, we found no significant correlations between climate indices and local temperature or zooplankton abundance, nor between stations for zooplankton abundance, therefore we suggest that for these coastal stations local drivers (climatic, anthropogenic) are dominant and that the link between local and larger scale of climate should be investigated further if we are to understand zooplankton fluctuations.
The Massive Hosts of Radio Galaxies Across Cosmic Time
NASA Astrophysics Data System (ADS)
Seymour, Nick; SHzRG Collaboration
2007-05-01
We present the results of a comprehensive Spitzer survey of 69 radio galaxies across 1
NASA Astrophysics Data System (ADS)
Vyhnalek, Brian; Zurcher, Ulrich; O'Dwyer, Rebecca; Kaufman, Miron
2009-10-01
A wide range of heart rate irregularities have been reported in small studies of patients with temporal lobe epilepsy [TLE]. We hypothesize that patients with TLE display cardiac dysautonomia in either a subclinical or clinical manner. In a small study, we have retrospectively identified (2003-8) two groups of patients from the epilepsy monitoring unit [EMU] at the Cleveland Clinic. No patients were diagnosed with cardiovascular morbidities. The control group consisted of patients with confirmed pseudoseizures and the experimental group had confirmed right temporal lobe epilepsy through a seizure free outcome after temporal lobectomy. We quantified the heart rate variability using the approximate entropy [ApEn]. We found similar values of the ApEn in all three states of consciousness (awake, sleep, and proceeding seizure onset). In the TLE group, there is some evidence for greater variability in the awake than in either the sleep or proceeding seizure onset. Here we present results for mathematically-generated time series: the heart rate fluctuations ξ follow the γ statistics i.e., p(ξ)=γ-1(k) ξ^k exp(-ξ). This probability function has well-known properties and its Shannon entropy can be expressed in terms of the γ-function. The parameter k allows us to generate a family of heart rate time series with different statistics. The ApEn calculated for the generated time series for different values of k mimic the properties found for the TLE and pseudoseizure group. Our results suggest that the ApEn is an effective tool to probe differences in statistics of heart rate fluctuations.
Multiscale entropy to distinguish physiologic and synthetic RR time series.
Costa, M; Goldberger, A L; Peng, C-K
2002-01-01
We address the challenge of distinguishing physiologic interbeat interval time series from those generated by synthetic algorithms via a newly developed multiscale entropy method. Traditional measures of time series complexity only quantify the degree of regularity on a single time scale. However, many physiologic variables, such as heart rate, fluctuate in a very complex manner and present correlations over multiple time scales. We have proposed a new method to calculate multiscale entropy from complex signals. In order to distinguish between physiologic and synthetic time series, we first applied the method to a learning set of RR time series derived from healthy subjects. We empirically established selected criteria characterizing the entropy dependence on scale factor for these datasets. We then applied this algorithm to the CinC 2002 test datasets. Using only the multiscale entropy method, we correctly classified 48 of 50 (96%) time series. In combination with Fourier spectral analysis, we correctly classified all time series. PMID:14686448
Efficient Algorithms for Segmentation of Item-Set Time Series
NASA Astrophysics Data System (ADS)
Chundi, Parvathi; Rosenkrantz, Daniel J.
We propose a special type of time series, which we call an item-set time series, to facilitate the temporal analysis of software version histories, email logs, stock market data, etc. In an item-set time series, each observed data value is a set of discrete items. We formalize the concept of an item-set time series and present efficient algorithms for segmenting a given item-set time series. Segmentation of a time series partitions the time series into a sequence of segments where each segment is constructed by combining consecutive time points of the time series. Each segment is associated with an item set that is computed from the item sets of the time points in that segment, using a function which we call a measure function. We then define a concept called the segment difference, which measures the difference between the item set of a segment and the item sets of the time points in that segment. The segment difference values are required to construct an optimal segmentation of the time series. We describe novel and efficient algorithms to compute segment difference values for each of the measure functions described in the paper. We outline a dynamic programming based scheme to construct an optimal segmentation of the given item-set time series. We use the item-set time series segmentation techniques to analyze the temporal content of three different data sets—Enron email, stock market data, and a synthetic data set. The experimental results show that an optimal segmentation of item-set time series data captures much more temporal content than a segmentation constructed based on the number of time points in each segment, without examining the item set data at the time points, and can be used to analyze different types of temporal data.
Multifractal Analysis of Aging and Complexity in Heartbeat Time Series
NASA Astrophysics Data System (ADS)
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.
Time efficient 3-D electromagnetic modeling on massively parallel computers
Alumbaugh, D.L.; Newman, G.A.
1995-08-01
A numerical modeling algorithm has been developed to simulate the electromagnetic response of a three dimensional earth to a dipole source for frequencies ranging from 100 to 100MHz. The numerical problem is formulated in terms of a frequency domain--modified vector Helmholtz equation for the scattered electric fields. The resulting differential equation is approximated using a staggered finite difference grid which results in a linear system of equations for which the matrix is sparse and complex symmetric. The system of equations is solved using a preconditioned quasi-minimum-residual method. Dirichlet boundary conditions are employed at the edges of the mesh by setting the tangential electric fields equal to zero. At frequencies less than 1MHz, normal grid stretching is employed to mitigate unwanted reflections off the grid boundaries. For frequencies greater than this, absorbing boundary conditions must be employed by making the stretching parameters of the modified vector Helmholtz equation complex which introduces loss at the boundaries. To allow for faster calculation of realistic models, the original serial version of the code has been modified to run on a massively parallel architecture. This modification involves three distinct tasks; (1) mapping the finite difference stencil to a processor stencil which allows for the necessary information to be exchanged between processors that contain adjacent nodes in the model, (2) determining the most efficient method to input the model which is accomplished by dividing the input into ``global`` and ``local`` data and then reading the two sets in differently, and (3) deciding how to output the data which is an inherently nonparallel process.
Visibility graph network analysis of gold price time series
NASA Astrophysics Data System (ADS)
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.
Apparatus for statistical time-series analysis of electrical signals
NASA Technical Reports Server (NTRS)
Stewart, C. H. (Inventor)
1973-01-01
An apparatus for performing statistical time-series analysis of complex electrical signal waveforms, permitting prompt and accurate determination of statistical characteristics of the signal is presented.
Interpretable Early Classification of Multivariate Time Series
ERIC Educational Resources Information Center
Ghalwash, Mohamed F.
2013-01-01
Recent advances in technology have led to an explosion in data collection over time rather than in a single snapshot. For example, microarray technology allows us to measure gene expression levels in different conditions over time. Such temporal data grants the opportunity for data miners to develop algorithms to address domain-related problems,…
Time series change detection: Algorithms for land cover change
NASA Astrophysics Data System (ADS)
Boriah, Shyam
can be used for decision making and policy planning purposes. In particular, previous change detection studies have primarily relied on examining differences between two or more satellite images acquired on different dates. Thus, a technological solution that detects global land cover change using high temporal resolution time series data will represent a paradigm-shift in the field of land cover change studies. To realize these ambitious goals, a number of computational challenges in spatio-temporal data mining need to be addressed. Specifically, analysis and discovery approaches need to be cognizant of climate and ecosystem data characteristics such as seasonality, non-stationarity/inter-region variability, multi-scale nature, spatio-temporal autocorrelation, high-dimensionality and massive data size. This dissertation, a step in that direction, translates earth science challenges to computer science problems, and provides computational solutions to address these problems. In particular, three key technical capabilities are developed: (1) Algorithms for time series change detection that are effective and can scale up to handle the large size of earth science data; (2) Change detection algorithms that can handle large numbers of missing and noisy values present in satellite data sets; and (3) Spatio-temporal analysis techniques to identify the scale and scope of disturbance events.
Simulation of Ground Winds Time Series
NASA Technical Reports Server (NTRS)
Adelfang, S. I.
2008-01-01
A simulation process has been developed for generation of the longitudinal and lateral components of ground wind atmospheric turbulence as a function of mean wind speed, elevation, temporal frequency range and distance between locations. The distance between locations influences the spectral coherence between the simulated series at adjacent locations. Short distances reduce correlation only at high frequencies; as distances increase correlation is reduced over a wider range of frequencies. The choice of values for the constants d1 and d3 in the PSD model is the subject of work in progress. An improved knowledge of the values for zO as a function of wind direction at the ARES-1 launch pads is necessary for definition of d1. Results of other studies at other locations may be helpful as summarized in Fichtl's recent correspondence. Ideally, further research is needed based on measurements of ground wind turbulence with high resolution anemometers at a number of altitudes at a new KSC tower located closer to the ARES-1 launch pad .The proposed research would be based on turbulence measurements that may be influenced by surface terrain roughness that may be significantly different from roughness prior to 1970 in Fichtl's measurements. Significant improvements in instrumentation, data storage end processing will greatly enhance the capability to model ground wind profiles and ground wind turbulence.
Astrophysics in the Era of Massive Time-Domain Surveys
NASA Astrophysics Data System (ADS)
Djorgovski, G.
Synoptic sky surveys are now the largest data producers in astronomy, entering the Petascale regime, opening the time domain for a systematic exploration. A great variety of interesting phenomena, spanning essentially all subfields of astronomy, can only be studied in the time domain, and these new surveys are producing large statistical samples of the known types of objects and events for further studies (e.g., SNe, AGN, variable stars of many kinds), and have already uncovered previously unknown subtypes of these (e.g., rare or peculiar types of SNe). These surveys are generating a new science, and paving the way for even larger surveys to come, e.g., the LSST; our ability to fully exploit such forthcoming facilities depends critically on the science, methodology, and experience that are being accumulated now. Among the outstanding challenges, the foremost is our ability to conduct an effective follow-up of the interesting events discovered by the surveys in any wavelength regime. The follow-up resources, especially spectroscopy, are already and, for the predictable future, will be severely limited, thus requiring an intelligent down-selection of the most astrophysically interesting events to follow. The first step in that process is an automated, real-time, iterative classification of events, that incorporates heterogeneous data from the surveys themselves, archival and contextual information (spatial, temporal, and multiwavelength), and the incoming follow-up observations. The second step is an optimal automated event prioritization and allocation of the available follow-up resources that also change in time. Both of these challenges are highly non-trivial, and require a strong cyber-infrastructure based on the Virtual Observatory data grid, and the various astroinformatics efforts. Time domain astronomy is inherently an astronomy of telescope-computational systems, and will increasingly depend on novel machine learning and artificial intelligence tools
How to analyse irregularly sampled geophysical time series?
NASA Astrophysics Data System (ADS)
Eroglu, Deniz; Ozken, Ibrahim; Stemler, Thomas; Marwan, Norbert; Wyrwoll, Karl-Heinz; Kurths, Juergen
2015-04-01
One of the challenges of time series analysis is to detect dynamical changes in the dynamics of the underlying system.There are numerous methods that can be used to detect such regime changes in regular sampled times series. Here we present a new approach, that can be applied, when the time series is irregular sampled. Such data sets occur frequently in real world applications as in paleo climate proxy records. The basic idea follows Victor and Purpura [1] and considers segments of the time series. For each segment we compute the cost of transforming the segment into the following one. If the time series is from one dynamical regime the cost of transformation should be similar for each segment of the data. Dramatic changes in the cost time series indicate a change in the underlying dynamics. Any kind of analysis can be applicable to the cost time series since it is a regularly sampled time series. While recurrence plots are not the best choice for irregular sampled data with some measurement noise component, we show that a recurrence plot analysis based on the cost time series can successfully identify the changes in the dynamics of the system. We tested this method using synthetically created time series and will use these results to highlight the performance of our method. Furthermore we present our analysis of a suite of calcite and aragonite stalagmites located in the eastern Kimberley region of tropical Western Australia. This oxygen isotopic data is a proxy for the monsoon activity over the last 8,000 years. In this time series our method picks up several so far undetected changes from wet to dry in the monsoon system and therefore enables us to get a better understanding of the monsoon dynamics in the North-East of Australia over the last couple of thousand years. [1] J. D. Victor and K. P. Purpura, Network: Computation in Neural Systems 8, 127 (1997)
Volatility modeling of rainfall time series
NASA Astrophysics Data System (ADS)
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.
