NASA Astrophysics Data System (ADS)
Shin, Min-Su; Sekora, Michael; Byun, Yong-Ik
2009-12-01
We present a new framework to detect various types of variable objects within massive astronomical time series data. Assuming that the dominant population of objects is non-variable, we find outliers from this population by using a non-parametric Bayesian clustering algorithm based on an infinite Gaussian mixture model (GMM) and the Dirichlet process. The algorithm extracts information from a given data set, which is described by six variability indices. The GMM uses those variability indices to recover clusters that are described by six-dimensional multivariate Gaussian distributions, allowing our approach to consider the sampling pattern of time series data, systematic biases, the number of data points for each light curve and photometric quality. Using the Northern Sky Variability Survey data, we test our approach and prove that the infinite GMM is useful at detecting variable objects, while providing statistical inference estimation that suppresses false detection. The proposed approach will be effective in the exploration of future surveys such as Gaia, Panoramic Survey Telescope and Rapid Response System (Pan-STARRS) and Large Synoptic Survey Telescope (LSST), which will produce massive time series data.
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)
Casu, F.; de Luca, C.; Lanari, R.; Manunta, M.; Zinno, I.
2016-12-01
A methodology for computing surface deformation time series and mean velocity maps of large areas is presented. Our approach relies on the availability of a multi-temporal set of Synthetic Aperture Radar (SAR) data collected from ascending and descending orbits over an area of interest, and also permits to estimate the vertical and horizontal (East-West) displacement components of the Earth's surface. The adopted methodology is based on an advanced Cloud Computing implementation of the Differential SAR Interferometry (DInSAR) Parallel Small Baseline Subset (P-SBAS) processing chain which allows the unsupervised processing of large SAR data volumes, from the raw data (level-0) imagery up to the generation of DInSAR time series and maps. The presented solution, which is highly scalable, has been tested on the ascending and descending ENVISAT SAR archives, which have been acquired over a large area of Southern California (US) that extends for about 90.000 km2. Such an input dataset has been processed in parallel by exploiting 280 computing nodes of the Amazon Web Services Cloud environment. Moreover, to produce the final mean deformation velocity maps of the vertical and East-West displacement components of the whole investigated area, we took also advantage of the information available from external GPS measurements that permit to account for possible regional trends not easily detectable by DInSAR and to refer the P-SBAS measurements to an external geodetic datum. The presented results clearly demonstrate the effectiveness of the proposed approach that paves the way to the extensive use of the available ERS and ENVISAT SAR data archives. Furthermore, the proposed methodology can be particularly suitable to deal with the very huge data flow provided by the Sentinel-1 constellation, thus permitting to extend the DInSAR analyses at a nearly global scale. This work is partially supported by: the DPC-CNR agreement, the EPOS-IP project and the ESA GEP project.
NASA Astrophysics Data System (ADS)
Scargle, J.
With the generation of long, precise, and finely sampled time series the Age of Digital Astronomy is uncovering and elucidating energetic dynamical processes throughout the Universe. Fulfilling these opportunities requires data effective analysis techniques rapidly and automatically implementing advanced concepts. The Time Series Explorer, under development in collaboration with Tom Loredo, provides tools ranging from simple but optimal histograms to time and frequency domain analysis for arbitrary data modes with any time sampling. Examples of application of these tools for automated time series discovery will be given.
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
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
NASA Astrophysics Data System (ADS)
Božić, Bojan; Havlik, Denis
2010-05-01
Many applications commonly used in sensor service networks operate on the same type of data repeatedly over time. This kind of data is most naturally represented in the form of "time series". In its simplest form, a time series may consist of a single floating point number (e.g. temperature), that is recorded at regular intervals. More complex forms of time series include time series of complex observations (e.g. aggregations of related measurements, spectra, 2D coverages/images, ...), and time series recorded at irregular intervals. In addition, the time series may contain meta-information describing e.g. the provenance, uncertainty, and reliability of observations. The Time Series Toolbox (TS Toolbox) provides a set of software components and application programming interfaces that simplify recording, storage, processing and publishing of time series. This includes (1) "data connector" components implementing access to data using various protocols and data formats; (2) core components interfacing with the connector components and providing specific additional functionalities like data processing or caching; and (3) front-end components implementing interface functionality (user interfaces or software interfaces). The functionalities implemented by TS Toolbox components provide application developers with higher-level building blocks than typical general purpose libraries, and allow rapid development of fully fledged applications. The TS Toolbox also includes example applications that can be either used as they are, or as a basis for developing more complex applications. The TS-Toolbox, which was initially developed by the Austrian Institute of Technology in the scope of SANY "Sensors Anywhere", is written in Java, published under the terms of the GPL, and available for download on the SANY web site.
Growth of massive galaxies through cosmic time
NASA Astrophysics Data System (ADS)
Peralta de Arriba, Luis
2016-07-01
The discovery that massive galaxies are on average more compact in the primitive Universe has shown the importance of the mechanisms which are growing galaxies in size with cosmic time. A better understanding of the characteristics of these compact objects will give us clues about the nature of the mechanism which is contributing to the growth of massive galaxies. In the first part of this thesis we investigated the discrepancy between dynamical and stellar masses in massive compact early-type galaxies. We obtained velocity dispersions at different redshifts using our own observations with the GTC telescope as well as stacked spectra from a public survey built with the Keck II telescope. Our findings indicate that this discrepancy scales with galaxy compactness, but it does not correlate with redshift. These results lead us to interpret the discrepancy between these two mass estimators as a violation of the homology hypothesis assumed in the computation of dynamical masses, i.e. massive compact galaxies are not self-similar objects to normal-sized massive galaxies. The next step of our research was to guess what constraints on the evolutionary mechanisms of massive galaxies are implied by this non-homology. We find that galaxies populate a plane in the stellar mass-effective radius-velocity dispersion space, and we analyse the constraints that it means on a generic mechanism. Furthermore, we check that these constraints are compatible with simulations of the growth of early-type massive galaxies due to mergers. Finally we addressed the question of which is the best environment for looking for relic galaxies, i.e. old galaxies which have not suffered the size evolution. We find that they prefer dense environments. Comparing our observational results with simulations, we obtain an agreement between both. The most popular way to explain growth of massive galaxies is the accretion of galaxy satellites through mergers. The global conclusion of this thesis is that all
Disaggregating times series data
Joubert, S.B.; Burr, T.; Scovel, J.C.
1997-05-01
This report describes our experiences with disaggregating time series data. Suppose we have gathered data every two seconds and want to guess the data at one-second intervals. Under certain assumptions, there are several reasonable disaggregation methods as well as several performance measures to judge their performance. Here we present results for both simulated and real data for two methods using several performance criteria.
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
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
Linear Time Vertex Partitioning on Massive Graphs.
Mell, Peter; Harang, Richard; Gueye, Assane
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.
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
Network structure of multivariate time series.
Lacasa, Lucas; Nicosia, Vincenzo; Latora, Vito
2015-10-21
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
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
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
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.
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.
Predicting Nonlinear Time Series
1993-12-01
response becomes R,(k) = f (Y FV,(k)) (2.4) where Wy specifies the weight associated with the output of node i to the input of nodej in the next layer and...interconnections for each of these previous nodes. 18 prr~~~o• wfe :t iam i -- ---- --- --- --- Figure 5: Delay block for ATNN [9] Thus, nodej receives the...computed values, aj(tn), and dj(tn) denotes the desired output of nodej at time in. In this thesis, the weights and time delays update after each input
Langevin equations from time series.
Racca, E; Porporato, A
2005-02-01
We discuss the link between the approach to obtain the drift and diffusion of one-dimensional Langevin equations from time series, and Pope and Ching's relationship for stationary signals. The two approaches are based on different interpretations of conditional averages of the time derivatives of the time series at given levels. The analysis provides a useful indication for the correct application of Pope and Ching's relationship to obtain stochastic differential equations from time series and shows its validity, in a generalized sense, for nondifferentiable processes originating from Langevin equations.
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)
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)
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.
Time series prediction in agroecosystems
NASA Astrophysics Data System (ADS)
Cortina-Januchs, M. G.; Quintanilla-Dominguez, J.; Vega-Corona, A.; Andina, D.
2012-04-01
This work proposes a novel model to predict time series such as frost, precipitation, temperature, solar radiation, all of them important variables for the agriculture process. In the proposed model, Artificial Neural Networks (ANN) combined with clustering algorithms and sensor data fusion are used. The real time series are obtained from different sensors. The clustering algorithms find relationships between variables, clustering involves the task of dividing data sets, which assigns the same label to members who belong to the same group, so that each group is homogeneous and distinct from the others. Those relationships provide information to the ANN in order to obtain the time series prediction. The most important issue of ANN in time series prediction is generalization, which refers to their ability to produce reasonable predictions on data sets other than those used for the estimation of the model parameters.
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.
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.
Time series analysis of injuries.
Martinez-Schnell, B; Zaidi, A
1989-12-01
We used time series models in the exploratory and confirmatory analysis of selected fatal injuries in the United States from 1972 to 1983. We built autoregressive integrated moving average (ARIMA) models for monthly, weekly, and daily series of deaths and used these models to generate hypotheses. These deaths resulted from six causes of injuries: motor vehicles, suicides, homicides, falls, drownings, and residential fires. For each cause of injury, we estimated calendar effects on the monthly death counts. We confirmed the significant effect of vehicle miles travelled on motor vehicle fatalities with a transfer function model. Finally, we applied intervention analysis to deaths due to motor vehicles.
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.
High performance biomedical time series indexes using salient segmentation.
Woodbridge, Jonathan; Mortazavi, Bobak; Bui, Alex A T; Sarrafzadeh, Majid
2012-01-01
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.
Modeling North Pacific Time Series
NASA Astrophysics Data System (ADS)
Overland, J. E.; Percival, D. B.; Mofjeld, H. O.
2002-05-01
We present a case study in modeling the North Pacific (NP) index, a time series of the wintertime Aleutian low sea level pressure from 1900 to 1999. We consider three statistical models, namely, a Gaussian stationary autoregressive process, a Gaussian fractionally difference (FD) or ``long-memory" process, and a ``signal plus noise" process consisting of a square wave oscillation with a pentadecadal period embedded in Gaussian white noise. Each model depends upon three parameters, so all three models are equally simple. The shortness of the time series makes it unrealistic to formally prefer one model over the other: we estimate it would take a 300 year record to differentiate between the models. Although the models fit equally well, they have quite different implications for the long-term behavior of the NP index, e.g. generation of regimes of characteristic lengths. Additional information and physical arguments may add support for a particular model. The FD - ``long memory" process suggests multiple physical contributions with different damping constants many North Pacific biological time series which are influenced by atmospheric and oceanic processes, show regime-like ecosystem reorganizations.
Time series, periodograms, and significance
NASA Astrophysics Data System (ADS)
Hernandez, G.
1999-05-01
The geophysical literature shows a wide and conflicting usage of methods employed to extract meaningful information on coherent oscillations from measurements. This makes it difficult, if not impossible, to relate the findings reported by different authors. Therefore, we have undertaken a critical investigation of the tests and methodology used for determining the presence of statistically significant coherent oscillations in periodograms derived from time series. Statistical significance tests are only valid when performed on the independent frequencies present in a measurement. Both the number of possible independent frequencies in a periodogram and the significance tests are determined by the number of degrees of freedom, which is the number of true independent measurements, present in the time series, rather than the number of sample points in the measurement. The number of degrees of freedom is an intrinsic property of the data, and it must be determined from the serial coherence of the time series. As part of this investigation, a detailed study has been performed which clearly illustrates the deleterious effects that the apparently innocent and commonly used processes of filtering, de-trending, and tapering of data have on periodogram analysis and the consequent difficulties in the interpretation of the statistical significance thus derived. For the sake of clarity, a specific example of actual field measurements containing unevenly-spaced measurements, gaps, etc., as well as synthetic examples, have been used to illustrate the periodogram approach, and pitfalls, leading to the (statistical) significance tests for the presence of coherent oscillations. Among the insights of this investigation are: (1) the concept of a time series being (statistically) band limited by its own serial coherence and thus having a critical sampling rate which defines one of the necessary requirements for the proper statistical design of an experiment; (2) the design of a critical
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.
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…
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…
Detecting chaos from time series
NASA Astrophysics Data System (ADS)
Xiaofeng, Gong; Lai, C. H.
2000-02-01
In this paper, an entirely data-based method to detect chaos from the time series is developed by introducing icons/Journals/Common/epsilon" ALT="epsilon" ALIGN="TOP"/> p -neighbour points (the p -steps icons/Journals/Common/epsilon" ALT="epsilon" ALIGN="TOP"/> -neighbour points). We demonstrate that for deterministic chaotic systems, there exists a linear relationship between the logarithm of the average number of icons/Journals/Common/epsilon" ALT="epsilon" ALIGN="TOP"/> p -neighbour points, lnn p ,icons/Journals/Common/epsilon" ALT="epsilon" ALIGN="TOP"/> , and the time step, p . The coefficient can be related to the KS entropy of the system. The effects of the embedding dimension and noise are also discussed.
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.
Regenerating time series from ordinal networks.
McCullough, Michael; Sakellariou, Konstantinos; Stemler, Thomas; Small, Michael
2017-03-01
Recently proposed ordinal networks not only afford novel methods of nonlinear time series analysis but also constitute stochastic approximations of the deterministic flow time series from which the network models are constructed. In this paper, we construct ordinal networks from discrete sampled continuous chaotic time series and then regenerate new time series by taking random walks on the ordinal network. We then investigate the extent to which the dynamics of the original time series are encoded in the ordinal networks and retained through the process of regenerating new time series by using several distinct quantitative approaches. First, we use recurrence quantification analysis on traditional recurrence plots and order recurrence plots to compare the temporal structure of the original time series with random walk surrogate time series. Second, we estimate the largest Lyapunov exponent from the original time series and investigate the extent to which this invariant measure can be estimated from the surrogate time series. Finally, estimates of correlation dimension are computed to compare the topological properties of the original and surrogate time series dynamics. Our findings show that ordinal networks constructed from univariate time series data constitute stochastic models which approximate important dynamical properties of the original systems.
Regenerating time series from ordinal networks
NASA Astrophysics Data System (ADS)
McCullough, Michael; Sakellariou, Konstantinos; Stemler, Thomas; Small, Michael
2017-03-01
Recently proposed ordinal networks not only afford novel methods of nonlinear time series analysis but also constitute stochastic approximations of the deterministic flow time series from which the network models are constructed. In this paper, we construct ordinal networks from discrete sampled continuous chaotic time series and then regenerate new time series by taking random walks on the ordinal network. We then investigate the extent to which the dynamics of the original time series are encoded in the ordinal networks and retained through the process of regenerating new time series by using several distinct quantitative approaches. First, we use recurrence quantification analysis on traditional recurrence plots and order recurrence plots to compare the temporal structure of the original time series with random walk surrogate time series. Second, we estimate the largest Lyapunov exponent from the original time series and investigate the extent to which this invariant measure can be estimated from the surrogate time series. Finally, estimates of correlation dimension are computed to compare the topological properties of the original and surrogate time series dynamics. Our findings show that ordinal networks constructed from univariate time series data constitute stochastic models which approximate important dynamical properties of the original systems.
Duality between Time Series and Networks
Campanharo, Andriana S. L. O.; Sirer, M. Irmak; Malmgren, R. Dean; Ramos, Fernando M.; Amaral, Luís A. Nunes.
2011-01-01
Studying the interaction between a system's components and the temporal evolution of the system are two common ways to uncover and characterize its internal workings. Recently, several maps from a time series to a network have been proposed with the intent of using network metrics to characterize time series. Although these maps demonstrate that different time series result in networks with distinct topological properties, it remains unclear how these topological properties relate to the original time series. Here, we propose a map from a time series to a network with an approximate inverse operation, making it possible to use network statistics to characterize time series and time series statistics to characterize networks. As a proof of concept, we generate an ensemble of time series ranging from periodic to random and confirm that application of the proposed map retains much of the information encoded in the original time series (or networks) after application of the map (or its inverse). Our results suggest that network analysis can be used to distinguish different dynamic regimes in time series and, perhaps more importantly, time series analysis can provide a powerful set of tools that augment the traditional network analysis toolkit to quantify networks in new and useful ways. PMID:21858093
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
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.
Association mining of dependency between time series
NASA Astrophysics Data System (ADS)
Hafez, Alaaeldin
2001-03-01
Time series analysis is considered as a crucial component of strategic control over a broad variety of disciplines in business, science and engineering. Time series data is a sequence of observations collected over intervals of time. Each time series describes a phenomenon as a function of time. Analysis on time series data includes discovering trends (or patterns) in a time series sequence. In the last few years, data mining has emerged and been recognized as a new technology for data analysis. Data Mining is the process of discovering potentially valuable patterns, associations, trends, sequences and dependencies in data. Data mining techniques can discover information that many traditional business analysis and statistical techniques fail to deliver. In this paper, we adapt and innovate data mining techniques to analyze time series data. By using data mining techniques, maximal frequent patterns are discovered and used in predicting future sequences or trends, where trends describe the behavior of a sequence. In order to include different types of time series (e.g. irregular and non- systematic), we consider past frequent patterns of the same time sequences (local patterns) and of other dependent time sequences (global patterns). We use the word 'dependent' instead of the word 'similar' for emphasis on real life time series where two time series sequences could be completely different (in values, shapes, etc.), but they still react to the same conditions in a dependent way. In this paper, we propose the Dependence Mining Technique that could be used in predicting time series sequences. The proposed technique consists of three phases: (a) for all time series sequences, generate their trend sequences, (b) discover maximal frequent trend patterns, generate pattern vectors (to keep information of frequent trend patterns), use trend pattern vectors to predict future time series sequences.
Smoothing of climate time series revisited
NASA Astrophysics Data System (ADS)
Mann, Michael E.
2008-08-01
We present an easily implemented method for smoothing climate time series, generalizing upon an approach previously described by Mann (2004). The method adaptively weights the three lowest order time series boundary constraints to optimize the fit with the raw time series. We apply the method to the instrumental global mean temperature series from 1850-2007 and to various surrogate global mean temperature series from 1850-2100 derived from the CMIP3 multimodel intercomparison project. These applications demonstrate that the adaptive method systematically out-performs certain widely used default smoothing methods, and is more likely to yield accurate assessments of long-term warming trends.
TSAN: a package for time series analysis.
Wang, D C; Vagnucci, A H
1980-04-01
Many biomedical data are in the form of time series. Analyses of these data include: (1) search for any biorhythm; (2) test of homogeneity of several time series; (3) assessment of stationarity; (4) test of normality of the time series histogram; (5) evaluation of dependence between data points. In this paper we present a subroutine package called TSAN. It is developed to accomplish these tasks. Computational methods, as well as flowcharts, for these subroutines are described. Two sample runs are demonstrated.
The Theory of Standardized Time Series.
1985-04-01
3.1)),’the method of standardized time series produces asymptotically valid confidence intevals for steady7&tepi1Tsmneters. However, these intervals...the method of standardized time series produces asymptotically valid confidence intevals for steady-state parameters. However, these intervals are...fa o & s d ......ary O W f, . .d by W eek m b o ), Da~cn an o~simulation output analysis confidence intervals standardized time series functional
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…
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.
Transfer entropy between multivariate time series
NASA Astrophysics Data System (ADS)
Mao, Xuegeng; Shang, Pengjian
2017-06-01
It is a crucial topic to identify the direction and strength of the interdependence between time series in multivariate systems. In this paper, we propose the method of transfer entropy based on the theory of time-delay reconstruction of a phase space, which is a model-free approach to detect causalities in multivariate time series. This method overcomes the limitation that original transfer entropy only can capture which system drives the transition probabilities of another in scalar time series. Using artificial time series, we show that the driving character is obviously reflected with the increase of the coupling strength between two signals and confirm the effectiveness of the method with noise added. Furthermore, we utilize it to real-world data, namely financial time series, in order to characterize the information flow among different stocks.
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.
Linear Relations in Time Series Models. I.
ERIC Educational Resources Information Center
Villegas, C.
1976-01-01
A multiple time series is defined as the sum of an autoregressive process on a line and independent Gaussian white noise or a hyperplane that goes through the origin and intersects the line at a single point. This process is a multiple autoregressive time series in which the regression matrices satisfy suitable conditions. For a related article…
On reconstruction of time series in climatology
NASA Astrophysics Data System (ADS)
Privalsky, V.; Gluhovsky, A.
2015-10-01
The approach to time series reconstruction in climatology based upon cross-correlation coefficients and regression equations is mathematically incorrect because it ignores the dependence of time series upon their past. The proper method described here for the bivariate case requires the autoregressive time- and frequency domains modeling of the time series which contains simultaneous observations of both scalar series with subsequent application of the model to restore the shorter one into the past. The method presents further development of previous efforts taken by a number of authors starting from A. Douglass who introduced some concepts of time series analysis into paleoclimatology. The method is applied to the monthly data of total solar irradiance (TSI), 1979-2014, and sunspot numbers (SSN), 1749-2014, to restore the TSI data over 1749-1978. The results of the reconstruction are in statistical agreement with observations.
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.
NASA Technical Reports Server (NTRS)
Leberl, F.; Fuchs, H.; Ford, J. P.
1981-01-01
A set of ten side-looking radar images of a mining area in Arizona that were aquired over a period of 14 yr are studied to demonstrate the photogrammetric differential-rectification technique applied to radar images and to examine changes that occurred in the area over time. Five of the images are rectified by using ground control points and a digital height model taken from a map. Residual coordinate errors in ground control are reduced from several hundred meters in all cases to + or - 19 to 70 m. The contents of the radar images are compared with a Landsat image and with aerial photographs. Effects of radar system parameters on radar images are briefly reviewed.
1998-06-10
These mosaics of Jupiter's night side show the Jovian aurora at approximately 45 minute intervals as the auroral ring rotated with the planet below the spacecraft. The images were obtained by the Solid State Imaging (SSI) system on NASA's Galileo spacecraft. during its eleventh orbit of Jupiter. The auroral ring is offset from Jupiter's pole of rotation and reaches the lowest latitude near 165 degrees west longitude. The aurora is hundreds of kilometers wide, and when it crosses the edge of Jupiter, it is about 250 kilometers above the planet. As on Earth, the auroral emission is caused by electrically charged particles striking atoms in the upper atmosphere from above. The particles travel along Jupiter's magnetic field lines, but their origin is not fully understood. The field lines where the aurora is most intense cross the Jovian equator at large distances (many Jovian radii) from the planet. The faint background throughout the image is scattered light in the camera. This stray light comes from the sunlit portion of Jupiter, which is out of the image. In multispectral observations the aurora appears red, consistent with how atomic hydrogen in Jupiter's atmosphere would glow. Galileo's unique perspective allows it to view the night side of the planet at short range, revealing details that cannot be seen from Earth. These detailed features are time dependent, and can be followed in this sequence of Galileo images. In the first mosaic, the auroral ring is directly over Jupiter's limb and is seen "edge on." In the fifth mosaic, the auroral emission is coming from several distinct bands. This mosaic also shows the footprint of the Io flux tube. Volcanic eruptions on Jupiter's moon, Io, spew forth particles that become ionized and are pulled into Jupiter's magnetic field to form an invisible tube, the Io flux tube, between Jupiter and Io. The bright circular feature towards the lower right may mark the location where these energetic particles impact Jupiter. Stars
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…
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
USDA-ARS?s Scientific Manuscript database
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...
Modelling of nonlinear filtering Poisson time series
NASA Astrophysics Data System (ADS)
Bochkarev, Vladimir V.; Belashova, Inna A.
2016-08-01
In this article, algorithms of non-linear filtering of Poisson time series are tested using statistical modelling. The objective is to find a representation of a time series as a wavelet series with a small number of non-linear coefficients, which allows distinguishing statistically significant details. There are well-known efficient algorithms of non-linear wavelet filtering for the case when the values of a time series have a normal distribution. However, if the distribution is not normal, good results can be expected using the maximum likelihood estimations. The filtration is studied according to the criterion of maximum likelihood by the example of Poisson time series. For direct optimisation of the likelihood function, different stochastic (genetic algorithms, annealing method) and deterministic optimization algorithms are used. Testing of the algorithm using both simulated series and empirical data (series of rare words frequencies according to the Google Books Ngram data were used) showed that filtering based on the criterion of maximum likelihood has a great advantage over well-known algorithms for the case of Poisson series. Also, the most perspective methods of optimisation were selected for this problem.
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
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.
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.
Regularization of Nutation Time Series at GSFC
NASA Astrophysics Data System (ADS)
Le Bail, K.; Gipson, J. M.; Bolotin, S.
2012-12-01
VLBI is unique in its ability to measure all five Earth orientation parameters. In this paper we focus on the two nutation parameters which characterize the orientation of the Earth's rotation axis in space. We look at the periodicities and the spectral characteristics of these parameters for both R1 and R4 sessions independently. The study of the most significant periodic signals for periods shorter than 600 days is common for these four time series (period of 450 days), and the type of noise determined by the Allan variance is a white noise for the four series. To investigate methods of regularizing the series, we look at a Singular Spectrum Analysis-derived method and at the Kalman filter. The two methods adequately reproduce the tendency of the nutation time series, but the resulting series are noisier using the Singular Spectrum Analysis-derived method.
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
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.
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.
Improving Intercomparability of Marine Biogeochemical Time Series
NASA Astrophysics Data System (ADS)
Benway, Heather M.; Telszewski, Maciej; Lorenzoni, Laura
2013-04-01
Shipboard biogeochemical time series represent one of the most valuable tools scientists have to quantify marine elemental fluxes and associated biogeochemical processes and to understand their links to changing climate. They provide the long, temporally resolved data sets needed to characterize ocean climate, biogeochemistry, and ecosystem variability and change. However, to monitor and differentiate natural cycles and human-driven changes in the global oceans, time series methodologies must be transparent and intercomparable when possible. To review current shipboard biogeochemical time series sampling and analytical methods, the International Ocean Carbon Coordination Project (IOCCP; http://www.ioccp.org/) and the Ocean Carbon and Biogeochemistry Program (http://www.us-ocb.org/) convened an international ocean time series workshop at the Bermuda Institute for Ocean Sciences.
Spectra: Time series power spectrum calculator
NASA Astrophysics Data System (ADS)
Gallardo, Tabaré
2017-01-01
Spectra calculates the power spectrum of a time series equally spaced or not based on the Spectral Correlation Coefficient (Ferraz-Mello 1981, Astron. Journal 86 (4), 619). It is very efficient for detection of low frequencies.
Spectral analysis of multiple time series
NASA Technical Reports Server (NTRS)
Dubman, M. R.
1972-01-01
Application of spectral analysis for mathematically determining relationship of random vibrations in structures and concurrent events in electric circuits, physiology, economics, and seismograms is discussed. Computer program for performing spectral analysis of multiple time series is described.
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.
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.
Multivariate Time Series Decomposition into Oscillation Components.
Matsuda, Takeru; Komaki, Fumiyasu
2017-08-01
Many time series are considered to be a superposition of several oscillation components. We have proposed a method for decomposing univariate time series into oscillation components and estimating their phases (Matsuda & Komaki, 2017 ). In this study, we extend that method to multivariate time series. We assume that several oscillators underlie the given multivariate time series and that each variable corresponds to a superposition of the projections of the oscillators. Thus, the oscillators superpose on each variable with amplitude and phase modulation. Based on this idea, we develop gaussian linear state-space models and use them to decompose the given multivariate time series. The model parameters are estimated from data using the empirical Bayes method, and the number of oscillators is determined using the Akaike information criterion. Therefore, the proposed method extracts underlying oscillators in a data-driven manner and enables investigation of phase dynamics in a given multivariate time series. Numerical results show the effectiveness of the proposed method. From monthly mean north-south sunspot number data, the proposed method reveals an interesting phase relationship.
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.
Ordinal pattern dependence between hydrological time series
NASA Astrophysics Data System (ADS)
Fischer, Svenja; Schumann, Andreas; Schnurr, Alexander
2017-05-01
Ordinal patterns provide a method to measure dependencies between time series. In contrast to classical correlation measures like the Pearson correlation coefficient they are able to measure not only linear correlation but also non-linear correlation even in the presence of non-stationarity. Hence, they are a noteworthy alternative to the classical approaches when considering discharge series. Discharge series naturally show a high variation as well as single extraordinary extreme events and, caused by anthropogenic and climatic impacts, non-stationary behaviour. Here, the method of ordinal patterns is used to compare pairwise discharge series derived from macro- and mesoscale catchments in Germany. Differences of coincident groups were detected for winter and summer annual maxima. Hydrological series, which are mainly driven by annual climatic conditions (yearly discharges and low water discharges) showed other and in some cases surprising interdependencies between macroscale catchments. Anthropogenic impacts as the construction of a reservoir or different flood conditions caused by urbanization could be detected.
Time averaging, ageing and delay analysis of financial time series
NASA Astrophysics Data System (ADS)
Cherstvy, Andrey G.; Vinod, Deepak; Aghion, Erez; Chechkin, Aleksei V.; Metzler, Ralf
2017-06-01
We introduce three strategies for the analysis of financial time series based on time averaged observables. These comprise the time averaged mean squared displacement (MSD) as well as the ageing and delay time methods for varying fractions of the financial time series. We explore these concepts via statistical analysis of historic time series for several Dow Jones Industrial indices for the period from the 1960s to 2015. Remarkably, we discover a simple universal law for the delay time averaged MSD. The observed features of the financial time series dynamics agree well with our analytical results for the time averaged measurables for geometric Brownian motion, underlying the famed Black-Scholes-Merton model. The concepts we promote here are shown to be useful for financial data analysis and enable one to unveil new universal features of stock market dynamics.
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.
Forbidden patterns in financial time series
NASA Astrophysics Data System (ADS)
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.
Highly comparative time-series analysis: the empirical structure of time series and their methods
Fulcher, Ben D.; Little, Max A.; Jones, Nick S.
2013-01-01
The process of collecting and organizing sets of observations represents a common theme throughout the history of science. However, despite the ubiquity of scientists measuring, recording and analysing the dynamics of different processes, an extensive organization of scientific time-series data and analysis methods has never been performed. Addressing this, annotated collections of over 35 000 real-world and model-generated time series, and over 9000 time-series analysis algorithms are analysed in this work. We introduce reduced representations of both time series, in terms of their properties measured by diverse scientific methods, and of time-series analysis methods, in terms of their behaviour on empirical time series, and use them to organize these interdisciplinary resources. This new approach to comparing across diverse scientific data and methods allows us to organize time-series datasets automatically according to their properties, retrieve alternatives to particular analysis methods developed in other scientific disciplines and automate the selection of useful methods for time-series classification and regression tasks. The broad scientific utility of these tools is demonstrated on datasets of electroencephalograms, self-affine time series, heartbeat intervals, speech signals and others, in each case contributing novel analysis techniques to the existing literature. Highly comparative techniques that compare across an interdisciplinary literature can thus be used to guide more focused research in time-series analysis for applications across the scientific disciplines. PMID:23554344
Highly comparative time-series analysis: the empirical structure of time series and their methods.
Fulcher, Ben D; Little, Max A; Jones, Nick S
2013-06-06
The process of collecting and organizing sets of observations represents a common theme throughout the history of science. However, despite the ubiquity of scientists measuring, recording and analysing the dynamics of different processes, an extensive organization of scientific time-series data and analysis methods has never been performed. Addressing this, annotated collections of over 35 000 real-world and model-generated time series, and over 9000 time-series analysis algorithms are analysed in this work. We introduce reduced representations of both time series, in terms of their properties measured by diverse scientific methods, and of time-series analysis methods, in terms of their behaviour on empirical time series, and use them to organize these interdisciplinary resources. This new approach to comparing across diverse scientific data and methods allows us to organize time-series datasets automatically according to their properties, retrieve alternatives to particular analysis methods developed in other scientific disciplines and automate the selection of useful methods for time-series classification and regression tasks. The broad scientific utility of these tools is demonstrated on datasets of electroencephalograms, self-affine time series, heartbeat intervals, speech signals and others, in each case contributing novel analysis techniques to the existing literature. Highly comparative techniques that compare across an interdisciplinary literature can thus be used to guide more focused research in time-series analysis for applications across the scientific disciplines.
Turbulencelike Behavior of Seismic Time Series
Manshour, P.; Saberi, S.; Sahimi, Muhammad; Peinke, J.; Pacheco, Amalio F.; Rahimi Tabar, M. Reza
2009-01-09
We report on a stochastic analysis of Earth's vertical velocity time series by using methods originally developed for complex hierarchical systems and, in particular, for turbulent flows. Analysis of the fluctuations of the detrended increments of the series reveals a pronounced transition in their probability density function from Gaussian to non-Gaussian. The transition occurs 5-10 hours prior to a moderate or large earthquake, hence representing a new and reliable precursor for detecting such earthquakes.
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.
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.
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.
Alternative predictors in chaotic time series
NASA Astrophysics Data System (ADS)
Alves, P. R. L.; Duarte, L. G. S.; da Mota, L. A. C. P.
2017-06-01
In the scheme of reconstruction, non-polynomial predictors improve the forecast from chaotic time series. The algebraic manipulation in the Maple environment is the basis for obtaining of accurate predictors. Beyond the different times of prediction, the optional arguments of the computational routines optimize the running and the analysis of global mappings.
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
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.
Complex network analysis of time series
NASA Astrophysics Data System (ADS)
Gao, Zhong-Ke; Small, Michael; Kurths, Jürgen
2016-12-01
Revealing complicated behaviors from time series constitutes a fundamental problem of continuing interest and it has attracted a great deal of attention from a wide variety of fields on account of its significant importance. The past decade has witnessed a rapid development of complex network studies, which allow to characterize many types of systems in nature and technology that contain a large number of components interacting with each other in a complicated manner. Recently, the complex network theory has been incorporated into the analysis of time series and fruitful achievements have been obtained. Complex network analysis of time series opens up new venues to address interdisciplinary challenges in climate dynamics, multiphase flow, brain functions, ECG dynamics, economics and traffic systems.
Global periodic effects of GPS time series
NASA Astrophysics Data System (ADS)
Poutanen, M.; Jokela, J.; Bilker, M.; Ollikainen, M.; Koivula, H.
2003-04-01
We have analysed time series of permanent GPS stations of the IGS network. Data used are the daily station coordinates of the IGS official solutions. Lomb periodograms show in most cases a statistically significant annual period in station height, which can be addressed to the periodic vertical motion of the site. We determined the amplitude and phase of the variation, and confirmed the phase shift between the Northern and Southern hemisphere. A similar behaviour can be seen in DORIS time series. In a regional network, the Finnish permanent GPS network, FinnRef, we have discovered an annual scale variation which can be explained as a loading effect of the crust. For the global network, a similar analysis will be made. We discuss on the geophysical reasons of the annual periods, and their consequences on the high-precision GPS observations. Additonal constraints, e.g. time series from a superconducting gravimeter are also discussed.
Time series of the northeast Pacific
NASA Astrophysics Data System (ADS)
Peña, M. Angelica; Bograd, Steven J.
2007-10-01
In July 2006, the North Pacific Marine Science Organization (PICES) and Fisheries & Oceans Canada sponsored the symposium “Time Series of the Northeast Pacific: A symposium to mark the 50th anniversary of Line P”. The symposium, which celebrated 50 years of oceanography along Line P and at Ocean Station Papa (OSP), explored the scientific value of the Line P and other long oceanographic time series of the northeast Pacific (NEP). Overviews of the principal NEP time-series were presented, which facilitated regional comparisons and promoted interaction and exchange of information among investigators working in the NEP. More than 80 scientists from 8 countries attended the symposium. This introductory essay is a brief overview of the symposium and the 10 papers that were selected for this special issue of Progress in Oceanography.
Self-accelerating massive gravity: Time for field fluctuations
NASA Astrophysics Data System (ADS)
Wyman, Mark; Hu, Wayne; Gratia, Pierre
2013-04-01
The ghost-free theory of massive gravity has exact solutions where the effective stress energy generated by the graviton mass term is a cosmological constant for any isotropic metric. Since they are exact, these solutions mimic a cosmological constant in the presence of any matter-induced isotropic metric perturbation. In the Stückelberg formulation, this stress energy is carried entirely by the spatial Stückelberg field. We show that any stress energy carried by fluctuations in the spatial field away from the exact solution always decays away in an expanding universe. However, the dynamics of the spatial Stückelberg field perturbation depend on the background temporal Stückelberg field, which is equivalent to the unitary gauge time coordinate. This dependence resolves an apparent conflict in the existing literature by showing that there is a special unitary time choice for which the field dynamics and energy density perturbations vanish identically. In general, the isotropic system has a single dynamical degree of freedom requiring two sets of initial data; however, only one of these initial data choices will affect the observable metric. Finally, we construct cosmological solutions with a well-defined perturbative initial value formulation and comment on alternate solutions that evolve to singularities.
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.
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.
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.
Interrupted time series analysis in clinical research.
Matowe, Lloyd K; Leister, Cathie A; Crivera, Concetta; Korth-Bradley, Joan M
2003-01-01
To demonstrate the usefulness of interrupted time series analysis in clinical trial design. A safety data set of electrocardiographic (ECG) information was simulated from actual data that had been collected in a Phase I study. Simulated data on 18 healthy volunteers based on a study performed in a contract research facility were collected based on single doses of an experimental medication that may affect ECG parameters. Serial ECGs were collected before and during treatment with the experimental medication. Data from 7 real subjects receiving placebo were used to simulate the pretreatment phase of time series; data from 18 real subjects receiving active treatment were used to simulate the treatment phase of the time series. Visual inspection of data was performed, followed by tests for trend, seasonality, and autocorrelation by use of SAS. There was no evidence of trend, seasonality, or autocorrelation. In 11 of 18 simulated individuals, statistically significant changes in QTc intervals were observed following treatment with the experimental medication. A significant time of day and treatment interaction was observed in 4 simulated patients. Interrupted time series analysis techniques offer an additional tool for the study of clinical situations in which patients must act as their own controls and where serial data can be collected at evenly distributed intervals.
Determinism test for very short time series.
Binder, P-M; Igarashi, Ryu; Seymour, William; Takeishi, Candy
2005-03-01
A test for determinism suitable for time series shorter than 100 points is presented, and applied to numerical and observed data. The method exploits the linear d(d(0)) dependence in the expression d(t) approximately d(0)e(lambda t) which describes the growth of small separations between trajectories in chaotic 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.
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 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.
Circulant Matrices and Time-Series Analysis
ERIC Educational Resources Information Center
Pollock, D. S. G.
2002-01-01
This paper sets forth some salient results in the algebra of circulant matrices which can be used in time-series analysis. It provides easy derivations of some results that are central to the analysis of statistical periodograms and empirical spectral density functions. A statistical test for the stationarity or homogeneity of empirical processes…
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.
Complex dynamic in ecological time series
Peter Turchin; Andrew D. Taylor
1992-01-01
Although the possibility of complex dynamical behaviors-limit cycles, quasiperiodic oscillations, and aperiodic chaos-has been recognized theoretically, most ecologists are skeptical of their importance in nature. In this paper we develop a methodology for reconstructing endogenous (or deterministic) dynamics from ecological time series. Our method consists of fitting...
Flood prediction using Time Series Data Mining
NASA Astrophysics Data System (ADS)
Damle, Chaitanya; Yalcin, Ali
2007-02-01
SummaryThis paper describes a novel approach to river flood prediction using Time Series Data Mining which combines chaos theory and data mining to characterize and predict events in complex, nonperiodic and chaotic time series. Geophysical phenomena, including earthquakes, floods and rainfall, represent a class of nonlinear systems termed chaotic, in which the relationships between variables in a system are dynamic and disproportionate, however completely deterministic. Chaos theory provides a structured explanation for irregular behavior and anomalies in systems that are not inherently stochastic. While nonlinear approaches such as Artificial Neural Networks, Hidden Markov Models and Nonlinear Prediction are useful in forecasting of daily discharge values in a river, the focus of these approaches is on forecasting magnitudes of future discharge values rather than the prediction of floods. The described Time Series Data Mining methodology focuses on the prediction of events where floods constitute the events in a river daily discharge time series. The methodology is demonstrated using data collected at the St. Louis gauging station located on the Mississippi River in the USA. Results associated with the impact of earliness of prediction and the acceptable risk-level vs. prediction accuracy are presented.
Parsimonious Linear Fingerprinting for Time Series
2010-09-01
like to detect such groups of harmonics. Fig. 1(d) gives a quick preview of the visualization and effectiveness of the proposed PLiF method: For the...coefficients of each individual frequency. As we find harmonic frequency sets in music , in real time- series like motions, we will expect to usually find
Time Series Analysis Without Model Identification.
ERIC Educational Resources Information Center
Velicer, Wayne F.; McDonald, Roderick P.
1984-01-01
A new approach to time series analysis was developed. It employs a generalized transformation of the observed data to meet the assumptions of the general linear model, thus eliminating the need to identify a specific model. This approach permits alternative computational procedures, based on a generalized least squares algorithm. (Author/BW)
Circulant Matrices and Time-Series Analysis
ERIC Educational Resources Information Center
Pollock, D. S. G.
2002-01-01
This paper sets forth some salient results in the algebra of circulant matrices which can be used in time-series analysis. It provides easy derivations of some results that are central to the analysis of statistical periodograms and empirical spectral density functions. A statistical test for the stationarity or homogeneity of empirical processes…
Three Analysis Examples for Time Series Data
USDA-ARS?s Scientific Manuscript database
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...
Offset detection in GPS coordinate time series
NASA Astrophysics Data System (ADS)
Gazeaux, J.; King, M. A.; Williams, S. D.
2013-12-01
Global Positioning System (GPS) time series are commonly affected by offsets of unknown magnitude and the large volume of data globally warrants investigation of automated detection approaches. The Detection of Offsets in GPS Experiment (DOGEx) showed that accuracy of Global Positioning System (GPS) time series can be significantly improved by applying statistical offset detection methods (see Gazeaux et al. (2013)). However, the best of these approaches did not perform as well as manual detection by expert analysts. Many of the features of GPS coordinates time series have not yet been fully taken into account in existing methods. Here, we apply Bayesian theory in order to make use of prior knowledge of the site noise characteristics and metadata in an attempt to make the offset detection more accurate. In the past decades, Bayesian theory has shown relevant results for a widespread range of applications, but has not yet been applied to GPS coordinates time series. Such methods incorporate different inputs such as a dynamic model (linear trend, periodic signal..) and a-priori information in a process that provides the best estimate of parameters (velocity, phase and amplitude of periodic signals...) based on all the available information. We test the new method on the DOGEx simulated dataset and compare it to previous solutions, and to Monte-Carlo method to test the accuracy of the procedure. We make a preliminary extension of the DOGEx dataset to introduce metadata information, allowing us to test the value of this data type in detecting offsets. The flexibility, robustness and limitations of the new approach are discussed. Gazeaux, J. Williams, S., King, M., Bos, M., Dach, R., Deo, M.,Moore, A.W., Ostini, L., Petrie, E., Roggero, M., Teferle, F.N., Olivares, G.,Webb, F.H. 2013. Detecting offsets in GPS time series: First results from the detection of offsets in GPS experiment. Journal of Geophysical Research: Solid Earth 118. 5. pp:2169-9356. Keywords : GPS
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
Delay differential analysis of time series.
Lainscsek, Claudia; Sejnowski, Terrence J
2015-03-01
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
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
Time-frequency analysis of electroencephalogram series
NASA Astrophysics Data System (ADS)
Blanco, S.; Quiroga, R. Quian; Rosso, O. A.; Kochen, S.
1995-03-01
In this paper we propose a method, based on the Gabor transform, to quantify and visualize the time evolution of the traditional frequency bands defined in the analysis of electroencephalogram (EEG) series. The information obtained in this way can be used for the information transfer analyses of the epileptic seizure as well as for their characterization. We found an optimal correlation between EEG visual inspection and the proposed method in the characterization of paroxism, spikes, and other transient alterations of background activity. The dynamical changes during an epileptic seizure are shown through the phase portrait. The method proposed was examplified with EEG series obtained with depth electrodes in refractory epileptic patients.
Periodic Effects In GPS Time Series
NASA Astrophysics Data System (ADS)
Koivula, H.; Ollikainen, M.; Poutanen, M.
We have computed the Lomb periodograms of GPS time series in the Finnish per- manent GPS network FinnRef. We can distinguish an annual period but also a diur- nal period in all vector components between any two stations, including the baseline length. The amplitude of the annual period is a function of the baseline length, thus behaving like a scale error. We have also analysed the diurnal period, which is most clearly visible between neighbouring stations. The FinnRef network is used e.g. for studying the Fennoscandian postglacial rebound. The periodic terms may be cancelled out in the solution of the height components of the stations by including seasonal terms in the solution. The method can be used when long series of observations are available, but in episodic campaigns the periodicity will degrade the accuracy. A geophysical interpretation of the annual variations in the height component of the GPS time series must be done with caution because the reason can be computational, not a physical one. We discuss on the effect and possible reasons for periods and tests made for studying the periodicity. We also discuss on the loading effect and their causes on the crustal deformation that can explain the observed scale variation in GPS time series.
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.; McCullough, D.R.; Barrett, R.H.
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.
Pseudotime estimation: deconfounding single cell time series
Reid, John E.; Wernisch, Lorenz
2016-01-01
Motivation: Repeated cross-sectional time series single cell data confound several sources of variation, with contributions from measurement noise, stochastic cell-to-cell variation and cell progression at different rates. Time series from single cell assays are particularly susceptible to confounding as the measurements are not averaged over populations of cells. When several genes are assayed in parallel these effects can be estimated and corrected for under certain smoothness assumptions on cell progression. Results: We present a principled probabilistic model with a Bayesian inference scheme to analyse such data. We demonstrate our method’s utility on public microarray, nCounter and RNA-seq datasets from three organisms. Our method almost perfectly recovers withheld capture times in an Arabidopsis dataset, it accurately estimates cell cycle peak times in a human prostate cancer cell line and it correctly identifies two precocious cells in a study of paracrine signalling in mouse dendritic cells. Furthermore, our method compares favourably with Monocle, a state-of-the-art technique. We also show using held-out data that uncertainty in the temporal dimension is a common confounder and should be accounted for in analyses of repeated cross-sectional time series. Availability and Implementation: Our method is available on CRAN in the DeLorean package. Contact: john.reid@mrc-bsu.cam.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27318198
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
Pseudotime estimation: deconfounding single cell time series.
Reid, John E; Wernisch, Lorenz
2016-10-01
Repeated cross-sectional time series single cell data confound several sources of variation, with contributions from measurement noise, stochastic cell-to-cell variation and cell progression at different rates. Time series from single cell assays are particularly susceptible to confounding as the measurements are not averaged over populations of cells. When several genes are assayed in parallel these effects can be estimated and corrected for under certain smoothness assumptions on cell progression. We present a principled probabilistic model with a Bayesian inference scheme to analyse such data. We demonstrate our method's utility on public microarray, nCounter and RNA-seq datasets from three organisms. Our method almost perfectly recovers withheld capture times in an Arabidopsis dataset, it accurately estimates cell cycle peak times in a human prostate cancer cell line and it correctly identifies two precocious cells in a study of paracrine signalling in mouse dendritic cells. Furthermore, our method compares favourably with Monocle, a state-of-the-art technique. We also show using held-out data that uncertainty in the temporal dimension is a common confounder and should be accounted for in analyses of repeated cross-sectional time series. Our method is available on CRAN in the DeLorean package. john.reid@mrc-bsu.cam.ac.uk Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press.
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
Hurst exponents for short time series
NASA Astrophysics Data System (ADS)
Qi, Jingchao; Yang, Huijie
2011-12-01
A concept called balanced estimator of diffusion entropy is proposed to detect quantitatively scalings in short time series. The effectiveness is verified by detecting successfully scaling properties for a large number of artificial fractional Brownian motions. Calculations show that this method can give reliable scalings for short time series with length ˜102. It is also used to detect scalings in the Shanghai Stock Index, five stock catalogs, and a total of 134 stocks collected from the Shanghai Stock Exchange Market. The scaling exponent for each catalog is significantly larger compared with that for the stocks included in the catalog. Selecting a window with size 650, the evolution of scaling for the Shanghai Stock Index is obtained by the window's sliding along the series. Global patterns in the evolutionary process are captured from the smoothed evolutionary curve. By comparing the patterns with the important event list in the history of the considered stock market, the evolution of scaling is matched with the stock index series. We can find that the important events fit very well with global transitions of the scaling behaviors.
Hurst exponents for short time series.
Qi, Jingchao; Yang, Huijie
2011-12-01
A concept called balanced estimator of diffusion entropy is proposed to detect quantitatively scalings in short time series. The effectiveness is verified by detecting successfully scaling properties for a large number of artificial fractional Brownian motions. Calculations show that this method can give reliable scalings for short time series with length ~10(2). It is also used to detect scalings in the Shanghai Stock Index, five stock catalogs, and a total of 134 stocks collected from the Shanghai Stock Exchange Market. The scaling exponent for each catalog is significantly larger compared with that for the stocks included in the catalog. Selecting a window with size 650, the evolution of scaling for the Shanghai Stock Index is obtained by the window's sliding along the series. Global patterns in the evolutionary process are captured from the smoothed evolutionary curve. By comparing the patterns with the important event list in the history of the considered stock market, the evolution of scaling is matched with the stock index series. We can find that the important events fit very well with global transitions of the scaling behaviors.
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.
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.
Visibility graphlet approach to chaotic time series
Mutua, Stephen; Gu, Changgui E-mail: hjyang@ustc.edu.cn; Yang, Huijie E-mail: hjyang@ustc.edu.cn
2016-05-15
Many novel methods have been proposed for mapping time series into complex networks. Although some dynamical behaviors can be effectively captured by existing approaches, the preservation and tracking of the temporal behaviors of a chaotic system remains an open problem. In this work, we extended the visibility graphlet approach to investigate both discrete and continuous chaotic time series. We applied visibility graphlets to capture the reconstructed local states, so that each is treated as a node and tracked downstream to create a temporal chain link. Our empirical findings show that the approach accurately captures the dynamical properties of chaotic systems. Networks constructed from periodic dynamic phases all converge to regular networks and to unique network structures for each model in the chaotic zones. Furthermore, our results show that the characterization of chaotic and non-chaotic zones in the Lorenz system corresponds to the maximal Lyapunov exponent, thus providing a simple and straightforward way to analyze chaotic systems.
Detecting anomalous phase synchronization from time series
Tokuda, Isao T.; Kumar Dana, Syamal; Kurths, Juergen
2008-06-15
Modeling approaches are presented for detecting an anomalous route to phase synchronization from time series of two interacting nonlinear oscillators. The anomalous transition is characterized by an enlargement of the mean frequency difference between the oscillators with an initial increase in the coupling strength. Although such a structure is common in a large class of coupled nonisochronous oscillators, prediction of the anomalous transition is nontrivial for experimental systems, whose dynamical properties are unknown. Two approaches are examined; one is a phase equational modeling of coupled limit cycle oscillators and the other is a nonlinear predictive modeling of coupled chaotic oscillators. Application to prototypical models such as two interacting predator-prey systems in both limit cycle and chaotic regimes demonstrates the capability of detecting the anomalous structure from only a few sets of time series. Experimental data from two coupled Chua circuits shows its applicability to real experimental system.
Multivariate Voronoi Outlier Detection for Time Series.
Zwilling, Chris E; Wang, Michelle Yongmei
2014-10-01
Outlier detection is a primary step in many data mining and analysis applications, including healthcare and medical research. This paper presents a general method to identify outliers in multivariate time series based on a Voronoi diagram, which we call Multivariate Voronoi Outlier Detection (MVOD). The approach copes with outliers in a multivariate framework, via designing and extracting effective attributes or features from the data that can take parametric or nonparametric forms. Voronoi diagrams allow for automatic configuration of the neighborhood relationship of the data points, which facilitates the differentiation of outliers and non-outliers. Experimental evaluation demonstrates that our MVOD is an accurate, sensitive, and robust method for detecting outliers in multivariate time series data.
Visibility graphlet approach to chaotic time series.
Mutua, Stephen; Gu, Changgui; Yang, Huijie
2016-05-01
Many novel methods have been proposed for mapping time series into complex networks. Although some dynamical behaviors can be effectively captured by existing approaches, the preservation and tracking of the temporal behaviors of a chaotic system remains an open problem. In this work, we extended the visibility graphlet approach to investigate both discrete and continuous chaotic time series. We applied visibility graphlets to capture the reconstructed local states, so that each is treated as a node and tracked downstream to create a temporal chain link. Our empirical findings show that the approach accurately captures the dynamical properties of chaotic systems. Networks constructed from periodic dynamic phases all converge to regular networks and to unique network structures for each model in the chaotic zones. Furthermore, our results show that the characterization of chaotic and non-chaotic zones in the Lorenz system corresponds to the maximal Lyapunov exponent, thus providing a simple and straightforward way to analyze chaotic systems.
Automatic pattern recognition in ECG time series.
Sternickel, Karsten
2002-05-01
In this paper, a technique for the automatic detection of any recurrent pattern in ECG time series is introduced. The wavelet transform is used to obtain a multiresolution representation of some example patterns for signal structure extraction. Neural Networks are trained with the wavelet transformed templates providing an efficient detector even for temporally varying patterns within the complete time series. The method is also robust against offsets and stable for signal to noise ratios larger than one. Its reliability was tested on 60 Holter ECG recordings of patients at the Department of Cardiology (University of Bonn). Due to the convincing results and its fast implementation the method can easily be used in clinical medicine. In particular, it solves the problem of automatic P wave detection in Holter ECG recordings.
Limits on Planets Orbiting Massive Stars from Radio Pulsar Timing
NASA Technical Reports Server (NTRS)
Thorsett, S. E.; Dewey, R. J.
1993-01-01
When a massive star collapses to a neutron star, rapidly losing over half its mass in a symmetric supernova explosiosn, any planets orbiting the star will be unbound. However, to explain the observed space velocity and binary fraction of radio pulsars, an asymmetric kick must be given to the neutron star of birth.
Limits on Planets Orbiting Massive Stars from Radio Pulsar Timing
NASA Technical Reports Server (NTRS)
Thorsett, S. E.; Dewey, R. J.
1993-01-01
When a massive star collapses to a neutron star, rapidly losing over half its mass in a symmetric supernova explosiosn, any planets orbiting the star will be unbound. However, to explain the observed space velocity and binary fraction of radio pulsars, an asymmetric kick must be given to the neutron star of birth.
Aggregated Indexing of Biomedical Time Series Data.
Woodbridge, Jonathan; Mortazavi, Bobak; Sarrafzadeh, Majid; Bui, Alex A T
2012-09-01
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.
Weighted Dynamic Time Warping for Time Series Classification
Jeong, Young-Seon; Jeong, Myong K; Omitaomu, Olufemi A
2011-01-01
Dynamic time warping (DTW), which finds the minimum path by providing non-linear alignments between two time series, has been widely used as a distance measure for time series classification and clustering. However, DTW does not account for the relative importance regarding the phase difference between a reference point and a testing point. This may lead to misclassification especially in applications where the shape similarity between two sequences is a major consideration for an accurate recognition. Therefore, we propose a novel distance measure, called a weighted DTW (WDTW), which is a penalty-based DTW. Our approach penalizes points with higher phase difference between a reference point and a testing point in order to prevent minimum distance distortion caused by outliers. The rationale underlying the proposed distance measure is demonstrated with some illustrative examples. A new weight function, called the modified logistic weight function (MLWF), is also proposed to systematically assign weights as a function of the phase difference between a reference point and a testing point. By applying different weights to adjacent points, the proposed algorithm can enhance the detection of similarity between two time series. We show that some popular distance measures such as DTW and Euclidean distance are special cases of our proposed WDTW measure. We extend the proposed idea to other variants of DTW such as derivative dynamic time warping (DDTW) and propose the weighted version of DDTW. We have compared the performances of our proposed procedures with other popular approaches using public data sets available through the UCR Time Series Data Mining Archive for both time series classification and clustering problems. The experimental results indicate that the proposed approaches can achieve improved accuracy for time series classification and clustering problems.
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.
Radar Interferometry Time Series Analysis and Tools
NASA Astrophysics Data System (ADS)
Buckley, S. M.
2006-12-01
We consider the use of several multi-interferogram analysis techniques for identifying transient ground motions. Our approaches range from specialized InSAR processing for persistent scatterer and small baseline subset methods to the post-processing of geocoded displacement maps using a linear inversion-singular value decomposition solution procedure. To better understand these approaches, we have simulated sets of interferograms spanning several deformation phenomena, including localized subsidence bowls with constant velocity and seasonal deformation fluctuations. We will present results and insights from the application of these time series analysis techniques to several land subsidence study sites with varying deformation and environmental conditions, e.g., arid Phoenix and coastal Houston-Galveston metropolitan areas and rural Texas sink holes. We consistently find that the time invested in implementing, applying and comparing multiple InSAR time series approaches for a given study site is rewarded with a deeper understanding of the techniques and deformation phenomena. To this end, and with support from NSF, we are preparing a first-version of an InSAR post-processing toolkit to be released to the InSAR science community. These studies form a baseline of results to compare against the higher spatial and temporal sampling anticipated from TerraSAR-X as well as the trade-off between spatial coverage and resolution when relying on ScanSAR interferometry.
Modeling stylized facts for financial time series
NASA Astrophysics Data System (ADS)
Krivoruchenko, M. I.; Alessio, E.; Frappietro, V.; Streckert, L. J.
2004-12-01
Multivariate probability density functions of returns are constructed in order to model the empirical behavior of returns in a financial time series. They describe the well-established deviations from the Gaussian random walk, such as an approximate scaling and heavy tails of the return distributions, long-ranged volatility-volatility correlations (volatility clustering) and return-volatility correlations (leverage effect). The model is tested successfully to fit joint distributions of the 100+ years of daily price returns of the Dow Jones 30 Industrial Average.
Confidence bands for time series trends
NASA Astrophysics Data System (ADS)
Gluhovsky, A.
2010-12-01
This talk will discuss the construction of subsampling simultaneous confidence bands for an unknown trend in time series composed of deterministic and stochastic components. For the latter, an iid noise, a stationary short-memory process, and a stationary long-memory process will be considered. Subsampling is a computer-intensive statistical method, which works under the weakest assumptions about data (contrasting standard statistical methods, which are based on strong assumptions rarely met in geosciences). This work is supported by the National Science Foundation Grant ATM-0756624.
Consistency of IVS nutation time series
NASA Astrophysics Data System (ADS)
Gattano, César; Lambert, Sébastien; Bizouard, Christian
2016-04-01
We give a review of the various VLBI-derived nutation time series provided by the different operational analysis centers of the IVS and three combination centers (IVS, IERS EOP Center, and Rapid Service/Prediction Center). We focus on the stability of small nutation amplitudes, including the free core nutation and other atmospherically-driven nutations, that are of interest for improving Earth models. We discuss the possible origins of the differences (software packaged, inversion methods, analysis configuration including a priori and estimation strategy) and the consequences for scientific exploitation of the data, especially in terms of nutation modeling and inference of the Earth's internal structure.
Gwilym Jenkins, Experimental Design and Time Series.
1984-04-01
of a changing process. This led to studies of discrete dynamic models and control problems and finally to work on time series and forecasting. A4S...practice based on sound -2- I theory in a never-ending iteration. The results of this mode of thinking come through strongly for example in his book with...arrival in Princeton marked the beginning of a long and happy collaboration between us which later resulted in much visiting to and from between England and
Time series modeling for automatic target recognition
NASA Astrophysics Data System (ADS)
Sokolnikov, Andre
2012-05-01
Time series modeling is proposed for identification of targets whose images are not clearly seen. The model building takes into account air turbulence, precipitation, fog, smoke and other factors obscuring and distorting the image. The complex of library data (of images, etc.) serving as a basis for identification provides the deterministic part of the identification process, while the partial image features, distorted parts, irrelevant pieces and absence of particular features comprise the stochastic part of the target identification. The missing data approach is elaborated that helps the prediction process for the image creation or reconstruction. The results are provided.
Detecting noise in a time series.
Cellucci, C. J.; Albano, A. M.; Rapp, P. E.; Pittenger, R. A.; Josiassen, R. C.
1997-09-01
A numerical algorithm is presented for estimating whether, and roughly to what extent, a time series is noise corrupted. Using phase-randomized surrogates constructed from the original signal, metrics are defined which can be used to quantify the noise level. A saturation occurs in these metrics at signal to noise ratios (SNRs) of around 0 dB and below, and also at around 20 dB and above. In between these two regions there is a monotonic transition in the value of the metrics from one region to the other corresponding to changes in the SNR. (c) 1997 American Institute of Physics.
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
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.
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
Dimensionless embedding for nonlinear time series analysis
NASA Astrophysics Data System (ADS)
Hirata, Yoshito; Aihara, Kazuyuki
2017-09-01
Recently, infinite-dimensional delay coordinates (InDDeCs) have been proposed for predicting high-dimensional dynamics instead of conventional delay coordinates. Although InDDeCs can realize faster computation and more accurate short-term prediction, it is still not well-known whether InDDeCs can be used in other applications of nonlinear time series analysis in which reconstruction is needed for the underlying dynamics from a scalar time series generated from a dynamical system. Here, we give theoretical support for justifying the use of InDDeCs and provide numerical examples to show that InDDeCs can be used for various applications for obtaining the recurrence plots, correlation dimensions, and maximal Lyapunov exponents, as well as testing directional couplings and extracting slow-driving forces. We demonstrate performance of the InDDeCs using the weather data. Thus, InDDeCs can eventually realize "dimensionless embedding" while we enjoy faster and more reliable computations.
Forecasting the Time Series of Sunspot Numbers
NASA Astrophysics Data System (ADS)
Aguirre, L. A.; Letellier, C.; Maquet, J.
2008-05-01
Forecasting the solar cycle is of great importance for weather prediction and environmental monitoring, and also constitutes a difficult scientific benchmark in nonlinear dynamical modeling. This paper describes the identification of a model and its use in the forecasting the time series comprised of Wolf’s sunspot numbers. A key feature of this procedure is that the original time series is first transformed into a symmetrical space where the dynamics of the solar dynamo are unfolded in a better way, thus improving the model. The nonlinear model obtained is parsimonious and has both deterministic and stochastic parts. Monte Carlo simulation of the whole model produces very consistent results with the deterministic part of the model but allows for the determination of confidence bands. The obtained model was used to predict cycles 24 and 25, although the forecast of the latter is seen as a crude approximation, given the long prediction horizon required. As for the 24th cycle, two estimates were obtained with peaks of 65±16 and of 87±13 units of sunspot numbers. The simulated results suggest that the 24th cycle will be shorter and less active than the preceding one.
Tremor classification and tremor time series analysis
NASA Astrophysics Data System (ADS)
Deuschl, Günther; Lauk, Michael; Timmer, Jens
1995-03-01
The separation between physiologic tremor (PT) in normal subjects and the pathological tremors of essential tremor (ET) or Parkinson's disease (PD) was investigated on the basis of monoaxial accelerometric recordings of 35 s hand tremor epochs. Frequency and amplitude were insufficient to separate between these conditions, except for the trivial distinction between normal and pathologic tremors that is already defined on the basis of amplitude. We found that waveform analysis revealed highly significant differences between normal and pathologic tremors, and, more importantly, among different forms of pathologic tremors. We found in our group of 25 patients with PT and 15 with ET a reasonable distinction with the third momentum and the time reversal invariance. A nearly complete distinction between these two conditions on the basis of the asymmetric decay of the autocorrelation function. We conclude that time series analysis can probably be developed into a powerful tool for the objective analysis of tremors.
Managing distribution changes in time series prediction
NASA Astrophysics Data System (ADS)
Matias, J. M.; Gonzalez-Manteiga, W.; Taboada, J.; Ordonez, C.
2006-07-01
When a problem is modeled statistically, a single distribution model is usually postulated that is assumed to be valid for the entire space. Nonetheless, this practice may be somewhat unrealistic in certain application areas, in which the conditions of the process that generates the data may change; as far as we are aware, however, no techniques have been developed to tackle this problem.This article proposes a technique for modeling and predicting this change in time series with a view to improving estimates and predictions. The technique is applied, among other models, to the hypernormal distribution recently proposed. When tested on real data from a range of stock market indices the technique produces better results that when a single distribution model is assumed to be valid for the entire period of time studied.Moreover, when a global model is postulated, it is highly recommended to select the hypernormal distribution parameter in the same likelihood maximization process.
Time series for blind biosignal classification model.
Wong, Derek F; Chao, Lidia S; Zeng, Xiaodong; Vai, Mang-I; Lam, Heng-Leong
2014-11-01
Biosignals such as electrocardiograms (ECG), electroencephalograms (EEG), and electromyograms (EMG), are important noninvasive measurements useful for making diagnostic decisions. Recently, considerable research has been conducted in order to potentially automate signal classification for assisting in disease diagnosis. However, the biosignal type (ECG, EEG, EMG or other) needs to be known prior to the classification process. If the given biosignal is of an unknown type, none of the existing methodologies can be utilized. In this paper, a blind biosignal classification model (B(2)SC Model) is proposed in order to identify the source biosignal type automatically, and thus ultimately benefit the diagnostic decision. The approach employs time series algorithms for constructing the model. It uses a dynamic time warping (DTW) algorithm with clustering to discover the similarity between two biosignals, and consequently classifies disease without prior knowledge of the source signal type. The empirical experiments presented in this paper demonstrate the effectiveness of the method as well as the scalability of the approach.