Common trends in northeast Atlantic squid time series
NASA Astrophysics Data System (ADS)
Zuur, A. F.; Pierce, G. J.
2004-06-01
In this paper, dynamic factor analysis is used to estimate common trends in time series of squid catch per unit effort in Scottish (UK) waters. Results indicated that time series of most months were related to sea surface temperature measured at Millport (UK) and a few series were related to the NAO index. The DFA methodology identified three common trends in the squid time series not revealed by traditional approaches, which suggest a possible shift in relative abundance of summer- and winter-spawning populations.
Time series analysis of air pollutants in Beirut, Lebanon.
Farah, Wehbeh; Nakhlé, Myriam Mrad; Abboud, Maher; Annesi-Maesano, Isabella; Zaarour, Rita; Saliba, Nada; Germanos, Georges; Gerard, Jocelyne
2014-12-01
This study reports for the first time a time series analysis of daily urban air pollutant levels (CO, NO, NO2, O3, PM10, and SO2) in Beirut, Lebanon. The study examines data obtained between September 2005 and July 2006, and their descriptive analysis shows long-term variations of daily levels of air pollution concentrations. Strong persistence of these daily levels is identified in the time series using an autocorrelation function, except for SO2. Time series of standardized residual values (SRVs) are also calculated to compare fluctuations of the time series with different levels. Time series plots of the SRVs indicate that NO and NO2 had similar temporal fluctuations. However, NO2 and O3 had opposite temporal fluctuations, attributable to weather conditions and the accumulation of vehicular emissions. The effects of both desert dust storms and airborne particulate matter resulting from the Lebanon War in July 2006 are also discernible in the SRV plots. PMID:25150052
Horizontal visibility graphs: exact results for random time series.
Luque, B; Lacasa, L; Ballesteros, F; Luque, J
2009-10-01
The visibility algorithm has been recently introduced as a mapping between time series and complex networks. This procedure allows us to apply methods of complex network theory for characterizing time series. In this work we present the horizontal visibility algorithm, a geometrically simpler and analytically solvable version of our former algorithm, focusing on the mapping of random series (series of independent identically distributed random variables). After presenting some properties of the algorithm, we present exact results on the topological properties of graphs associated with random series, namely, the degree distribution, the clustering coefficient, and the mean path length. We show that the horizontal visibility algorithm stands as a simple method to discriminate randomness in time series since any random series maps to a graph with an exponential degree distribution of the shape P(k)=(1/3)(2/3)(k-2), independent of the probability distribution from which the series was generated. Accordingly, visibility graphs with other P(k) are related to nonrandom series. Numerical simulations confirm the accuracy of the theorems for finite series. In a second part, we show that the method is able to distinguish chaotic series from independent and identically distributed (i.i.d.) theory, studying the following situations: (i) noise-free low-dimensional chaotic series, (ii) low-dimensional noisy chaotic series, even in the presence of large amounts of noise, and (iii) high-dimensional chaotic series (coupled map lattice), without needs for additional techniques such as surrogate data or noise reduction methods. Finally, heuristic arguments are given to explain the topological properties of chaotic series, and several sequences that are conjectured to be random are analyzed. PMID:19905386
Spectral Procedures Enhance the Analysis of Three Agricultural Time Series
Technology Transfer Automated Retrieval System (TEKTRAN)
Many agricultural and environmental variables are influenced by cyclic processes that occur naturally. Consequently their time series often have cyclic behavior. This study developed times series models for three different phenomenon: (1) a 60 year-long state average crop yield record, (2) a four ...
A Computer Evolution in Teaching Undergraduate Time Series
ERIC Educational Resources Information Center
Hodgess, Erin M.
2004-01-01
In teaching undergraduate time series courses, we have used a mixture of various statistical packages. We have finally been able to teach all of the applied concepts within one statistical package; R. This article describes the process that we use to conduct a thorough analysis of a time series. An example with a data set is provided. We compare…
Small Sample Properties of Bayesian Multivariate Autoregressive Time Series Models
ERIC Educational Resources Information Center
Price, Larry R.
2012-01-01
The aim of this study was to compare the small sample (N = 1, 3, 5, 10, 15) performance of a Bayesian multivariate vector autoregressive (BVAR-SEM) time series model relative to frequentist power and parameter estimation bias. A multivariate autoregressive model was developed based on correlated autoregressive time series vectors of varying…
Nonlinear parametric model for Granger causality of time series
NASA Astrophysics Data System (ADS)
Marinazzo, Daniele; Pellicoro, Mario; Stramaglia, Sebastiano
2006-06-01
The notion of Granger causality between two time series examines if the prediction of one series could be improved by incorporating information of the other. In particular, if the prediction error of the first time series is reduced by including measurements from the second time series, then the second time series is said to have a causal influence on the first one. We propose a radial basis function approach to nonlinear Granger causality. The proposed model is not constrained to be additive in variables from the two time series and can approximate any function of these variables, still being suitable to evaluate causality. Usefulness of this measure of causality is shown in two applications. In the first application, a physiological one, we consider time series of heart rate and blood pressure in congestive heart failure patients and patients affected by sepsis: we find that sepsis patients, unlike congestive heart failure patients, show symmetric causal relationships between the two time series. In the second application, we consider the feedback loop in a model of excitatory and inhibitory neurons: we find that in this system causality measures the combined influence of couplings and membrane time constants.
Using Time-Series Regression to Predict Academic Library Circulations.
ERIC Educational Resources Information Center
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…
Analysis of Time-Series Quasi-Experiments. Final Report.
ERIC Educational Resources Information Center
Glass, Gene V.; Maguire, Thomas O.
The objective of this project was to investigate the adequacy of statistical models developed by G. E. P. Box and G. C. Tiao for the analysis of time-series quasi-experiments: (1) The basic model developed by Box and Tiao is applied to actual time-series experiment data from two separate experiments, one in psychology and one in educational…
Measurements of spatial population synchrony: influence of time series transformations.
Chevalier, Mathieu; Laffaille, Pascal; Ferdy, Jean-Baptiste; Grenouillet, Gaël
2015-09-01
Two mechanisms have been proposed to explain spatial population synchrony: dispersal among populations, and the spatial correlation of density-independent factors (the "Moran effect"). To identify which of these two mechanisms is driving spatial population synchrony, time series transformations (TSTs) of abundance data have been used to remove the signature of one mechanism, and highlight the effect of the other. However, several issues with TSTs remain, and to date no consensus has emerged about how population time series should be handled in synchrony studies. Here, by using 3131 time series involving 34 fish species found in French rivers, we computed several metrics commonly used in synchrony studies to determine whether a large-scale climatic factor (temperature) influenced fish population dynamics at the regional scale, and to test the effect of three commonly used TSTs (detrending, prewhitening and a combination of both) on these metrics. We also tested whether the influence of TSTs on time series and population synchrony levels was related to the features of the time series using both empirical and simulated time series. For several species, and regardless of the TST used, we evidenced a Moran effect on freshwater fish populations. However, these results were globally biased downward by TSTs which reduced our ability to detect significant signals. Depending on the species and the features of the time series, we found that TSTs could lead to contradictory results, regardless of the metric considered. Finally, we suggest guidelines on how population time series should be processed in synchrony studies. PMID:25953116
Sunspot Time Series: Passive and Active Intervals
NASA Astrophysics Data System (ADS)
Zięba, S.; Nieckarz, Z.
2014-07-01
Solar activity slowly and irregularly decreases from the first spotless day (FSD) in the declining phase of the old sunspot cycle and systematically, but also in an irregular way, increases to the new cycle maximum after the last spotless day (LSD). The time interval between the first and the last spotless day can be called the passive interval (PI), while the time interval from the last spotless day to the first one after the new cycle maximum is the related active interval (AI). Minima of solar cycles are inside PIs, while maxima are inside AIs. In this article, we study the properties of passive and active intervals to determine the relation between them. We have found that some properties of PIs, and related AIs, differ significantly between two group of solar cycles; this has allowed us to classify Cycles 8 - 15 as passive cycles, and Cycles 17 - 23 as active ones. We conclude that the solar activity in the PI declining phase (a descending phase of the previous cycle) determines the strength of the approaching maximum in the case of active cycles, while the activity of the PI rising phase (a phase of the ongoing cycle early growth) determines the strength of passive cycles. This can have implications for solar dynamo models. Our approach indicates the important role of solar activity during the declining and the rising phases of the solar-cycle minimum.
Functional and stochastic models estimation for GNSS coordinates time series
NASA Astrophysics Data System (ADS)
Galera Monico, J. F.; Silva, H. A.; Marques, H. A.
2014-12-01
GNSS has been largely used in Geodesy and correlated areas for positioning. The position and velocity of terrestrial stations have been estimated using GNSS data based on daily solutions. So, currently it is possible to analyse the GNSS coordinates time series aiming to improve the functional and stochastic models what can help to understand geodynamic phenomena. Several sources of errors are mathematically modelled or estimated in the GNSS data processing to obtain precise coordinates what in general is carried out by using scientific software. However, due to impossibility to model all errors some kind of noises can remain contaminating the coordinate time series, especially those related with seasonal effects. The noise affecting GNSS coordinate time series can be composed by white and coloured noises what can be characterized from Variance Component Estimation technique through Least Square Method. The methodology to characterize noise in GNSS coordinates time series will be presented in this paper so that the estimated variance can be used to reconstruct stochastic and functional models of the times series providing a more realistic and reliable modeling of time series. Experiments were carried out by using GNSS time series for few Brazilian stations considering almost ten years of daily solutions. The noises components were characterized as white, flicker and random walk noise and applied to estimate the times series functional model considering semiannual and annual effects. The results show that the adoption of an adequate stochastic model considering the noises variances of time series can produce more realistic and reliable functional model for GNSS coordinate time series. Such results may be applied in the context of the realization of the Brazilian Geodetic System.
The delay time distribution of massive double compact star mergers
NASA Astrophysics Data System (ADS)
Mennekens, N.; Vanbeveren, D.
2016-05-01
To investigate the temporal evolution of binary populations, in general, and double compact-star binaries and mergers, in particular, within a galactic evolution context, a very straightforward method is obviously to implement a detailed binary evolutionary model in a galactic chemical evolution code. To our knowledge, the Brussels galactic chemical evolution code is the only one that fully and consistently accounts for the important effects of interacting binaries on the predictions of chemical evolution. With a galactic code that does not explicitly include binaries, the temporal evolution of the population of double compact star binaries and mergers can be estimated with reasonable accuracy if the delay time distribution (DTD) for these mergers is available. The DTD for supernovae type Ia has been studied extensively in the past decade. In the present paper we present the DTD for merging double neutron-star binaries and mixed systems consisting of a neutron star and a black hole. The latter mergers are very promising sites for producing r-process elements, and the DTDs can be used to study the galactic evolution of these elements with a code that does not explicitly account for binaries.
Comparison of New and Old Sunspot Number Time Series
NASA Astrophysics Data System (ADS)
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.
Time series photometry and starspot properties
NASA Astrophysics Data System (ADS)
Oláh, Katalin
2011-08-01
Systematic efforts of monitoring starspots from the middle of the XXth century, and the results obtained from the datasets, are summarized with special focus on the observations made by automated telescopes. Multicolour photometry shows correlations between colour indices and brightness, indicating spotted regions with different average temperatures originating from spots and faculae. Long-term monitoring of spotted stars reveals variability on different timescales. On the rotational timescale new spot appearances and starspot proper motions are followed from continuous changes of light curves during subsequent rotations. Sudden interchange of the more and less active hemispheres on the stellar surfaces is the so called flip-flop phenomenon. The existence and strength of the differential rotation is seen from the rotational signals of spots being at different stellar latitudes. Long datasets, with only short, annual interruptions, shed light on the nature of stellar activity cycles and multiple cycles. The systematic and/or random changes of the spot cycle lengths are discovered and described using various time-frequency analysis tools. Positions and sizes of spotted regions on stellar surfaces are calculated from photometric data by various softwares. From spot positions derived for decades, active longitudes on the stellar surfaces are found, which, in case of synchronized eclipsing binaries can be well positioned in the orbital frame, with respect to, and affected by, the companion stars.