Automated time series forecasting for biosurveillance.
Burkom, Howard S; Murphy, Sean Patrick; Shmueli, Galit
2007-09-30
For robust detection performance, traditional control chart monitoring for biosurveillance is based on input data free of trends, day-of-week effects, and other systematic behaviour. Time series forecasting methods may be used to remove this behaviour by subtracting forecasts from observations to form residuals for algorithmic input. We describe three forecast methods and compare their predictive accuracy on each of 16 authentic syndromic data streams. The methods are (1) a non-adaptive regression model using a long historical baseline, (2) an adaptive regression model with a shorter, sliding baseline, and (3) the Holt-Winters method for generalized exponential smoothing. Criteria for comparing the forecasts were the root-mean-square error, the median absolute per cent error (MedAPE), and the median absolute deviation. The median-based criteria showed best overall performance for the Holt-Winters method. The MedAPE measures over the 16 test series averaged 16.5, 11.6, and 9.7 for the non-adaptive regression, adaptive regression, and Holt-Winters methods, respectively. The non-adaptive regression forecasts were degraded by changes in the data behaviour in the fixed baseline period used to compute model coefficients. The mean-based criterion was less conclusive because of the effects of poor forecasts on a small number of calendar holidays. The Holt-Winters method was also most effective at removing serial autocorrelation, with most 1-day-lag autocorrelation coefficients below 0.15. The forecast methods were compared without tuning them to the behaviour of individual series. We achieved improved predictions with such tuning of the Holt-Winters method, but practical use of such improvements for routine surveillance will require reliable data classification methods.
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.
Correcting and combining time series forecasters.
Firmino, Paulo Renato A; de Mattos Neto, Paulo S G; Ferreira, Tiago A E
2014-02-01
Combined forecasters have been in the vanguard of stochastic time series modeling. In this way it has been usual to suppose that each single model generates a residual or prediction error like a white noise. However, mostly because of disturbances not captured by each model, it is yet possible that such supposition is violated. The present paper introduces a two-step method for correcting and combining forecasting models. Firstly, the stochastic process underlying the bias of each predictive model is built according to a recursive ARIMA algorithm in order to achieve a white noise behavior. At each iteration of the algorithm the best ARIMA adjustment is determined according to a given information criterion (e.g. Akaike). Then, in the light of the corrected predictions, it is considered a maximum likelihood combined estimator. Applications involving single ARIMA and artificial neural networks models for Dow Jones Industrial Average Index, S&P500 Index, Google Stock Value, and Nasdaq Index series illustrate the usefulness of the proposed framework.
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.
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.
Spectrophotometric Time Series of η Carinae's Great Eruption
NASA Astrophysics Data System (ADS)
Rest, Armin; Bianco, Federica; Chornock, Ryan; Kunder, Andrea; Matheson, Thomas; Prieto, Jose Luis; Sinnott, Brendan; Smith, Chris; Smith, Nathan; Walborn, Nolan; Welch, Doug
2013-08-01
η Carinae (η Car) is one of the most massive binaries in the Milky Way teDH97, and its expanding circumstellar nebula has been studied in detail teSmith06. It was seen as the second brightest star in the sky during its 1800s ``Great Eruption'' (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 and warrant continued monitoring of its echoes. 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 draw a connection to the most energetic core-collapse supernovae that are being discovered in synoptic surveys. The recent observation (September 2012), of the SN impostor SN 2009ip transitioning to a real SN explosion teSmith12 highlights the importance of studying η Car's GE in great detail.
Spectrophotometric Time Series of eta Carinae's Great Eruption
NASA Astrophysics Data System (ADS)
Rest, Armin; Bianco, Federica; Chornock, Ryan; Matheson, Thomas; Prieto, Jose Luis; Sinnott, Brendan; Smith, Chris; Smith, Nathan; Walborn, Nolan; Welch, Doug
2013-02-01
eta Carinae (eta Car) is one of the most massive binaries in the Milky Way teDH97, and its expanding circumstellar nebula has been studied in detail teSmith06. It was seen as the second brightest star in the sky during its 1800s ``Great Eruption'' (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 eta 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 and warrant continued monitoring of its echoes. We propose to obtain a spectrophotometric time series of the GE from it different directions, allowing the original eruption of eta Car to be studied as a function of time as well as latitude. A detailed spectroscopic study of the LEs of eta Car could help us understand (episodic) mass- loss in the most massive evolved stars and their connection to the most energetic core-collapse supernovae that are being discovered in synoptic surveys. Very recently (September 2012), a SN impostor discovered in 2009 (SN 2009ip) was observed to transition to a real SN explosion teSmith12. This discovery highlights the importance of studying eta Car's GE in great detail.
Inflation and Late Time Acceleration Designed by Stueckelberg Massive Photon
NASA Astrophysics Data System (ADS)
Akarsu, Özgür; Arık, Metin; Katırcı, Nihan
2017-01-01
We present a mini review of the Stueckelberg mechanism, which was proposed to make the abelian gauge theories massive as an alternative to Higgs mechanism, within the framework of Minkowski as well as curved spacetimes. The higher the scale the tighter the bounds on the photon mass, which might be gained via the Stueckelberg mechanism, may be signalling that even an extremely small mass of the photon which cannot be measured directly could have far reaching effects in cosmology. We present a cosmological model where Stueckelberg fields, which consist of both scalar and vector fields, are non-minimally coupled to gravity and the universe could go through a decelerating expansion phase sandwiched by two different accelerated expansion phases. We discuss also the possible anisotropic extensions of the model.
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.
Deconvolution of time series in the laboratory
NASA Astrophysics Data System (ADS)
John, Thomas; Pietschmann, Dirk; Becker, Volker; Wagner, Christian
2016-10-01
In this study, we present two practical applications of the deconvolution of time series in Fourier space. First, we reconstruct a filtered input signal of sound cards that has been heavily distorted by a built-in high-pass filter using a software approach. Using deconvolution, we can partially bypass the filter and extend the dynamic frequency range by two orders of magnitude. Second, we construct required input signals for a mechanical shaker in order to obtain arbitrary acceleration waveforms, referred to as feedforward control. For both situations, experimental and theoretical approaches are discussed to determine the system-dependent frequency response. Moreover, for the shaker, we propose a simple feedback loop as an extension to the feedforward control in order to handle nonlinearities of the system.
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.
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
Geodesic Regression for Image Time-Series
Niethammer, Marc; Huang, Yang; Vialard, François-Xavier
2014-01-01
Registration of image-time series has so far been accomplished (i) by concatenating registrations between image pairs, (ii) by solving a joint estimation problem resulting in piecewise geodesic paths between image pairs, (iii) by kernel based local averaging or (iv) by augmenting the joint estimation with additional temporal irregularity penalties. Here, we propose a generative model extending least squares linear regression to the space of images by using a second-order dynamic formulation for image registration. Unlike previous approaches, the formulation allows for a compact representation of an approximation to the full spatio-temporal trajectory through its initial values. The method also opens up possibilities to design image-based approximation algorithms. The resulting optimization problem is solved using an adjoint method. PMID:21995085
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.
Reconstructing complex networks without time series
NASA Astrophysics Data System (ADS)
Ma, Chuang; Zhang, Hai-Feng; Lai, Ying-Cheng
2017-08-01
In the real world there are situations where the network dynamics are transient (e.g., various spreading processes) and the final nodal states represent the available data. Can the network topology be reconstructed based on data that are not time series? Assuming that an ensemble of the final nodal states resulting from statistically independent initial triggers (signals) of the spreading dynamics is available, we develop a maximum likelihood estimation-based framework to accurately infer the interaction topology. For dynamical processes that result in a binary final state, the framework enables network reconstruction based solely on the final nodal states. Additional information, such as the first arrival time of each signal at each node, can improve the reconstruction accuracy. For processes with a uniform final state, the first arrival times can be exploited to reconstruct the network. We derive a mathematical theory for our framework and validate its performance and robustness using various combinations of spreading dynamics and real-world network topologies.
Phase correlation of foreign exchange time series
NASA Astrophysics Data System (ADS)
Wu, Ming-Chya
2007-03-01
Correlation of foreign exchange rates in currency markets is investigated based on the empirical data of USD/DEM and USD/JPY exchange rates for a period from February 1 1986 to December 31 1996. The return of exchange time series is first decomposed into a number of intrinsic mode functions (IMFs) by the empirical mode decomposition method. The instantaneous phases of the resultant IMFs calculated by the Hilbert transform are then used to characterize the behaviors of pricing transmissions, and the correlation is probed by measuring the phase differences between two IMFs in the same order. From the distribution of phase differences, our results show explicitly that the correlations are stronger in daily time scale than in longer time scales. The demonstration for the correlations in periods of 1986-1989 and 1990-1993 indicates two exchange rates in the former period were more correlated than in the latter period. The result is consistent with the observations from the cross-correlation calculation.
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.
PERIODOGRAMS FOR MULTIBAND ASTRONOMICAL TIME SERIES
VanderPlas, Jacob T.; Ivezic, Željko
2015-10-10
This paper introduces the multiband periodogram, a general extension of the well-known Lomb–Scargle approach for detecting periodic signals in time-domain data. In addition to advantages of the Lomb–Scargle method such as treatment of non-uniform sampling and heteroscedastic errors, the multiband periodogram significantly improves period finding for randomly sampled multiband light curves (e.g., Pan-STARRS, DES, and LSST). The light curves in each band are modeled as arbitrary truncated Fourier series, with the period and phase shared across all bands. The key aspect is the use of Tikhonov regularization which drives most of the variability into the so-called base model common to all bands, while fits for individual bands describe residuals relative to the base model and typically require lower-order Fourier series. This decrease in the effective model complexity is the main reason for improved performance. After a pedagogical development of the formalism of least-squares spectral analysis, which motivates the essential features of the multiband model, we use simulated light curves and randomly subsampled SDSS Stripe 82 data to demonstrate the superiority of this method compared to other methods from the literature and find that this method will be able to efficiently determine the correct period in the majority of LSST’s bright RR Lyrae stars with as little as six months of LSST data, a vast improvement over the years of data reported to be required by previous studies. A Python implementation of this method, along with code to fully reproduce the results reported here, is available on GitHub.
Periodograms for Multiband Astronomical Time Series
NASA Astrophysics Data System (ADS)
VanderPlas, Jacob T.; Ivezić, 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.
Comparative Analysis on Time Series with Included Structural Break
NASA Astrophysics Data System (ADS)
Andreeski, Cvetko J.; Vasant, Pandian
2009-08-01
The time series analysis (ARIMA models) is a good approach for identification of time series. But, if we have structural break in the time series, we cannot create only one model of time series. Further more, if we don't have enough data between two structural breaks, it's impossible to create valid time series models for identification of the time series. This paper explores the possibility of identification of the inflation process dynamics via of the system-theoretic, by means of both Box-Jenkins ARIMA methodologies and artificial neural networks.
Extraction of stochastic dynamics from time series.
Petelczyc, M; Żebrowski, J J; Gac, J M
2012-07-01
We present a method for the reconstruction of the dynamics of processes with discrete time. The time series from such a system is described by a stochastic recurrence equation, the continuous form of which is known as the Langevin equation. The deterministic f and stochastic g components of the stochastic equation are directly extracted from the measurement data with the assumption that the noise has finite moments and has a zero mean and a unit variance. No other information about the noise distribution is needed. This is contrary to the usual Langevin description, in which the additional assumption that the noise is Gaussian (δ-correlated) distributed as necessary. We test the method using one dimensional deterministic systems (the tent and logistic maps) with Gaussian and with Gumbel noise. In addition, results for human heart rate variability are presented as an example of the application of our method to real data. The differences between cardiological cases can be observed in the properties of the deterministic part f and of the reconstructed noise distribution.
Fisher information framework for time series modeling
NASA Astrophysics Data System (ADS)
Venkatesan, R. C.; Plastino, A.
2017-08-01
A robust prediction model invoking the Takens embedding theorem, whose working hypothesis is obtained via an inference procedure based on the minimum Fisher information principle, is presented. The coefficients of the ansatz, central to the working hypothesis satisfy a time independent Schrödinger-like equation in a vector setting. The inference of (i) the probability density function of the coefficients of the working hypothesis and (ii) the establishing of constraint driven pseudo-inverse condition for the modeling phase of the prediction scheme, is made, for the case of normal distributions, with the aid of the quantum mechanical virial theorem. The well-known reciprocity relations and the associated Legendre transform structure for the Fisher information measure (FIM, hereafter)-based model in a vector setting (with least square constraints) are self-consistently derived. These relations are demonstrated to yield an intriguing form of the FIM for the modeling phase, which defines the working hypothesis, solely in terms of the observed data. Cases for prediction employing time series' obtained from the: (i) the Mackey-Glass delay-differential equation, (ii) one ECG signal from the MIT-Beth Israel Deaconess Hospital (MIT-BIH) cardiac arrhythmia database, and (iii) one ECG signal from the Creighton University ventricular tachyarrhythmia database. The ECG samples were obtained from the Physionet online repository. These examples demonstrate the efficiency of the prediction model. Numerical examples for exemplary cases are provided.
Extraction of stochastic dynamics from time series
NASA Astrophysics Data System (ADS)
Petelczyc, M.; Żebrowski, J. J.; Gac, J. M.
2012-07-01
We present a method for the reconstruction of the dynamics of processes with discrete time. The time series from such a system is described by a stochastic recurrence equation, the continuous form of which is known as the Langevin equation. The deterministic f and stochastic g components of the stochastic equation are directly extracted from the measurement data with the assumption that the noise has finite moments and has a zero mean and a unit variance. No other information about the noise distribution is needed. This is contrary to the usual Langevin description, in which the additional assumption that the noise is Gaussian (δ-correlated) distributed as necessary. We test the method using one dimensional deterministic systems (the tent and logistic maps) with Gaussian and with Gumbel noise. In addition, results for human heart rate variability are presented as an example of the application of our method to real data. The differences between cardiological cases can be observed in the properties of the deterministic part f and of the reconstructed noise distribution.
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.
Rotavirus and adenovirus gastroenteritis: time series analysis.
Celik, Cem; Gozel, Mustafa Gokhan; Turkay, Hakan; Bakici, Mustafa Zahir; Güven, Ahmet Sami; Elaldi, Nazif
2015-08-01
This study investigated the effects of changes in weather conditions (monthly average temperature, monthly minimum temperature, monthly average humidity) on rotavirus and adenovirus gastroenteritis frequency and whether there was a seasonal correlation. Between 2006 and 2012, 4702 fecal samples were taken from patients ≤ 5 years of age with acute gastroenteritis; these samples were analyzed in terms of rotavirus group A and adenovirus serotype 40-41 antigens using time-series and negative binomial regression analysis. Rotavirus antigens were found in 797 samples (17.0%), adenovirus antigens in 113 samples (2.4%), and rotavirus and adenovirus antigens together in 16 samples (0.3%). There was a seasonal change in rotavirus gastroenteritis (P < 0.001), and a 1°C decrease in average temperature increased the ratio of rotavirus cases in those with diarrhea by 0.523%. In addition, compared with data from other years, the number of patients was lower in the first month of 2008 and in the second month of 2012, when the temperature was below -20°C (monthly minimum temperature). There was no statistically significant relationship between adenovirus infection and change in weather conditions. Various factors such as change in weather conditions, as well as the population's sensitivity and associated changes in activity, play a role in the spread of rotavirus infection. © 2015 Japan Pediatric Society.
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.
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.
A Course in Teaching Time Series to Chemical Engineers.
ERIC Educational Resources Information Center
Graham, B. P.; Jutan, A.
1985-01-01
A one-month graduate course on time series analysis is offered in the department of chemical engineering at the University of Queensland (Australia). Describes the course, which is based on an interactive graphics time series identification and modelling computer package (TSIM). Also describes time-series analysis procedure and the TSIM package.…
Time Series Analysis of Mother-Infant Interaction.
ERIC Educational Resources Information Center
Rosenfeld, Howard M.
A method of studying attachment behavior in infants was devised using time series and time sequence analyses. Time series analysis refers to relationships between events coded over adjacent fixed-time units. Time sequence analysis refers to the distribution of exact times at which particular events happen. Using these techniques, multivariate…
Carbon time series in the Norwegian sea
NASA Astrophysics Data System (ADS)
Gislefoss, Jorunn S.; Nydal, Reidar; Slagstad, Dag; Sonninen, Eloni; Holmén, Kim
1998-02-01
Depth profiles of carbon parameters were obtained monthly from 1991 to 1994 as the first time series from the weathership station M located in the Norwegian Sea at 66°N 2°E. CO 2 was extracted from acidified seawater by a flushing procedure, with nitrogen as the carrier gas. The pure CO 2 gas was measured using a manometric technique, and the gas was further used for 13C and 14C measurements. The precision of the dissolved inorganic carbon (DIC) was better than ±6‰. Satisfactory agreement was obtained with standard seawater from Scripps Institution of Oceanography. The partial pressure of CO 2 (pCO 2) was measured in the atmosphere and surface water, beginning in October 1991. The most visible seasonal variation in DIC, 13C and pCO 2 was due to the plankton bloom in the upper 50-100 m. Typical values for surface water in the winter were: 2.140±0.012 mmol kg -1 for DIC, 1.00±0.04‰ for δ 13C and 357±15 μatm for pCO 2, and the corresponding values in the summer were as low as 2.04 mmol kg -1, greater than 2.1‰, and as low as 270-300 μatm. The values for deep water are more constant during the year, with DIC values of about 2.17±0.01 mmol kg -1, and δ 13C values between 0.97 and 1.14‰. A simple one-dimensional biological model was applied in order to investigate possible short-term variability in DIC caused by the phytoplankton growth and depth variations of the wind-mixed layer. The simulated seasonal pattern was in reasonable agreement with the observed data, but there were significant temporal variations with shorter time interval than the monthly measurements. As a supplement to the measurements at station M, some representative profiles of DIC, δ 13C, Δ 14C, salinity and temperature from other locations in the Nordic Seas and the North Atlantic Ocean are also presented. The results are also compared with some data obtained ( Δ 14C) by the TTO expedition in 1981 and the GEOSECS expedition in 1972. The carbon profiles reflect the stable deep
Measuring persistence in time series of temperature anomalies
NASA Astrophysics Data System (ADS)
Triacca, Umberto; Pasini, Antonello; Attanasio, Alessandro
2014-11-01
Studies on persistence are important for the clarification of statistical properties of the analyzed time series and for understanding the dynamics of the systems which create these series. In climatology, the analysis of the autocorrelation function has been the main tool to investigate the persistence of a time series. In this paper, we propose to use a more sophisticated econometric instrument. Using this tool, we obtain an estimate of the persistence in global land and ocean and hemispheric temperature time series.
Noise reduction by recycling dynamically coupled time series.
Mera, M Eugenia; Morán, Manuel
2011-12-01
We say that several scalar time series are dynamically coupled if they record the values of measurements of the state variables of the same smooth dynamical system. We show that much of the information lost due to measurement noise in a target time series can be recovered with a noise reduction algorithm by crossing the time series with another time series with which it is dynamically coupled. The method is particularly useful for reduction of measurement noise in short length time series with high uncertainties.
The scaling of time series size towards detrended fluctuation analysis
NASA Astrophysics Data System (ADS)
Gao, Xiaolei; Ren, Liwei; Shang, Pengjian; Feng, Guochen
2016-06-01
In this paper, we introduce a modification of detrended fluctuation analysis (DFA), called multivariate DFA (MNDFA) method, based on the scaling of time series size N. In traditional DFA method, we obtained the influence of the sequence segmentation interval s, and it inspires us to propose a new model MNDFA to discuss the scaling of time series size towards DFA. The effectiveness of the procedure is verified by numerical experiments with both artificial and stock returns series. Results show that the proposed MNDFA method contains more significant information of series compared to traditional DFA method. The scaling of time series size has an influence on the auto-correlation (AC) in time series. For certain series, we obtain an exponential relationship, and also calculate the slope through the fitting function. Our analysis and finite-size effect test demonstrate that an appropriate choice of the time series size can avoid unnecessary influences, and also make the testing results more accurate.
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
NASA Astrophysics Data System (ADS)
Chen, Siyuan; Middleton, Hannah; Sesana, Alberto; Del Pozzo, Walter; Vecchio, Alberto
2017-06-01
We consider the inverse problem in pulsar timing array (PTA) analysis, investigating what astrophysical information about the underlying massive black hole binary (MBHB) population can be recovered from the detection of a stochastic gravitational wave background (GWB). We employ a physically motivated model that connects the GWB spectrum to a series of parameters describing the underlying redshift evolution of the MBHB mass function and to the typical eccentricity they acquire while interacting with the dense environment of post-merger galactic nuclei. This allows the folding in of information about the spectral shape of the GWB into the analysis. The priors on the model parameters are assumed to be uninformative and consistent with the current lack of secure observations of sub-parsec MBHBs. We explore the implications of current upper limits and of future detections with a variety of PTA configurations. We confirm our previous finding that current upper limits can only place an upper bound on the overall MBHB merger rate. Depending on the properties of the array, future detections can also constrain several MBHB population models at different degrees of fidelity. In particular, a simultaneous detection of a steepening of the spectrum at high frequency and a bending at low frequency will place strong constraints on both the MBHB mass function and on the typical eccentricity of inspiralling MBHBs, providing insights into MBHB astrophysics unlikely to be achievable by any other means.
Detecting inhomogeneities in pan evaporation time series
NASA Astrophysics Data System (ADS)
Kirono, D. G. C.
2009-04-01
There is increasingly growing demand for evaporation data for studies of surface water and energy fluxes, especially for studies which address the impacts of global warming. To serve this purpose, a homogeneous evaporation data are necessary. This paper describes the use of two tests for detecting and adjusting discontinuities in Class A pan evaporation time series for 28 stations across Australia, and illustrates the benefit of using corrected records in climate studies. The two tests being the bivariate test of Maronna and Yohai (1978), also known as the Potter method (WMO 2003), and the RHTest of Wang and Feng (2004). Overall, 58 per cent of the inhomogeneities detected by the bivariate test were also identified by the RHTest. The fact that the other 42 per cent of inhomogeneities were not consistently detected is due to different sensitivities of the two methods. Ninety-two per cent of the inhomogeneities detected by the bivariate test are consistent with documented changes that can be strongly associated with the discontinuity. Having identified inhomogeneities, the adjusments were only applied to records which contained inhomogeneities that could be verified as having a non-climatic origin. The benefit of using the original and adjusted pan evaporation records in a climate study were then investigated from two points of view: correlation analyses and trend analysis. As an illustration, the results show that the trend (1970-2004) in the all-stations average was -2.8±1.7 for the original data but only -0.7±1.6 mm/year/year for the adjusted data, demonstrating the importance of screening the data before their use in climate studies. References Maronna, R. and Yohai, V.J. 1978. A bivariate test for the detection of a systematic change in mean. J. Amer. Statis. Assoc., 73, 640-645. Wang, X.L. and Feng, Y. 2004. RHTest User manual. Available from http://cccma.seos.uvic.ca/ETCCDMI/RHTestUserManual.doc WMO. 2003. Guidelines on climate metadata and homogenization
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.
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.
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.
Adequate Sampling of a Chaotic Time Series
1991-12-01
Dab values exist. This average value (Dab) assures us not only of better finding a minimum data set that defines convergence in each case, but also...generating a long series. 118 More specifically, although 480,000 points represents the minimum data set required to achieve maximum convergence, we...is a dependence of he minimum data set necessary to produce histogram convergence on the sampling interval that we use, at least for intervals less
Bernstein polynomials for evolutionary algebraic prediction of short time series
NASA Astrophysics Data System (ADS)
Lukoseviciute, Kristina; Howard, Daniel; Ragulskis, Minvydas
2017-07-01
Short time series prediction technique based on Bernstein polynomials is presented in this paper. Firstly, the straightforward Bernstein polynomial extrapolation scheme is improved by extending the interval of approximation. Secondly, the forecasting scheme is designed in the evolutionary computational setup which is based on the conciliation between the coarseness of the algebraic prediction and the smoothness of the time average prediction. Computational experiments with the test time series suggest that this time series prediction technique could be applicable for various forecasting applications.
Analysis of Nonstationary Time Series for Biological Rhythms Research.
Leise, Tanya L
2017-06-01
This article is part of a Journal of Biological Rhythms series exploring analysis and statistics topics relevant to researchers in biological rhythms and sleep research. The goal is to provide an overview of the most common issues that arise in the analysis and interpretation of data in these fields. In this article on time series analysis for biological rhythms, we describe some methods for assessing the rhythmic properties of time series, including tests of whether a time series is indeed rhythmic. Because biological rhythms can exhibit significant fluctuations in their period, phase, and amplitude, their analysis may require methods appropriate for nonstationary time series, such as wavelet transforms, which can measure how these rhythmic parameters change over time. We illustrate these methods using simulated and real time series.
A novel weight determination method for time series data aggregation
NASA Astrophysics Data System (ADS)
Xu, Paiheng; Zhang, Rong; Deng, Yong
2017-09-01
Aggregation in time series is of great importance in time series smoothing, predicting and other time series analysis process, which makes it crucial to address the weights in times series correctly and reasonably. In this paper, a novel method to obtain the weights in time series is proposed, in which we adopt induced ordered weighted aggregation (IOWA) operator and visibility graph averaging (VGA) operator and linearly combine the weights separately generated by the two operator. The IOWA operator is introduced to the weight determination of time series, through which the time decay factor is taken into consideration. The VGA operator is able to generate weights with respect to the degree distribution in the visibility graph constructed from the corresponding time series, which reflects the relative importance of vertices in time series. The proposed method is applied to two practical datasets to illustrate its merits. The aggregation of Construction Cost Index (CCI) demonstrates the ability of proposed method to smooth time series, while the aggregation of The Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) illustrate how proposed method maintain the variation tendency of original data.
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.
Foot gait time series estimation based on support vector machine.
Pant, Jeevan K; Krishnan, Sridhar
2014-01-01
A new algorithm for the estimation of stride interval time series from foot gait signals is proposed. The algorithm is based on the detection of beginning of heel strikes in the signal by using the support vector machine. Morphological operations are used to enhance the accuracy of detection. By taking backward differences of the detected beginning of heel strikes, stride interval time series is estimated. Simulation results are presented which shows that the proposed algorithm yields fairly accurate estimation of stride interval time series where estimation error for mean and standard deviation of the time series is of the order of 10(-4).
Using neural networks for dynamic light scattering time series processing
NASA Astrophysics Data System (ADS)
Chicea, Dan
2017-04-01
A basic experiment to record dynamic light scattering (DLS) time series was assembled using basic components. The DLS time series processing using the Lorentzian function fit was considered as reference. A Neural Network was designed and trained using simulated frequency spectra for spherical particles in the range 0-350 nm, assumed to be scattering centers, and the neural network design and training procedure are described in detail. The neural network output accuracy was tested both on simulated and on experimental time series. The match with the DLS results, considered as reference, was good serving as a proof of concept for using neural networks in fast DLS time series processing.
Trend time-series modeling and forecasting with neural networks.
Qi, Min; Zhang, G Peter
2008-05-01
Despite its great importance, there has been no general consensus on how to model the trends in time-series data. Compared to traditional approaches, neural networks (NNs) have shown some promise in time-series forecasting. This paper investigates how to best model trend time series using NNs. Four different strategies (raw data, raw data with time index, detrending, and differencing) are used to model various trend patterns (linear, nonlinear, deterministic, stochastic, and breaking trend). We find that with NNs differencing often gives meritorious results regardless of the underlying data generating processes (DGPs). This finding is also confirmed by the real gross national product (GNP) series.
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.
gatspy: General tools for Astronomical Time Series in Python
NASA Astrophysics Data System (ADS)
VanderPlas, Jake
2016-10-01
Gatspy contains efficient, well-documented implementations of several common routines for Astronomical time series analysis, including the Lomb-Scargle periodogram, the Supersmoother method, and others.
NASA Astrophysics Data System (ADS)
Gong, Pu; Yu, Hongyi; Wang, Yong; Yao, Wang
2017-03-01
We investigate the optical transition selection rules for excitonic Rydberg series formed in massive Dirac cones. The entanglement of the exciton envelop function with the pseudospin texture leads to anomalous selection rules for one-photon generation of excitons, where d orbitals can be excited with the opposite helicity selection rule from the s orbitals in a given valley. The trigonal warping effects in realistic hexagonal lattices further renders more excited states bright, where p orbitals can also be accessed by one-photon excitation with the opposite valley selection rules to the s orbitals. The one-photon generation of exciton in the various states and the intraexcitonic transition between these states are both dictated by the discrete in-plane rotational symmetry of the lattices, and our results show that in hexagonal 2D materials the symmetry allowed transitions are enabled when trigonal warping effects are included in the massive Dirac fermion model. In monolayer transition metal dichalcogenides where excitons can be generated by visible light and intraexcitonic transitions can be induced by infrared light, we give the strength of these optical transitions, estimated using modified hydrogenlike envelope functions combined with the optical transition matrix elements between the Bloch states calculated at various k points.
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,…
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,…
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.
Testing time series irreversibility using complex network methods
NASA Astrophysics Data System (ADS)
Donges, Jonathan F.; Donner, Reik V.; Kurths, Jürgen
2013-04-01
The absence of time-reversal symmetry is a fundamental property of many nonlinear time series. Here, we propose a new set of statistical tests for time series irreversibility based on standard and horizontal visibility graphs. Specifically, we statistically compare the distributions of time-directed variants of the common complex network measures degree and local clustering coefficient. Our approach does not involve surrogate data and is applicable to relatively short time series. We demonstrate its performance for paradigmatic model systems with known time-reversal properties as well as for picking up signatures of nonlinearity in neuro-physiological data.
Modeling multivariate covariance nonstationary time series and their dependency structure
Gersch, W.
1985-08-01
The parametric modeling of covariance nonstationary time series and the computation of their changing interdependency structure from the fitted model are treated. The nonstationary time series are modeled by a multivariate time varying autoregressive (AR) model. The time evolution of the AR parameters is expressed as linear combinations of discrete Legendre orthogonal polynomial functions of time. The model is fitted by a Householder transformation-AIC order determination, regression subset selection method. The computation of the instantaneous dependence, feedback and causality structure of the time series from the fitted model, is discussed. An example of the modeling and determination of instantaneous causality in a human implanted electrode seizure event EEG is shown.
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.
Distance measure with improved lower bound for multivariate time series
NASA Astrophysics Data System (ADS)
Li, Hailin
2017-02-01
Lower bound function is one of the important techniques used to fast search and index time series data. Multivariate time series has two aspects of high dimensionality including the time-based dimension and the variable-based dimension. Due to the influence of variable-based dimension, a novel method is proposed to deal with the lower bound distance computation for multivariate time series. The proposed method like the traditional ones also reduces the dimensionality of time series in its first step and thus does not directly apply the lower bound function on the multivariate time series. The dimensionality reduction is that multivariate time series is reduced to univariate time series denoted as center sequences according to the principle of piecewise aggregate approximation. In addition, an extended lower bound function is designed to obtain good tightness and fast measure the distance between any two center sequences. The experimental results demonstrate that the proposed lower bound function has better tightness and improves the performance of similarity search in multivariate time series datasets.
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.
Multiscale structure of time series revealed by the monotony spectrum.
Vamoş, Călin
2017-03-01
Observation of complex systems produces time series with specific dynamics at different time scales. The majority of the existing numerical methods for multiscale analysis first decompose the time series into several simpler components and the multiscale structure is given by the properties of their components. We present a numerical method which describes the multiscale structure of arbitrary time series without decomposing them. It is based on the monotony spectrum defined as the variation of the mean amplitude of the monotonic segments with respect to the mean local time scale during successive averagings of the time series, the local time scales being the durations of the monotonic segments. The maxima of the monotony spectrum indicate the time scales which dominate the variations of the time series. We show that the monotony spectrum can correctly analyze a diversity of artificial time series and can discriminate the existence of deterministic variations at large time scales from the random fluctuations. As an application we analyze the multifractal structure of some hydrological time series.
Multiscale structure of time series revealed by the monotony spectrum
NASA Astrophysics Data System (ADS)
Vamoş, Cǎlin
2017-03-01
Observation of complex systems produces time series with specific dynamics at different time scales. The majority of the existing numerical methods for multiscale analysis first decompose the time series into several simpler components and the multiscale structure is given by the properties of their components. We present a numerical method which describes the multiscale structure of arbitrary time series without decomposing them. It is based on the monotony spectrum defined as the variation of the mean amplitude of the monotonic segments with respect to the mean local time scale during successive averagings of the time series, the local time scales being the durations of the monotonic segments. The maxima of the monotony spectrum indicate the time scales which dominate the variations of the time series. We show that the monotony spectrum can correctly analyze a diversity of artificial time series and can discriminate the existence of deterministic variations at large time scales from the random fluctuations. As an application we analyze the multifractal structure of some hydrological time series.
Short time-series microarray analysis: Methods and challenges
Wang, Xuewei; Wu, Ming; Li, Zheng; Chan, Christina
2008-01-01
The detection and analysis of steady-state gene expression has become routine. Time-series microarrays are of growing interest to systems biologists for deciphering the dynamic nature and complex regulation of biosystems. Most temporal microarray data only contain a limited number of time points, giving rise to short-time-series data, which imposes challenges for traditional methods of extracting meaningful information. To obtain useful information from the wealth of short-time series data requires addressing the problems that arise due to limited sampling. Current efforts have shown promise in improving the analysis of short time-series microarray data, although challenges remain. This commentary addresses recent advances in methods for short-time series analysis including simplification-based approaches and the integration of multi-source information. Nevertheless, further studies and development of computational methods are needed to provide practical solutions to fully exploit the potential of this data. PMID:18605994
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.
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…
The Prediction of Teacher Turnover Employing Time Series Analysis.
ERIC Educational Resources Information Center
Costa, Crist H.
The purpose of this study was to combine knowledge of teacher demographic data with time-series forecasting methods to predict teacher turnover. Moving averages and exponential smoothing were used to forecast discrete time series. The study used data collected from the 22 largest school districts in Iowa, designated as FACT schools. Predictions…
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.
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.
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…
Transition Icons for Time Series Visualization and Exploratory Analysis.
Nickerson, Paul; Baharloo, Raheleh; Wanigatunga, Amal A; Manini, Todd D; Tighe, Patrick J; Rashidi, Parisa
2017-05-16
The modern healthcare landscape has seen the rapid emergence of techniques and devices which temporally monitor and record physiological signals. The prevalence of time series data within the healthcare field necessitates the development of methods which can analyze the data in order to draw meaningful conclusions. Time series behavior is notoriously difficult to intuitively understand due to its intrinsic high-dimensionality, which is compounded in the case of analyzing groups of time series collected from different patients. Our framework, which we call Transition Icons, renders common patterns in a visual format useful for understanding the shared behavior within groups of time series. Transition Icons are adept at detecting and displaying subtle differences and similarities e.g. between measurements taken from patients receiving different treatment strategies or stratified by demographics. We introduce various methods which collectively allow for exploratory analysis of groups of time series, while being free of distribution assumptions and including simple heuristics for parameter determination. Our technique extracts discrete transition patterns from Symbolic Aggregate approXimation (SAX) representations, and compiles transition frequencies into a Bag of Patterns (BoP) constructed for each group. These transition frequencies are normalized and aligned in icon form to intuitively display the underlying patterns. We demonstrate the Transition Icon technique for two time series data sets - postoperative pain scores, and hip-worn accelerometer activity counts. We believe Transition Icons can be an important tool for researchers approaching time series data, as they give rich and intuitive information about collective time series behaviors.
Improved singular spectrum analysis for time series with missing data
NASA Astrophysics Data System (ADS)
Shen, Y.; Peng, F.; Li, B.
2015-07-01
Singular spectrum analysis (SSA) is a powerful technique for time series analysis. Based on the property that the original time series can be reproduced from its principal components, this contribution develops an improved SSA (ISSA) for processing the incomplete time series and the modified SSA (SSAM) of Schoellhamer (2001) is its special case. The approach is evaluated with the synthetic and real incomplete time series data of suspended-sediment concentration from San Francisco Bay. The result from the synthetic time series with missing data shows that the relative errors of the principal components reconstructed by ISSA are much smaller than those reconstructed by SSAM. Moreover, when the percentage of the missing data over the whole time series reaches 60 %, the improvements of relative errors are up to 19.64, 41.34, 23.27 and 50.30 % for the first four principal components, respectively. Both the mean absolute error and mean root mean squared error of the reconstructed time series by ISSA are also smaller than those by SSAM. The respective improvements are 34.45 and 33.91 % when the missing data accounts for 60 %. The results from real incomplete time series also show that the standard deviation (SD) derived by ISSA is 12.27 mg L-1, smaller than the 13.48 mg L-1 derived by SSAM.
Improved singular spectrum analysis for time series with missing data
NASA Astrophysics Data System (ADS)
Shen, Y.; Peng, F.; Li, B.
2014-12-01
Singular spectrum analysis (SSA) is a powerful technique for time series analysis. Based on the property that the original time series can be reproduced from its principal components, this contribution will develop an improved SSA (ISSA) for processing the incomplete time series and the modified SSA (SSAM) of Schoellhamer (2001) is its special case. The approach was evaluated with the synthetic and real incomplete time series data of suspended-sediment concentration from San Francisco Bay. The result from the synthetic time series with missing data shows that the relative errors of the principal components reconstructed by ISSA are much smaller than those reconstructed by SSAM. Moreover, when the percentage of the missing data over the whole time series reaches 60%, the improvements of relative errors are up to 19.64, 41.34, 23.27 and 50.30% for the first four principal components, respectively. Besides, both the mean absolute errors and mean root mean squared errors of the reconstructed time series by ISSA are also much smaller than those by SSAM. The respective improvements are 34.45 and 33.91% when the missing data accounts for 60%. The results from real incomplete time series also show that the SD derived by ISSA is 12.27 mg L-1, smaller than 13.48 mg L-1 derived by SSAM.
Investigation on gait time series by means of factorial moments
NASA Astrophysics Data System (ADS)
Yang, Huijie; Zhao, Fangcui; Zhuo, Yizhong; Wu, Xizhen; Li, Zhuxia
2002-09-01
By means of factorial moments (FM), the fractal structures embedded in gait time series are investigated. Intermittency is found in records for healthy objects. And this kind of intermittency is much sensitive to disease or outside influences. It is found that FM is an effective tool to deal with this kind of time series.
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…
Time Series Econometrics for the 21st Century
ERIC Educational Resources Information Center
Hansen, Bruce E.
2017-01-01
The field of econometrics largely started with time series analysis because many early datasets were time-series macroeconomic data. As the field developed, more cross-sectional and longitudinal datasets were collected, which today dominate the majority of academic empirical research. In nonacademic (private sector, central bank, and governmental)…
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…
Time Series Model Identification by Estimating Information, Memory, and Quantiles.
1983-07-01
G. J. (1982) Determining the degree of differencing for time series via the log spectrum. Journal of Time Series Analysis, 3, 177-183. Mandelbrot , B... Mandelbrot , B. (1982) The Fractal Geometry of Nature, Freeman: San Francisco. Rosenblatt, M. (1981) Limit theorems for Fourier transforms of
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…
Scaling and Multiscaling in Financial Time Series
2007-11-02
Prescribed by ANSI Std Z39-18 Outline 1/ A brief overview of financial markets • Basic definitions and problems related to finance • Scaling in finance 2...quantitative finance • Rational investment and risk management - Price dynamics - Risk quantification and control - Financial instruments: derivatives... finance • Supported by empirical observations • Practical interests. - Stability over time scales (by aggregation) - The same model is valid over a wide
Time Series Analysis Programs for Stratigraphic Data,
1984-07-01
species of planktonic foraminifers with changing relative abundances in the same core will show apparent offsets in the timing of events due to mixing...isotope carrier ( foraminifer species) as described in Hutson (1980). The user is asked for input file- names for isotopes, abundances and the mixing...complicated driver program that attempts to remove stratigraphic offset between two stable isotope signals from different foraminifer species in a single core
Time series diagnosis of tree hydraulic characteristics.
Phillips, Nathan G; Oren, Ram; Licata, Julian; Linder, Sune
2004-08-01
An in vivo method for diagnosing hydraulic characteristics of branches and whole trees is described. The method imposes short-lived perturbations of transpiration and traces the propagation of the hydraulic response through trees. The water uptake response contains the integrated signature of hydraulic resistance and capacitance within trees. The method produces large signal to noise ratios for analysis, but does not cause damage or destruction to tree stems or branches. Based on results with two conifer tree species, we show that the method allows for the simple parameterization of bulk hydraulic resistance and capacitance of trees. Bulk tree parameterization of resistance and capacitance predicted the overall diel shape of water uptake, but did not predict the overshoot water uptake response in trees to shorter-term variations in transpiration, created by step changes in transpiration rate. Stomatal dynamics likely complicated the use of simple resistance-capacitance models of tree water transport on these short time scales. The results provide insight into dominant hydraulic and physiological factors controlling tree water flux on varying time scales, and allow for the practical assessment of necessary tree hydraulic model complexity in relation to the time step of soil- vegetation-atmosphere transport models.
Time Series of North Pacific Volcanic Eruptions
NASA Astrophysics Data System (ADS)
Dehn, J.; Worden, A. K.; Webley, P. W.
2011-12-01
The record of volcanic eruptions was gathered from the 1986 eruption of Augustine Volcano to present for Alaska, Kamchatka and the Kuriles Islands. In this time over 400 ash producing eruptions were noted, and many more events that produced some other activity, e.g. lava, lahar, small explosion, seismic crisis. This represents a minimum for the volcanic activity in this region. It is thought that the records for Alaska are complete for this time period, but it is possible that activity in the Kuriles and Kamchatka could have been overlooked, particularly smaller events. For the Alaska region, 19 different volcanoes have been active in this time. Mt. Cleveland shows the most activity over the time period (40 % likely to have activity in a 3 month period), followed closely by Pavlof (34% likely)volcano. In Kamchatka only 7 volcanoes have been active, Shiveluch is the most active (83% likely) followed by Bezymianny and Kliuchevskoi volcanoes (tied at 60%). The Kuriles only has had 4 active volcanoes, and only 6 known eruptions. Overall this region is one of the most active in the world, in any 3 month period there is a 77% likelihood of volcano activity. For well instrumented volcanoes, the majority of activity is preceded by significant seismicity. For just over half of the events, explosive activity is preceded by thermal signals in infrared satellite data. Rarely (only about 5% of the time) is a stand alone thermal signal not followed within 3 months by an explosive eruption. For remaining events where an ash plume begins the activity, over 90% of the cases show a thermal signal the eruption. The volcanoes with the most activity are the least likely to produce large ash plumes. Conversely the volcanoes that erupt rarely often begin with larger ash producing events. Though there appears to be a recurrent progression of volcanic activity down the chain from east to west, this may be an artifact of several independent systems, each working at their own rate, that
Scale Invariance in Rain Time Series
NASA Astrophysics Data System (ADS)
Deluca, A.; Corral, A.
2009-09-01
In the last few years there have been pieces of evidence that rain events can be considered analogous to other nonequilibrium relaxation processes in Nature such as earthquakes, solar flares and avalanches. In this work we compare the probability densities of rain event size, duration, and recurrence times (i.e., drought periods) between one Mediterranean site and different sites worldwide. We test the existence of scale invariance in these distributions and the possibility of a universal scaling exponent, despite the different climatic characteristics of the different places.
Infrared dynamics of massive scalars from the complementary series in de Sitter space
NASA Astrophysics Data System (ADS)
Akhmedov, E. T.; Moschella, U.; Pavlenko, K. E.; Popov, F. K.
2017-07-01
We continue a previous study about the infrared loop effects in the D -dimensional de Sitter space for a real scalar ϕ4 theory from the complementary series whose bare mass belongs to the interval √{3/}4 (D -1 )
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.
Comparison of New and Old Sunspot Number Time Series
NASA Astrophysics Data System (ADS)
Cliver, E. W.
2016-11-01
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.
Inference on periodicity of circadian time series
Costa, Maria J.; Finkenstädt, Bärbel; Roche, Véronique; Lévi, Francis; Gould, Peter D.; Foreman, Julia; Halliday, Karen; Hall, Anthony; Rand, David A.
2013-01-01
Estimation of the period length of time-course data from cyclical biological processes, such as those driven by the circadian pacemaker, is crucial for inferring the properties of the biological clock found in many living organisms. We propose a methodology for period estimation based on spectrum resampling (SR) techniques. Simulation studies show that SR is superior and more robust to non-sinusoidal and noisy cycles than a currently used routine based on Fourier approximations. In addition, a simple fit to the oscillations using linear least squares is available, together with a non-parametric test for detecting changes in period length which allows for period estimates with different variances, as frequently encountered in practice. The proposed methods are motivated by and applied to various data examples from chronobiology. PMID:23743206
Detecting unstable periodic orbits from transient chaotic time series
Dhamala; Lai; Kostelich
2000-06-01
We address the detection of unstable periodic orbits from experimentally measured transient chaotic time series. In particular, we examine recurrence times of trajectories in the vector space reconstructed from an ensemble of such time series. Numerical experiments demonstrate that this strategy can yield periodic orbits of low periods even when noise is present. We analyze the probability of finding periodic orbits from transient chaotic time series and derive a scaling law for this probability. The scaling law implies that unstable periodic orbits of high periods are practically undetectable from transient chaos.
Characterizing time series: when Granger causality triggers complex networks
NASA Astrophysics Data System (ADS)
Ge, Tian; Cui, Yindong; Lin, Wei; Kurths, Jürgen; Liu, Chong
2012-08-01
In this paper, we propose a new approach to characterize time series with noise perturbations in both the time and frequency domains by combining Granger causality and complex networks. We construct directed and weighted complex networks from time series and use representative network measures to describe their physical and topological properties. Through analyzing the typical dynamical behaviors of some physical models and the MIT-BIHMassachusetts Institute of Technology-Beth Israel Hospital. human electrocardiogram data sets, we show that the proposed approach is able to capture and characterize various dynamics and has much potential for analyzing real-world time series of rather short length.
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
Detecting and visualizing structural changes in groundwater head time series
NASA Astrophysics Data System (ADS)
van Geer, Frans
2013-04-01
Since the fifties of the past century the dynamic behavior of the groundwater head has been monitored at many locations throughout the Netherlands and elsewhere. The data base of the Geological Survey of the Netherlands contains over 30,000 groundwater time series. For many water management purposes characteristics of the dynamic behavior are required, such as average, median, percentile etc.. These characteristics are estimated from the time series. In principle, the longer the time series, the more reliable the estimate. However, due to natural as well as man induced changes, the characteristics of a long time series are often changing in time as well. For water management it is important to be able to distinguish extreme values as part of the 'normal' pattern from structural changes in the groundwater regime. Whether or not structural changes are present in the time series can't be decided completely objective. Choices have to be made concerning the length of the period and the statistical parameters. Here a method is proposed to visualize the probability of structural changes in the time series using well known basic statistical tests. The visualization method is based on the mean values and standard deviation in a moving window. Apart from several characteristics that are calculated for each period separately, all pairs of two periods are compared and the difference is statistically tested. The results of these well known tests are combined in a visualization to supply to the user comprehensive information to examine structural changes in time series.
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.
Automated analysis of brachial ultrasound time series
NASA Astrophysics Data System (ADS)
Liang, Weidong; Browning, Roger L.; Lauer, Ronald M.; Sonka, Milan
1998-07-01
Atherosclerosis begins in childhood with the accumulation of lipid in the intima of arteries to form fatty streaks, advances through adult life when occlusive vascular disease may result in coronary heart disease, stroke and peripheral vascular disease. Non-invasive B-mode ultrasound has been found useful in studying risk factors in the symptom-free population. Large amount of data is acquired from continuous imaging of the vessels in a large study population. A high quality brachial vessel diameter measurement method is necessary such that accurate diameters can be measured consistently in all frames in a sequence, across different observers. Though human expert has the advantage over automated computer methods in recognizing noise during diameter measurement, manual measurement suffers from inter- and intra-observer variability. It is also time-consuming. An automated measurement method is presented in this paper which utilizes quality assurance approaches to adapt to specific image features, to recognize and minimize the noise effect. Experimental results showed the method's potential for clinical usage in the epidemiological studies.
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.
Nonlinear independent component analysis and multivariate time series analysis
NASA Astrophysics Data System (ADS)
Storck, Jan; Deco, Gustavo
1997-02-01
We derive an information-theory-based unsupervised learning paradigm for nonlinear independent component analysis (NICA) with neural networks. We demonstrate that under the constraint of bounded and invertible output transfer functions the two main goals of unsupervised learning, redundancy reduction and maximization of the transmitted information between input and output (Infomax-principle), are equivalent. No assumptions are made concerning the kind of input and output distributions, i.e. the kind of nonlinearity of correlations. An adapted version of the general NICA network is used for the modeling of multivariate time series by unsupervised learning. Given time series of various observables of a dynamical system, our net learns their evolution in time by extracting statistical dependencies between past and present elements of the time series. Multivariate modeling is obtained by making present value of each time series statistically independent not only from their own past but also from the past of the other series. Therefore, in contrast to univariate methods, the information lying in the couplings between the observables is also used and a detection of higher-order cross correlations is possible. We apply our method to time series of the two-dimensional Hénon map and to experimental time series obtained from the measurements of axial velocities in different locations in weakly turbulent Taylor-Couette flow.
Time Series Decomposition into Oscillation Components and Phase Estimation.
Matsuda, Takeru; Komaki, Fumiyasu
2017-02-01
Many time series are naturally considered as a superposition of several oscillation components. For example, electroencephalogram (EEG) time series include oscillation components such as alpha, beta, and gamma. We propose a method for decomposing time series into such oscillation components using state-space models. Based on the concept of random frequency modulation, gaussian linear state-space models for oscillation components are developed. In this model, the frequency of an oscillator fluctuates by noise. Time series decomposition is accomplished by this model like the Bayesian seasonal adjustment method. Since the model parameters are estimated from data by the empirical Bayes' method, the amplitudes and the frequencies of oscillation components are determined in a data-driven manner. Also, the appropriate number of oscillation components is determined with the Akaike information criterion (AIC). In this way, the proposed method provides a natural decomposition of the given time series into oscillation components. In neuroscience, the phase of neural time series plays an important role in neural information processing. The proposed method can be used to estimate the phase of each oscillation component and has several advantages over a conventional method based on the Hilbert transform. Thus, the proposed method enables an investigation of the phase dynamics of time series. Numerical results show that the proposed method succeeds in extracting intermittent oscillations like ripples and detecting the phase reset phenomena. We apply the proposed method to real data from various fields such as astronomy, ecology, tidology, and neuroscience.
Model-free quantification of time-series predictability.
Garland, Joshua; James, Ryan; Bradley, Elizabeth
2014-11-01
This paper provides insight into when, why, and how forecast strategies fail when they are applied to complicated time series. We conjecture that the inherent complexity of real-world time-series data, which results from the dimension, nonlinearity, and nonstationarity of the generating process, as well as from measurement issues such as noise, aggregation, and finite data length, is both empirically quantifiable and directly correlated with predictability. In particular, we argue that redundancy is an effective way to measure complexity and predictive structure in an experimental time series and that weighted permutation entropy is an effective way to estimate that redundancy. To validate these conjectures, we study 120 different time-series data sets. For each time series, we construct predictions using a wide variety of forecast models, then compare the accuracy of the predictions with the permutation entropy of that time series. We use the results to develop a model-free heuristic that can help practitioners recognize when a particular prediction method is not well matched to the task at hand: that is, when the time series has more predictive structure than that method can capture and exploit.
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.
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
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.
Clinical time series prediction: Toward a hierarchical dynamical system framework.
Liu, Zitao; Hauskrecht, Milos
2015-09-01
Developing machine learning and data mining algorithms for building temporal models of clinical time series is important for understanding of the patient condition, the dynamics of a disease, effect of various patient management interventions and clinical decision making. In this work, we propose and develop a novel hierarchical framework for modeling clinical time series data of varied length and with irregularly sampled observations. Our hierarchical dynamical system framework for modeling clinical time series combines advantages of the two temporal modeling approaches: the linear dynamical system and the Gaussian process. We model the irregularly sampled clinical time series by using multiple Gaussian process sequences in the lower level of our hierarchical framework and capture the transitions between Gaussian processes by utilizing the linear dynamical system. The experiments are conducted on the complete blood count (CBC) panel data of 1000 post-surgical cardiac patients during their hospitalization. Our framework is evaluated and compared to multiple baseline approaches in terms of the mean absolute prediction error and the absolute percentage error. We tested our framework by first learning the time series model from data for the patients in the training set, and then using it to predict future time series values for the patients in the test set. We show that our model outperforms multiple existing models in terms of its predictive accuracy. Our method achieved a 3.13% average prediction accuracy improvement on ten CBC lab time series when it was compared against the best performing baseline. A 5.25% average accuracy improvement was observed when only short-term predictions were considered. A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive performance. Copyright © 2014 Elsevier B.V. All rights reserved.
Clinical time series prediction: towards a hierarchical dynamical system framework
Liu, Zitao; Hauskrecht, Milos
2014-01-01
Objective Developing machine learning and data mining algorithms for building temporal models of clinical time series is important for understanding of the patient condition, the dynamics of a disease, effect of various patient management interventions and clinical decision making. In this work, we propose and develop a novel hierarchical framework for modeling clinical time series data of varied length and with irregularly sampled observations. Materials and methods Our hierarchical dynamical system framework for modeling clinical time series combines advantages of the two temporal modeling approaches: the linear dynamical system and the Gaussian process. We model the irregularly sampled clinical time series by using multiple Gaussian process sequences in the lower level of our hierarchical framework and capture the transitions between Gaussian processes by utilizing the linear dynamical system. The experiments are conducted on the complete blood count (CBC) panel data of 1000 post-surgical cardiac patients during their hospitalization. Our framework is evaluated and compared to multiple baseline approaches in terms of the mean absolute prediction error and the absolute percentage error. Results We tested our framework by first learning the time series model from data for the patient in the training set, and then applying the model in order to predict future time series values on the patients in the test set. We show that our model outperforms multiple existing models in terms of its predictive accuracy. Our method achieved a 3.13% average prediction accuracy improvement on ten CBC lab time series when it was compared against the best performing baseline. A 5.25% average accuracy improvement was observed when only short-term predictions were considered. Conclusion A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive
Modeling Persistence In Hydrological Time Series Using Fractional Differencing
NASA Astrophysics Data System (ADS)
Hosking, J. R. M.
1984-12-01
The class of autoregressive integrated moving average (ARIMA) time series models may be generalized by permitting the degree of differencing d to take fractional values. Models including fractional differencing are capable of representing persistent series (d > 0) or short-memory series (d = 0). The class of fractionally differenced ARIMA processes provides a more flexible way than has hitherto been available of simultaneously modeling the long-term and short-term behavior of a time series. In this paper some fundamental properties of fractionally differenced ARIMA processes are presented. Methods of simulating these processes are described. Estimation of the parameters of fractionally differenced ARIMA models is discussed, and an approximate maximum likelihood method is proposed. The methodology is illustrated by fitting fractionally differenced models to time series of streamflows and annual temperatures.
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.
Analyzing multiple nonlinear time series with extended Granger causality
NASA Astrophysics Data System (ADS)
Chen, Yonghong; Rangarajan, Govindan; Feng, Jianfeng; Ding, Mingzhou
2004-04-01
Identifying causal relations among simultaneously acquired signals is an important problem in multivariate time series analysis. For linear stochastic systems Granger proposed a simple procedure called the Granger causality to detect such relations. In this work we consider nonlinear extensions of Granger's idea and refer to the result as extended Granger causality. A simple approach implementing the extended Granger causality is presented and applied to multiple chaotic time series and other types of nonlinear signals. In addition, for situations with three or more time series we propose a conditional extended Granger causality measure that enables us to determine whether the causal relation between two signals is direct or mediated by another process.
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.
A Dimensionality Reduction Technique for Efficient Time Series Similarity Analysis
Wang, Qiang; Megalooikonomou, Vasileios
2008-01-01
We propose a dimensionality reduction technique for time series analysis that significantly improves the efficiency and accuracy of similarity searches. In contrast to piecewise constant approximation (PCA) techniques that approximate each time series with constant value segments, the proposed method--Piecewise Vector Quantized Approximation--uses the closest (based on a distance measure) codeword from a codebook of key-sequences to represent each segment. The new representation is symbolic and it allows for the application of text-based retrieval techniques into time series similarity analysis. Experiments on real and simulated datasets show that the proposed technique generally outperforms PCA techniques in clustering and similarity searches. PMID:18496587
Scalable Prediction of Energy Consumption using Incremental Time Series Clustering
Simmhan, Yogesh; Noor, Muhammad Usman
2013-10-09
Time series datasets are a canonical form of high velocity Big Data, and often generated by pervasive sensors, such as found in smart infrastructure. Performing predictive analytics on time series data can be computationally complex, and requires approximation techniques. In this paper, we motivate this problem using a real application from the smart grid domain. We propose an incremental clustering technique, along with a novel affinity score for determining cluster similarity, which help reduce the prediction error for cumulative time series within a cluster. We evaluate this technique, along with optimizations, using real datasets from smart meters, totaling ~700,000 data points, and show the efficacy of our techniques in improving the prediction error of time series data within polynomial time.
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.
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. © 2016 The Author(s).
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
Rodgers, Joseph Lee; Beasley, William Howard; Schuelke, Matthew
2014-01-01
Many data structures, particularly time series data, are naturally seasonal, cyclical, or otherwise circular. Past graphical methods for time series have focused on linear plots. In this article, we move graphical analysis onto the circle. We focus on 2 particular methods, one old and one new. Rose diagrams are circular histograms and can be produced in several different forms using the RRose software system. In addition, we propose, develop, illustrate, and provide software support for a new circular graphical method, called Wrap-Around Time Series Plots (WATS Plots), which is a graphical method useful to support time series analyses in general but in particular in relation to interrupted time series designs. We illustrate the use of WATS Plots with an interrupted time series design evaluating the effect of the Oklahoma City bombing on birthrates in Oklahoma County during the 10 years surrounding the bombing of the Murrah Building in Oklahoma City. We compare WATS Plots with linear time series representations and overlay them with smoothing and error bands. Each method is shown to have advantages in relation to the other; in our example, the WATS Plots more clearly show the existence and effect size of the fertility differential.
Distinguishing chaotic time series from noise: A random matrix approach
NASA Astrophysics Data System (ADS)
Ye, Bin; Chen, Jianxing; Ju, Chen; Li, Huijun; Wang, Xuesong
2017-03-01
Deterministically chaotic systems can often give rise to random and unpredictable behaviors which make the time series obtained from them to be almost indistinguishable from noise. Motivated by the fact that data points in a chaotic time series will have intrinsic correlations between them, we propose a random matrix theory (RMT) approach to identify the deterministic or stochastic dynamics of the system. We show that the spectral distributions of the correlation matrices, constructed from the chaotic time series, deviate significantly from the predictions of random matrix ensembles. On the contrary, the eigenvalue statistics for a noisy signal follow closely those of random matrix ensembles. Numerical results also indicate that the approach is to some extent robust to additive observational noise which pollutes the data in many practical situations. Our approach is efficient in recognizing the continuous chaotic dynamics underlying the evolution of the time series.
A probability distribution approach to synthetic turbulence time series
NASA Astrophysics Data System (ADS)
Sinhuber, Michael; Bodenschatz, Eberhard; Wilczek, Michael
2016-11-01
The statistical features of turbulence can be described in terms of multi-point probability density functions (PDFs). The complexity of these statistical objects increases rapidly with the number of points. This raises the question of how much information has to be incorporated into statistical models of turbulence to capture essential features such as inertial-range scaling and intermittency. Using high Reynolds number hot-wire data obtained at the Variable Density Turbulence Tunnel at the Max Planck Institute for Dynamics and Self-Organization, we establish a PDF-based approach on generating synthetic time series that reproduce those features. To do this, we measure three-point conditional PDFs from the experimental data and use an adaption-rejection method to draw random velocities from this distribution to produce synthetic time series. Analyzing these synthetic time series, we find that time series based on even low-dimensional conditional PDFs already capture some essential features of real turbulent flows.
Mount Etna InSAR Time Series Animation
2012-02-06
This animation depicts a time-series of ground deformation at Mount Etna Volcano between 1992 and 2001. The deformation results from changes in the volume of a shallow chamber centered approximately 5 km 3 miles below sea level.
Searching for periodicity in weighted time point series.
NASA Astrophysics Data System (ADS)
Jetsu, L.; Pelt, J.
1996-09-01
Consistent statistics for two methods of searching for periodicity in a series of weighted time points are formulated. An approach based on the bootstrap method to estimate the accuracy of detected periodicity is presented.
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.
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.
Identification of Significant Outliers in Time Series Data
1993-03-01
Control (Revised Edition). London: Holden-Day, 1976. 5. Brockwell , Peter J . and Richard A . Davis . Time Series: Theory and Methods (Second Edition...through 20 November, 1992. 8. Currie, Dr. Lloyd A , "Pseudo-Code for Plume Detection." Unpublished. 18 July 1991. 9. Diggle, Peter J . Time Series: A ...place. I am indebted to Dr. Peter J . Rousseeuw, upon whose work and book my methodology is based. I am especially grateful to Dr. Rousseeuw for
Digital time series analysis for flutter test data
NASA Technical Reports Server (NTRS)
Batill, S. M.; Carey, D. M.; Kehoe, M. W.
1992-01-01
An application of digital time series analysis to flutter test data processing was conducted. A numerical investigation was used to evaluate the method, as well as its sensitivity to noise and parameter variations. These parameters included those involved with data acquisition, as well as system response characteristics. This digital time series method was then used to predict flutter speed from subcritical response wind tunnel tests. Flutter speeds predicted from forced response, subcritical wind tunnel tests were compared to the experimental flutter speeds.
Visualizing frequent patterns in large multivariate time series
NASA Astrophysics Data System (ADS)
Hao, M.; Marwah, M.; Janetzko, H.; Sharma, R.; Keim, D. A.; Dayal, U.; Patnaik, D.; Ramakrishnan, N.
2011-01-01
The detection of previously unknown, frequently occurring patterns in time series, often called motifs, has been recognized as an important task. However, it is difficult to discover and visualize these motifs as their numbers increase, especially in large multivariate time series. To find frequent motifs, we use several temporal data mining and event encoding techniques to cluster and convert a multivariate time series to a sequence of events. Then we quantify the efficiency of the discovered motifs by linking them with a performance metric. To visualize frequent patterns in a large time series with potentially hundreds of nested motifs on a single display, we introduce three novel visual analytics methods: (1) motif layout, using colored rectangles for visualizing the occurrences and hierarchical relationships of motifs in a multivariate time series, (2) motif distortion, for enlarging or shrinking motifs as appropriate for easy analysis and (3) motif merging, to combine a number of identical adjacent motif instances without cluttering the display. Analysts can interactively optimize the degree of distortion and merging to get the best possible view. A specific motif (e.g., the most efficient or least efficient motif) can be quickly detected from a large time series for further investigation. We have applied these methods to two real-world data sets: data center cooling and oil well production. The results provide important new insights into the recurring patterns.
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.
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.
Prediction of Long-Memory Time Series: A Tutorial Review
NASA Astrophysics Data System (ADS)
Bhansali, R. J.; Kokoszka, P. S.
Two different approaches, called Type-I and Type-II, to linear least-squares prediction of a long-memory time series are distinguished. In the former, no new theory is required and a long-memory time series is treated on par with a standard short-memory time series and its multistep predictions are obtained by using the existing modelling approaches to prediction of such time series. The latter, by contrast, seeks to model the long-memory stochastic characteristics of the observed time series by a fractional process such that its dth fractional difference, 0 < d < 0.5, follows a standard short-memory process. The various approaches to constructing long-memory stochastic models are reviewed, and the associated question of parameter estimation for these models is discussed. Having fitted a long-memory stochastic model to a time series, linear multi-step forecasts of its future values are constructed from the model itself. The question of how to evaluate the multistep prediction constants is considered and three different methods proposed for doing so are outlined; it is further noted that, under appropriate regularity conditions, these methods apply also to the class of linear long memory processes with infinite variance. In addition, a brief review of the class of non-linear chaotic maps implying long-memory is given.
Vowel Recognition from Articulatory Position Time-Series Data.
Wang, Jun; Samal, Ashok; Green, Jordan R; Carrell, Tom D
2009-09-28
A new approach of recognizing vowels from articulatory position time-series data was proposed and tested in this paper. This approach directly mapped articulatory position time-series data to vowels without extracting articulatory features such as mouth opening. The input time-series data were time-normalized and sampled to fixed-width vectors of articulatory positions. Three commonly used classifiers, Neural Network, Support Vector Machine and Decision Tree were used and their performances were compared on the vectors. A single speaker dataset of eight major English vowels acquired using Electromagnetic Articulograph (EMA) AG500 was used. Recognition rate using cross validation ranged from 76.07% to 91.32% for the three classifiers. In addition, the trained decision trees were consistent with articulatory features commonly used to descriptively distinguish vowels in classical phonetics. The findings are intended to improve the accuracy and response time of a real-time articulatory-to-acoustics synthesizer.