Sensor-Generated Time Series Events: A Definition Language
Anguera, Aurea; Lara, Juan A.; Lizcano, David; Martínez, Maria Aurora; Pazos, Juan
2012-01-01
There are now a great many domains where information is recorded by sensors over a limited time period or on a permanent basis. This data flow leads to sequences of data known as time series. In many domains, like seismography or medicine, time series analysis focuses on particular regions of interest, known as events, whereas the remainder of the time series contains hardly any useful information. In these domains, there is a need for mechanisms to identify and locate such events. In this paper, we propose an events definition language that is general enough to be used to easily and naturally define events in time series recorded by sensors in any domain. The proposed language has been applied to the definition of time series events generated within the branch of medicine dealing with balance-related functions in human beings. A device, called posturograph, is used to study balance-related functions. The platform has four sensors that record the pressure intensity being exerted on the platform, generating four interrelated time series. As opposed to the existing ad hoc proposals, the results confirm that the proposed language is valid, that is generally applicable and accurate, for identifying the events contained in the time series.
From time series to complex networks: The visibility graph
Lacasa, Lucas; Luque, Bartolo; Ballesteros, Fernando; Luque, Jordi; Nuño, Juan Carlos
2008-01-01
In this work we present a simple and fast computational method, the visibility algorithm, that converts a time series into a graph. The constructed graph inherits several properties of the series in its structure. Thereby, periodic series convert into regular graphs, and random series do so into random graphs. Moreover, fractal series convert into scale-free networks, enhancing the fact that power law degree distributions are related to fractality, something highly discussed recently. Some remarkable examples and analytical tools are outlined to test the method's reliability. Many different measures, recently developed in the complex network theory, could by means of this new approach characterize time series from a new point of view. PMID:18362361
From time series to complex networks: the visibility graph.
Lacasa, Lucas; Luque, Bartolo; Ballesteros, Fernando; Luque, Jordi; Nuño, Juan Carlos
2008-04-01
In this work we present a simple and fast computational method, the visibility algorithm, that converts a time series into a graph. The constructed graph inherits several properties of the series in its structure. Thereby, periodic series convert into regular graphs, and random series do so into random graphs. Moreover, fractal series convert into scale-free networks, enhancing the fact that power law degree distributions are related to fractality, something highly discussed recently. Some remarkable examples and analytical tools are outlined to test the method's reliability. Many different measures, recently developed in the complex network theory, could by means of this new approach characterize time series from a new point of view. PMID:18362361
DEM time series of an agricultural watershed
NASA Astrophysics Data System (ADS)
Pineux, Nathalie; Lisein, Jonathan; Swerts, Gilles; Degré, Aurore
2014-05-01
In agricultural landscape soil surface evolves notably due to erosion and deposition phenomenon. Even if most of the field data come from plot scale studies, the watershed scale seems to be more appropriate to understand them. Currently, small unmanned aircraft systems and images treatments are improving. In this way, 3D models are built from multiple covering shots. When techniques for large areas would be to expensive for a watershed level study or techniques for small areas would be too time consumer, the unmanned aerial system seems to be a promising solution to quantify the erosion and deposition patterns. The increasing technical improvements in this growth field allow us to obtain a really good quality of data and a very high spatial resolution with a high Z accuracy. In the center of Belgium, we equipped an agricultural watershed of 124 ha. For three years (2011-2013), we have been monitoring weather (including rainfall erosivity using a spectropluviograph), discharge at three different locations, sediment in runoff water, and watershed microtopography through unmanned airborne imagery (Gatewing X100). We also collected all available historical data to try to capture the "long-term" changes in watershed morphology during the last decades: old topography maps, soil historical descriptions, etc. An erosion model (LANDSOIL) is also used to assess the evolution of the relief. Short-term evolution of the surface are now observed through flights done at 200m height. The pictures are taken with a side overlap equal to 80%. To precisely georeference the DEM produced, ground control points are placed on the study site and surveyed using a Leica GPS1200 (accuracy of 1cm for x and y coordinates and 1.5cm for the z coordinate). Flights are done each year in December to have an as bare as possible ground surface. Specific treatments are developed to counteract vegetation effect because it is know as key sources of error in the DEM produced by small unmanned aircraft
Performance of multifractal detrended fluctuation analysis on short time series
NASA Astrophysics Data System (ADS)
López, Juan Luis; Contreras, Jesús Guillermo
2013-02-01
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.
Time series modeling of system self-assessment of survival
Lu, H.; Kolarik, W.J.
1999-06-01
Self-assessment of survival for a system, subsystem or component is implemented by assessing conditional performance reliability in real-time, which includes modeling and analysis of physical performance data. This paper proposes a time series analysis approach to system self-assessment (prediction) of survival. In the approach, physical performance data are modeled in a time series. The performance forecast is based on the model developed and is converted to the reliability of system survival. In contrast to a standard regression model, a time series model, using on-line data, is suitable for the real-time performance prediction. This paper illustrates an example of time series modeling and survival assessment, regarding an excessive tool edge wear failure mode for a twist drill operation.
Database for Hydrological Time Series of Inland Waters (DAHITI)
NASA Astrophysics Data System (ADS)
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.
Estimation of Parameters from Discrete Random Nonstationary Time Series
NASA Astrophysics Data System (ADS)
Takayasu, H.; Nakamura, T.
For the analysis of nonstationary stochastic time series we introduce a formulation to estimate the underlying time-dependent parameters. This method is designed for random events with small numbers that are out of the applicability range of the normal distribution. The method is demonstrated for numerical data generated by a known system, and applied to time series of traffic accidents, batting average of a baseball player and sales volume of home electronics.
Detecting temporal and spatial correlations in pseudoperiodic time series
NASA Astrophysics Data System (ADS)
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.
Wavelet analysis and scaling properties of time series
NASA Astrophysics Data System (ADS)
Manimaran, P.; Panigrahi, Prasanta K.; Parikh, Jitendra C.
2005-10-01
We propose a wavelet based method for the characterization of the scaling behavior of nonstationary time series. It makes use of the built-in ability of the wavelets for capturing the trends in a data set, in variable window sizes. Discrete wavelets from the Daubechies family are used to illustrate the efficacy of this procedure. After studying binomial multifractal time series with the present and earlier approaches of detrending for comparison, we analyze the time series of averaged spin density in the 2D Ising model at the critical temperature, along with several experimental data sets possessing multifractal behavior.
Estimation of connectivity measures in gappy time series
NASA Astrophysics Data System (ADS)
Papadopoulos, G.; Kugiumtzis, D.
2015-10-01
A new method is proposed to compute connectivity measures on multivariate time series with gaps. Rather than removing or filling the gaps, the rows of the joint data matrix containing empty entries are removed and the calculations are done on the remainder matrix. The method, called measure adapted gap removal (MAGR), can be applied to any connectivity measure that uses a joint data matrix, such as cross correlation, cross mutual information and transfer entropy. MAGR is favorably compared using these three measures to a number of known gap-filling techniques, as well as the gap closure. The superiority of MAGR is illustrated on time series from synthetic systems and financial time series.
Modelling road accidents: An approach using structural time series
NASA Astrophysics Data System (ADS)
Junus, Noor Wahida Md; Ismail, Mohd Tahir
2014-09-01
In this paper, the trend of road accidents in Malaysia for the years 2001 until 2012 was modelled using a structural time series approach. The structural time series model was identified using a stepwise method, and the residuals for each model were tested. The best-fitted model was chosen based on the smallest Akaike Information Criterion (AIC) and prediction error variance. In order to check the quality of the model, a data validation procedure was performed by predicting the monthly number of road accidents for the year 2012. Results indicate that the best specification of the structural time series model to represent road accidents is the local level with a seasonal model.
Wavelet analysis and scaling properties of time series.
Manimaran, P; Panigrahi, Prasanta K; Parikh, Jitendra C
2005-10-01
We propose a wavelet based method for the characterization of the scaling behavior of nonstationary time series. It makes use of the built-in ability of the wavelets for capturing the trends in a data set, in variable window sizes. Discrete wavelets from the Daubechies family are used to illustrate the efficacy of this procedure. After studying binomial multifractal time series with the present and earlier approaches of detrending for comparison, we analyze the time series of averaged spin density in the 2D Ising model at the critical temperature, along with several experimental data sets possessing multifractal behavior. PMID:16383481
Quantifying Memory in Complex Physiological Time-Series
Shirazi, Amir H.; Raoufy, Mohammad R.; Ebadi, Haleh; De Rui, Michele; Schiff, Sami; Mazloom, Roham; Hajizadeh, Sohrab; Gharibzadeh, Shahriar; Dehpour, Ahmad R.; Amodio, Piero; Jafari, G. Reza; Montagnese, Sara; Mani, Ali R.
2013-01-01
In a time-series, memory is a statistical feature that lasts for a period of time and distinguishes the time-series from a random, or memory-less, process. In the present study, the concept of “memory length” was used to define the time period, or scale over which rare events within a physiological time-series do not appear randomly. The method is based on inverse statistical analysis and provides empiric evidence that rare fluctuations in cardio-respiratory time-series are ‘forgotten’ quickly in healthy subjects while the memory for such events is significantly prolonged in pathological conditions such as asthma (respiratory time-series) and liver cirrhosis (heart-beat time-series). The memory length was significantly higher in patients with uncontrolled asthma compared to healthy volunteers. Likewise, it was significantly higher in patients with decompensated cirrhosis compared to those with compensated cirrhosis and healthy volunteers. We also observed that the cardio-respiratory system has simple low order dynamics and short memory around its average, and high order dynamics around rare fluctuations. PMID:24039811
Scale-dependent intrinsic entropies of complex time series.
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. PMID:26953181
A mixed time series model of binomial counts
NASA Astrophysics Data System (ADS)
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.
Nonstationary time series prediction combined with slow feature analysis
NASA Astrophysics Data System (ADS)
Wang, G.; Chen, X.
2015-07-01
Almost all climate time series have some degree of nonstationarity due to external driving forces perturbing the observed system. Therefore, these external driving forces should be taken into account when constructing the climate dynamics. This paper presents a new technique of obtaining the driving forces of a time series from the slow feature analysis (SFA) approach, and then introduces them into a predictive model to predict nonstationary time series. The basic theory of the technique is to consider the driving forces as state variables and to incorporate them into the predictive model. Experiments using a modified logistic time series and winter ozone data in Arosa, Switzerland, were conducted to test the model. The results showed improved prediction skills.
The use of synthetic input sequences in time series modeling
NASA Astrophysics Data System (ADS)
de Oliveira, Dair José; Letellier, Christophe; Gomes, Murilo E. D.; Aguirre, Luis A.
2008-08-01
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.
Time Series Analysis of Insar Data: Methods and Trends
NASA Technical Reports Server (NTRS)
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.
Comparison of New and Old Sunspot Number Time Series
NASA Astrophysics Data System (ADS)
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.
A method for detecting changes in long time series
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``.
Symplectic geometry spectrum regression for prediction of noisy time series
NASA Astrophysics Data System (ADS)
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).
Symplectic geometry spectrum regression for prediction of noisy time series.
Xie, Hong-Bo; Dokos, Socrates; Sivakumar, Bellie; Mengersen, Kerrie
2016-05-01
We present the symplectic geometry spectrum regression (SGSR) technique as well as a regularized method based on SGSR for prediction of nonlinear time series. The main tool of analysis is the symplectic geometry spectrum analysis, which decomposes a time series into the sum of a small number of independent and interpretable components. The key to successful regularization is to damp higher order symplectic geometry spectrum components. The effectiveness of SGSR and its superiority over local approximation using ordinary least squares are demonstrated through prediction of two noisy synthetic chaotic time series (Lorenz and Rössler series), and then tested for prediction of three real-world data sets (Mississippi River flow data and electromyographic and mechanomyographic signal recorded from human body). PMID:27300890
Exploratory Causal Analysis in Bivariate Time Series Data
NASA Astrophysics Data System (ADS)
McCracken, James M.