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).
Similarity estimators for irregular and age-uncertain time series
NASA Astrophysics Data System (ADS)
Rehfeld, K.; Kurths, J.
2014-01-01
Paleoclimate time series are often irregularly sampled and age uncertain, which is an important technical challenge to overcome for successful reconstruction of past climate variability and dynamics. Visual comparison and interpolation-based linear correlation approaches have been used to infer dependencies from such proxy time series. While the first is subjective, not measurable and not suitable for the comparison of many data sets at a time, the latter introduces interpolation bias, and both face difficulties if the underlying dependencies are nonlinear. In this paper we investigate similarity estimators that could be suitable for the quantitative investigation of dependencies in irregular and age-uncertain time series. We compare the Gaussian-kernel-based cross-correlation (gXCF, Rehfeld et al., 2011) and mutual information (gMI, Rehfeld et al., 2013) against their interpolation-based counterparts and the new event synchronization function (ESF). We test the efficiency of the methods in estimating coupling strength and coupling lag numerically, using ensembles of synthetic stalagmites with short, autocorrelated, linear and nonlinearly coupled proxy time series, and in the application to real stalagmite time series. In the linear test case, coupling strength increases are identified consistently for all estimators, while in the nonlinear test case the correlation-based approaches fail. The lag at which the time series are coupled is identified correctly as the maximum of the similarity functions in around 60-55% (in the linear case) to 53-42% (for the nonlinear processes) of the cases when the dating of the synthetic stalagmite is perfectly precise. If the age uncertainty increases beyond 5% of the time series length, however, the true coupling lag is not identified more often than the others for which the similarity function was estimated. Age uncertainty contributes up to half of the uncertainty in the similarity estimation process. Time series irregularity
Similarity estimators for irregular and age uncertain time series
NASA Astrophysics Data System (ADS)
Rehfeld, K.; Kurths, J.
2013-09-01
Paleoclimate time series are often irregularly sampled and age uncertain, which is an important technical challenge to overcome for successful reconstruction of past climate variability and dynamics. Visual comparison and interpolation-based linear correlation approaches have been used to infer dependencies from such proxy time series. While the first is subjective, not measurable and not suitable for the comparison of many datasets at a time, the latter introduces interpolation bias, and both face difficulties if the underlying dependencies are nonlinear. In this paper we investigate similarity estimators that could be suitable for the quantitative investigation of dependencies in irregular and age uncertain time series. We compare the Gaussian-kernel based cross correlation (gXCF, Rehfeld et al., 2011) and mutual information (gMI, Rehfeld et al., 2013) against their interpolation-based counterparts and the new event synchronization function (ESF). We test the efficiency of the methods in estimating coupling strength and coupling lag numerically, using ensembles of synthetic stalagmites with short, autocorrelated, linear and nonlinearly coupled proxy time series, and in the application to real stalagmite time series. In the linear test case coupling strength increases are identified consistently for all estimators, while in the nonlinear test case the correlation-based approaches fail. The lag at which the time series are coupled is identified correctly as the maximum of the similarity functions in around 60-55% (in the linear case) to 53-42% (for the nonlinear processes) of the cases when the dating of the synthetic stalagmite is perfectly precise. If the age uncertainty increases beyond 5% of the time series length, however, the true coupling lag is not identified more often than the others for which the similarity function was estimated. Age uncertainty contributes up to half of the uncertainty in the similarity estimation process. Time series irregularity
Analyses of Inhomogeneities in Radiosonde Temperature and Humidity Time Series.
NASA Astrophysics Data System (ADS)
Zhai, Panmao; Eskridge, Robert E.
1996-04-01
Twice daily radiosonde data from selected stations in the United States (period 1948 to 1990) and China (period 1958 to 1990) were sorted into time series. These stations have one sounding taken in darkness and the other in sunlight. The analysis shows that the 0000 and 1200 UTC time series are highly correlated. Therefore, the Easterling and Peterson technique was tested on the 0000 and 1200 time series to detect inhomogeneities and to estimate the size of the biases. Discontinuities were detected using the difference series created from the 0000 and 1200 UTC time series. To establish that the detected bias was significant, a t test was performed to confirm that the change occurs in the daytime series but not in the nighttime series.Both U.S. and Chinese radiosonde temperature and humidity data include inhomogeneities caused by changes in radiosonde sensors and observation times. The U.S. humidity data have inhomogeneities that were caused by instrument changes and the censoring of data. The practice of reporting relative humidity as 19% when it is lower than 20% or the temperature is below 40°C is called censoring. This combination of procedural and instrument changes makes the detection of biases and adjustment of the data very difficult. In the Chinese temperatures, them are inhomogeneities related to a change in the radiation correction procedure.Test results demonstrate that a modified Easterling and Peterson method is suitable for use in detecting and adjusting time series radiosonde data.Accurate stations histories are very desirable. Stations histories can confirm that detected inhomogeneities are related to instrument or procedural changes. Adjustments can then he made to the data with some confidence.
Sharmin, Moushumi; Raij, Andrew; Epstien, David; Nahum-Shani, Inbal; Beck, J Gayle; Vhaduri, Sudip; Preston, Kenzie; Kumar, Santosh
2015-09-01
We investigate needs, challenges, and opportunities in visualizing time-series sensor data on stress to inform the design of just-in-time adaptive interventions (JITAIs). We identify seven key challenges: massive volume and variety of data, complexity in identifying stressors, scalability of space, multifaceted relationship between stress and time, a need for representation at multiple granularities, interperson variability, and limited understanding of JITAI design requirements due to its novelty. We propose four new visualizations based on one million minutes of sensor data (n=70). We evaluate our visualizations with stress researchers (n=6) to gain first insights into its usability and usefulness in JITAI design. Our results indicate that spatio-temporal visualizations help identify and explain between- and within-person variability in stress patterns and contextual visualizations enable decisions regarding the timing, content, and modality of intervention. Interestingly, a granular representation is considered informative but noise-prone; an abstract representation is the preferred starting point for designing JITAIs.
Time is Money: Designing Cost-Effective Time Series Experiments.
Slonim, Donna K
2016-07-01
A new theoretical model helps to evaluate the tradeoffs between running technical replicates in high-throughput experiments and sampling at more time points. Copyright © 2016 Elsevier Inc. All rights reserved.
Multiresolution analysis of Bursa Malaysia KLCI time series
NASA Astrophysics Data System (ADS)
Ismail, Mohd Tahir; Dghais, Amel Abdoullah Ahmed
2017-05-01
In general, a time series is simply a sequence of numbers collected at regular intervals over a period. Financial time series data processing is concerned with the theory and practice of processing asset price over time, such as currency, commodity data, and stock market data. The primary aim of this study is to understand the fundamental characteristics of selected financial time series by using the time as well as the frequency domain analysis. After that prediction can be executed for the desired system for in sample forecasting. In this study, multiresolution analysis which the assist of discrete wavelet transforms (DWT) and maximal overlap discrete wavelet transform (MODWT) will be used to pinpoint special characteristics of Bursa Malaysia KLCI (Kuala Lumpur Composite Index) daily closing prices and return values. In addition, further case study discussions include the modeling of Bursa Malaysia KLCI using linear ARIMA with wavelets to address how multiresolution approach improves fitting and forecasting results.
Correlation measure to detect time series distances, whence economy globalization
NASA Astrophysics Data System (ADS)
Miśkiewicz, Janusz; Ausloos, Marcel
2008-11-01
An instantaneous time series distance is defined through the equal time correlation coefficient. The idea is applied to the Gross Domestic Product (GDP) yearly increments of 21 rich countries between 1950 and 2005 in order to test the process of economic globalisation. Some data discussion is first presented to decide what (EKS, GK, or derived) GDP series should be studied. Distances are then calculated from the correlation coefficient values between pairs of series. The role of time averaging of the distances over finite size windows is discussed. Three network structures are next constructed based on the hierarchy of distances. It is shown that the mean distance between the most developed countries on several networks actually decreases in time, -which we consider as a proof of globalization. An empirical law is found for the evolution after 1990, similar to that found in flux creep. The optimal observation time window size is found ≃15 years.
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
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
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 ~10(2). Calculations with specified Hurst exponent values of 0.2,0.3,...,0.9 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 (≤0.03) and sharp confidential interval (standard deviation ≤0.05). 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.
Modeling Non-Gaussian Time Series with Nonparametric Bayesian Model.
Xu, Zhiguang; MacEachern, Steven; Xu, Xinyi
2015-02-01
We present a class of Bayesian copula models whose major components are the marginal (limiting) distribution of a stationary time series and the internal dynamics of the series. We argue that these are the two features with which an analyst is typically most familiar, and hence that these are natural components with which to work. For the marginal distribution, we use a nonparametric Bayesian prior distribution along with a cdf-inverse cdf transformation to obtain large support. For the internal dynamics, we rely on the traditionally successful techniques of normal-theory time series. Coupling the two components gives us a family of (Gaussian) copula transformed autoregressive models. The models provide coherent adjustments of time scales and are compatible with many extensions, including changes in volatility of the series. We describe basic properties of the models, show their ability to recover non-Gaussian marginal distributions, and use a GARCH modification of the basic model to analyze stock index return series. The models are found to provide better fit and improved short-range and long-range predictions than Gaussian competitors. The models are extensible to a large variety of fields, including continuous time models, spatial models, models for multiple series, models driven by external covariate streams, and non-stationary models.
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.
Drunk driving detection based on classification of multivariate time series.
Li, Zhenlong; Jin, Xue; Zhao, Xiaohua
2015-09-01
This paper addresses the problem of detecting drunk driving based on classification of multivariate time series. First, driving performance measures were collected from a test in a driving simulator located in the Traffic Research Center, Beijing University of Technology. Lateral position and steering angle were used to detect drunk driving. Second, multivariate time series analysis was performed to extract the features. A piecewise linear representation was used to represent multivariate time series. A bottom-up algorithm was then employed to separate multivariate time series. The slope and time interval of each segment were extracted as the features for classification. Third, a support vector machine classifier was used to classify driver's state into two classes (normal or drunk) according to the extracted features. The proposed approach achieved an accuracy of 80.0%. Drunk driving detection based on the analysis of multivariate time series is feasible and effective. The approach has implications for drunk driving detection. Copyright © 2015 Elsevier Ltd and National Safety Council. All rights reserved.
Self-affinity in the dengue fever time series
NASA Astrophysics Data System (ADS)
Azevedo, S. M.; Saba, H.; Miranda, J. G. V.; Filho, A. S. Nascimento; Moret, M. A.
2016-06-01
Dengue is a complex public health problem that is common in tropical and subtropical regions. This disease has risen substantially in the last three decades, and the physical symptoms depict the self-affine behavior of the occurrences of reported dengue cases in Bahia, Brazil. This study uses detrended fluctuation analysis (DFA) to verify the scale behavior in a time series of dengue cases and to evaluate the long-range correlations that are characterized by the power law α exponent for different cities in Bahia, Brazil. The scaling exponent (α) presents different long-range correlations, i.e. uncorrelated, anti-persistent, persistent and diffusive behaviors. The long-range correlations highlight the complex behavior of the time series of this disease. The findings show that there are two distinct types of scale behavior. In the first behavior, the time series presents a persistent α exponent for a one-month period. For large periods, the time series signal approaches subdiffusive behavior. The hypothesis of the long-range correlations in the time series of the occurrences of reported dengue cases was validated. The observed self-affinity is useful as a forecasting tool for future periods through extrapolation of the α exponent behavior. This complex system has a higher predictability in a relatively short time (approximately one month), and it suggests a new tool in epidemiological control strategies. However, predictions for large periods using DFA are hidden by the subdiffusive behavior.
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
Sun, Tao; Liu, Hongbo; Yu, Hong; Chen, C L Philip
2016-06-28
The central time series crystallizes the common patterns of the set it represents. In this paper, we propose a global constrained degree-pruning dynamic programming (g(dp)²) approach to obtain the central time series through minimizing dynamic time warping (DTW) distance between two time series. The DTW matching path theory with global constraints is proved theoretically for our degree-pruning strategy, which is helpful to reduce the time complexity and computational cost. Our approach can achieve the optimal solution between two time series. An approximate method to the central time series of multiple time series [called as m_g(dp)²] is presented based on DTW barycenter averaging and our g(dp)² approach by considering hierarchically merging strategy. As illustrated by the experimental results, our approaches provide better within-group sum of squares and robustness than other relevant algorithms.
Multiscale multifractal diffusion entropy analysis of financial time series
NASA Astrophysics Data System (ADS)
Huang, Jingjing; Shang, Pengjian
2015-02-01
This paper introduces a multiscale multifractal diffusion entropy analysis (MMDEA) method to analyze long-range correlation then applies this method to stock index series. The method combines the techniques of diffusion process and Rényi entropy to focus on the scaling behaviors of stock index series using a multiscale, which allows us to extend the description of stock index variability to include the dependence on the magnitude of the variability and time scale. Compared to multifractal diffusion entropy analysis, the MMDEA can show more details of scale properties and provide a reliable analysis. In this paper, we concentrate not only on the fact that the stock index series has multifractal properties but also that these properties depend on the time scale in which the multifractality is measured. This time scale is related to the frequency band of the signal. We find that stock index variability appears to be far more complex than reported in the studies using a fixed time scale.
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
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.
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.
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.
An introduction to chaotic and random time series analysis
NASA Technical Reports Server (NTRS)
Scargle, Jeffrey D.
1989-01-01
The origin of chaotic behavior and the relation of chaos to randomness are explained. Two mathematical results are described: (1) a representation theorem guarantees the existence of a specific time-domain model for chaos and addresses the relation between chaotic, random, and strictly deterministic processes; (2) a theorem assures that information on the behavior of a physical system in its complete state space can be extracted from time-series data on a single observable. Focus is placed on an important connection between the dynamical state space and an observable time series. These two results lead to a practical deconvolution technique combining standard random process modeling methods with new embedded techniques.
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.
An introduction to chaotic and random time series analysis
NASA Technical Reports Server (NTRS)
Scargle, Jeffrey D.
1989-01-01
The origin of chaotic behavior and the relation of chaos to randomness are explained. Two mathematical results are described: (1) a representation theorem guarantees the existence of a specific time-domain model for chaos and addresses the relation between chaotic, random, and strictly deterministic processes; (2) a theorem assures that information on the behavior of a physical system in its complete state space can be extracted from time-series data on a single observable. Focus is placed on an important connection between the dynamical state space and an observable time series. These two results lead to a practical deconvolution technique combining standard random process modeling methods with new embedded techniques.
Higher-Order Hurst Signatures: Dynamical Information in Time Series
NASA Astrophysics Data System (ADS)
Ferenbaugh, Willis
2005-10-01
Understanding and comparing time series from different systems requires characteristic measures of the dynamics embedded in the series. The Hurst exponent is a second-order dynamical measure of a time series which grew up within the blossoming fractal world of Mandelbrot. This characteristic measure is directly related to the behavior of the autocorrelation, the power-spectrum, and other second-order things. And as with these other measures, the Hurst exponent captures and quantifies some but not all of the intrinsic nature of a series. The more elusive characteristics live in the phase spectrum and the higher-order spectra. This research is a continuing quest to (more) fully characterize the dynamical information in time series produced by plasma experiments or models. The goal is to supplement the series information which can be represented by a Hurst exponent, and we would like to develop supplemental techniques in analogy with Hurst's original R/S analysis. These techniques should be another way to plumb the higher-order dynamics.
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.
Recurrent Neural Network Applications for Astronomical Time Series
NASA Astrophysics Data System (ADS)
Protopapas, Pavlos
2017-06-01
The benefits of good predictive models in astronomy lie in early event prediction systems and effective resource allocation. Current time series methods applicable to regular time series have not evolved to generalize for irregular time series. In this talk, I will describe two Recurrent Neural Network methods, Long Short-Term Memory (LSTM) and Echo State Networks (ESNs) for predicting irregular time series. Feature engineering along with a non-linear modeling proved to be an effective predictor. For noisy time series, the prediction is improved by training the network on error realizations using the error estimates from astronomical light curves. In addition to this, we propose a new neural network architecture to remove correlation from the residuals in order to improve prediction and compensate for the noisy data. Finally, I show how to set hyperparameters for a stable and performant solution correctly. In this work, we circumvent this obstacle by optimizing ESN hyperparameters using Bayesian optimization with Gaussian Process priors. This automates the tuning procedure, enabling users to employ the power of RNN without needing an in-depth understanding of the tuning procedure.
Characterizing time series via complexity-entropy curves
NASA Astrophysics Data System (ADS)
Ribeiro, Haroldo V.; Jauregui, Max; Zunino, Luciano; Lenzi, Ervin K.
2017-06-01
The search for patterns in time series is a very common task when dealing with complex systems. This is usually accomplished by employing a complexity measure such as entropies and fractal dimensions. However, such measures usually only capture a single aspect of the system dynamics. Here, we propose a family of complexity measures for time series based on a generalization of the complexity-entropy causality plane. By replacing the Shannon entropy by a monoparametric entropy (Tsallis q entropy) and after considering the proper generalization of the statistical complexity (q complexity), we build up a parametric curve (the q -complexity-entropy curve) that is used for characterizing and classifying time series. Based on simple exact results and numerical simulations of stochastic processes, we show that these curves can distinguish among different long-range, short-range, and oscillating correlated behaviors. Also, we verify that simulated chaotic and stochastic time series can be distinguished based on whether these curves are open or closed. We further test this technique in experimental scenarios related to chaotic laser intensity, stock price, sunspot, and geomagnetic dynamics, confirming its usefulness. Finally, we prove that these curves enhance the automatic classification of time series with long-range correlations and interbeat intervals of healthy subjects and patients with heart disease.
Characterizing time series via complexity-entropy curves.
Ribeiro, Haroldo V; Jauregui, Max; Zunino, Luciano; Lenzi, Ervin K
2017-06-01
The search for patterns in time series is a very common task when dealing with complex systems. This is usually accomplished by employing a complexity measure such as entropies and fractal dimensions. However, such measures usually only capture a single aspect of the system dynamics. Here, we propose a family of complexity measures for time series based on a generalization of the complexity-entropy causality plane. By replacing the Shannon entropy by a monoparametric entropy (Tsallis q entropy) and after considering the proper generalization of the statistical complexity (q complexity), we build up a parametric curve (the q-complexity-entropy curve) that is used for characterizing and classifying time series. Based on simple exact results and numerical simulations of stochastic processes, we show that these curves can distinguish among different long-range, short-range, and oscillating correlated behaviors. Also, we verify that simulated chaotic and stochastic time series can be distinguished based on whether these curves are open or closed. We further test this technique in experimental scenarios related to chaotic laser intensity, stock price, sunspot, and geomagnetic dynamics, confirming its usefulness. Finally, we prove that these curves enhance the automatic classification of time series with long-range correlations and interbeat intervals of healthy subjects and patients with heart disease.
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.
Time Series Analysis Based on Running Mann Whitney Z Statistics
USDA-ARS?s Scientific Manuscript database
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-...
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
Improvements to surrogate data methods for nonstationary time series.
Lucio, J H; Valdés, R; Rodríguez, L R
2012-05-01
The method of surrogate data has been extensively applied to hypothesis testing of system linearity, when only one realization of the system, a time series, is known. Normally, surrogate data should preserve the linear stochastic structure and the amplitude distribution of the original series. Classical surrogate data methods (such as random permutation, amplitude adjusted Fourier transform, or iterative amplitude adjusted Fourier transform) are successful at preserving one or both of these features in stationary cases. However, they always produce stationary surrogates, hence existing nonstationarity could be interpreted as dynamic nonlinearity. Certain modifications have been proposed that additionally preserve some nonstationarity, at the expense of reproducing a great deal of nonlinearity. However, even those methods generally fail to preserve the trend (i.e., global nonstationarity in the mean) of the original series. This is the case of time series with unit roots in their autoregressive structure. Additionally, those methods, based on Fourier transform, either need first and last values in the original series to match, or they need to select a piece of the original series with matching ends. These conditions are often inapplicable and the resulting surrogates are adversely affected by the well-known artefact problem. In this study, we propose a simple technique that, applied within existing Fourier-transform-based methods, generates surrogate data that jointly preserve the aforementioned characteristics of the original series, including (even strong) trends. Moreover, our technique avoids the negative effects of end mismatch. Several artificial and real, stationary and nonstationary, linear and nonlinear time series are examined, in order to demonstrate the advantages of the methods. Corresponding surrogate data are produced with the classical and with the proposed methods, and the results are compared.
Absorption of a Massive Scalar Field by Wormhole Space-Times
NASA Astrophysics Data System (ADS)
Huang, Hai; Chen, Juhua; Wang, Yongjiu; Jin, Yao
2017-04-01
In this paper we consider the problem of the test massive scalar field propagating in the background of a class of wormhole space-times. Basing on the quantum scattering theory, we analyze the Schrödinger-type scalar wave equation and compute transmission coefficients for arbitrary coupling of the field to the background geometry with the WKB approximation. We numerically investigate its absorption cross section and analyze them in the high frequency regime. We find that the absorption cross section oscillates about the geometric optical value and the limit of absorption cross section is uniform in the high frequency regime.
Absorption of a Massive Scalar Field by Wormhole Space-Times
NASA Astrophysics Data System (ADS)
Huang, Hai; Chen, Juhua; Wang, Yongjiu; Jin, Yao
2017-01-01
In this paper we consider the problem of the test massive scalar field propagating in the background of a class of wormhole space-times. Basing on the quantum scattering theory, we analyze the Schrödinger-type scalar wave equation and compute transmission coefficients for arbitrary coupling of the field to the background geometry with the WKB approximation. We numerically investigate its absorption cross section and analyze them in the high frequency regime. We find that the absorption cross section oscillates about the geometric optical value and the limit of absorption cross section is uniform in the high frequency regime.
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
Cloud masking and removal in remote sensing image time series
NASA Astrophysics Data System (ADS)
Gómez-Chova, Luis; Amorós-López, Julia; Mateo-García, Gonzalo; Muñoz-Marí, Jordi; Camps-Valls, Gustau
2017-01-01
Automatic cloud masking of Earth observation images is one of the first required steps in optical remote sensing data processing since the operational use and product generation from satellite image time series might be hampered by undetected clouds. The high temporal revisit of current and forthcoming missions and the scarcity of labeled data force us to cast cloud screening as an unsupervised change detection problem in the temporal domain. We introduce a cloud screening method based on detecting abrupt changes along the time dimension. The main assumption is that image time series follow smooth variations over land (background) and abrupt changes will be mainly due to the presence of clouds. The method estimates the background surface changes using the information in the time series. In particular, we propose linear and nonlinear least squares regression algorithms that minimize both the prediction and the estimation error simultaneously. Then, significant differences in the image of interest with respect to the estimated background are identified as clouds. The use of kernel methods allows the generalization of the algorithm to account for higher-order (nonlinear) feature relations. After the proposed cloud masking and cloud removal, cloud-free time series at high spatial resolution can be used to obtain a better monitoring of land cover dynamics and to generate more elaborated products. The method is tested in a dataset with 5-day revisit time series from SPOT-4 at high resolution and with Landsat-8 time series. Experimental results show that the proposed method yields more accurate cloud masks when confronted with state-of-the-art approaches typically used in operational settings. In addition, the algorithm has been implemented in the Google Earth Engine platform, which allows us to access the full Landsat-8 catalog and work in a parallel distributed platform to extend its applicability to a global planetary scale.
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.
Time series characterization via horizontal visibility graph and Information Theory
NASA Astrophysics Data System (ADS)
Gonçalves, Bruna Amin; Carpi, Laura; Rosso, Osvaldo A.; Ravetti, Martín G.
2016-12-01
Complex networks theory have gained wider applicability since methods for transformation of time series to networks were proposed and successfully tested. In the last few years, horizontal visibility graph has become a popular method due to its simplicity and good results when applied to natural and artificially generated data. In this work, we explore different ways of extracting information from the network constructed from the horizontal visibility graph and evaluated by Information Theory quantifiers. Most works use the degree distribution of the network, however, we found alternative probability distributions, more efficient than the degree distribution in characterizing dynamical systems. In particular, we find that, when using distributions based on distances and amplitude values, significant shorter time series are required. We analyze fractional Brownian motion time series, and a paleoclimatic proxy record of ENSO from the Pallcacocha Lake to study dynamical changes during the Holocene.
Neural network versus classical time series forecasting models
NASA Astrophysics Data System (ADS)
Nor, Maria Elena; Safuan, Hamizah Mohd; Shab, Noorzehan Fazahiyah Md; Asrul, Mohd; Abdullah, Affendi; Mohamad, Nurul Asmaa Izzati; Lee, Muhammad Hisyam
2017-05-01
Artificial neural network (ANN) has advantage in time series forecasting as it has potential to solve complex forecasting problems. This is because ANN is data driven approach which able to be trained to map past values of a time series. In this study the forecast performance between neural network and classical time series forecasting method namely seasonal autoregressive integrated moving average models was being compared by utilizing gold price data. Moreover, the effect of different data preprocessing on the forecast performance of neural network being examined. The forecast accuracy was evaluated using mean absolute deviation, root mean square error and mean absolute percentage error. It was found that ANN produced the most accurate forecast when Box-Cox transformation was used as data preprocessing.
Characterizing Complex Time Series from the Scaling of Prediction Error.
NASA Astrophysics Data System (ADS)
Hinrichs, Brant Eric
This thesis concerns characterizing complex time series from the scaling of prediction error. We use the global modeling technique of radial basis function approximation to build models from a state-space reconstruction of a time series that otherwise appears complicated or random (i.e. aperiodic, irregular). Prediction error as a function of prediction horizon is obtained from the model using the direct method. The relationship between the underlying dynamics of the time series and the logarithmic scaling of prediction error as a function of prediction horizon is investigated. We use this relationship to characterize the dynamics of both a model chaotic system and physical data from the optic tectum of an attentive pigeon exhibiting the important phenomena of nonstationary neuronal oscillations in response to visual stimuli.
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.
Test to determine the Markov order of a time series.
Racca, E; Laio, F; Poggi, D; Ridolfi, L
2007-01-01
The Markov order of a time series is an important measure of the "memory" of a process, and its knowledge is fundamental for the correct simulation of the characteristics of the process. For this reason, several techniques have been proposed in the past for its estimation. However, most of this methods are rather complex, and often can be applied only in the case of Markov chains. Here we propose a simple and robust test to evaluate the Markov order of a time series. Only the first-order moment of the conditional probability density function characterizing the process is used to evaluate the memory of the process itself. This measure is called the "expected value Markov (EVM) order." We show that there is good agreement between the EVM order and the known Markov order of some synthetic time series.
Causal analysis of time series from hydrological systems
NASA Astrophysics Data System (ADS)
Selle, Benny; Aufgebauer, Britta; Knorr, Klaus-Holger
2017-04-01
It is often difficult to infer cause and effect in hydrological systems for which time series of system inputs, outputs and state variables are observed. A recently published technique called Convergent Cross Mapping could be a promising tool to detect causality between time series. A response variable Y may be causally related to a forcing variable X, if the so called cross mapping of X using Y improves with the amount of data included. The idea is that a response variable contains information on the history of its driving variable whereas the reverse may not be true. We propose an alternative approach based on similar ideas using neural networks. Our approach is firstly compared to Convergent Cross Mapping using a synthetic time series of precipitation and streamflow generated by a rainfall runoff model. Secondly, measured concentrations of dissolved organic carbon and dissolved iron from a mountainous stream in Germany, that were previously hypothesised to be casually linked, are tested.
Appropriate Algorithms for Nonlinear Time Series Analysis in Psychology
NASA Astrophysics Data System (ADS)
Scheier, Christian; Tschacher, Wolfgang
Chaos theory has a strong appeal for psychology because it allows for the investigation of the dynamics and nonlinearity of psychological systems. Consequently, chaos-theoretic concepts and methods have recently gained increasing attention among psychologists and positive claims for chaos have been published in nearly every field of psychology. Less attention, however, has been paid to the appropriateness of chaos-theoretic algorithms for psychological time series. An appropriate algorithm can deal with short, noisy data sets and yields `objective' results. In the present paper it is argued that most of the classical nonlinear techniques don't satisfy these constraints and thus are not appropriate for psychological data. A methodological approach is introduced that is based on nonlinear forecasting and the method of surrogate data. In artificial data sets and empirical time series we can show that this methodology reliably assesses nonlinearity and chaos in time series even if they are short and contaminated by noise.
Permutation test for periodicity in short time series data
Ptitsyn, Andrey A; Zvonic, Sanjin; Gimble, Jeffrey M
2006-01-01
Background Periodic processes, such as the circadian rhythm, are important factors modulating and coordinating transcription of genes governing key metabolic pathways. Theoretically, even small fluctuations in the orchestration of circadian gene expression patterns among different tissues may result in functional asynchrony at the organism level and may contribute to a wide range of pathologic disorders. Identification of circadian expression pattern in time series data is important, but equally challenging. Microarray technology allows estimation of relative expression of thousands of genes at each time point. However, this estimation often lacks precision and microarray experiments are prohibitively expensive, limiting the number of data points in a time series expression profile. The data produced in these experiments carries a high degree of stochastic variation, obscuring the periodic pattern and a limited number of replicates, typically covering not more than two complete periods of oscillation. Results To address this issue, we have developed a simple, but effective, computational technique for the identification of a periodic pattern in relatively short time series, typical for microarray studies of circadian expression. This test is based on a random permutation of time points in order to estimate non-randomness of a periodogram. The Permutated time, or Pt-test, is able to detect oscillations within a given period in expression profiles dominated by a high degree of stochastic fluctuations or oscillations of different irrelevant frequencies. We have conducted a comprehensive study of circadian expression on a large data set produced at PBRC, representing three different peripheral murine tissues. We have also re-analyzed a number of similar time series data sets produced and published independently by other research groups over the past few years. Conclusion The Permutated time test (Pt-test) is demonstrated to be effective for detection of periodicity in
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.
Noise analysis of GPS time series in Taiwan
NASA Astrophysics Data System (ADS)
Lee, You-Chia; Chang, Wu-Lung
2017-04-01
Global positioning system (GPS) usually used for researches of plate tectonics and crustal deformation. In most studies, GPS time series considered only time-independent noises (white noise), but time-dependent noises (flicker noise, random walk noise) which were found by nearly twenty years are also important to the precision of data. The rate uncertainties of stations will be underestimated if the GPS time series are assumed only time-independent noise. Therefore studying the noise properties of GPS time series is necessary in order to realize the precision and reliability of velocity estimates. The lengths of our GPS time series are from over 500 stations around Taiwan with time spans longer than 2.5 years up to 20 years. The GPS stations include different monument types such as deep drill braced, roof, metal tripod, and concrete pier, and the most common type in Taiwan is the metal tripod. We investigated the noise properties of continuous GPS time series by using the spectral index and amplitude of the power law noise. During the process we first remove the data outliers, and then estimate linear trend, size of offsets, and seasonal signals, and finally the amplitudes of the power-law and white noise are estimated simultaneously. Our preliminary results show that the noise amplitudes of the north component are smaller than that of the other two components, and the largest amplitudes are in the vertical. We also find that the amplitudes of white noise and power-law noises are positively correlated in three components. Comparisons of noise amplitudes of different monument types in Taiwan reveal that the deep drill braced monuments have smaller data uncertainties and therefore are more stable than other monuments.
A novel time series link prediction method: Learning automata approach
NASA Astrophysics Data System (ADS)
Moradabadi, Behnaz; Meybodi, Mohammad Reza
2017-09-01
Link prediction is a main social network challenge that uses the network structure to predict future links. The common link prediction approaches to predict hidden links use a static graph representation where a snapshot of the network is analyzed to find hidden or future links. For example, similarity metric based link predictions are a common traditional approach that calculates the similarity metric for each non-connected link and sort the links based on their similarity metrics and label the links with higher similarity scores as the future links. Because people activities in social networks are dynamic and uncertainty, and the structure of the networks changes over time, using deterministic graphs for modeling and analysis of the social network may not be appropriate. In the time-series link prediction problem, the time series link occurrences are used to predict the future links In this paper, we propose a new time series link prediction based on learning automata. In the proposed algorithm for each link that must be predicted there is one learning automaton and each learning automaton tries to predict the existence or non-existence of the corresponding link. To predict the link occurrence in time T, there is a chain consists of stages 1 through T - 1 and the learning automaton passes from these stages to learn the existence or non-existence of the corresponding link. Our preliminary link prediction experiments with co-authorship and email networks have provided satisfactory results when time series link occurrences are considered.
Time series patterns and language support in DBMS
NASA Astrophysics Data System (ADS)
Telnarova, Zdenka
2017-07-01
This contribution is focused on pattern type Time Series as a rich in semantics representation of data. Some example of implementation of this pattern type in traditional Data Base Management Systems is briefly presented. There are many approaches how to manipulate with patterns and query patterns. Crucial issue can be seen in systematic approach to pattern management and specific pattern query language which takes into consideration semantics of patterns. Query language SQL-TS for manipulating with patterns is shown on Time Series data.
Detecting unstable periodic orbits in chaotic time series using synchronization
NASA Astrophysics Data System (ADS)
Olyaei, Ali Azimi; Wu, Christine; Kinsner, Witold
2017-07-01
An alternative approach of detecting unstable periodic orbits in chaotic time series is proposed using synchronization techniques. A master-slave synchronization scheme is developed, in which the chaotic system drives a system of harmonic oscillators through a proper coupling condition. The proposed scheme is designed so that the power of the coupling signal exhibits notches that drop to zero once the system approaches an unstable orbit yielding an explicit indication of the presence of a periodic motion. The results shows that the proposed approach is particularly suitable in practical situations, where the time series is short and noisy, or it is obtained from high-dimensional chaotic systems.
Microbial oceanography and the Hawaii Ocean Time-series programme.
Karl, David M; Church, Matthew J
2014-10-01
The Hawaii Ocean Time-series (HOT) programme has been tracking microbial and biogeochemical processes in the North Pacific Subtropical Gyre since October 1988. The near-monthly time series observations have revealed previously undocumented phenomena within a temporally dynamic ecosystem that is vulnerable to climate change. Novel microorganisms, genes and unexpected metabolic pathways have been discovered and are being integrated into our evolving ecological paradigms. Continued research, including higher-frequency observations and at-sea experimentation, will help to provide a comprehensive scientific understanding of microbial processes in the largest biome on Earth.
Testing for intracycle determinism in pseudoperiodic time series
NASA Astrophysics Data System (ADS)
Coelho, Mara C. S.; Mendes, Eduardo M. A. M.; Aguirre, Luis A.
2008-06-01
A determinism test is proposed based on the well-known method of the surrogate data. Assuming predictability to be a signature of determinism, the proposed method checks for intracycle (e.g., short-term) determinism in the pseudoperiodic time series for which standard methods of surrogate analysis do not apply. The approach presented is composed of two steps. First, the data are preprocessed to reduce the effects of seasonal and trend components. Second, standard tests of surrogate analysis can then be used. The determinism test is applied to simulated and experimental pseudoperiodic time series and the results show the applicability of the proposed test.
The time series modelling of non-Gaussian engineering processes
NASA Astrophysics Data System (ADS)
Watson, W.; Spedding, T. A.
1982-12-01
The basic methods of the time series modeling of surface profiles are extended to non-Gaussian processes which can involve complex correlation structures (e.g., periodic components obtained from turning and other similar processes). Particular attention is given to a class of models for time series formed by a combination of autoregressive (AR) and moving average (MA) processes. The results presented here show that these models are capable of accurately simulating a wide range of surface profile characteristics. The models can be programmed to run automatically and can be combined with standard procedures for fitting ARMA models and, if required, with one or several methods for separating random and periodic components.
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.
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.
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.
Ozone Time Series From GOMOS and SAGE II Measurements
NASA Astrophysics Data System (ADS)
Kyrola, E. T.; Laine, M.; Tukiainen, S.; Sofieva, V.; Zawodny, J. M.; Thomason, L. W.
2011-12-01
Satellite measurements are essential for monitoring changes in the global stratospheric ozone distribution. Both the natural variation and anthropogenic change are strongly dependent on altitude. Stratospheric ozone has been measured from space with good vertical resolution since 1985 by the SAGE II solar occultation instrument. The advantage of the occultation measurement principle is the self-calibration, which is essential to ensuring stable time series. SAGE II measurements in 1985-2005 have been a valuable data set in investigations of trends in the vertical distribution of ozone. This time series can now be extended by the GOMOS measurements started in 2002. GOMOS is a stellar occultation instrument and offers, therefore, a natural continuation of SAGE II measurements. In this paper we study how well GOMOS and SAGE II measurements agree with each other in the period 2002-2005 when both instruments were measuring. We detail how the different spatial and temporal sampling of these two instruments affect the conformity of measurements. We study also how the retrieval specifics like absorption cross sections and assumed aerosol modeling affect the results. Various combined time series are constructed using different estimators and latitude-time grids. We also show preliminary results from a novel time series analysis based on Markov chain Monte Carlo approach.
Fractal dimension of electroencephalographic time series and underlying brain processes.
Lutzenberger, W; Preissl, H; Pulvermüller, F
1995-10-01
Fractal dimension has been proposed as a useful measure for the characterization of electrophysiological time series. This paper investigates what the pointwise dimension of electroencephalographic (EEG) time series can reveal about underlying neuronal generators. The following theoretical assumptions concerning brain function were made (i) within the cortex, strongly coupled neural assemblies exist which oscillate at certain frequencies when they are active, (ii) several such assemblies can oscillate at a time, and (iii) activity flow between assemblies is minimal. If these assumptions are made, cortical activity can be considered as the weighted sum of a finite number of oscillations (plus noise). It is shown that the correlation dimension of finite time series generated by multiple oscillators increases monotonically with the number of oscillators. Furthermore, it is shown that a reliable estimate of the pointwise dimension of the raw EEG signal can be calculated from a time series as short as a few seconds. These results indicate that (i) The pointwise dimension of the EEG allows conclusions regarding the number of independently oscillating networks in the cortex, and (ii) a reliable estimate of the pointwise dimension of the EEG is possible on the basis of short raw signals.
A window-based time series feature extraction method.
Katircioglu-Öztürk, Deniz; Güvenir, H Altay; Ravens, Ursula; Baykal, Nazife
2017-08-09
This study proposes a robust similarity score-based time series feature extraction method that is termed as Window-based Time series Feature ExtraCtion (WTC). Specifically, WTC generates domain-interpretable results and involves significantly low computational complexity thereby rendering itself useful for densely sampled and populated time series datasets. In this study, WTC is applied to a proprietary action potential (AP) time series dataset on human cardiomyocytes and three precordial leads from a publicly available electrocardiogram (ECG) dataset. This is followed by comparing WTC in terms of predictive accuracy and computational complexity with shapelet transform and fast shapelet transform (which constitutes an accelerated variant of the shapelet transform). The results indicate that WTC achieves a slightly higher classification performance with significantly lower execution time when compared to its shapelet-based alternatives. With respect to its interpretable features, WTC has a potential to enable medical experts to explore definitive common trends in novel datasets. Copyright © 2017 Elsevier Ltd. All rights reserved.
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.
Power Computations in Time Series Analyses for Traffic Safety Interventions
McLeod, A. Ian; Vingilis, E. R.
2008-01-01
The evaluation of traffic safety interventions or other policies that can affect road safety often requires the collection of administrative time series data, such as monthly motor vehicle collision data that may be difficult and/or expensive to collect. Furthermore, since policy decisions may be based on the results found from the intervention analysis of the policy, it is important to ensure that the statistical tests have enough power, that is, that we have collected enough time series data both before and after the intervention so that a meaningful change in the series will likely be detected. In this short paper we present a simple methodology for doing this. It is expected that the methodology presented will be useful for sample size determination in a wide variety of traffic safety intervention analysis applications. Our method is illustrated with a proposed traffic safety study that was funded by NIH. PMID:18460394
Segmentation of time series with long-range fractal correlations
NASA Astrophysics Data System (ADS)
Bernaola-Galván, P.; Oliver, J. L.; Hackenberg, M.; Coronado, A. V.; Ivanov, P. Ch.; Carpena, P.
2012-06-01
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.
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
Long GPS coordinate time series: multipath and geometry effects
NASA Astrophysics Data System (ADS)
King, M.; Watson, C. S.
2009-12-01
Within analyses of Global Positioning System (GPS) observations, unmodelled sub-daily signals are known to propagate into long-period signals via a number of different mechanisms. We report on the effects of time-variable satellite geometry and the propagation of an unmodelled multipath signal. Multipath reflectors at H=0.1 m, 0.2 m and 1.5 m below the antenna are modeled and their effects on GPS coordinate time series are examined. Simulated time series at 20 global IGS sites for 2000-2008 were derived using the satellite geometry as defined by daily broadcast orbits, in addition to that defined using a perfectly repeating synthetic orbit. For the simulations generated using the broadcast orbits with a perfectly clear horizon, we observe the introduction of a time variable bias in the time series of up to several centimeters. Considerable site to site variability of the frequency and magnitude of the signal is observed, in addition to variation as a function of multipath source. When adopting realistic GPS observation geometries obtained from real data (e.g., those that include the effects of tracking outages, local obstructions, etc.), we observe concerning levels of temporal coordinate variation in the presence of the multipath signals. In these cases, we observe spurious signals across the frequency domain, in addition to what appears as offsets and secular trends. Velocity biases of more than 1mm/yr are evident at some few sites. The propagated signal in the vertical component is consistent with a noise model with a spectral index marginally above flicker noise (mean index -1.4), with some sites exhibiting power law magnitudes at comparable levels to actual height time series generated in GIPSY. The propagated signal also shows clear spectral peaks across all coordinate components at harmonics of the draconitic year for a GPS satellite (351.2 days). When a perfectly repeating synthetic GPS constellation is used, the simulations show near-negligible power law
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.
A Data Mining Framework for Time Series Estimation
Hu, Xiao; Xu, Peng; Wu, Shaozhi; Asgari, Shadnaz; Bergsneider, Marvin
2009-01-01
Time series estimation techniques are usually employed in biomedical research to derive variables less accessible from a set of related and more accessible variables. These techniques are traditionally built from systems modeling approaches including simulation, blind decovolution, and state estimation. In this work, we define target time series (TTS) and its related time series (RTS) as the output and input of a time series estimation process, respectively. We then propose a novel data mining framework for time series estimation when TTS and RTS represent different sets of observed variables from the same dynamic system. This is made possible by mining a database of instances of TTS, its simultaneously recorded RTS, and the input/output dynamic models between them. The key mining strategy is to formulate a mapping function for each TTS-RTS pair in the database that translates a feature vector extracted from RTS to the dissimilarity between true TTS and its estimate from the dynamic model associated with the same TTS-RTS pair. At run time, a feature vector is extracted from an inquiry RTS and supplied to the mapping function associated with each TTS-RTS pair to calculate a dissimilarity measure. An optimal TTS-RTS pair is then selected by analyzing these dissimilarity measures. The associated input/output model of the selected TTS-RTS pair is then used to simulate the TTS given the inquiry RTS as an input. An exemplary implementation was built to address a biomedical problem of noninvasive intracranial pressure assessment. The performance of the proposed method was superior to that of a simple training-free approach of finding the optimal TTS-RTS pair by a conventional similarity-based search on RTS features. PMID:19900575
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.
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-...
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)
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
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-...
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…
TSNet--a distributed architecture for time series analysis.
Hunter, Jim
2008-01-01
This paper describes an infrastructure (TSNet) which can be used by geographically separated research groups to develop algorithms for the abstraction of complex time series data. The framework was specifically designed for the kinds of abstractions required for the application of clinical guidelines within intensive care.
Time series analysis of monthly pulpwood use in the Northeast
James T. Bones
1980-01-01
Time series analysis was used to develop a model that depicts pulpwood use in the Northeast. The model is useful in forecasting future pulpwood requirements (short term) or monitoring pulpwood-use activity in relation to past use patterns. The model predicted a downturn in use during 1980.
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.
New Confidence Interval Estimators Using Standardized Time Series.
1984-12-01
We develop new confidence interval estimators for the underlying mean of a stationary simulation process. These estimators can be viewed as...generalizations of Schruben’s so-called standardized time series area confidence interval estimators. Various properties of the new estimators are given.
A Time-Series Analysis of Student and Teacher Interaction.
ERIC Educational Resources Information Center
Schempp, Paul G.
The stability of teaching behavior was examined by observing student/teacher interaction over one academic year. One teacher was studied using a time-series analysis. He had 14 years experience and taught physical education in grades K-6 in a single school. Data were collected over one academic year using the Cheffers Adaptation of Flanders…
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…
Daily time series evapotranspiration maps for Oklahoma and Texas panhandle
USDA-ARS?s Scientific Manuscript database
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. ...
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)
Time Series, Stochastic Processes and Completeness of Quantum Theory
NASA Astrophysics Data System (ADS)
Kupczynski, Marian
2011-03-01
Most of physical experiments are usually described as repeated measurements of some random variables. Experimental data registered by on-line computers form time series of outcomes. The frequencies of different outcomes are compared with the probabilities provided by the algorithms of quantum theory (QT). In spite of statistical predictions of QT a claim was made that it provided the most complete description of the data and of the underlying physical phenomena. This claim could be easily rejected if some fine structures, averaged out in the standard descriptive statistical analysis, were found in time series of experimental data. To search for these structures one has to use more subtle statistical tools which were developed to study time series produced by various stochastic processes. In this talk we review some of these tools. As an example we show how the standard descriptive statistical analysis of the data is unable to reveal a fine structure in a simulated sample of AR (2) stochastic process. We emphasize once again that the violation of Bell inequalities gives no information on the completeness or the non locality of QT. The appropriate way to test the completeness of quantum theory is to search for fine structures in time series of the experimental data by means of the purity tests or by studying the autocorrelation and partial autocorrelation functions.
Application of time series analysis for assessing reservoir trophic status
Paris Honglay Chen; Ka-Chu Leung
2000-01-01
This study is to develop and apply a practical procedure for the time series analysis of reservoir eutrophication conditions. A multiplicative decomposition method is used to determine the trophic variations including seasonal, circular, long-term and irregular changes. The results indicate that (1) there is a long high peak for seven months from April to October...
United States forest disturbance trends observed with landsat time series
Jeffrey G. Masek; Samuel N. Goward; Robert E. Kennedy; Warren B. Cohen; Gretchen G. Moisen; Karen Schleweiss; Chengquan. Huang
2013-01-01
Disturbance events strongly affect the composition, structure, and function of forest ecosystems; however, existing US land management inventories were not designed to monitor disturbance. To begin addressing this gap, the North American Forest Dynamics (NAFD) project has examined a geographic sample of 50 Landsat satellite image time series to assess trends in forest...
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.…
Catchment classification and similarity using correlation in streamflow time series
NASA Astrophysics Data System (ADS)
Fleming, B.; Archfield, S. A.
2012-12-01
Catchment classification is an important component of hydrologic analyses, particularly for linking changes in ecological integrity to streamflow alteration, transferring time series or model parameters from gauged to ungauged locations, and as a way to understand the similarity in the response of catchments to change. Metrics of similarity used in catchment classification have ranged from aggregate catchment properties such as geologic or climate characteristics to variables derived from the daily streamflow hydrograph; however, no one set of classification variables can fully describe similarity between catchments as the variables used for such assessments often depend on the question being asked. We propose an alternative method based on similarity for hydrologic classification: correlation between the daily streamflow time series. If one assumes that the streamflow signal is the integrated response of a catchment to both climate and geology, then the strength of correlation in streamflow between two catchments is a measure of the strength of similarity in hydrologic response between those two catchments. Using the nonparametric Spearman rho correlation coefficient between streamflow time series at 54 unregulated and unaltered streamgauges in the mid-Atlantic United States, we show that correlation is a parsimonious classification metric that results in physically interpretable classes. Using the correlation between the deseasonalized streamflow time series and reclassifying the streamgauges, we also find that seasonality plays an important role in understanding catchment flow dynamics, especially those that can be linked to ecological response and similarity although not to a large extent in this study area.
Identification of Tectonic Signals in GPS Positional Time Series
NASA Astrophysics Data System (ADS)
Comte, D.; Ortega-Culaciati, F.; Krumm, N.
2016-12-01
During the last decades, the development of space geodesy resulted in an increased amount and quality of crustal deformation observations. In particular, instruments of the Global Positioning System (GPS) provide positional time series constituted by crustal displacement signals carrying information about different geophysical processes. For instance, signals associated to tectonic processes that occur during the different stages of the seismic cycle. The aim of this work is to efficiently separate out and characterize the different signals present in GPS time series with the ultimate goal of obtaining precise crustal surface observations that can be used to better understand the geophysical processes occurring during the seismic cycle. We use a Basis Pursue scheme in which we identify and separate the different signals in the positional time series from a vast library of ad-hoc basis functions. We use an optimization algorithm (SPGL1, Van der Berg & Friedlander, 2008) that allows for a sparse representation of the positional time series by selecting the minimum amount of basis functions that are needed to represent such signal. We apply the methodology to GPS observations from the Chilean National Seismological Center to separate and analyze the tectonic and non tectonic signals present in such observations.
Chaotic time series prediction using artificial neural networks
Bartlett, E.B.
1991-12-31
This paper describes the use of artificial neural networks to model the complex oscillations defined by a chaotic Verhuist animal population dynamic. A predictive artificial neural network model is developed and tested, and results of computer simulations are given. These results show that the artificial neural network model predicts the chaotic time series with various initial conditions, growth parameters, or noise.
Chaotic time series prediction using artificial neural networks
Bartlett, E.B.
1991-01-01
This paper describes the use of artificial neural networks to model the complex oscillations defined by a chaotic Verhuist animal population dynamic. A predictive artificial neural network model is developed and tested, and results of computer simulations are given. These results show that the artificial neural network model predicts the chaotic time series with various initial conditions, growth parameters, or noise.
Application of modern time series analysis to high stability oscillators
NASA Technical Reports Server (NTRS)
Farrell, B. F.; Mattison, W. M.; Vessot, R. F. C.
1980-01-01
Techniques of modern time series analysis useful for investigating the characteristics of high-stability oscillators and identifying systematic perturbations are discussed with reference to an experiment in which the frequencies of superconducting cavity-stabilized oscillators and hydrogen masers were compared. The techniques examined include transformation to stationarity, autocorrelation and cross-correlation, superresolution, and transfer function determination.
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.
Model Identification in Time-Series Analysis: Some Empirical Results.
ERIC Educational Resources Information Center
Padia, William L.
Model identification of time-series data is essential to valid statistical tests of intervention effects. Model identification is, at best, inexact in the social and behavioral sciences where one is often confronted with small numbers of observations. These problems are discussed, and the results of independent identifications of 130 social and…
Dynamic Factor Analysis of Nonstationary Multivariate Time Series.
ERIC Educational Resources Information Center
Molenaar, Peter C. M.; And Others
1992-01-01
The dynamic factor model proposed by P. C. Molenaar (1985) is exhibited, and a dynamic nonstationary factor model (DNFM) is constructed with latent factor series that have time-varying mean functions. The use of a DNFM is illustrated using data from a television viewing habits study. (SLD)
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
Long GPS coordinate time series: multipath and geometry effects
NASA Astrophysics Data System (ADS)
King, M. A.; Watson, C. S.
2009-04-01
Within analyses of Global Positioning System (GPS) observations, unmodelled sub-daily signals are known to propagate into long-period signals via a number of different mechanisms. In this paper, we investigate the effects of time-variable satellite geometry and the propagation of an unmodelled multipath signal that is analogous to a change in the elevation dependant phase centre of the receiving antenna. Multipath reflectors at H=0.1 m, 0.2 m and 1.5 m below the antenna are modeled and their effects on GPS coordinate time series are examined. Simulated time series at 20 global IGS sites for 2000-2008 were derived using the satellite geometry as defined by daily broadcast orbits, in addition to that defined using a perfectly repeating synthetic orbit. For the simulations generated using the broadcast orbits with a perfectly clear horizon, we observe the introduction of a time variable bias in the time series of up to several centimeters. Considerable site to site variability of the frequency and magnitude of the signal is observed, in addition to variation as a function of multipath source. When adopting realistic GPS observation geometries obtained from real data (e.g., those that include the effects of tracking outages, local obstructions, etc.), we observe concerning levels of temporal coordinate variation in the presence of the multipath signals. In these cases, we observe spurious signals across the frequency domain, in addition to what appears as offsets and secular trends. Velocity biases of more than 1mm/yr are evident at some few sites. The propagated signal in the vertical component is consistent with a noise model with a spectral index marginally above flicker noise (mean index -1.4), with some sites exhibiting power law magnitudes at comparable levels to actual height time series generated in GIPSY. The propagated signal also shows clear spectral peaks across all coordinate components at harmonics of the draconitic year for a GPS satellite (351.4 days
[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.
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.
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.
Distinguishing quasiperiodic dynamics from chaos in short-time series.
Zou, Y; Pazó, D; Romano, M C; Thiel, M; Kurths, J
2007-07-01
We propose a procedure to distinguish quasiperiodic from chaotic orbits in short-time series, which is based on the recurrence properties in phase space. The histogram of the return times in a recurrence plot is introduced to disclose the recurrence property consisting of only three peaks imposed by Slater's theorem. Noise effects on the statistics are studied. Our approach is demonstrated to be efficient in recognizing regular and chaotic trajectories of a Hamiltonian system with mixed phase space.
Improving predictability of time series using maximum entropy methods
NASA Astrophysics Data System (ADS)
Chliamovitch, G.; Dupuis, A.; Golub, A.; Chopard, B.
2015-04-01
We discuss how maximum entropy methods may be applied to the reconstruction of Markov processes underlying empirical time series and compare this approach to usual frequency sampling. It is shown that, in low dimension, there exists a subset of the space of stochastic matrices for which the MaxEnt method is more efficient than sampling, in the sense that shorter historical samples have to be considered to reach the same accuracy. Considering short samples is of particular interest when modelling smoothly non-stationary processes, which provides, under some conditions, a powerful forecasting tool. The method is illustrated for a discretized empirical series of exchange rates.
Time-dependent spectral analysis of epidemiological time-series with wavelets.
Cazelles, Bernard; Chavez, Mario; Magny, Guillaume Constantin de; Guégan, Jean-Francois; Hales, Simon
2007-08-22
In the current context of global infectious disease risks, a better understanding of the dynamics of major epidemics is urgently needed. Time-series analysis has appeared as an interesting approach to explore the dynamics of numerous diseases. Classical time-series methods can only be used for stationary time-series (in which the statistical properties do not vary with time). However, epidemiological time-series are typically noisy, complex and strongly non-stationary. Given this specific nature, wavelet analysis appears particularly attractive because it is well suited to the analysis of non-stationary signals. Here, we review the basic properties of the wavelet approach as an appropriate and elegant method for time-series analysis in epidemiological studies. The wavelet decomposition offers several advantages that are discussed in this paper based on epidemiological examples. In particular, the wavelet approach permits analysis of transient relationships between two signals and is especially suitable for gradual change in force by exogenous variables.
Classifying of financial time series based on multiscale entropy and multiscale time irreversibility
NASA Astrophysics Data System (ADS)
Xia, Jianan; Shang, Pengjian; Wang, Jing; Shi, Wenbin
2014-04-01
Time irreversibility is a fundamental property of many time series. We apply the multiscale entropy (MSE) and multiscale time irreversibility (MSTI) to analyze the financial time series, and succeed to classify the financial markets. Interestingly, both methods have nearly the same classification results, which mean that they are capable of distinguishing different series in a reliable manner. By comparing the results of shuffled data with the original results, we confirm that the asymmetry property is an inherent property of financial time series and it can extend over a wide range of scales. In addition, the effect of noise on Americas markets and Europe markets are relatively more significant than the effect on Asia markets, and loss of time irreversibility has been detected in high noise added series.
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
Scale-space analysis of time series in circulatory research.
Mortensen, Kim Erlend; Godtliebsen, Fred; Revhaug, Arthur
2006-12-01
Statistical analysis of time series is still inadequate within circulation research. With the advent of increasing computational power and real-time recordings from hemodynamic studies, one is increasingly dealing with vast amounts of data in time series. This paper aims to illustrate how statistical analysis using the significant nonstationarities (SiNoS) method may complement traditional repeated-measures ANOVA and linear mixed models. We applied these methods on a dataset of local hepatic and systemic circulatory changes induced by aortoportal shunting and graded liver resection. We found SiNoS analysis more comprehensive when compared with traditional statistical analysis in the following four ways: 1) the method allows better signal-to-noise detection; 2) including all data points from real time recordings in a statistical analysis permits better detection of significant features in the data; 3) analysis with multiple scales of resolution facilitates a more differentiated observation of the material; and 4) the method affords excellent visual presentation by combining group differences, time trends, and multiscale statistical analysis allowing the observer to quickly view and evaluate the material. It is our opinion that SiNoS analysis of time series is a very powerful statistical tool that may be used to complement conventional statistical methods.
An entropic approach to the analysis of time series
NASA Astrophysics Data System (ADS)
Scafetta, Nicola
Statistical analysis of time series. With compelling arguments we show that the Diffusion Entropy Analysis (DEA) is the only method of the literature of the Science of Complexity that correctly determines the scaling hidden within a time series reflecting a Complex Process. The time series is thought of as a source of fluctuations, and the DEA is based on the Shannon entropy of the diffusion process generated by these fluctuations. All traditional methods of scaling analysis, instead, are based on the variance of this diffusion process. The variance methods detect the real scaling only if the Gaussian assumption holds true. We call H the scaling exponent detected by the variance methods and delta the real scaling exponent. If the time series is characterized by Fractional Brownian Motion, we have H = delta and the scaling can be safely determined, in this case, by using the variance methods. If, on the contrary, the time series is characterized, for example, by Levy statistics, H ≠ delta and the variance methods cannot be used to detect the true scaling. Levy walk yields the relation delta = 1/(3 - 2H). In the case of Levy flights, the variance diverges and the exponent H cannot be determined, whereas the scaling delta exists and can be established by using the DEA. Therefore, only the joint use of two different scaling analysis methods, the variance scaling analysis and the DEA, can assess the real nature, Gauss or Levy or something else, of a time series. Moreover, the DEA determines the information content, under the form of Shannon entropy, or of any other convenient entropic indicator, at each time step of the process that, given a sufficiently large number of data, is expected to become diffusion with scaling. This makes it possible to study the regime of transition from dynamics to thermodynamics, non-stationary regimes, and the saturation regime as well. First of all, the efficiency of the DEA is proved with theoretical arguments and with numerical work
Nonlinear transformation on the transfer entropy of financial time series
NASA Astrophysics Data System (ADS)
Wu, Zhenyu; Shang, Pengjian
2017-09-01
Transfer entropy (TE) now is widely used in the data mining and economic field. However, TE itself demands that time series intend to be stationary and meet Markov condition. Naturally, we are interested in investigating the effect of the nonlinear transformation of the two series on the TE. Therefore, the paper is designed to study the TE of five nonlinear ;volatile; transformations based on the data which are generated by the linear modeling and the logistic maps modeling, as well as the dataset that come from financial markets. With only one of the TE of nonlinear transformations fluctuating around the TE of original series, the TE of others all have increased with different degrees.
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.
The Mount Wilson Ca ii K Plage Index Time Series
NASA Astrophysics Data System (ADS)
Bertello, L.; Ulrich, R. K.; Boyden, J. E.
2010-06-01
It is well established that both total and spectral solar irradiance are modulated by variable magnetic activity on the solar surface. However, there is still disagreement about the contribution of individual solar features for changes in the solar output, in particular over decadal time scales. Ionized Ca ii K line spectroheliograms are one of the major resources for these long-term trend studies, mainly because such measurements have been available now for more than 100 years. In this paper we introduce a new Ca ii K plage and active network index time series derived from the digitization of almost 40 000 photographic solar images that were obtained at the 60-foot solar tower, between 1915 and 1985, as a part of the monitoring program of the Mount Wilson Observatory. We describe here the procedure we applied to calibrate the images and the properties of our new defined index, which is strongly correlated to the average fractional area of the visible solar disk occupied by plages and active network. We show that the long-term variation of this index is in an excellent agreement with the 11-year solar-cycle trend determined from the annual international sunspot numbers series. Our time series agrees also very well with similar indicators derived from a different reduction of the same data base and other Ca ii K spectroheliograms long-term synoptic programs, such as those at Kodaikanal Observatory (India), and at the National Solar Observatory at Sacramento Peak (USA). Finally, we show that using appropriate proxies it is possible to extend this time series up to date, making this data set one of the longest Ca ii K index series currently available.
Autoregression of Quasi-Stationary Time Series (Invited)
NASA Astrophysics Data System (ADS)
Meier, T. M.; Küperkoch, L.
2009-12-01
Autoregression is a model based tool for spectral analysis and prediction of time series. It has the potential to increase the resolution of spectral estimates. However, the validity of the assumed model has to be tested. Here we review shortly methods for the determination of the parameters of autoregression and summarize properties of autoregressive prediction and autoregressive spectral analysis. Time series with a limited number of dominant frequencies varying slowly in time (quasi-stationary time series) may well be described by a time-dependent autoregressive model of low order. An algorithm for the estimation of the autoregression parameters in a moving window is presented. Time-varying dominant frequencies are estimated. The comparison to results obtained by Fourier transform based methods and the visualization of the time dependent normalized prediction error are essential for quality assessment of the results. The algorithm is applied to synthetic examples as well as to mircoseism and tremor. The sensitivity of the results to the choice of model and filter parameters is discussed. Autoregressive forward prediction offers the opportunity to detect body wave phases in seismograms and to determine arrival times automatically. Examples are shown for P- and S-phases at local and regional distances. In order to determine S-wave arrival times the autoregressive model is extended to multi-component recordings. For the detection of significant temporal changes in waveforms, the choice of the model appears to be less crucial compared to spectral analysis. Temporal changes in frequency, amplitude, phase, and polarisation are detectable by autoregressive prediction. Quality estimates of automatically determined onset times may be obtained from the slope of the absolute prediction error as a function of time and the signal-to-noise ratio. Results are compared to manual readings.
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.
A noise model for InSAR time series
NASA Astrophysics Data System (ADS)
Agram, P. S.; Simons, M.
2015-04-01
Interferometric synthetic aperture radar (InSAR) time series methods estimate the spatiotemporal evolution of surface deformation by incorporating information from multiple SAR interferograms. While various models have been developed to describe the interferometric phase and correlation statistics in individual interferograms, efforts to model the generalized covariance matrix that is directly applicable to joint analysis of networks of interferograms have been limited in scope. In this work, we build on existing decorrelation and atmospheric phase screen models and develop a covariance model for interferometric phase noise over space and time. We present arguments to show that the exploitation of the full 3-D covariance structure within conventional time series inversion techniques is computationally challenging. However, the presented covariance model can aid in designing new inversion techniques that can at least mitigate the impact of spatial correlated nature of InSAR observations.
A multivariate heuristic model for fuzzy time-series forecasting.
Huarng, Kun-Huang; Yu, Tiffany Hui-Kuang; Hsu, Yu Wei
2007-08-01
Fuzzy time-series models have been widely applied due to their ability to handle nonlinear data directly and because no rigid assumptions for the data are needed. In addition, many such models have been shown to provide better forecasting results than their conventional counterparts. However, since most of these models require complicated matrix computations, this paper proposes the adoption of a multivariate heuristic function that can be integrated with univariate fuzzy time-series models into multivariate models. Such a multivariate heuristic function can easily be extended and integrated with various univariate models. Furthermore, the integrated model can handle multiple variables to improve forecasting results and, at the same time, avoid complicated computations due to the inclusion of multiple variables.
Learning dynamics from nonstationary time series: Analysis of electroencephalograms
NASA Astrophysics Data System (ADS)
Gribkov, Dmitrii; Gribkova, Valentina
2000-06-01
We propose an empirical modeling technique for a nonstationary time series analysis. Proposed methods include a high-dimensional (N>3) dynamical model construction in the form of delay differential equations, a nonparametric method of respective time delay calculation, the detection of quasistationary regions of the process by reccurence analysis in the space of model coefficients, and final fitting of the model to quasistationary segments of observed time series. We also demonstrate the effectiveness of our approach for nonstationary signal classification in the space of model coefficients. Applying the empirical modeling technique to electroencephalogram (EEG) records analysis, we find evidence of high-dimensional nonlinear dynamics in quasistationary EEG segments. Reccurence analysis of model parameters reveals long-term correlations in nonstationary EEG records. Using the dynamical model as a nonlinear filter, we find that different emotional states of subjects can be clearly distinguished in the space of model coefficients.
Examination of time series through randomly broken windows
NASA Technical Reports Server (NTRS)
Sturrock, P. A.; Shoub, E. C.
1981-01-01
In order to determine the Fourier transform of a quasi-periodic time series (linear problem), or the power spectrum of a stationary random time series (quadratic problem), data should be recorded without interruption over a long time interval. The effect of regular interruption such as the day/night cycle is well known. The effect of irregular interruption of data collection (the "breaking" of the window function) with the simplifying assumption that there is a uniform probability p that each interval of length tau, of the total interval of length T = N sub tau, yields no data, is investigated. For the linear case it is found that the noise-to-signal ratio will have a (one-sigma) value less than epsilon if N exceeds p(-1)(1-p)epsilon(-2). For the quadratic case, the same requirement is met by the less restrictive requirement that N exceed p(-1)(1-p)epsilon(-1).