Many scientific disciplines rely on observational data of systems for which it is difficult (or impossible) to implement controlled experiments and data analysis techniques are required for identifying causal information and relationships directly from observational data. This need has lead to the development of many different time series causality approaches and tools including transfer entropy, convergent cross-mapping (CCM), and Granger causality statistics. In this thesis, the existing time series causality method of CCM is extended by introducing a new method called pairwise asymmetric inference (PAI). It is found that CCM may provide counter-intuitive causal inferences for simple dynamics with strong intuitive notions of causality, and the CCM causal inference can be a function of physical parameters that are seemingly unrelated to the existence of a driving relationship in the system. For example, a CCM causal inference might alternate between ''voltage drives current'' and ''current drives voltage'' as the frequency of the voltage signal is changed in a series circuit with a single resistor and inductor. PAI is introduced to address both of these limitations. Many of the current approaches in the times series causality literature are not computationally straightforward to apply, do not follow directly from assumptions of probabilistic causality, depend on assumed models for the time series generating process, or rely on embedding procedures. A new approach, called causal leaning, is introduced in this work to avoid these issues. The leaning is found to provide causal inferences that agree with intuition for both simple systems and more complicated empirical examples, including space weather data sets. The leaning may provide a clearer interpretation of the results than those from existing time series causality tools. A practicing analyst can explore the literature to find many proposals for identifying drivers and causal connections in times series data
Late time tails of the massive vector field in a black hole background
Konoplya, R. A.; Zhidenko, A.; Molina, C.
2007-04-15
We investigate the late-time behavior of the massive vector field in the background of the Schwarzschild and Schwarzschild-de Sitter black holes. For Schwarzschild black hole, at intermediately late times the massive vector field is represented by three functions with different decay law {psi}{sub 0}{approx}t{sup -(l+3/2)}sinmt, {psi}{sub 1}{approx}t{sup -(l+5/2)}sinmt, {psi}{sub 2}{approx}t{sup -(l+1/2)}sinmt, while at asymptotically late times the decay law {psi}{approx}t{sup -5/6}sin(mt) is universal and does not depend on the multipole number l. Together with a previous study of massive scalar and Dirac fields where the same asymptotically late-time decay law was found, it means that the asymptotically late-time decay law {approx}t{sup -5/6}sin(mt) does not depend also on the spin of the field under consideration. For Schwarzschild-de Sitter black holes it is observed in two different regimes in the late-time decay of perturbations: nonoscillatory exponential damping for small values of m and oscillatory quasinormal mode decay for high enough m. Numerical and analytical results are found for these quasinormal frequencies.
Scalable Hyper-parameter Estimation for Gaussian Process Based Time Series Analysis
Chandola, Varun; Vatsavai, Raju
2010-01-01
Gaussian process (GP) is increasingly becoming popular as a kernel machine learning tool for non-parametric data analysis. Recently, GP has been applied to model non-linear dependencies in time series data. GP based analysis can be used to solve problems of time series prediction, forecasting, missing data imputation, change point detection, anomaly detection, etc. But the use of GP to handle massive scientific time series data sets has been limited, owing to its expensive computational complexity. The primary bottleneck is the handling of the covariance matrix whose size is quadratic in the length of the time series. In this paper we propose a scalable method that exploit the special structure of the covariance matrix for hyper-parameter estimation in GP based learning. The proposed method allows estimation of hyper parameters associated with GP in quadratic time, which is an order of magnitude improvement over standard methods with cubic complexity. Moreover, the proposed method does not require explicit computation of the covariance matrix and hence has memory requirement linear to the length of the time series as opposed to the quadratic memory requirement of standard methods. To further improve the computational complexity of the proposed method, we provide a parallel version to concurrently estimate the log likelihood for a set of time series which is the key step in the hyper-parameter estimation. Performance results on a multi-core system show that our proposed method provides significant speedups as high as 1000, even when running in serial mode, while maintaining a small memory footprint. The parallel version exploits the natural parallelization potential of the serial algorithm and is shown to perform significantly better than the serial faster algorithm, with speedups as high as 10.
Evaluation of Scaling Invariance Embedded in Short Time Series
Pan, Xue; Hou, Lei; Stephen, Mutua; Yang, Huijie; Zhu, Chenping
2014-01-01
Scaling invariance of time series has been making great contributions in diverse research fields. But how to evaluate scaling exponent from a real-world series is still an open problem. Finite length of time series may induce unacceptable fluctuation and bias to statistical quantities and consequent invalidation of currently used standard methods. In this paper a new concept called correlation-dependent balanced estimation of diffusion entropy is developed to evaluate scale-invariance in very short time series with length . Calculations with specified Hurst exponent values of show that by using the standard central moving average de-trending procedure this method can evaluate the scaling exponents for short time series with ignorable bias () and sharp confidential interval (standard deviation ). Considering the stride series from ten volunteers along an approximate oval path of a specified length, we observe that though the averages and deviations of scaling exponents are close, their evolutionary behaviors display rich patterns. It has potential use in analyzing physiological signals, detecting early warning signals, and so on. As an emphasis, the our core contribution is that by means of the proposed method one can estimate precisely shannon entropy from limited records. PMID:25549356
Detection of flood events in hydrological discharge time series
NASA Astrophysics Data System (ADS)
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
Statistical modelling of agrometeorological time series by exponential smoothing
NASA Astrophysics Data System (ADS)
Murat, Małgorzata; Malinowska, Iwona; Hoffmann, Holger; Baranowski, Piotr
2016-01-01
Meteorological time series are used in modelling agrophysical processes of the soil-plant-atmosphere system which determine plant growth and yield. Additionally, long-term meteorological series are used in climate change scenarios. Such studies often require forecasting or projection of meteorological variables, eg the projection of occurrence of the extreme events. The aim of the article was to determine the most suitable exponential smoothing models to generate forecast using data on air temperature, wind speed, and precipitation time series in Jokioinen (Finland), Dikopshof (Germany), Lleida (Spain), and Lublin (Poland). These series exhibit regular additive seasonality or non-seasonality without any trend, which is confirmed by their autocorrelation functions and partial autocorrelation functions. The most suitable models were indicated by the smallest mean absolute error and the smallest root mean squared error.
Stochastic modeling of hourly rainfall times series in Campania (Italy)
NASA Astrophysics Data System (ADS)
Giorgio, M.; Greco, R.
2009-04-01
Occurrence of flowslides and floods in small catchments is uneasy to predict, since it is affected by a number of variables, such as mechanical and hydraulic soil properties, slope morphology, vegetation coverage, rainfall spatial and temporal variability. Consequently, landslide risk assessment procedures and early warning systems still rely on simple empirical models based on correlation between recorded rainfall data and observed landslides and/or river discharges. Effectiveness of such systems could be improved by reliable quantitative rainfall prediction, which can allow gaining larger lead-times. Analysis of on-site recorded rainfall height time series represents the most effective approach for a reliable prediction of local temporal evolution of rainfall. Hydrological time series analysis is a widely studied field in hydrology, often carried out by means of autoregressive models, such as AR, ARMA, ARX, ARMAX (e.g. Salas [1992]). Such models gave the best results when applied to the analysis of autocorrelated hydrological time series, like river flow or level time series. Conversely, they are not able to model the behaviour of intermittent time series, like point rainfall height series usually are, especially when recorded with short sampling time intervals. More useful for this issue are the so-called DRIP (Disaggregated Rectangular Intensity Pulse) and NSRP (Neymann-Scott Rectangular Pulse) model [Heneker et al., 2001; Cowpertwait et al., 2002], usually adopted to generate synthetic point rainfall series. In this paper, the DRIP model approach is adopted, in which the sequence of rain storms and dry intervals constituting the structure of rainfall time series is modeled as an alternating renewal process. Final aim of the study is to provide a useful tool to implement an early warning system for hydrogeological risk management. Model calibration has been carried out with hourly rainfall hieght data provided by the rain gauges of Campania Region civil
Compounding approach for univariate time series with nonstationary variances
NASA Astrophysics Data System (ADS)
Schäfer, Rudi; Barkhofen, Sonja; Guhr, Thomas; Stöckmann, Hans-Jürgen; Kuhl, Ulrich
2015-12-01
A defining feature of nonstationary systems is the time dependence of their statistical parameters. Measured time series may exhibit Gaussian statistics on short time horizons, due to the central limit theorem. The sample statistics for long time horizons, however, averages over the time-dependent variances. To model the long-term statistical behavior, we compound the local distribution with the distribution of its parameters. Here, we consider two concrete, but diverse, examples of such nonstationary systems: the turbulent air flow of a fan and a time series of foreign exchange rates. Our main focus is to empirically determine the appropriate parameter distribution for the compounding approach. To this end, we extract the relevant time scales by decomposing the time signals into windows and determine the distribution function of the thus obtained local variances.
Compounding approach for univariate time series with nonstationary variances.
Schäfer, Rudi; Barkhofen, Sonja; Guhr, Thomas; Stöckmann, Hans-Jürgen; Kuhl, Ulrich
2015-12-01
A defining feature of nonstationary systems is the time dependence of their statistical parameters. Measured time series may exhibit Gaussian statistics on short time horizons, due to the central limit theorem. The sample statistics for long time horizons, however, averages over the time-dependent variances. To model the long-term statistical behavior, we compound the local distribution with the distribution of its parameters. Here, we consider two concrete, but diverse, examples of such nonstationary systems: the turbulent air flow of a fan and a time series of foreign exchange rates. Our main focus is to empirically determine the appropriate parameter distribution for the compounding approach. To this end, we extract the relevant time scales by decomposing the time signals into windows and determine the distribution function of the thus obtained local variances. PMID:26764768
Generalized Dynamic Factor Models for Mixed-Measurement Time Series
Cui, Kai; Dunson, David B.
2013-01-01
In this article, we propose generalized Bayesian dynamic factor models for jointly modeling mixed-measurement time series. The framework allows mixed-scale measurements associated with each time series, with different measurements having different distributions in the exponential family conditionally on time-varying latent factor(s). Efficient Bayesian computational algorithms are developed for posterior inference on both the latent factors and model parameters, based on a Metropolis Hastings algorithm with adaptive proposals. The algorithm relies on a Greedy Density Kernel Approximation (GDKA) and parameter expansion with latent factor normalization. We tested the framework and algorithms in simulated studies and applied them to the analysis of intertwined credit and recovery risk for Moody’s rated firms from 1982–2008, illustrating the importance of jointly modeling mixed-measurement time series. The article has supplemental materials available online. PMID:24791133
Generalized Dynamic Factor Models for Mixed-Measurement Time Series.
Cui, Kai; Dunson, David B
2014-02-12
In this article, we propose generalized Bayesian dynamic factor models for jointly modeling mixed-measurement time series. The framework allows mixed-scale measurements associated with each time series, with different measurements having different distributions in the exponential family conditionally on time-varying latent factor(s). Efficient Bayesian computational algorithms are developed for posterior inference on both the latent factors and model parameters, based on a Metropolis Hastings algorithm with adaptive proposals. The algorithm relies on a Greedy Density Kernel Approximation (GDKA) and parameter expansion with latent factor normalization. We tested the framework and algorithms in simulated studies and applied them to the analysis of intertwined credit and recovery risk for Moody's rated firms from 1982-2008, illustrating the importance of jointly modeling mixed-measurement time series. The article has supplemental materials available online. PMID:24791133
A refined fuzzy time series model for stock market forecasting
NASA Astrophysics Data System (ADS)
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.
Multiscale entropy analysis of complex physiologic time series.
Costa, Madalena; Goldberger, Ary L; Peng, C-K
2002-08-01
There has been considerable interest in quantifying the complexity of physiologic time series, such as heart rate. However, traditional algorithms indicate higher complexity for certain pathologic processes associated with random outputs than for healthy dynamics exhibiting long-range correlations. This paradox may be due to the fact that conventional algorithms fail to account for the multiple time scales inherent in healthy physiologic dynamics. We introduce a method to calculate multiscale entropy (MSE) for complex time series. We find that MSE robustly separates healthy and pathologic groups and consistently yields higher values for simulated long-range correlated noise compared to uncorrelated noise. PMID:12190613
Minimum entropy density method for the time series analysis
NASA Astrophysics Data System (ADS)
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.
Massively parallel algorithms for real-time wavefront control of a dense adaptive optics system
Fijany, A.; Milman, M.; Redding, D.