Least Squares Time-Series Synchronization in Image Acquisition Systems.
Piazzo, Lorenzo; Raguso, Maria Carmela; Calzoletti, Luca; Seu, Roberto; Altieri, Bruno
2016-07-18
We consider an acquisition system constituted by an array of sensors scanning an image. Each sensor produces a sequence of readouts, called a time-series. In this framework, we discuss the image estimation problem when the time-series are affected by noise and by a time shift. In particular, we introduce an appropriate data model and consider the Least Squares (LS) estimate, showing that it has no closed form. However, the LS problem has a structure that can be exploited to simplify the solution. In particular, based on two known techniques, namely Separable Nonlinear Least Squares (SNLS) and Alternating Least Squares (ALS), we propose and analyze several practical estimation methods. As an additional contribution, we discuss the application of these methods to the data of the Photodetector Array Camera and Spectrometer (PACS), which is an infrared photometer onboard the Herschel satellite. In this context, we investigate the accuracy and the computational complexity of the methods, using both true and simulated data.
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.
Reconstruction of ensembles of coupled time-delay systems from time series.
Sysoev, I V; Prokhorov, M D; Ponomarenko, V I; Bezruchko, B P
2014-06-01
We propose a method to recover from time series the parameters of coupled time-delay systems and the architecture of couplings between them. The method is based on a reconstruction of model delay-differential equations and estimation of statistical significance of couplings. It can be applied to networks composed of nonidentical nodes with an arbitrary number of unidirectional and bidirectional couplings. We test our method on chaotic and periodic time series produced by model equations of ensembles of diffusively coupled time-delay systems in the presence of noise, and apply it to experimental time series obtained from electronic oscillators with delayed feedback coupled by resistors.
Factors That Have An Influence On Time Series
NASA Astrophysics Data System (ADS)
Notti, D.; Meisina, C.; Zucca, F.; Crosetto, M.; Montserrat, O.
2012-01-01
In the last years the development in the processing of SAR persistent scatterers interferometry (PSI) data has allowed an improvement in time series precision, also with the data processed on regional scale. It is possible now to study the behaviour in the time of different type of natural process. The more recent data are elaborated also with non-linear models and this allows, even if with many restrictions and problems, to study also the temporal variation in the evolution of a process. In this work we have analyzed the time series (TS) of ERS (1992-2001) and RADARSAT (2003-2010) data elaborated with SqueeSARTM processing over three studied areas in NW Italy (Western Piemonte, Province of Pavia and Province of Imperia). We compared the time series with other monitoring data in order to validate them and to find the positive and negative aspects in the detection of natural processes. At the same time the TS were used to understand the kinematics of some geological processes.
Active Mining from Process Time Series by Learning Classifier System
NASA Astrophysics Data System (ADS)
Kurahashi, Setsuya; Terano, Takao
Continuation processes in chemical and/or biotechnical plants always generate a large amount of time series data. However, since conventional process models are described as a set of control models, it is difficult to explain the complicated and active plant behaviors. Based on the background, this research proposes a novel method to develop a process response model from continuous time-series data. The method consists of the following phases: 1) Collect continuous process data at each tag point in a target plant; 2) Normalize the data in the interval between zero and one; 3) Get the delay time, which maximizes the correlation between given two time series data; 4) Select tags with the higher correlation; 5) Develop a process response model to describe the relations among the process data using the delay time and the correlation values; 6) Develop a process prediction model via several tag points data using a neural network; 1) Discover control rules from the process prediction model using Learning Classifier system. The main contribution of the research is to establish a method to mine a set of meaningful control rules from Learning Classifier System using the Minimal Description Length criteria. The proposed method has been applied to an actual process of a biochemical plant and has shown the validity and the effectiveness.
Nonlinear time series analysis of solar and stellar data
NASA Astrophysics Data System (ADS)
Jevtic, Nada
2003-06-01
Nonlinear time series analysis was developed to study chaotic systems. Its utility was investigated for the study of solar and stellar data time series. Sunspot data are the longest astronomical time series, and it reflects the long-term variation of the solar magnetic field. Due to periods of low solar activity, such as the Maunder minimum, and the solar cycle's quasiperiodicity, it has been postulated that the solar dynamo is a chaotic system. We show that, due to the definition of sunspot number, using nonlinear time series methods, it is not possible to test this postulate. To complement the sunspot data analysis, theoretically generated data for the α-Ω solar dynamo with meridional circulation were analyzed. Effects of stochastic fluctuations on the energy of an α-Ω dynamo with meridional circulation were investigated. This proved extremely useful in generating a clearer understanding of the effect of dynamical noise on the unperturbed system. This was useful in the study of the light intensity curve of white dwarf PG 1351+489. Dynamical resetting was identified for PG 1351+489, using phase space methods, and then, using nonlinear noise reduction methods, the white noise tail of the power spectrum was lowered by a factor of 40. This allowed the identification of 10 new lines in the power spectrum. Finally, using Poincare section return times, a periodicity in the light curve of cataclysmic variable SS Cygni was identified. We initially expected that time delay methods would be useful as a qualitative comparison tool. However, they were capable, under the proper set of constraints on the data sets, of providing quantitative information about the signal source.
Interpolation based consensus clustering for gene expression time series.
Chiu, Tai-Yu; Hsu, Ting-Chieh; Yen, Chia-Cheng; Wang, Jia-Shung
2015-04-16
Unsupervised analyses such as clustering are the essential tools required to interpret time-series expression data from microarrays. Several clustering algorithms have been developed to analyze gene expression data. Early methods such as k-means, hierarchical clustering, and self-organizing maps are popular for their simplicity. However, because of noise and uncertainty of measurement, these common algorithms have low accuracy. Moreover, because gene expression is a temporal process, the relationship between successive time points should be considered in the analyses. In addition, biological processes are generally continuous; therefore, the datasets collected from time series experiments are often found to have an insufficient number of data points and, as a result, compensation for missing data can also be an issue. An affinity propagation-based clustering algorithm for time-series gene expression data is proposed. The algorithm explores the relationship between genes using a sliding-window mechanism to extract a large number of features. In addition, the time-course datasets are resampled with spline interpolation to predict the unobserved values. Finally, a consensus process is applied to enhance the robustness of the method. Some real gene expression datasets were analyzed to demonstrate the accuracy and efficiency of the algorithm. The proposed algorithm has benefitted from the use of cubic B-splines interpolation, sliding-window, affinity propagation, gene relativity graph, and a consensus process, and, as a result, provides both appropriate and effective clustering of time-series gene expression data. The proposed method was tested with gene expression data from the Yeast galactose dataset, the Yeast cell-cycle dataset (Y5), and the Yeast sporulation dataset, and the results illustrated the relationships between the expressed genes, which may give some insights into the biological processes involved.
Time warp edit distance with stiffness adjustment for time series matching.
Marteau, Pierre-François
2009-02-01
In a way similar to the string-to-string correction problem, we address discrete time series similarity in light of a time-series-to-time-series-correction problem for which the similarity between two time series is measured as the minimum cost sequence of edit operations needed to transform one time series into another. To define the edit operations, we use the paradigm of a graphical editing process and end up with a dynamic programming algorithm that we call Time Warp Edit Distance (TWED). TWED is slightly different in form from Dynamic Time Warping (DTW), Longest Common Subsequence (LCSS), or Edit Distance with Real Penalty (ERP) algorithms. In particular, it highlights a parameter that controls a kind of stiffness of the elastic measure along the time axis. We show that the similarity provided by TWED is a potentially useful metric in time series retrieval applications since it could benefit from the triangular inequality property to speed up the retrieval process while tuning the parameters of the elastic measure. In that context, a lower bound is derived to link the matching of time series into downsampled representation spaces to the matching into the original space. The empiric quality of the TWED distance is evaluated on a simple classification task. Compared to Edit Distance, DTW, LCSS, and ERP, TWED has proved to be quite effective on the considered experimental task.
A Time-Frequency Functional Model for Locally Stationary Time Series Data
Qin, Li; Guo, Wensheng; Litt, Brian
2009-01-01
Unlike traditional time series analysis that focuses on one long time series, in many biomedical experiments, it is common to collect multiple time series and focus on how the design covariates impact the patterns of stochastic variation over time. In this article, we propose a time-frequency functional model for a family of time series indexed by a set of covariates. This model can be used to compare groups of time series in terms of the patterns of stochastic variation and to estimate the covariate effects. We focus our development on locally stationary time series and propose the covariate-indexed locally stationary setting, which include stationary processes as special cases. We use smoothing spline ANOVA models for the time-frequency coefficients. A two-stage procedure is introduced for estimation. To reduce the computational demand, we develop an equivalent state space model to the proposed model with an efficient algorithm. We also propose a new simulation method to generate replicated time series from their design spectra. An epileptic intracranial electroencephalogram (IEEG) dataset is analyzed for illustration. PMID:20228961
Exploring large scale time-series data using nested timelines
NASA Astrophysics Data System (ADS)
Xie, Zaixian; Ward, Matthew O.; Rundensteiner, Elke A.
2013-01-01
When data analysts study time-series data, an important task is to discover how data patterns change over time. If the dataset is very large, this task becomes challenging. Researchers have developed many visualization techniques to help address this problem. However, little work has been done regarding the changes of multivariate patterns, such as linear trends and clusters, on time-series data. In this paper, we describe a set of history views to fill this gap. This technique works under two modes: merge and non-merge. For the merge mode, merge algorithms were applied to selected time windows to generate a change-based hierarchy. Contiguous time windows having similar patterns are merged first. Users can choose different levels of merging with the tradeoff between more details in the data and less visual clutter in the visualizations. In the non-merge mode, the framework can use natural hierarchical time units or one defined by domain experts to represent timelines. This can help users navigate across long time periods. Gridbased views were designed to provide a compact overview for the history data. In addition, MDS pattern starfields and distance maps were developed to enable users to quickly investigate the degree of pattern similarity among different time periods. The usability evaluation demonstrated that most participants could understand the concepts of the history views correctly and finished assigned tasks with a high accuracy and relatively fast response time.
Perception of acoustically presented time series with varied intervals.
Wackermann, Jiří; Pacer, Jakob; Wittmann, Marc
2014-03-01
Data from three experiments on serial perception of temporal intervals in the supra-second domain are reported. Sequences of short acoustic signals ("pips") separated by periods of silence were presented to the observers. Two types of time series, geometric or alternating, were used, where the modulus 1+δ of the inter-pip series and the base duration Tb (range from 1.1 to 6s) were varied as independent parameters. The observers had to judge whether the series were accelerating, decelerating, or uniform (3 paradigm), or to distinguish regular from irregular sequences (2 paradigm). "Intervals of subjective uniformity" (isus) were obtained by fitting Gaussian psychometric functions to individual subjects' responses. Progression towards longer base durations (Tb=4.4 or 6s) shifts the isus towards negative δs, i.e., accelerating series. This finding is compatible with the phenomenon of "subjective shortening" of past temporal intervals, which is naturally accounted for by the lossy integration model of internal time representation. The opposite effect observed for short durations (Tb=1.1 or 1.5s) remains unexplained by the lossy integration model, and presents a challenge for further research. © 2013 Elsevier B.V. All rights reserved.
Andrade, Xavier; Alberdi-Rodriguez, Joseba; Strubbe, David A; Oliveira, Micael J T; Nogueira, Fernando; Castro, Alberto; Muguerza, Javier; Arruabarrena, Agustin; Louie, Steven G; Aspuru-Guzik, Alán; Rubio, Angel; Marques, Miguel A L
2012-06-13
Octopus is a general-purpose density-functional theory (DFT) code, with a particular emphasis on the time-dependent version of DFT (TDDFT). In this paper we present the ongoing efforts to achieve the parallelization of octopus. We focus on the real-time variant of TDDFT, where the time-dependent Kohn-Sham equations are directly propagated in time. This approach has great potential for execution in massively parallel systems such as modern supercomputers with thousands of processors and graphics processing units (GPUs). For harvesting the potential of conventional supercomputers, the main strategy is a multi-level parallelization scheme that combines the inherent scalability of real-time TDDFT with a real-space grid domain-partitioning approach. A scalable Poisson solver is critical for the efficiency of this scheme. For GPUs, we show how using blocks of Kohn-Sham states provides the required level of data parallelism and that this strategy is also applicable for code optimization on standard processors. Our results show that real-time TDDFT, as implemented in octopus, can be the method of choice for studying the excited states of large molecular systems in modern parallel architectures.
NASA Astrophysics Data System (ADS)
Andrade, Xavier; Alberdi-Rodriguez, Joseba; Strubbe, David A.; Oliveira, Micael J. T.; Nogueira, Fernando; Castro, Alberto; Muguerza, Javier; Arruabarrena, Agustin; Louie, Steven G.; Aspuru-Guzik, Alán; Rubio, Angel; Marques, Miguel A. L.
2012-06-01
Octopus is a general-purpose density-functional theory (DFT) code, with a particular emphasis on the time-dependent version of DFT (TDDFT). In this paper we present the ongoing efforts to achieve the parallelization of octopus. We focus on the real-time variant of TDDFT, where the time-dependent Kohn-Sham equations are directly propagated in time. This approach has great potential for execution in massively parallel systems such as modern supercomputers with thousands of processors and graphics processing units (GPUs). For harvesting the potential of conventional supercomputers, the main strategy is a multi-level parallelization scheme that combines the inherent scalability of real-time TDDFT with a real-space grid domain-partitioning approach. A scalable Poisson solver is critical for the efficiency of this scheme. For GPUs, we show how using blocks of Kohn-Sham states provides the required level of data parallelism and that this strategy is also applicable for code optimization on standard processors. Our results show that real-time TDDFT, as implemented in octopus, can be the method of choice for studying the excited states of large molecular systems in modern parallel architectures.
Modeling the evolution of galaxies and massive black holes across cosmic time
NASA Astrophysics Data System (ADS)
Angles-Alcazar, Daniel
I use cosmological hydrodynamic simulations to investigate different aspects of the evolution of galaxies and massive black holes across cosmic time. First, I present high resolution "zoom-in" simulations including various prescriptions for galactic outflows designed to explore the impact of star-formation driven winds on the morphological, dynamical, and structural properties of individual galaxies from early times down to z = 2. Simulations without winds produce massive, compact galaxies with low gas fractions, super-solar metallicities, high bulge fractions, and much of the star formation concentrated within the inner kpc. I show that strong winds are required to suppress early star formation, maintain high gas fractions, redistribute star-forming gas and metals over larger scales, and increase the velocity dispersion of simulated galaxies, more in agreement with the large, extended, turbulent disks typical of high-redshift star-forming galaxies. Next, I combine cosmological simulations with analytic models of black hole growth to investigate the physical mechanisms driving the observed connection between massive black holes and their host galaxies. I describe a plausible model consistent with available observations in which black hole growth is limited by galaxy-scale torques. In this torque-limited growth scenario, black holes and host galaxies evolve on average toward the observed scaling relations, regardless of the initial conditions, and with no need for mass averaging through mergers or additional self-regulation processes. Outflows from the accretion disk play a key role by providing significant mass loss, but there is no need for strong interaction with the inflowing gas in order to regulate black holes in a non-linear feedback loop. I discuss some of the main implications of this scenario in the context of current observations, including the distribution and evolution of Eddington ratios, the connection between major galaxy mergers, star formation, and
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.
Dynamical Analysis and Visualization of Tornadoes Time Series
2015-01-01
In this paper we analyze the behavior of tornado time-series in the U.S. from the perspective of dynamical systems. A tornado is a violently rotating column of air extending from a cumulonimbus cloud down to the ground. Such phenomena reveal features that are well described by power law functions and unveil characteristics found in systems with long range memory effects. Tornado time series are viewed as the output of a complex system and are interpreted as a manifestation of its dynamics. Tornadoes are modeled as sequences of Dirac impulses with amplitude proportional to the events size. First, a collection of time series involving 64 years is analyzed in the frequency domain by means of the Fourier transform. The amplitude spectra are approximated by power law functions and their parameters are read as an underlying signature of the system dynamics. Second, it is adopted the concept of circular time and the collective behavior of tornadoes analyzed. Clustering techniques are then adopted to identify and visualize the emerging patterns. PMID:25790281
Inverse problem for multivariate time series using dynamical latent variables
NASA Astrophysics Data System (ADS)
Zamparo, M.; Stramaglia, S.; Banavar, J. R.; Maritan, A.
2012-06-01
Factor analysis is a well known statistical method to describe the variability among observed variables in terms of a smaller number of unobserved latent variables called factors. While dealing with multivariate time series, the temporal correlation structure of data may be modeled by including correlations in latent factors, but a crucial choice is the covariance function to be implemented. We show that analyzing multivariate time series in terms of latent Gaussian processes, which are mutually independent but with each of them being characterized by exponentially decaying temporal correlations, leads to an efficient implementation of the expectation-maximization algorithm for the maximum likelihood estimation of parameters, due to the properties of block-tridiagonal matrices. The proposed approach solves an ambiguity known as the identifiability problem, which renders the solution of factor analysis determined only up to an orthogonal transformation. Samples with just two temporal points are sufficient for the parameter estimation: hence the proposed approach may be applied even in the absence of prior information about the correlation structure of latent variables by fitting the model to pairs of points with varying time delay. Our modeling allows one to make predictions of the future values of time series and we illustrate our method by applying it to an analysis of published gene expression data from cell culture HeLa.
Dynamical analysis and visualization of tornadoes time series.
Lopes, António M; Tenreiro Machado, J A
2015-01-01
In this paper we analyze the behavior of tornado time-series in the U.S. from the perspective of dynamical systems. A tornado is a violently rotating column of air extending from a cumulonimbus cloud down to the ground. Such phenomena reveal features that are well described by power law functions and unveil characteristics found in systems with long range memory effects. Tornado time series are viewed as the output of a complex system and are interpreted as a manifestation of its dynamics. Tornadoes are modeled as sequences of Dirac impulses with amplitude proportional to the events size. First, a collection of time series involving 64 years is analyzed in the frequency domain by means of the Fourier transform. The amplitude spectra are approximated by power law functions and their parameters are read as an underlying signature of the system dynamics. Second, it is adopted the concept of circular time and the collective behavior of tornadoes analyzed. Clustering techniques are then adopted to identify and visualize the emerging patterns.
A multivariate time-series approach to marital interaction
Kupfer, Jörg; Brosig, Burkhard; Brähler, Elmar
2005-01-01
Time-series analysis (TSA) is frequently used in order to clarify complex structures of mutually interacting panel data. The method helps in understanding how the course of a dependent variable is predicted by independent time-series with no time lag, as well as by previous observations of that dependent variable (autocorrelation) and of independent variables (cross-correlation). The study analyzes the marital interaction of a married couple under clinical conditions over a period of 144 days by means of TSA. The data were collected within a course of couple therapy. The male partner was affected by a severe condition of atopic dermatitis and the woman suffered from bulimia nervosa. Each of the partners completed a mood questionnaire and a body symptom checklist. After the determination of auto- and cross-correlations between and within the parallel data sets, multivariate time-series models were specified. Mutual and individual patterns of emotional reactions explained 14% (skin) and 33% (bulimia) of the total variance in both dependent variables (adj. R², p<0.0001 for the multivariate models). The question was discussed whether multivariate TSA-models represent a suitable approach to the empirical exploration of clinical marital interaction. PMID:19742066
A multivariate time-series approach to marital interaction.
Kupfer, Jörg; Brosig, Burkhard; Brähler, Elmar
2005-08-02
Time-series analysis (TSA) is frequently used in order to clarify complex structures of mutually interacting panel data. The method helps in understanding how the course of a dependent variable is predicted by independent time-series with no time lag, as well as by previous observations of that dependent variable (autocorrelation) and of independent variables (cross-correlation).The study analyzes the marital interaction of a married couple under clinical conditions over a period of 144 days by means of TSA. The data were collected within a course of couple therapy. The male partner was affected by a severe condition of atopic dermatitis and the woman suffered from bulimia nervosa.Each of the partners completed a mood questionnaire and a body symptom checklist. After the determination of auto- and cross-correlations between and within the parallel data sets, multivariate time-series models were specified. Mutual and individual patterns of emotional reactions explained 14% (skin) and 33% (bulimia) of the total variance in both dependent variables (adj. R(2), p<0.0001 for the multivariate models).The question was discussed whether multivariate TSA-models represent a suitable approach to the empirical exploration of clinical marital interaction.
Deducing acidification rates based on short-term time series
Lui, Hon-Kit; Arthur Chen, Chen-Tung
2015-01-01
We show that, statistically, the simple linear regression (SLR)-determined rate of temporal change in seawater pH (βpH), the so-called acidification rate, can be expressed as a linear combination of a constant (the estimated rate of temporal change in pH) and SLR-determined rates of temporal changes in other variables (deviation largely due to various sampling distributions), despite complications due to different observation durations and temporal sampling distributions. Observations show that five time series data sets worldwide, with observation times from 9 to 23 years, have yielded βpH values that vary from 1.61 × 10−3 to −2.5 × 10−3 pH unit yr−1. After correcting for the deviation, these data now all yield an acidification rate similar to what is expected under the air-sea CO2 equilibrium (−1.6 × 10−3 ~ −1.8 × 10−3 pH unit yr−1). Although long-term time series stations may have evenly distributed datasets, shorter time series may suffer large errors which are correctable by this method. PMID:26143749
Nonstationary hydrological time series forecasting using nonlinear dynamic methods
NASA Astrophysics Data System (ADS)
Coulibaly, Paulin; Baldwin, Connely K.
2005-06-01
Recent evidence of nonstationary trends in water resources time series as result of natural and/or anthropogenic climate variability and change, has raised more interest in nonlinear dynamic system modeling methods. In this study, the effectiveness of dynamically driven recurrent neural networks (RNN) for complex time-varying water resources system modeling is investigated. An optimal dynamic RNN approach is proposed to directly forecast different nonstationary hydrological time series. The proposed method automatically selects the most optimally trained network in any case. The simulation performance of the dynamic RNN-based model is compared with the results obtained from optimal multivariate adaptive regression splines (MARS) models. It is shown that the dynamically driven RNN model can be a good alternative for the modeling of complex dynamics of a hydrological system, performing better than the MARS model on the three selected hydrological time series, namely the historical storage volumes of the Great Salt Lake, the Saint-Lawrence River flows, and the Nile River flows.
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.
Satellite time series analysis using Empirical Mode Decomposition
NASA Astrophysics Data System (ADS)
Pannimpullath, R. Renosh; Doolaeghe, Diane; Loisel, Hubert; Vantrepotte, Vincent; Schmitt, Francois G.
2016-04-01
Geophysical fields possess large fluctuations over many spatial and temporal scales. Satellite successive images provide interesting sampling of this spatio-temporal multiscale variability. Here we propose to consider such variability by performing satellite time series analysis, pixel by pixel, using Empirical Mode Decomposition (EMD). EMD is a time series analysis technique able to decompose an original time series into a sum of modes, each one having a different mean frequency. It can be used to smooth signals, to extract trends. It is built in a data-adaptative way, and is able to extract information from nonlinear signals. Here we use MERIS Suspended Particulate Matter (SPM) data, on a weekly basis, during 10 years. There are 458 successive time steps. We have selected 5 different regions of coastal waters for the present study. They are Vietnam coastal waters, Brahmaputra region, St. Lawrence, English Channel and McKenzie. These regions have high SPM concentrations due to large scale river run off. Trend and Hurst exponents are derived for each pixel in each region. The energy also extracted using Hilberts Spectral Analysis (HSA) along with EMD method. Normalised energy computed for each mode for each region with the total energy. The total energy computed using all the modes are extracted using EMD method.
West Africa land use and land cover time series
Cotillon, Suzanne E.
2017-02-16
Started in 1999, the West Africa Land Use Dynamics project represents an effort to map land use and land cover, characterize the trends in time and space, and understand their effects on the environment across West Africa. The outcome of the West Africa Land Use Dynamics project is the production of a three-time period (1975, 2000, and 2013) land use and land cover dataset for the Sub-Saharan region of West Africa, including the Cabo Verde archipelago. The West Africa Land Use Land Cover Time Series dataset offers a unique basis for characterizing and analyzing land changes across the region, systematically and at an unprecedented level of detail.
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.
Time-Modulation of Orbital Electron Capture Decays by Mixing of Massive Neutrinos
NASA Astrophysics Data System (ADS)
Sms Collaboration; Kienle, P.; SMS Collaboration
2009-08-01
We report on the observation of time-modulated orbital EC decays of H-like 140Pr58+, 142Pm60+, and 122I52+ (preliminary) ions with only one electron in the K-shell coasting in the ESR storage ring of GSI with a velocity β=0.71 and a spread Δv/v˜5×10. The decays were observed with time resolved single ion Schottky Mass Spectroscopy by observation of the time of change of the precisely measured revolution frequency of the mother into the daughter ion which is proportional to the mass change or Q-value of the decay. We observed in the EC-branches exponential decay curves time-modulated with periods T=7.06(8)s and amplitude a=0.18(3) for 140Pr decays, T=7.10(22)s and a=0.23(4) for 142Pm decays, and T=6.04(6)s and a=0.19(3) for 122I decays (preliminary) in the laboratory frame. The simultaneously measured β branch of 142Pm shows no modulation with a<0.03. An explanation by mixing of massive electron neutrinos has been suggested, according to which the observed modulation frequency yields a value for the quadratic mass difference: m22-m12=2.22(3)×10eV. This value is 2.9 times larger than the value derived by the KamLAND antineutrino oscillation experiment.
Time perspective as a predictor of massive multiplayer online role-playing game playing.
Lukavska, Katerina
2012-01-01
This article focuses on the relationship between the time perspective (TP) personality trait and massive multiplayer online role-playing game (MMORPG) playing. We investigate the question of frequency of playing. The TP was measured with Zimbardo's TP Inventory (ZTPI), which includes five factors-past negative, past positive, present hedonistic, present fatalistic, and future. The study used data from 154 MMORPG players. We demonstrated that TP partially explained differences within a group of players with respect to the frequency of playing. Significant positive correlations were found between present factors and the amount of time spent playing MMORPGs, and significant negative correlation was found between the future factor and the time spent playing MMORPGs. Our study also revealed the influence of future-present balance on playing time. Players who scored lower in future-present balance variables (their present score was relatively high compared with their future score) reported higher values in playing time. In contrast to referential studies on TP and drug abuse and gambling, present fatalistic TP was demonstrated to be a stronger predictor of extensive playing than present hedonistic TP, which opened the question of motivation for playing. The advantage of our study compared with other personality-based studies lies in the fact that TP is a stable but malleable personality trait with a direct link to playing behavior. Therefore, TP is a promising conceptual resource for excessive playing therapy.
Nonlinear modeling of chaotic time series: Theory and applications
NASA Astrophysics Data System (ADS)
Casdagli, M.; Eubank, S.; Farmer, J. D.; Gibson, J.; Desjardins, D.; Hunter, N.; Theiler, J.
We review recent developments in the modeling and prediction of nonlinear time series. In some cases, apparent randomness in time series may be due to chaotic behavior of a nonlinear but deterministic system. In such cases, it is possible to exploit the determinism to make short term forecasts that are much more accurate than one could make from a linear stochastic model. This is done by first reconstructing a state space, and then using nonlinear function approximation methods to create a dynamical model. Nonlinear models are valuable not only as short term forecasters, but also as diagnostic tools for identifying and quantifying low-dimensional chaotic behavior. During the past few years, methods for nonlinear modeling have developed rapidly, and have already led to several applications where nonlinear models motivated by chaotic dynamics provide superior predictions to linear models. These applications include prediction of fluid flows, sunspots, mechanical vibrations, ice ages, measles epidemics, and human speech.
Modeling Philippine Stock Exchange Composite Index Using Time Series Analysis
NASA Astrophysics Data System (ADS)
Gayo, W. S.; Urrutia, J. D.; Temple, J. M. F.; Sandoval, J. R. D.; Sanglay, J. E. A.
2015-06-01
This study was conducted to develop a time series model of the Philippine Stock Exchange Composite Index and its volatility using the finite mixture of ARIMA model with conditional variance equations such as ARCH, GARCH, EG ARCH, TARCH and PARCH models. Also, the study aimed to find out the reason behind the behaviorof PSEi, that is, which of the economic variables - Consumer Price Index, crude oil price, foreign exchange rate, gold price, interest rate, money supply, price-earnings ratio, Producers’ Price Index and terms of trade - can be used in projecting future values of PSEi and this was examined using Granger Causality Test. The findings showed that the best time series model for Philippine Stock Exchange Composite index is ARIMA(1,1,5) - ARCH(1). Also, Consumer Price Index, crude oil price and foreign exchange rate are factors concluded to Granger cause Philippine Stock Exchange Composite Index.
A Surrogate Test for Pseudo-periodic Time Series Data
NASA Astrophysics Data System (ADS)
Small, Michael; Harrison, Robert G.; Tse, C. K.
2002-07-01
Standard (linear) surrogate methods are only useful for time series exhibiting no pseudo-periodic structure. We describe a new algorithm that can distinguish between a noisy periodic orbit and deterministic non-periodic inter-cycle dynamics. Possible origins of deterministic non-periodic inter-cycle dynamics include: non-periodic linear or nonlinear dynamics, or chaos. This new algorithm is based on mimicking the large-scale dynamics with a local model, but obliterating the fine scale features with dynamic noise. We demonstrate the application of this method to artificial data and experimental time series, including human electrocardiogram (ECG) recordings during sinus rhythm and ventricular tachycardia (VT). The method is able to successfully differentiate between the chaotic Rössler system and a pseudo periodic realization of the Rössler equations with dynamic noise. Application to ECG data demonstrates that both sinus rhythm and VT exhibit nontrivial inter-cycle dynamics.
Analyzing Single-Molecule Time Series via Nonparametric Bayesian Inference
Hines, Keegan E.; Bankston, John R.; Aldrich, Richard W.
2015-01-01
The ability to measure the properties of proteins at the single-molecule level offers an unparalleled glimpse into biological systems at the molecular scale. The interpretation of single-molecule time series has often been rooted in statistical mechanics and the theory of Markov processes. While existing analysis methods have been useful, they are not without significant limitations including problems of model selection and parameter nonidentifiability. To address these challenges, we introduce the use of nonparametric Bayesian inference for the analysis of single-molecule time series. These methods provide a flexible way to extract structure from data instead of assuming models beforehand. We demonstrate these methods with applications to several diverse settings in single-molecule biophysics. This approach provides a well-constrained and rigorously grounded method for determining the number of biophysical states underlying single-molecule data. PMID:25650922
Subsampling confidence bands for trends in atmospheric time series
NASA Astrophysics Data System (ADS)
Gluhovsky, A.
2009-04-01
Assessment of trends is an important problem in time series analysis, particularly in its weather and climate applications. In the talk, construction of simultaneous confidence bands for the unknown trend will be considered for a time series that can be modeled as a sum of two components: deterministic (trend) and stochastic. The stochastic component is a zero-mean stationary process (not necessarily an iid noise as is often assumed). The trend may be recovered by kernel, spline, wavelet and local linear methods, with confidence bands quantifying the associated uncertainty. When dependence is present, constructing confidence bands becomes a difficult problem. It will be addressed non-parametrically via the subsampling method. The procedure will be illustrated with modeled and observed data. This work is supported by NSF grants ATM-0514674 and ATM-0756624.
Nonparametric autocovariance estimation from censored time series by Gaussian imputation
Park, Jung Wook; Genton, Marc G.; Ghosh, Sujit K.
2009-01-01
One of the most frequently used methods to model the autocovariance function of a second-order stationary time series is to use the parametric framework of autoregressive and moving average models developed by Box and Jenkins. However, such parametric models, though very flexible, may not always be adequate to model autocovariance functions with sharp changes. Furthermore, if the data do not follow the parametric model and are censored at a certain value, the estimation results may not be reliable. We develop a Gaussian imputation method to estimate an autocovariance structure via nonparametric estimation of the autocovariance function in order to address both censoring and incorrect model specification. We demonstrate the effectiveness of the technique in terms of bias and efficiency with simulations under various rates of censoring and underlying models. We describe its application to a time series of silicon concentrations in the Arctic. PMID:20072705
Causal Discovery from Subsampled Time Series Data by Constraint Optimization
Hyttinen, Antti; Plis, Sergey; Järvisalo, Matti; Eberhardt, Frederick; Danks, David
2017-01-01
This paper focuses on causal structure estimation from time series data in which measurements are obtained at a coarser timescale than the causal timescale of the underlying system. Previous work has shown that such subsampling can lead to significant errors about the system’s causal structure if not properly taken into account. In this paper, we first consider the search for the system timescale causal structures that correspond to a given measurement timescale structure. We provide a constraint satisfaction procedure whose computational performance is several orders of magnitude better than previous approaches. We then consider finite-sample data as input, and propose the first constraint optimization approach for recovering the system timescale causal structure. This algorithm optimally recovers from possible conflicts due to statistical errors. More generally, these advances allow for a robust and non-parametric estimation of system timescale causal structures from subsampled time series data. PMID:28203316
Interpreting time series of patient satisfaction: macro vs. micro components.