1994-12-31
In this paper massively parallel algorithms and architectures for real-time wavefront control of a dense adaptive optic system (SELENE) are presented. The authors have already shown that the computation of a near optimal control algorithm for SELENE can be reduced to the solution of a discrete Poisson equation on a regular domain. Although, this represents an optimal computation, due the large size of the system and the high sampling rate requirement, the implementation of this control algorithm poses a computationally challenging problem since it demands a sustained computational throughput of the order of 10 GFlops. They develop a novel algorithm, designated as Fast Invariant Imbedding algorithm, which offers a massive degree of parallelism with simple communication and synchronization requirements. Due to these features, this algorithm is significantly more efficient than other Fast Poisson Solvers for implementation on massively parallel architectures. The authors also discuss two massively parallel, algorithmically specialized, architectures for low-cost and optimal implementation of the Fast Invariant Imbedding algorithm.
Wavelet analysis for non-stationary, nonlinear time series
NASA Astrophysics Data System (ADS)
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.
Time Series Analysis Based on Running Mann Whitney Z Statistics
Technology Transfer Automated Retrieval System (TEKTRAN)
A sensitive and objective time series analysis method based on the calculation of Mann Whitney U statistics is described. This method samples data rankings over moving time windows, converts those samples to Mann-Whitney U statistics, and then normalizes the U statistics to Z statistics using Monte-...
Nonlinear Analysis of Surface EMG Time Series of Back Muscles
NASA Astrophysics Data System (ADS)
Dolton, Donald C.; Zurcher, Ulrich; Kaufman, Miron; Sung, Paul
2004-10-01
A nonlinear analysis of surface electromyography time series of subjects with and without low back pain is presented. The mean-square displacement and entropy shows anomalous diffusive behavior on intermediate time range 10 ms < t < 1 s. This behavior implies the presence of correlations in the signal. We discuss the shape of the power spectrum of the signal.
Long-range correlations in time series generated by time-fractional diffusion: A numerical study
NASA Astrophysics Data System (ADS)
Barbieri, Davide; Vivoli, Alessandro
2005-09-01
Time series models showing power law tails in autocorrelation functions are common in econometrics. A special non-Markovian model for such kind of time series is provided by the random walk introduced by Gorenflo et al. as a discretization of time fractional diffusion. The time series so obtained are analyzed here from a numerical point of view in terms of autocorrelations and covariance matrices.
MODIS Vegetation Indices time series improvement considering real acquisition dates
NASA Astrophysics Data System (ADS)
Testa, S.; Borgogno Mondino, E.
2013-12-01
Satellite Vegetation Indices (VI) time series images are widely used for the characterization phenology, which requires a high temporal accuracy of the satellite data. The present work is based on the MODerate resolution Imaging Spectroradiometer (MODIS) MOD13Q1 product - Vegetation Indices 16-Day L3 Global 250m, which is generated through a maximum value compositing process that reduces the number of cloudy pixels and excludes, when possible, off-nadir ones. Because of its 16-days compositing period, the distance between two adjacent-in-time values within each pixel NDVI time series can range from 1 to 32 days, thus not acceptable for phenologic studies. Moreover, most of the available smoothing algorithms, which are widely used for phenology characterization, assume that data points are equidistant in time and contemporary over the image. The objective of this work was to assess temporal features of NDVI time series over a test area, composed by Castanea sativa (chestnut) and Fagus sylvatica (beech) pure pixels within the Piemonte region in Northwestern Italy. Firstly, NDVI, Pixel Reliability (PR) and Composite Day of the Year (CDOY) data ranging from 2000 to 2011 were extracted from MOD13Q1 and corresponding time series were generated (in further computations, 2000 was not considered since it is not complete because acquisition began in February and calibration is unreliable until October). Analysis of CDOY time series (containing the actual reference date of each NDVI value) over the selected study areas showed NDVI values to be prevalently generated from data acquired at the centre of each 16-days period (the 9th day), at least constantly along the year. This leads to consider each original NDVI value nominally placed to the centre of its 16-days reference period. Then, a new NDVI time series was generated: a) moving each NDVI value to its actual "acquisition" date, b) interpolating the obtained temporary time series through SPLINE functions, c) sampling such
Finding unstable periodic orbits from chaotic time series
NASA Astrophysics Data System (ADS)
Buhl, Michael
Contained within a chaotic attractor is an infinite number of unstable periodic orbits (UPOs). Although these orbits have zero measure, they form a skeleton of the dynamics. However, they are difficult to find from an observed time series. In this thesis I present several methods to find UPOs from measured time series. In Chapter 2 I look at data measured from the stomatogastric system of the California spiny lobster as an example to find unstable periodic orbits. With this time series I use two methods. The first creates a local linear model of the dynamics and finds the periodic orbits of the model, and the second applies a linear transform to the model such that unstable orbits are stable. In addition, in this chapter I describe methods of filtering and embedding the chaotic time series. In Chapter 3 I look at a more complicated model system where the dynamics are described by delay differential equations. Now the future state of the system depends on both the current state and the state a time tau earlier. This makes the phase space of the system infinite dimensional. I present a method for modeling systems such as this and finding UPOs in the infinite dimensional phase space. In Chapters 4 and 5 I describe a new method to find UPOs using symbolic dynamics. This has many advantages over the methods described in Chapter 2; more orbits can be found using a smaller time series---even in the presence of noise. First in Chapter 4 I describe how the phase space can be partitioned so that we can use symbolic dynamics. Then in Chapter 5 I describe how the UPOs can be found from the symbolic time series. Here, I model the symbolic dynamics with a Markov chain, represented by a graph, and then the symbolic UPOs are found from the graph. These symbolic cycles can then be localized back in phase space.
Mining approximate periodic pattern in hydrological time series
NASA Astrophysics Data System (ADS)
Zhu, Y. L.; Li, S. J.; Bao, N. N.; Wan, D. S.
2012-04-01
There is a lot of information about the hidden laws of nature evolution and the influences of human beings activities on the earth surface in long sequence of hydrological time series. Data mining technology can help find those hidden laws, such as flood frequency and abrupt change, which is useful for the decision support of hydrological prediction and flood control scheduling. The periodic nature of hydrological time series is important for trend forecasting of drought and flood and hydraulic engineering planning. In Hydrology, the full period analysis of hydrological time series has attracted a lot of attention, such as the discrete periodogram, simple partial wave method, Fourier analysis method, and maximum entropy spectral analysis method and wavelet analysis. In fact, the hydrological process is influenced both by deterministic factors and stochastic ones. For example, the tidal level is also affected by moon circling the Earth, in addition to the Earth revolution and its rotation. Hence, there is some kind of approximate period hidden in the hydrological time series, sometimes which is also called the cryptic period. Recently, partial period mining originated from the data mining domain can be a remedy for the traditional period analysis methods in hydrology, which has a loose request of the data integrity and continuity. They can find some partial period in the time series. This paper is focused on the partial period mining in the hydrological time series. Based on asynchronous periodic pattern and partial period mining with suffix tree, this paper proposes to mine multi-event asynchronous periodic pattern based on modified suffix tree representation and traversal, and invent a dynamic candidate period intervals adjusting method, which can avoids period omissions or waste of time and space. The experimental results on synthetic data and real water level data of the Yangtze River at Nanjing station indicate that this algorithm can discover hydrological
Massively parallel per-pixel-based zerotree processing architecture for real-time video compression
NASA Astrophysics Data System (ADS)
Alagoda, Geoffrey; Rassau, Alexander M.; Eshraghian, Kamran
2001-11-01
In the span of a few years, mobile multimedia communication has rapidly become a significant area of research and development constantly challenging boundaries on a variety of technological fronts. Video compression, a fundamental component for most mobile multimedia applications, generally places heavy demands in terms of the required processing capacity. Hardware implementations of typical modern hybrid codecs require realisation of components such as motion compensation, wavelet transform, quantisation, zerotree coding and arithmetic coding in real-time. While the implementation of such codecs using a fast generic processor is possible, undesirable trade-offs in terms of power consumption and speed must generally be made. The improvement in power consumption that is achievable through the use of a slow-clocked massively parallel processing environment, while maintaining real-time processing speeds, should thus not be overlooked. An architecture to realise such a massively parallel solution for a zerotree entropy coder is, therefore, presented in this paper.
Entropy measure of stepwise component in GPS time series
NASA Astrophysics Data System (ADS)
Lyubushin, A. A.; Yakovlev, P. V.
2016-01-01
A new method for estimating the stepwise component in the time series is suggested. The method is based on the application of a pseudo-derivative. The advantage of this method lies in the simplicity of its practical implementation compared to the more common methods for identifying the peculiarities in the time series against the noise. The need for automatic detection of the jumps in the noised signal and for introducing a quantitative measure of a stepwise behavior of the signal arises in the problems of the GPS time series analysis. The interest in the jumps in the mean level of the GPS signal is associated with the fact that they may reflect the typical earthquakes or the so-called silent earthquakes. In this paper, we offer the criteria for quantifying the degree of the stepwise behavior of the noised time series. These criteria are based on calculating the entropy for the auxiliary series of averaged stepwise approximations, which are constructed with the use of pseudo-derivatives.
On fractal analysis of cardiac interbeat time series
NASA Astrophysics Data System (ADS)
Guzmán-Vargas, L.; Calleja-Quevedo, E.; Angulo-Brown, F.
2003-09-01
In recent years the complexity of a cardiac beat-to-beat time series has been taken as an auxiliary tool to identify the health status of human hearts. Several methods has been employed to characterize the time series complexity. In this work we calculate the fractal dimension of interbeat time series arising from three groups: 10 young healthy persons, 8 elderly healthy persons and 10 patients with congestive heart failures. Our numerical results reflect evident differences in the dynamic behavior corresponding to each group. We discuss these results within the context of the neuroautonomic control of heart rate dynamics. We also propose a numerical simulation which reproduce aging effects of heart rate behavior.
Time series, correlation matrices and random matrix models
Vinayak; Seligman, Thomas H.
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.
Improvements in Accurate GPS Positioning Using Time Series Analysis
NASA Astrophysics Data System (ADS)
Koyama, Yuichiro; Tanaka, Toshiyuki
Although the Global Positioning System (GPS) is used widely in car navigation systems, cell phones, surveying, and other areas, several issues still exist. We focus on the continuous data received in public use of GPS, and propose a new positioning algorithm that uses time series analysis. By fitting an autoregressive model to the time series model of the pseudorange, we propose an appropriate state-space model. We apply the Kalman filter to the state-space model and use the pseudorange estimated by the filter in our positioning calculations. The results of the authors' positioning experiment show that the accuracy of the proposed method is much better than that of the standard method. In addition, as we can obtain valid values estimated by time series analysis using the state-space model, the proposed state-space model can be applied to several other fields.
Pharmacokinetic modelling of multi-decadal luminescence time series in coral skeletons
NASA Astrophysics Data System (ADS)
Llewellyn, Lyndon E.; Everingham, Yvette L.; Lough, Janice M.
2012-04-01
As corals grow, they incorporate chemical indicators of seawater conditions into their aragonite skeleton after they have traversed an outer living tissue layer. Long-lived, massive coral skeletons can record decade- and century-long time series of seawater status. One such environmental clue is luminescence intensity which can correspond to river flow patterns and has been attributed to humic acid incorporation. Seawater humic acid levels are linked to river flow as rainfall extracts them from catchment soils to then flow into rivers and coastal seas. However, discrepancies exist when validating coral luminescence records against river flow data with intense luminescence sometimes occurring in the absence of increased flows. This contributes to uncertainty when reconstructing pre-instrumental river flows and rainfall from coral luminescence. Here we demonstrate that a major portion of coral core luminescence time series can be explained using a single-compartment, pharmacokinetic model that incorporates river flow measurements as the equivalent of drug dose. The model was robust for luminescence series in corals from near-shore reefs regularly influenced by river flow. The model implies that after floods, a proportion of subsequent luminescence peaks can be derived from the initial flood. This explains why some luminescence peaks after floods often do not correspond to additional significant river flows. This provides the first mechanism-based explanation for temporal changes in coral skeleton luminescence that incorporates a mathematical link between two independent time series making this proxy even more robust for reconstructing river flow and rainfall.
A multidisciplinary database for geophysical time series management
NASA Astrophysics Data System (ADS)
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.
Application of nonlinear time series models to driven systems
Hunter, N.F. Jr.
1990-01-01
In our laboratory we have been engaged in an effort to model nonlinear systems using time series methods. Our objectives have been, first, to understand how the time series response of a nonlinear system unfolds as a function of the underlying state variables, second, to model the evolution of the state variables, and finally, to predict nonlinear system responses. We hope to address the relationship between model parameters and system parameters in the near future. Control of nonlinear systems based on experimentally derived parameters is also a planned topic of future research. 28 refs., 15 figs., 2 tabs.
Dynamic Modeling of time series using Artificial Neural Networks
NASA Astrophysics Data System (ADS)
Nair, A. D.; Principe, Jose C.
1995-12-01
Artificial Neural Networks (ANN) have the ability to adapt to and learn complex topologies, they represent new technology with which to explore dynamical systems. Multi-step prediction is used to capture the dynamics of the system that produced the time series. Multi-step prediction is implemented by a recurrent ANN trained with trajectory learning. Two separate memories are employed in training the ANN, the common tapped delay-line memory and the new gamma memory. This methodology has been applied to the time series of a white dwarf and to the quasar 3C 345.
Scaling analysis of multi-variate intermittent time series
NASA Astrophysics Data System (ADS)
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.
Scale dependence of the directional relationships between coupled time series
NASA Astrophysics Data System (ADS)
Shirazi, Amir Hossein; Aghamohammadi, Cina; Anvari, Mehrnaz; Bahraminasab, Alireza; Rahimi Tabar, M. Reza; Peinke, Joachim; Sahimi, Muhammad; Marsili, Matteo
2013-02-01
Using the cross-correlation of the wavelet transformation, we propose a general method of studying the scale dependence of the direction of coupling for coupled time series. The method is first demonstrated by applying it to coupled van der Pol forced oscillators and coupled nonlinear stochastic equations. We then apply the method to the analysis of the log-return time series of the stock values of the IBM and General Electric (GE) companies. Our analysis indicates that, on average, IBM stocks react earlier to possible common sector price movements than those of GE.
Adaptive median filtering for preprocessing of time series measurements
NASA Technical Reports Server (NTRS)
Paunonen, Matti
1993-01-01
A median (L1-norm) filtering program using polynomials was developed. This program was used in automatic recycling data screening. Additionally, a special adaptive program to work with asymmetric distributions was developed. Examples of adaptive median filtering of satellite laser range observations and TV satellite time measurements are given. The program proved to be versatile and time saving in data screening of time series measurements.
Kālī: Time series data modeler
NASA Astrophysics Data System (ADS)
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.
Learning time series evolution by unsupervised extraction of correlations
Deco, G.; Schuermann, B. )
1995-03-01
As a consequence, we are able to model chaotic and nonchaotic time series. Furthermore, one critical point in modeling time series is the determination of the dimension of the embedding vector used, i.e., the number of components of the past that are needed to predict the future. With this method we can detect the embedding dimension by extracting the influence of the past on the future, i.e., the correlation of remote past and future. Optimal embedding dimensions are obtained for the Henon map and the Mackey-Glass series. When noisy data corrupted by colored noise are used, a model is still possible. The noise will then be decorrelated by the network. In the case of modeling a chemical reaction, the most natural architecture that conserves the volume is a symplectic network which describes a system that conserves the entropy and therefore the transmitted information.
A multiscale statistical model for time series forecasting
NASA Astrophysics Data System (ADS)
Wang, W.; Pollak, I.
2007-02-01
We propose a stochastic grammar model for random-walk-like time series that has features at several temporal scales. We use a tree structure to model these multiscale features. The inside-outside algorithm is used to estimate the model parameters. We develop an algorithm to forecast the sign of the first difference of a time series. We illustrate the algorithm using log-price series of several stocks and compare with linear prediction and a neural network approach. We furthermore illustrate our algorithm using synthetic data and show that it significantly outperforms both the linear predictor and the neural network. The construction of our synthetic data indicates what types of signals our algorithm is well suited for.
Segmentation of time series with long-range fractal correlations
Bernaola-Galván, P.; Oliver, J.L.; Hackenberg, M.; Coronado, A.V.; Ivanov, P.Ch.; Carpena, P.
2012-01-01
Segmentation is a standard method of data analysis to identify change-points dividing a nonstationary time series into homogeneous segments. However, for long-range fractal correlated series, most of the segmentation techniques detect spurious change-points which are simply due to the heterogeneities induced by the correlations and not to real nonstationarities. To avoid this oversegmentation, we present a segmentation algorithm which takes as a reference for homogeneity, instead of a random i.i.d. series, a correlated series modeled by a fractional noise with the same degree of correlations as the series to be segmented. We apply our algorithm to artificial series with long-range correlations and show that it systematically detects only the change-points produced by real nonstationarities and not those created by the correlations of the signal. Further, we apply the method to the sequence of the long arm of human chromosome 21, which is known to have long-range fractal correlations. We obtain only three segments that clearly correspond to the three regions of different G + C composition revealed by means of a multi-scale wavelet plot. Similar results have been obtained when segmenting all human chromosome sequences, showing the existence of previously unknown huge compositional superstructures in the human genome. PMID:23645997
Ocean time-series near Bermuda: Hydrostation S and the US JGOFS Bermuda Atlantic time-series study
NASA Technical Reports Server (NTRS)
Michaels, Anthony F.; Knap, Anthony H.
1992-01-01
Bermuda is the site of two ocean time-series programs. At Hydrostation S, the ongoing biweekly profiles of temperature, salinity and oxygen now span 37 years. This is one of the longest open-ocean time-series data sets and provides a view of decadal scale variability in ocean processes. In 1988, the U.S. JGOFS Bermuda Atlantic Time-series Study began a wide range of measurements at a frequency of 14-18 cruises each year to understand temporal variability in ocean biogeochemistry. On each cruise, the data range from chemical analyses of discrete water samples to data from electronic packages of hydrographic and optics sensors. In addition, a range of biological and geochemical rate measurements are conducted that integrate over time-periods of minutes to days. This sampling strategy yields a reasonable resolution of the major seasonal patterns and of decadal scale variability. The Sargasso Sea also has a variety of episodic production events on scales of days to weeks and these are only poorly resolved. In addition, there is a substantial amount of mesoscale variability in this region and some of the perceived temporal patterns are caused by the intersection of the biweekly sampling with the natural spatial variability. In the Bermuda time-series programs, we have added a series of additional cruises to begin to assess these other sources of variation and their impacts on the interpretation of the main time-series record. However, the adequate resolution of higher frequency temporal patterns will probably require the introduction of new sampling strategies and some emerging technologies such as biogeochemical moorings and autonomous underwater vehicles.
Estimating The Seasonal Components In Hydrological Time Series
NASA Astrophysics Data System (ADS)
Grimaldi, S.; Montanari, A.
The hydrological safety of dams is usually evaluated by analysing historical data of river flows into the reservoir. When only short observed records are available, one is often forced to generate synthetic flow series in order to verify the safety of the dam with respect to more equally likely hydrological scenarios. To this end, stochastic pro- cesses are frequently applied and a key point of many of the simulation procedures which can be used is the estimation of the seasonal periodicities that may be present in the analysed time series. Such seasonalities often have to be removed from the his- torical record before performing the estimation of the parameters of the simulation model. A usual procedure is to estimate and subsequently eliminate the periodicities which may be present in the mean and variance of the considered time series. This study analyses the performances of various techniques for the estimation of the sea- sonal components which may affect the statistics of hydrological time series observed at fine time step. The scientific literature proposed different approaches to this end, but nevertheless their application to records collected at fine time step is often diffi- cult, due to the high variability of the data and the major significance of measurement errors which may occur during extreme events. This study aims at comparing some of the techniques proposed by the literature with a simple approach, that is obtained by modifying the well known STL method. The proposed approach is tested by estimat- ing the periodical components of some synthetic time series and applied by analysing the daily river flows of two major rivers located in Italy.
Complexity analysis of the turbulent environmental fluid flow time series
NASA Astrophysics Data System (ADS)
Mihailović, D. T.; Nikolić-Đorić, E.; Drešković, N.; Mimić, G.
2014-02-01
We have used the Kolmogorov complexities, sample and permutation entropies to quantify the randomness degree in river flow time series of two mountain rivers in Bosnia and Herzegovina, representing the turbulent environmental fluid, for the period 1926-1990. In particular, we have examined the monthly river flow time series from two rivers (the Miljacka and the Bosnia) in the mountain part of their flow and then calculated the Kolmogorov complexity (KL) based on the Lempel-Ziv Algorithm (LZA) (lower-KLL and upper-KLU), sample entropy (SE) and permutation entropy (PE) values for each time series. The results indicate that the KLL, KLU, SE and PE values in two rivers are close to each other regardless of the amplitude differences in their monthly flow rates. We have illustrated the changes in mountain river flow complexity by experiments using (i) the data set for the Bosnia River and (ii) anticipated human activities and projected climate changes. We have explored the sensitivity of considered measures in dependence on the length of time series. In addition, we have divided the period 1926-1990 into three subintervals: (a) 1926-1945, (b) 1946-1965, (c) 1966-1990, and calculated the KLL, KLU, SE, PE values for the various time series in these subintervals. It is found that during the period 1946-1965, there is a decrease in their complexities, and corresponding changes in the SE and PE, in comparison to the period 1926-1990. This complexity loss may be primarily attributed to (i) human interventions, after the Second World War, on these two rivers because of their use for water consumption and (ii) climate change in recent times.
The application of the transfer entropy to gappy time series
NASA Astrophysics Data System (ADS)
Kulp, C. W.; Tracy, E. R.
2009-03-01
The application of the transfer entropy to gappy symbolic time series is discussed. Although the transfer entropy can fail to correctly identify the drive-response relationship, it is able to robustly detect phase relationships. Hence, it might still be of use in applications requiring the detection of changes in these relationships.
The Design of Time-Series Comparisons under Resource Constraints.
ERIC Educational Resources Information Center
Willemain, Thomas R.; Hartunian, Nelson S.
1982-01-01
Two methods for dividing an interrupted time-series study between baseline and experimental phases when study resources are limited are compared. In fixed designs, the baseline duration is predetermined. In flexible designs the baseline duration is contingent on remaining resources and the match of results to prior expectations of the evaluator.…
Synchronization-based parameter estimation from time series
NASA Astrophysics Data System (ADS)
Parlitz, U.; Junge, L.; Kocarev, L.
1996-12-01
The parameters of a given (chaotic) dynamical model are estimated from scalar time series by adapting a computer model until it synchronizes with the given data. This parameter identification method is applied to numerically generated and experimental data from Chua's circuit.
Ultrasound RF time series for classification of breast lesions.
Uniyal, Nishant; Eskandari, Hani; Abolmaesumi, Purang; Sojoudi, Samira; Gordon, Paula; Warren, Linda; Rohling, Robert N; Salcudean, Septimiu E; Moradi, Mehdi
2015-02-01
This work reports the use of ultrasound radio frequency (RF) time series analysis as a method for ultrasound-based classification of malignant breast lesions. The RF time series method is versatile and requires only a few seconds of raw ultrasound data with no need for additional instrumentation. Using the RF time series features, and a machine learning framework, we have generated malignancy maps, from the estimated cancer likelihood, for decision support in biopsy recommendation. These maps depict the likelihood of malignancy for regions of size 1 mm(2) within the suspicious lesions. We report an area under receiver operating characteristics curve of 0.86 (95% confidence interval [CI]: 0.84%-0.90%) using support vector machines and 0.81 (95% CI: 0.78-0.85) using Random Forests classification algorithms, on 22 subjects with leave-one-subject-out cross-validation. Changing the classification method yielded consistent results which indicates the robustness of this tissue typing method. The findings of this report suggest that ultrasound RF time series, along with the developed machine learning framework, can help in differentiating malignant from benign breast lesions, subsequently reducing the number of unnecessary biopsies after mammography screening. PMID:25350925
The Relationship of Negative Affect and Thought: Time Series Analyses.
ERIC Educational Resources Information Center
Rubin, Amy; And Others
In recent years, the relationship between moods and thoughts has been the focus of much theorizing and some empirical work. A study was undertaken to examine the intraindividual relationship between negative affect and negative thoughts using a Box-Jenkins time series analysis. College students (N=33) completed a measure of negative mood and…
Analysis of Complex Intervention Effects in Time-Series Experiments.
ERIC Educational Resources Information Center
Bower, Cathleen
An iterative least squares procedure for analyzing the effect of various kinds of intervention in time-series data is described. There are numerous applications of this design in economics, education, and psychology, although until recently, no appropriate analysis techniques had been developed to deal with the model adequately. This paper…
ADAPTIVE DATA ANALYSIS OF COMPLEX FLUCTUATIONS IN PHYSIOLOGIC TIME SERIES
PENG, C.-K.; COSTA, MADALENA; GOLDBERGER, ARY L.
2009-01-01
We introduce a generic framework of dynamical complexity to understand and quantify fluctuations of physiologic time series. In particular, we discuss the importance of applying adaptive data analysis techniques, such as the empirical mode decomposition algorithm, to address the challenges of nonlinearity and nonstationarity that are typically exhibited in biological fluctuations. PMID:20041035
A Time-Series Analysis of Hispanic Unemployment.
ERIC Educational Resources Information Center
Defreitas, Gregory
1986-01-01
This study undertakes the first systematic time-series research on the cyclical patterns and principal determinants of Hispanic joblessness in the United States. The principal findings indicate that Hispanics tend to bear a disproportionate share of increases in unemployment during recessions. (Author/CT)
Identification of human operator performance models utilizing time series analysis
NASA Technical Reports Server (NTRS)
Holden, F. M.; Shinners, S. M.
1973-01-01
The results of an effort performed by Sperry Systems Management Division for AMRL in applying time series analysis as a tool for modeling the human operator are presented. This technique is utilized for determining the variation of the human transfer function under various levels of stress. The human operator's model is determined based on actual input and output data from a tracking experiment.
Handbook for Using the Intensive Time-Series Design.
ERIC Educational Resources Information Center
Mayer, Victor J.; Monk, John S.
Work on the development of the intensive time-series design was initiated because of the dissatisfaction with existing research designs. This dissatisfaction resulted from the paucity of data obtained from designs such as the pre-post and randomized posttest-only designs. All have the common characteristic of yielding data from only one or two…
IDENTIFICATION OF REGIME SHIFTS IN TIME SERIES USING NEIGHBORHOOD STATISTICS
The identification of alternative dynamic regimes in ecological systems requires several lines of evidence. Previous work on time series analysis of dynamic regimes includes mainly model-fitting methods. We introduce two methods that do not use models. These approaches use state-...
Time Series Data Visualization in World Wide Telescope
NASA Astrophysics Data System (ADS)
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.
A Method for Comparing Multivariate Time Series with Different Dimensions
Tapinos, Avraam; Mendes, Pedro
2013-01-01
In many situations it is desirable to compare dynamical systems based on their behavior. Similarity of behavior often implies similarity of internal mechanisms or dependency on common extrinsic factors. While there are widely used methods for comparing univariate time series, most dynamical systems are characterized by multivariate time series. Yet, comparison of multivariate time series has been limited to cases where they share a common dimensionality. A semi-metric is a distance function that has the properties of non-negativity, symmetry and reflexivity, but not sub-additivity. Here we develop a semi-metric – SMETS – that can be used for comparing groups of time series that may have different dimensions. To demonstrate its utility, the method is applied to dynamic models of biochemical networks and to portfolios of shares. The former is an example of a case where the dependencies between system variables are known, while in the latter the system is treated (and behaves) as a black box. PMID:23393554
Daily time series evapotranspiration maps for Oklahoma and Texas panhandle
Technology Transfer Automated Retrieval System (TEKTRAN)
Evapotranspiration (ET) is an important process in ecosystems’ water budget and closely linked to its productivity. Therefore, regional scale daily time series ET maps developed at high and medium resolutions have large utility in studying the carbon-energy-water nexus and managing water resources. ...
What Makes a Coursebook Series Stand the Test of Time?
ERIC Educational Resources Information Center
Illes, Eva
2009-01-01
Intriguingly, at a time when the ELT market is inundated with state-of-the-art coursebooks teaching modern-day English, a 30-year-old series enjoys continuing popularity in some secondary schools in Hungary. Why would teachers, several of whom are school-based teacher-mentors in the vanguard of the profession, purposefully choose materials which…
Time Series Analysis for the Drac River Basin (france)
NASA Astrophysics Data System (ADS)
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
Multiple imputation for time series data with Amelia package.
Zhang, Zhongheng
2016-02-01
Time series data are common in medical researches. Many laboratory variables or study endpoints could be measured repeatedly over time. Multiple imputation (MI) without considering time trend of a variable may cause it to be unreliable. The article illustrates how to perform MI by using Amelia package in a clinical scenario. Amelia package is powerful in that it allows for MI for time series data. External information on the variable of interest can also be incorporated by using prior or bound argument. Such information may be based on previous published observations, academic consensus, and personal experience. Diagnostics of imputation model can be performed by examining the distributions of imputed and observed values, or by using over-imputation technique. PMID:26904578
[Anomaly Detection of Multivariate Time Series Based on Riemannian Manifolds].
Xu, Yonghong; Hou, Xiaoying; Li Shuting; Cui, Jie
2015-06-01
Multivariate time series problems widely exist in production and life in the society. Anomaly detection has provided people with a lot of valuable information in financial, hydrological, meteorological fields, and the research areas of earthquake, video surveillance, medicine and others. In order to quickly and efficiently find exceptions in time sequence so that it can be presented in front of people in an intuitive way, we in this study combined the Riemannian manifold with statistical process control charts, based on sliding window, with a description of the covariance matrix as the time sequence, to achieve the multivariate time series of anomaly detection and its visualization. We made MA analog data flow and abnormal electrocardiogram data from MIT-BIH as experimental objects, and verified the anomaly detection method. The results showed that the method was reasonable and effective. PMID:26485975
Irreversibility of financial time series: A graph-theoretical approach
NASA Astrophysics Data System (ADS)
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.
Mixed Spectrum Analysis on fMRI Time-Series.
Kumar, Arun; Lin, Feng; Rajapakse, Jagath C
2016-06-01
Temporal autocorrelation present in functional magnetic resonance image (fMRI) data poses challenges to its analysis. The existing approaches handling autocorrelation in fMRI time-series often presume a specific model of autocorrelation such as an auto-regressive model. The main limitation here is that the correlation structure of voxels is generally unknown and varies in different brain regions because of different levels of neurogenic noises and pulsatile effects. Enforcing a universal model on all brain regions leads to bias and loss of efficiency in the analysis. In this paper, we propose the mixed spectrum analysis of the voxel time-series to separate the discrete component corresponding to input stimuli and the continuous component carrying temporal autocorrelation. A mixed spectral analysis technique based on M-spectral estimator is proposed, which effectively removes autocorrelation effects from voxel time-series and identify significant peaks of the spectrum. As the proposed method does not assume any prior model for the autocorrelation effect in voxel time-series, varying correlation structure among the brain regions does not affect its performance. We have modified the standard M-spectral method for an application on a spatial set of time-series by incorporating the contextual information related to the continuous spectrum of neighborhood voxels, thus reducing considerably the computation cost. Likelihood of the activation is predicted by comparing the amplitude of discrete component at stimulus frequency of voxels across the brain by using normal distribution and modeling spatial correlations among the likelihood with a conditional random field. We also demonstrate the application of the proposed method in detecting other desired frequencies. PMID:26800533
An Introductory Overview of Statistical Methods for Discrete Time Series
NASA Astrophysics Data System (ADS)
Meng, X.-L.; California-Harvard AstroStat Collaboration
2004-08-01
A number of statistical problems encounted in astrophysics are concerned with discrete time series, such as photon counts with variation in source intensity over time. This talk provides an introductory overview of the current state-of-the-art methods in statistics, including Bayesian methods aided by Markov chain Monte Carlo, for modeling and analyzing such data. These methods have also been successfully applied in other fields, such as economics.
Normalization methods in time series of platelet function assays
Van Poucke, Sven; Zhang, Zhongheng; Roest, Mark; Vukicevic, Milan; Beran, Maud; Lauwereins, Bart; Zheng, Ming-Hua; Henskens, Yvonne; Lancé, Marcus; Marcus, Abraham
2016-01-01
Abstract Platelet function can be quantitatively assessed by specific assays such as light-transmission aggregometry, multiple-electrode aggregometry measuring the response to adenosine diphosphate (ADP), arachidonic acid, collagen, and thrombin-receptor activating peptide and viscoelastic tests such as rotational thromboelastometry (ROTEM). The task of extracting meaningful statistical and clinical information from high-dimensional data spaces in temporal multivariate clinical data represented in multivariate time series is complex. Building insightful visualizations for multivariate time series demands adequate usage of normalization techniques. In this article, various methods for data normalization (z-transformation, range transformation, proportion transformation, and interquartile range) are presented and visualized discussing the most suited approach for platelet function data series. Normalization was calculated per assay (test) for all time points and per time point for all tests. Interquartile range, range transformation, and z-transformation demonstrated the correlation as calculated by the Spearman correlation test, when normalized per assay (test) for all time points. When normalizing per time point for all tests, no correlation could be abstracted from the charts as was the case when using all data as 1 dataset for normalization. PMID:27428217
National Ignition Campaign (NIC) Precision Tuning Series Shock Timing Experiments
Robey, H F; Celliers, P M
2011-07-19
A series of precision shock timing experiments have been performed on NIF. These experiments continue to adjust the laser pulse shape and employ the adjusted cone fraction (CF) in the picket (1st 2 ns of the laser pulse) as determined from the re-emit experiment series. The NIF ignition laser pulse is precisely shaped and consists of a series of four impulses, which drive a corresponding series of shock waves of increasing strength to accelerate and compress the capsule ablator and fuel layer. To optimize the implosion, they tune not only the strength (or power) but also, to sub-nanosecond accuracy, the timing of the shock waves. In a well-tuned implosion, the shock waves work together to compress and heat the fuel. For the shock timing experiments, a re-entrant cone is inserted through both the hohlraum wall and the capsule ablator allowing a direct optical view of the propagating shocks in the capsule interior using the VISAR (Velocity Interferometer System for Any Reflector) diagnostic from outside the hohlraum. To emulate the DT ice of an ignition capsule, the inside of the cone and the capsule are filled with liquid deuterium.
Fast computation of recurrences in long time series
NASA Astrophysics Data System (ADS)
Rawald, Tobias; Sips, Mike; Marwan, Norbert; Dransch, Doris
2014-05-01
The quadratic time complexity of calculating basic RQA measures, doubling the size of the input time series leads to a quadrupling in operations, impairs the fast computation of RQA in many application scenarios. As an example, we analyze the Potsdamer Reihe, an ongoing non-interrupted hourly temperature profile since 1893, consisting of 1,043,112 data points. Using an optimized single-threaded CPU implementation this analysis requires about six hours. Our approach conducts RQA for the Potsdamer Reihe in five minutes. We automatically split a long time series into smaller chunks (Divide) and distribute the computation of RQA measures across multiple GPU devices. To guarantee valid RQA results, we employ carryover buffers that allow sharing information between pairs of chunks (Recombine). We demonstrate the capabilities of our Divide and Recombine approach to process long time series by comparing the runtime of our implementation to existing RQA tools. We support a variety of platforms by employing the computing framework OpenCL. Our current implementation supports the computation of standard RQA measures (recurrence rate, determinism, laminarity, ratio, average diagonal line length, trapping time, longest diagonal line, longest vertical line, divergence, entropy, trend) and also calculates recurrence times. To utilize the potential of our approach for a number of applications, we plan to release our implementation under an Open Source software license. It will be available at http://www.gfz-potsdam.de/fast-rqa/. Since our approach allows to compute RQA measures for a long time series fast, we plan to extend our implementation to support multi-scale RQA.
Efficient spectral estimation for time series with intermittent gaps
NASA Astrophysics Data System (ADS)
Smith, L. T.; Constable, C.
2009-12-01
Data from magnetic satellites like CHAMP, Ørsted, and Swarm can be used to study electromagnetic induction in Earth’s mantle. Time series of internal and external spherical harmonic coefficients (usually those associated with the predominantly dipolar structure of ring current variations) are used to determine Earth’s electromagnetic response as a function of frequency of the external variations. Inversion of this response can yield information about electrical conductivity variations in Earth’s mantle. The inductive response depends on frequency through skin depth, so it is desirable to work with the longest time series possible. Intermittent gaps in available data complicate attempts to estimate the power or cross spectra and thus the electromagnetic response for satellite records. Complete data series are most effectively analyzed using direct multi-taper spectral estimation, either with prolate multitapers that efficiently minimize broadband bias, or with a set designed to minimize local bias. The latter group have frequently been approximated by sine tapers. Intermittent gaps in data may be patched over using custom designed interpolation. We focus on a different approach, using sets of multitapers explicitly designed to accommodate gaps in the data. The optimization problems for the prolate and minimum bias tapers are altered to allow a specific arrangement of data samples, producing a modified eigenvalue-eigenfunction problem. We have shown that the prolate tapers with gaps and the minimum bias tapers with gaps provide higher resolution spectral estimates with less leakage than spectral averaging of data sections bounded by gaps. Current work is focused on producing efficient algorithms for spectral estimation of data series with gaps. A major limitation is the time and memory needed for the solution of large eigenvalue problems used to calculate the tapers for long time series. Fortunately only a limited set of the largest eigenvalues are needed, and
Wavelet transform approach for fitting financial time series data
NASA Astrophysics Data System (ADS)
Ahmed, Amel Abdoullah; Ismail, Mohd Tahir
2015-10-01
This study investigates a newly developed technique; a combined wavelet filtering and VEC model, to study the dynamic relationship among financial time series. Wavelet filter has been used to annihilate noise data in daily data set of NASDAQ stock market of US, and three stock markets of Middle East and North Africa (MENA) region, namely, Egypt, Jordan, and Istanbul. The data covered is from 6/29/2001 to 5/5/2009. After that, the returns of generated series by wavelet filter and original series are analyzed by cointegration test and VEC model. The results show that the cointegration test affirms the existence of cointegration between the studied series, and there is a long-term relationship between the US, stock markets and MENA stock markets. A comparison between the proposed model and traditional model demonstrates that, the proposed model (DWT with VEC model) outperforms traditional model (VEC model) to fit the financial stock markets series well, and shows real information about these relationships among the stock markets.
Segmentation of biological multivariate time-series data
NASA Astrophysics Data System (ADS)
Omranian, Nooshin; Mueller-Roeber, Bernd; Nikoloski, Zoran
2015-03-01
Time-series data from multicomponent systems capture the dynamics of the ongoing processes and reflect the interactions between the components. The progression of processes in such systems usually involves check-points and events at which the relationships between the components are altered in response to stimuli. Detecting these events together with the implicated components can help understand the temporal aspects of complex biological systems. Here we propose a regularized regression-based approach for identifying breakpoints and corresponding segments from multivariate time-series data. In combination with techniques from clustering, the approach also allows estimating the significance of the determined breakpoints as well as the key components implicated in the emergence of the breakpoints. Comparative analysis with the existing alternatives demonstrates the power of the approach to identify biologically meaningful breakpoints in diverse time-resolved transcriptomics data sets from the yeast Saccharomyces cerevisiae and the diatom Thalassiosira pseudonana.
Time series segmentation with shifting means hidden markov models
NASA Astrophysics Data System (ADS)
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.
Mulstiscale Stochastic Generator of Multivariate Met-Ocean Time Series
NASA Astrophysics Data System (ADS)
Guanche, Yanira; Mínguez, Roberto; Méndez, Fernando J.
2013-04-01
The design of maritime structures requires information on sea state conditions that influence its behavior during its life cycle. In the last decades, there has been a increasing development of sea databases (buoys, reanalysis, satellite) that allow an accurate description of the marine climate and its interaction with a given structure in terms of functionality and stability. However, these databases have a limited timelength, and its appliance entails an associated uncertainty. To avoid this limitation, engineers try to sample synthetically generated time series, statistically consistent, which allow the simulation of longer time periods. The present work proposes a hybrid methodology to deal with this issue. It is based in the combination of clustering algorithms (k-means) and an autoregressive logistic regression model (logit). Since the marine climate is directly related to the atmospheric conditions at a synoptic scale, the proposed methodology takes both systems into account; generating simultaneously circulation patterns (weather types) time series and the sea state time series related. The generation of these time series can be summarized in three steps: (1) By applying the clustering technique k-means the atmospheric conditions are classified into a representative number of synoptical patterns (2) Taking into account different covariates involved (such as seasonality, interannual variability, trends or autoregressive term) the autoregressive logistic model is adjusted (3) Once the model is able to simulate weather types time series the last step is to generate multivariate hourly metocean parameters related to these weather types. This is done by an autoregressive model (ARMA) for each variable, including cross-correlation between them. To show the goodness of the proposed method the following data has been used: Sea Level Pressure (SLP) databases from NCEP-NCAR and Global Ocean Wave (GOW) reanalysis from IH Cantabria. The synthetical met-ocean hourly
Alignment of Noisy and Uniformly Scaled Time Series
NASA Astrophysics Data System (ADS)
Lipowsky, Constanze; Dranischnikow, Egor; Göttler, Herbert; Gottron, Thomas; Kemeter, Mathias; Schömer, Elmar
The alignment of noisy and uniformly scaled time series is an important but difficult task. Given two time series, one of which is a uniformly stretched subsequence of the other, we want to determine the stretching factor and the offset of the second time series within the first one. We adapted and enhanced different methods to address this problem: classical FFT-based approaches to determine the offset combined with a naïve search for the stretching factor or its direct computation in the frequency domain, bounded dynamic time warping and a new approach called shotgun analysis, which is inspired by sequencing and reassembling of genomes in bioinformatics. We thoroughly examined the strengths and weaknesses of the different methods on synthetic and real data sets. The FFT-based approaches are very accurate on high quality data, the shotgun approach is especially suitable for data with outliers. Dynamic time warping is a candidate for non-linear stretching or compression. We successfully applied the presented methods to identify steel coils via their thickness profiles.
Supplementing environmental isotopes with time series methods to date groundwater
NASA Astrophysics Data System (ADS)
Farlin, Julien
2015-04-01
A popular method to estimate the transit time of groundwater is to fit the predictions of a lumped parameter model (LPM) to environmental isotope measurements. The fitting, or inverse modeling, procedure consists in rejecting all parameters (or parameter combinations for more complex LPMs) that exceeds a given error threshold. In many usual cases where this does not lead to a single acceptable solution, additional and independent data can prove useful to further eliminate some of the remaining solutions. In the case study presented here, groundwater transit times have been estimated by combining tritium, temperature, and discharge measurements. Tritium measurements from a series of contact springs draining the Luxembourg Sandstone aquifer were used to estimate the two parameters of an exponential piston flow model. The piston flow parameter gives the transit time of tritium through the thick unsaturated zone of the aquifer, while the exponential component corresponds to its mean transit time in the saturated zone. Due to the limited extent of the tritium time series and the fact that tritium activity has nearly returned to its background concentration, the solution of the inverse modeling was not unique. The discharge measurements were then used to reduce the number of retained parameter combinations by estimating independently from tritium the transit time through the unsaturated and saturated zones. The former was calculated from the time lag between a time series of net annual recharge over ten years and the fluctuations in discharge over that same period, while the latter was calculated from the discharge recession during the dry season. Although both methods necessitate relatively long time series of at least a few years, they reduce dramatically the range of estimated transit times. Another possibility is to use the temperature signal measured in spring water. The amplitude damping and its shift relatively to air temperature (which we used as proxy for the
The Puoko-nui CCD Time-Series Photometer
NASA Astrophysics Data System (ADS)
Chote, P.; Sullivan, D. J.
2013-01-01
Puoko-nui (te reo Maori for ‘big eye’) is a precision time series photometer developed at Victoria University of Wellington, primarily for use with the 1m McLellan telescope at Mt John University Observatory (MJUO), at Lake Tekapo, New Zealand. GPS based timing provides excellent timing accuracy, and online reduction software processes frames as they are acquired. The user is presented with a simple user interface that includes instrument control and an up to date lightcurve and Fourier amplitude spectrum of the target star. Puoko-nui has been operating in its current form since early 2011, where it is primarily used to monitor pulsating white dwarf stars.
Assessing spatial covariance among time series of abundance.
Jorgensen, Jeffrey C; Ward, Eric J; Scheuerell, Mark D; Zabel, Richard W
2016-04-01
For species of conservation concern, an essential part of the recovery planning process is identifying discrete population units and their location with respect to one another. A common feature among geographically proximate populations is that the number of organisms tends to covary through time as a consequence of similar responses to exogenous influences. In turn, high covariation among populations can threaten the persistence of the larger metapopulation. Historically, explorations of the covariance in population size of species with many (>10) time series have been computationally difficult. Here, we illustrate how dynamic factor analysis (DFA) can be used to characterize diversity among time series of population abundances and the degree to which all populations can be represented by a few common signals. Our application focuses on anadromous Chinook salmon (Oncorhynchus tshawytscha), a species listed under the US Endangered Species Act, that is impacted by a variety of natural and anthropogenic factors. Specifically, we fit DFA models to 24 time series of population abundance and used model selection to identify the minimum number of latent variables that explained the most temporal variation after accounting for the effects of environmental covariates. We found support for grouping the time series according to 5 common latent variables. The top model included two covariates: the Pacific Decadal Oscillation in spring and summer. The assignment of populations to the latent variables matched the currently established population structure at a broad spatial scale. At a finer scale, there was more population grouping complexity. Some relatively distant populations were grouped together, and some relatively close populations - considered to be more aligned with each other - were more associated with populations further away. These coarse- and fine-grained examinations of spatial structure are important because they reveal different structural patterns not evident
Rényi’s information transfer between financial time series
NASA Astrophysics Data System (ADS)
Jizba, Petr; Kleinert, Hagen; Shefaat, Mohammad
2012-05-01
In this paper, we quantify the statistical coherence between financial time series by means of the Rényi entropy. With the help of Campbell’s coding theorem, we show that the Rényi entropy selectively emphasizes only certain sectors of the underlying empirical distribution while strongly suppressing others. This accentuation is controlled with Rényi’s parameter q. To tackle the issue of the information flow between time series, we formulate the concept of Rényi’s transfer entropy as a measure of information that is transferred only between certain parts of underlying distributions. This is particularly pertinent in financial time series, where the knowledge of marginal events such as spikes or sudden jumps is of a crucial importance. We apply the Rényian information flow to stock market time series from 11 world stock indices as sampled at a daily rate in the time period 02.01.1990-31.12.2009. Corresponding heat maps and net information flows are represented graphically. A detailed discussion of the transfer entropy between the DAX and S&P500 indices based on minute tick data gathered in the period 02.04.2008-11.09.2009 is also provided. Our analysis shows that the bivariate information flow between world markets is strongly asymmetric with a distinct information surplus flowing from the Asia-Pacific region to both European and US markets. An important yet less dramatic excess of information also flows from Europe to the US. This is particularly clearly seen from a careful analysis of Rényi information flow between the DAX and S&P500 indices.
Financial time series analysis based on information categorization method
NASA Astrophysics Data System (ADS)
Tian, Qiang; Shang, Pengjian; Feng, Guochen
2014-12-01
The paper mainly applies the information categorization method to analyze the financial time series. The method is used to examine the similarity of different sequences by calculating the distances between them. We apply this method to quantify the similarity of different stock markets. And we report the results of similarity in US and Chinese stock markets in periods 1991-1998 (before the Asian currency crisis), 1999-2006 (after the Asian currency crisis and before the global financial crisis), and 2007-2013 (during and after global financial crisis) by using this method. The results show the difference of similarity between different stock markets in different time periods and the similarity of the two stock markets become larger after these two crises. Also we acquire the results of similarity of 10 stock indices in three areas; it means the method can distinguish different areas' markets from the phylogenetic trees. The results show that we can get satisfactory information from financial markets by this method. The information categorization method can not only be used in physiologic time series, but also in financial time series.