Frank, Björn; Sudo, Shuichi; Enkawa, Takao
2009-01-01
Recent research discovered that economic processes influence national averages of customer satisfaction. Using time-series data from Japanese and South Korean hospitals, we conducted principal component regression analyses to examine whether these findings are transferable to patient satisfaction. Our results reveal that aggregate income has a positive impact and economic expectations have a negative impact on patient satisfaction. Further analyses demonstrate that these strong economic influences make it difficult for hospital managers to use patient satisfaction scores to assess the performance impact of their customer-oriented actions. In order to improve performance evaluations based on patient surveys, we thus recommend managers to remove economic influences from time-series of patient satisfaction.
Assestment of correlations and crossover scale in electroseismic time series
NASA Astrophysics Data System (ADS)
Guzman-Vargas, L.; Ramírez-Rojas, A.; Angulo-Brown, F.
2009-04-01
Evaluating complex fluctuations in electroseismic time series is an important task not only for earthquake prediction but also for understanding complex processes related to earthquake preparation. Previous studies have reported alterations, as the emergence of correlated dynamics in geoelectric potentials prior to an important earthquake (EQ). In this work, we apply the detrended fluctuation analysis and introduce a statistical procedure to characterize the presence of crossovers in scaling exponents, to analyze the fluctuations of geoelectric time series monitored in two sites located in Mexico. We find a complex behavior characterized by the presence of a crossover in the correlation exponents in the vicinity of a M=7.4 EQ occurred on Sept. 14, 1995. Finally, we apply the t-student test to evaluate the level of significance between short and large scaling exponents.
Machine learning for cardiac ultrasound time series data
NASA Astrophysics Data System (ADS)
Yuan, Baichuan; Chitturi, Sathya R.; Iyer, Geoffrey; Li, Nuoyu; Xu, Xiaochuan; Zhan, Ruohan; Llerena, Rafael; Yen, Jesse T.; Bertozzi, Andrea L.
2017-03-01
We consider the problem of identifying frames in a cardiac ultrasound video associated with left ventricular chamber end-systolic (ES, contraction) and end-diastolic (ED, expansion) phases of the cardiac cycle. Our procedure involves a simple application of non-negative matrix factorization (NMF) to a series of frames of a video from a single patient. Rank-2 NMF is performed to compute two end-members. The end members are shown to be close representations of the actual heart morphology at the end of each phase of the heart function. Moreover, the entire time series can be represented as a linear combination of these two end-member states thus providing a very low dimensional representation of the time dynamics of the heart. Unlike previous work, our methods do not require any electrocardiogram (ECG) information in order to select the end-diastolic frame. Results are presented for a data set of 99 patients including both healthy and diseased examples.
Nonlinear modeling of chaotic time series: Theory and applications
Casdagli, M.; Eubank, S.; Farmer, J.D.; Gibson, J. Santa Fe Inst., NM ); Des Jardins, D.; Hunter, N.; Theiler, J. )
1990-01-01
We review recent developments in the modeling and prediction of nonlinear time series. In some cases apparent randomness in time series may be due to chaotic behavior of a nonlinear but deterministic system. In such cases it is possible to exploit the determinism to make short term forecasts that are much more accurate than one could make from a linear stochastic model. This is done by first reconstructing a state space, and then using nonlinear function approximation methods to create a dynamical model. Nonlinear models are valuable not only as short term forecasters, but also as diagnostic tools for identifying and quantifying low-dimensional chaotic behavior. During the past few years methods for nonlinear modeling have developed rapidly, and have already led to several applications where nonlinear models motivated by chaotic dynamics provide superior predictions to linear models. These applications include prediction of fluid flows, sunspots, mechanical vibrations, ice ages, measles epidemics and human speech. 162 refs., 13 figs.
Deviations from uniform power law scaling in nonstationary time series
NASA Technical Reports Server (NTRS)
Viswanathan, G. M.; Peng, C. K.; Stanley, H. E.; Goldberger, A. L.
1997-01-01
A classic problem in physics is the analysis of highly nonstationary time series that typically exhibit long-range correlations. Here we test the hypothesis that the scaling properties of the dynamics of healthy physiological systems are more stable than those of pathological systems by studying beat-to-beat fluctuations in the human heart rate. We develop techniques based on the Fano factor and Allan factor functions, as well as on detrended fluctuation analysis, for quantifying deviations from uniform power-law scaling in nonstationary time series. By analyzing extremely long data sets of up to N = 10(5) beats for 11 healthy subjects, we find that the fluctuations in the heart rate scale approximately uniformly over several temporal orders of magnitude. By contrast, we find that in data sets of comparable length for 14 subjects with heart disease, the fluctuations grow erratically, indicating a loss of scaling stability.
Nonparametric autocovariance estimation from censored time series by Gaussian imputation.
Park, Jung Wook; Genton, Marc G; Ghosh, Sujit K
2009-02-01
One of the most frequently used methods to model the autocovariance function of a second-order stationary time series is to use the parametric framework of autoregressive and moving average models developed by Box and Jenkins. However, such parametric models, though very flexible, may not always be adequate to model autocovariance functions with sharp changes. Furthermore, if the data do not follow the parametric model and are censored at a certain value, the estimation results may not be reliable. We develop a Gaussian imputation method to estimate an autocovariance structure via nonparametric estimation of the autocovariance function in order to address both censoring and incorrect model specification. We demonstrate the effectiveness of the technique in terms of bias and efficiency with simulations under various rates of censoring and underlying models. We describe its application to a time series of silicon concentrations in the Arctic.
Time series analysis of nuclear instrumentation in EBR-II
Imel, G.R.
1996-05-01
Results of a time series analysis of the scaler count data from the 3 wide range nuclear detectors in the Experimental Breeder Reactor-II are presented. One of the channels was replaced, and it was desired to determine if there was any statistically significant change (ie, improvement) in the channel`s response after the replacement. Data were collected from all 3 channels for 16-day periods before and after detector replacement. Time series analysis and statistical tests showed that there was no significant change after the detector replacement. Also, there were no statistically significant differences among the 3 channels, either before or after the replacement. Finally, it was determined that errors in the reactivity change inferred from subcritical count monitoring during fuel handling would be on the other of 20-30 cents for single count intervals.
Simple Patterns in Fluctuations of Time Series of Economic Interest
NASA Astrophysics Data System (ADS)
Fanchiotti, H.; García Canal, C. A.; García Zúñiga, H.
Time series corresponding to nominal exchange rates between the US dollar and Argentina, Brazil and European Economic Community currencies; different financial indexes as the Industrial Dow Jones, the British Footsie, the German DAX Composite, the Australian Share Price and the Nikkei Cash and also different Argentine local tax revenues, are analyzed looking for the appearance of simple patterns and the possible definition of forecast evaluators. In every case, the statistical fractal dimensions are obtained from the behavior of the corresponding variance of increments at a given lag. The detrended fluctuation analysis of the data in terms of the corresponding exponent in the resulting power law is carried out. Finally, the frequency power spectra of all the time series considered are computed and compared
Causal Discovery from Subsampled Time Series Data by Constraint Optimization.
Hyttinen, Antti; Plis, Sergey; Järvisalo, Matti; Eberhardt, Frederick; Danks, David
2016-08-01
This paper focuses on causal structure estimation from time series data in which measurements are obtained at a coarser timescale than the causal timescale of the underlying system. Previous work has shown that such subsampling can lead to significant errors about the system's causal structure if not properly taken into account. In this paper, we first consider the search for the system timescale causal structures that correspond to a given measurement timescale structure. We provide a constraint satisfaction procedure whose computational performance is several orders of magnitude better than previous approaches. We then consider finite-sample data as input, and propose the first constraint optimization approach for recovering the system timescale causal structure. This algorithm optimally recovers from possible conflicts due to statistical errors. More generally, these advances allow for a robust and non-parametric estimation of system timescale causal structures from subsampled time series data.
Deviations from uniform power law scaling in nonstationary time series
NASA Technical Reports Server (NTRS)
Viswanathan, G. M.; Peng, C. K.; Stanley, H. E.; Goldberger, A. L.
1997-01-01
A classic problem in physics is the analysis of highly nonstationary time series that typically exhibit long-range correlations. Here we test the hypothesis that the scaling properties of the dynamics of healthy physiological systems are more stable than those of pathological systems by studying beat-to-beat fluctuations in the human heart rate. We develop techniques based on the Fano factor and Allan factor functions, as well as on detrended fluctuation analysis, for quantifying deviations from uniform power-law scaling in nonstationary time series. By analyzing extremely long data sets of up to N = 10(5) beats for 11 healthy subjects, we find that the fluctuations in the heart rate scale approximately uniformly over several temporal orders of magnitude. By contrast, we find that in data sets of comparable length for 14 subjects with heart disease, the fluctuations grow erratically, indicating a loss of scaling stability.
The multiscale analysis between stock market time series
NASA Astrophysics Data System (ADS)
Shi, Wenbin; Shang, Pengjian
2015-11-01
This paper is devoted to multiscale cross-correlation analysis on stock market time series, where multiscale DCCA cross-correlation coefficient as well as multiscale cross-sample entropy (MSCE) is applied. Multiscale DCCA cross-correlation coefficient is a realization of DCCA cross-correlation coefficient on multiple scales. The results of this method present a good scaling characterization. More significantly, this method is able to group stock markets by areas. Compared to multiscale DCCA cross-correlation coefficient, MSCE presents a more remarkable scaling characterization and the value of each log return of financial time series decreases with the increasing of scale factor. But the results of grouping is not as good as multiscale DCCA cross-correlation coefficient.
A Multiscale Approach to InSAR Time Series Analysis
NASA Astrophysics Data System (ADS)
Hetland, E. A.; Muse, P.; Simons, M.; Lin, N.; Dicaprio, C. J.
2010-12-01
We present a technique to constrain time-dependent deformation from repeated satellite-based InSAR observations of a given region. This approach, which we call MInTS (Multiscale InSAR Time Series analysis), relies on a spatial wavelet decomposition to permit the inclusion of distance based spatial correlations in the observations while maintaining computational tractability. As opposed to single pixel InSAR time series techniques, MInTS takes advantage of both spatial and temporal characteristics of the deformation field. We use a weighting scheme which accounts for the presence of localized holes due to decorrelation or unwrapping errors in any given interferogram. We represent time-dependent deformation using a dictionary of general basis functions, capable of detecting both steady and transient processes. The estimation is regularized using a model resolution based smoothing so as to be able to capture rapid deformation where there are temporally dense radar acquisitions and to avoid oscillations during time periods devoid of acquisitions. MInTS also has the flexibility to explicitly parametrize known time-dependent processes that are expected to contribute to a given set of observations (e.g., co-seismic steps and post-seismic transients, secular variations, seasonal oscillations, etc.). We use cross validation to choose the regularization penalty parameter in the inversion of for the time-dependent deformation field. We demonstrate MInTS using a set of 63 ERS-1/2 and 29 Envisat interferograms for Long Valley Caldera.
Conditional adaptive Bayesian spectral analysis of nonstationary biomedical time series.
Bruce, Scott A; Hall, Martica H; Buysse, Daniel J; Krafty, Robert T
2017-05-08
Many studies of biomedical time series signals aim to measure the association between frequency-domain properties of time series and clinical and behavioral covariates. However, the time-varying dynamics of these associations are largely ignored due to a lack of methods that can assess the changing nature of the relationship through time. This article introduces a method for the simultaneous and automatic analysis of the association between the time-varying power spectrum and covariates, which we refer to as conditional adaptive Bayesian spectrum analysis (CABS). The procedure adaptively partitions the grid of time and covariate values into an unknown number of approximately stationary blocks and nonparametrically estimates local spectra within blocks through penalized splines. CABS is formulated in a fully Bayesian framework, in which the number and locations of partition points are random, and fit using reversible jump Markov chain Monte Carlo techniques. Estimation and inference averaged over the distribution of partitions allows for the accurate analysis of spectra with both smooth and abrupt changes. The proposed methodology is used to analyze the association between the time-varying spectrum of heart rate variability and self-reported sleep quality in a study of older adults serving as the primary caregiver for their ill spouse. © 2017, The International Biometric Society.
NASA Astrophysics Data System (ADS)
Phillips, D. A.; Meertens, C. M.; Hodgkinson, K. M.; Puskas, C. M.; Boler, F. M.; Snett, L.; Mattioli, G. S.
2013-12-01
We present an overview of time series data, tools and services available from UNAVCO along with two specific and compelling examples of geodetic time series analysis. UNAVCO provides a diverse suite of geodetic data products and cyberinfrastructure services to support community research and education. The UNAVCO archive includes data from 2500+ continuous GPS stations, borehole geophysics instruments (strainmeters, seismometers, tiltmeters, pore pressure sensors), and long baseline laser strainmeters. These data span temporal scales from seconds to decades and provide global spatial coverage with regionally focused networks including the EarthScope Plate Boundary Observatory (PBO) and COCONet. This rich, open access dataset is a tremendous resource that enables the exploration, identification and analysis of time varying signals associated with crustal deformation, reference frame determinations, isostatic adjustments, atmospheric phenomena, hydrologic processes and more. UNAVCO provides a suite of time series exploration and analysis resources including static plots, dynamic plotting tools, and data products and services designed to enhance time series analysis. The PBO GPS network allow for identification of ~1 mm level deformation signals. At some GPS stations seasonal signals and longer-term trends in both the vertical and horizontal components can be dominated by effects of hydrological loading from natural and anthropogenic sources. Modeling of hydrologic deformation using GLDAS and a variety of land surface models (NOAH, MOSAIC, VIC and CLM) shows promise for independently modeling hydrologic effects and separating them from tectonic deformation as well as anthropogenic loading sources. A major challenge is to identify where loading is dominant and corrections from GLDAS can apply and where pumping is the dominant signal and corrections are not possible without some other data. In another arena, the PBO strainmeter network was designed to capture small short
A Radial Basis Function Approach to Financial Time Series Analysis
1993-12-01
Massachusetts Institute of Technology Artificial Intelligence Laboratory AI-TR 1457 545 Technology Square Cambridge, Massachusetts 02139 9. SPONSORING...Function Approach to Financial Time Series Analysis Ihy James M. Hutchinson Master of Science in EE(S. Massachusetts Institute of Technology (1986...Philosophy 0e r . at tilt NTiS CRA&IDTIC TAB Massachusetts Institute of Technology Unannoun•ea February. I9-1 Justific.igo,, . @1991 Massachusetts Institut
New Comprehensive System to Construct Speleothem Fabrics Time Series
NASA Astrophysics Data System (ADS)
Frisia, S.; Borsato, A.
2014-12-01
Speleothem fabrics record processes that influence the way geochemical proxy data are encoded in speleothems, yet, there has been little advance in the use of fabrics as a complement to palaeo-proxy datasets since the fabric classification proposed by us in 2010. The systematic use of fabrics documentation in speleothem science has been limited by the absence of a comprehensive, numerical system that would allow constructing fabric time series comparable with the widely used geochemical time series. Documentation of speleothem fabrics is fundamental for a robust interpretation of speleothem time series where stable isotopes and trace elements are used as proxy, because fabrics highlight depositional as well as post-depositional processes whose understanding complements reconstructions based on geochemistry. Here we propose a logic system allowing transformation of microscope observations into numbers tied to acronyms that specify each fabric type and subtype. The rationale for ascribing progressive numbers to fabrics is based on the most up-to-date growth models. In this conceptual framework, the progression reflects hydrological conditions, bio-mediation and diagenesis. The lowest numbers are given to calcite fabrics formed at relatively constant drip rates: the columnar types (compact and open). Higher numbers are ascribed to columnar fabrics characterized by presence of impurities that cause elongation or lattice distortion (Elongated, Fascicular Optic and Radiaxial calcites). The sequence progresses with the dendritic fabrics, followed by micrite (M), which has been observed in association with microbial films. Microsparite (Ms) and mosaic calcite (Mc) have the highest numbers, being considered as diagenetic. Acronyms and subfixes are intended to become universally acknowledged. Thus, fabrics can be plotted vs. age to yield time series, where numbers are replaced by the acronyms. This will result in a visual representation of climate- or environmental
Visualizing Rank Time Series of Wikipedia Top-Viewed Pages.
Xia, Jing; Hou, Yumeng; Chen, Yingjie Victor; Qian, Zhenyu Cheryl; Ebert, David S; Chen, Wei
2017-01-01
Visual clutter is a common challenge when visualizing large rank time series data. WikiTopReader, a reader of Wikipedia page rank, lets users explore connections among top-viewed pages by connecting page-rank behaviors with page-link relations. Such a combination enhances the unweighted Wikipedia page-link network and focuses attention on the page of interest. A set of user evaluations shows that the system effectively represents evolving ranking patterns and page-wise correlation.
Mode Analysis with Autocorrelation Method (Single Time Series) in Tokamak
NASA Astrophysics Data System (ADS)
Saadat, Shervin; Salem, Mohammad K.; Goranneviss, Mahmoud; Khorshid, Pejman
2010-08-01
In this paper plasma mode analyzed with statistical method that designated Autocorrelation function. Auto correlation function used from one time series, so for this purpose we need one Minov coil. After autocorrelation analysis on mirnov coil data, spectral density diagram is plotted. Spectral density diagram from symmetries and trends can analyzed plasma mode. RHF fields effects with this method ate investigated in IR-T1 tokamak and results corresponded with multichannel methods such as SVD and FFT.
Time series prediction using artificial neural network for power stabilization
Puranik, G.; Philip, T.; Nail, B.
1996-12-31
Time series prediction has been applied to many business and scientific applications. Prominent among them are stock market prediction, weather forecasting, etc. Here, this technique has been applied to forecast plasma torch voltages to stabilize power using a backpropagation, a model of artificial neural network. The Extended-Delta-Bar-Delta algorithm is used to improve the convergence rate of the network and also to avoid local minima. Results from off-line data was quite promising to use in on-line.
Time series regression model for infectious disease and weather.
Imai, Chisato; Armstrong, Ben; Chalabi, Zaid; Mangtani, Punam; Hashizume, Masahiro
2015-10-01
Time series regression has been developed and long used to evaluate the short-term associations of air pollution and weather with mortality or morbidity of non-infectious diseases. The application of the regression approaches from this tradition to infectious diseases, however, is less well explored and raises some new issues. We discuss and present potential solutions for five issues often arising in such analyses: changes in immune population, strong autocorrelations, a wide range of plausible lag structures and association patterns, seasonality adjustments, and large overdispersion. The potential approaches are illustrated with datasets of cholera cases and rainfall from Bangladesh and influenza and temperature in Tokyo. Though this article focuses on the application of the traditional time series regression to infectious diseases and weather factors, we also briefly introduce alternative approaches, including mathematical modeling, wavelet analysis, and autoregressive integrated moving average (ARIMA) models. Modifications proposed to standard time series regression practice include using sums of past cases as proxies for the immune population, and using the logarithm of lagged disease counts to control autocorrelation due to true contagion, both of which are motivated from "susceptible-infectious-recovered" (SIR) models. The complexity of lag structures and association patterns can often be informed by biological mechanisms and explored by using distributed lag non-linear models. For overdispersed models, alternative distribution models such as quasi-Poisson and negative binomial should be considered. Time series regression can be used to investigate dependence of infectious diseases on weather, but may need modifying to allow for features specific to this context. Copyright © 2015 The Authors. Published by Elsevier Inc. All rights reserved.
One nanosecond time synchronization using series and GPS
NASA Technical Reports Server (NTRS)
Buennagel, A. A.; Spitzmesser, D. J.; Young, L. E.
1983-01-01
Subnanosecond time sychronization between two remote rubidium frequency standards is verified by a traveling clock comparison. Using a novel, code ignorant Global Positioning System (GPS) receiver developed at JPL, the SERIES geodetic baseline measurement system is applied to establish the offset between the 1 Hz. outputs of the remote standards. Results of the two intercomparison experiments to date are presented as well as experimental details.
Multifractal analysis of time series generated by discrete Ito equations
Telesca, Luciano; Czechowski, Zbigniew; Lovallo, Michele
2015-06-15
In this study, we show that discrete Ito equations with short-tail Gaussian marginal distribution function generate multifractal time series. The multifractality is due to the nonlinear correlations, which are hidden in Markov processes and are generated by the interrelation between the drift and the multiplicative stochastic forces in the Ito equation. A link between the range of the generalized Hurst exponents and the mean of the squares of all averaged net forces is suggested.
A method for detecting complex correlation in time series
NASA Astrophysics Data System (ADS)
Alfi, V.; Petri, A.; Pietronero, L.
2007-06-01
We propose a new method for detecting complex correlations in time series of limited size. The method is derived by the Spitzer's identity and proves to work successfully on different model processes, including the ARCH process, in which pairs of variables are uncorrelated, but the three point correlation function is non zero. The application to financial data allows to discriminate among dependent and independent stock price returns where standard statistical analysis fails.
A data-fitting procedure for chaotic time series
McDonough, J.M.; Mukerji, S.; Chung, S.
1998-10-01
In this paper the authors introduce data characterizations for fitting chaotic data to linear combinations of one-dimensional maps (say, of the unit interval) for use in subgrid-scale turbulence models. They test the efficacy of these characterizations on data generated by a chaotically-forced Burgers` equation and demonstrate very satisfactory results in terms of modeled time series, power spectra and delay maps.
Moment structures of parameter-driven count time series models
NASA Astrophysics Data System (ADS)
Bukhari, Nawwal Ahmad; Beng, Koh You; Mohamed, Ibrahim
2017-05-01
This paper focuses on a parameter-driven count time series model with three different distributions. We provide a brief description of the first order autoregressive, AR(1) latent process. We consider the first four central moments of each models that are mean, variance, skewness and kurtosis. Next, the autocovariance and autocorrelation functions for each models are derived. We outline and discuss the possible directions of future research.
The complexity of carbon flux time series in Europe
NASA Astrophysics Data System (ADS)
Lange, Holger; Sippel, Sebastian
2014-05-01
Observed geophysical time series usually exhibit pronounced variability, part of which is process-related and deterministic ("signal"), another part is due to random fluctuations ("noise"). To discern these two sources for fluctuations is notoriously difficult using conventional analysis methods, unless sophisticated model assumptions are made. Here, we present an almost parameter-free innovative approach with the potential to draw a distinction between deterministic processes and structured noise, based on ordinal pattern statistics. The method determines one measure for the information content of time series (Shannon entropy) and two complexity measures, one based on global properties of the order pattern distribution (Jensen-Shannon complexity) and one based on local (derivative) properties (Fisher information or complexity). Each time series gets classified via its location in an entropy-complexity plane; using this representation, the method draws a qualitative distinction between different types of natural processes. As a case study, we investigate Gross Primary Productivity (GPP) and respiration which are key variables in terrestrial ecosystems quantifying carbon allocation and biomass growth of vegetation. Changes in GPP and ecosystem respiration can be induced by land use change, environmental disasters or extreme events, and changing climate. Numerous attempts to quantify these variables on larger spatial scales exist. Here, we investigate gridded time series at monthly resolution for the European continent either based on upscaled measurements ("observations") or modelled with two different process-based terrestrial ecosystem models ("simulations"). The complexity analysis is either visualized as maps of Europe showing "hotspots" of complexity for GPP and respiration, or used to provide a detailed observations-simulations and model-model comparison. Values found for information and complexity will be compared to known artificial reference processes
The QuakeSim System for GPS Time Series Analysis
NASA Astrophysics Data System (ADS)
Granat, R. A.; Gao, X.; Pierce, M.; Wang, J.
2010-12-01
We present a system for analysis of GPS time series data available to geosciences users through a web services / web portal interface. The system provides two time series analysis methods, one based on hidden Markov model (HMM) segmentation, the other based on covariance descriptor analysis (CDA). In addition, it provides data pre-processing routines that perform spike noise removal, linear de-trending, sum-of-sines removal, and common mode removal using probabilistic principle components analysis (PPCA). These components can be composed by the user into the desired series of processing steps for analysis through an intuitive graphical interface. The system is accessed through a web portal that allows both micro-scale (individual station) and macro-scale (whole network) exploration of data sets and analysis results via Google Maps. Users can focus in on or scroll through particular spatial or temporal time windows, or observe dynamic behavior by created movies that display the system state. Analysis results can be exported to KML format for easy combination with other sources of data, such as fault databases and InSAR interferograms. GPS solutions for California member stations of the plate boundary observatory from both the SOPAC and JPL gipsy context groups are automatically imported into the system as that data becomes available. We show the results of the methods as applied to these data sets for an assortment of case studies, and show how the system can be used to analyze both seismic and aseismic signals.
Genetic programming and serial processing for time series classification.
Alfaro-Cid, Eva; Sharman, Ken; Esparcia-Alcázar, Anna I
2014-01-01
This work describes an approach devised by the authors for time series classification. In our approach genetic programming is used in combination with a serial processing of data, where the last output is the result of the classification. The use of genetic programming for classification, although still a field where more research in needed, is not new. However, the application of genetic programming to classification tasks is normally done by considering the input data as a feature vector. That is, to the best of our knowledge, there are not examples in the genetic programming literature of approaches where the time series data are processed serially and the last output is considered as the classification result. The serial processing approach presented here fills a gap in the existing literature. This approach was tested in three different problems. Two of them are real world problems whose data were gathered for online or conference competitions. As there are published results of these two problems this gives us the chance to compare the performance of our approach against top performing methods. The serial processing of data in combination with genetic programming obtained competitive results in both competitions, showing its potential for solving time series classification problems. The main advantage of our serial processing approach is that it can easily handle very large datasets.
Time series analysis for psychological research: examining and forecasting change
Jebb, Andrew T.; Tay, Louis; Wang, Wei; Huang, Qiming
2015-01-01
Psychological research has increasingly recognized the importance of integrating temporal dynamics into its theories, and innovations in longitudinal designs and analyses have allowed such theories to be formalized and tested. However, psychological researchers may be relatively unequipped to analyze such data, given its many characteristics and the general complexities involved in longitudinal modeling. The current paper introduces time series analysis to psychological research, an analytic domain that has been essential for understanding and predicting the behavior of variables across many diverse fields. First, the characteristics of time series data are discussed. Second, different time series modeling techniques are surveyed that can address various topics of interest to psychological researchers, including describing the pattern of change in a variable, modeling seasonal effects, assessing the immediate and long-term impact of a salient event, and forecasting future values. To illustrate these methods, an illustrative example based on online job search behavior is used throughout the paper, and a software tutorial in R for these analyses is provided in the Supplementary Materials. PMID:26106341
Time series analysis for psychological research: examining and forecasting change.
Jebb, Andrew T; Tay, Louis; Wang, Wei; Huang, Qiming
2015-01-01
Psychological research has increasingly recognized the importance of integrating temporal dynamics into its theories, and innovations in longitudinal designs and analyses have allowed such theories to be formalized and tested. However, psychological researchers may be relatively unequipped to analyze such data, given its many characteristics and the general complexities involved in longitudinal modeling. The current paper introduces time series analysis to psychological research, an analytic domain that has been essential for understanding and predicting the behavior of variables across many diverse fields. First, the characteristics of time series data are discussed. Second, different time series modeling techniques are surveyed that can address various topics of interest to psychological researchers, including describing the pattern of change in a variable, modeling seasonal effects, assessing the immediate and long-term impact of a salient event, and forecasting future values. To illustrate these methods, an illustrative example based on online job search behavior is used throughout the paper, and a software tutorial in R for these analyses is provided in the Supplementary Materials.
Characterization of aggressive prostate cancer using ultrasound RF time series
NASA Astrophysics Data System (ADS)
Khojaste, Amir; Imani, Farhad; Moradi, Mehdi; Berman, David; Siemens, D. Robert; Sauerberi, Eric E.; Boag, Alexander H.; Abolmaesumi, Purang; Mousavi, Parvin
2015-03-01
Prostate cancer is the most prevalently diagnosed and the second cause of cancer-related death in North American men. Several approaches have been proposed to augment detection of prostate cancer using different imaging modalities. Due to advantages of ultrasound imaging, these approaches have been the subject of several recent studies. This paper presents the results of a feasibility study on differentiating between lower and higher grade prostate cancer using ultrasound RF time series data. We also propose new spectral features of RF time series to highlight aggressive prostate cancer in small ROIs of size 1 mm × 1 mm in a cohort of 19 ex vivo specimens of human prostate tissue. In leave-one-patient-out cross-validation strategy, an area under accumulated ROC curve of 0.8 has been achieved with overall sensitivity and specificity of 81% and 80%, respectively. The current method shows promising results on differentiating between lower and higher grade of prostate cancer using ultrasound RF time series.
Toward automatic time-series forecasting using neural networks.
Yan, Weizhong
2012-07-01
Over the past few decades, application of artificial neural networks (ANN) to time-series forecasting (TSF) has been growing rapidly due to several unique features of ANN models. However, to date, a consistent ANN performance over different studies has not been achieved. Many factors contribute to the inconsistency in the performance of neural network models. One such factor is that ANN modeling involves determining a large number of design parameters, and the current design practice is essentially heuristic and ad hoc, this does not exploit the full potential of neural networks. Systematic ANN modeling processes and strategies for TSF are, therefore, greatly needed. Motivated by this need, this paper attempts to develop an automatic ANN modeling scheme. It is based on the generalized regression neural network (GRNN), a special type of neural network. By taking advantage of several GRNN properties (i.e., a single design parameter and fast learning) and by incorporating several design strategies (e.g., fusing multiple GRNNs), we have been able to make the proposed modeling scheme to be effective for modeling large-scale business time series. The initial model was entered into the NN3 time-series competition. It was awarded the best prediction on the reduced dataset among approximately 60 different models submitted by scholars worldwide.
Learning restricted Boolean network model by time-series data
2014-01-01
Restricted Boolean networks are simplified Boolean networks that are required for either negative or positive regulations between genes. Higa et al. (BMC Proc 5:S5, 2011) proposed a three-rule algorithm to infer a restricted Boolean network from time-series data. However, the algorithm suffers from a major drawback, namely, it is very sensitive to noise. In this paper, we systematically analyze the regulatory relationships between genes based on the state switch of the target gene and propose an algorithm with which restricted Boolean networks may be inferred from time-series data. We compare the proposed algorithm with the three-rule algorithm and the best-fit algorithm based on both synthetic networks and a well-studied budding yeast cell cycle network. The performance of the algorithms is evaluated by three distance metrics: the normalized-edge Hamming distance μhame, the normalized Hamming distance of state transition μhamst, and the steady-state distribution distance μssd. Results show that the proposed algorithm outperforms the others according to both μhame and μhamst, whereas its performance according to μssd is intermediate between best-fit and the three-rule algorithms. Thus, our new algorithm is more appropriate for inferring interactions between genes from time-series data. PMID:25093019
AE mapping of engines for spatially located time series
NASA Astrophysics Data System (ADS)
Nivesrangsan, P.; Steel, J. A.; Reuben, R. L.
2005-09-01
This paper represents the first step towards using multiple acoustic emission (AE) sensors to produce spatially located time series signals for a running engine. By this it is meant the decomposition of a multi-source signal by acquiring it with an array of sensors and using source location to reconstitute the individual time series attributable to some or all of these signals. Internal combustion engines are a group of monitoring targets which would benefit from such an approach. A series of experiments has been carried out where AE from a standard source has been mapped for a large number of source-sensor pairs on a small diesel engine and on various cast iron blocks of simple geometry. The wave propagation on a typical diesel engine cylinder head or block is complex because of the heterogeneity of the cast iron and the complex geometry with variations in wall-thickness, boundaries and discontinuities. The AE signal distortion for a range of source-sensor pairs has been estimated using time-frequency analysis, and using a reference sensor placed close to the source. At this stage, the emphasis has been on determining a suitable processing scheme to recover a measure of the signal energy, which depends only on the distance of the source and not upon the path. Tentative recommendations are made on a suitable approach to sensor positioning and signal processing with reference to a limited set of data acquired from the running engine.
Cross-sample entropy of foreign exchange time series
NASA Astrophysics Data System (ADS)
Liu, Li-Zhi; Qian, Xi-Yuan; Lu, Heng-Yao
2010-11-01
The correlation of foreign exchange rates in currency markets is investigated based on the empirical data of DKK/USD, NOK/USD, CAD/USD, JPY/USD, KRW/USD, SGD/USD, THB/USD and TWD/USD for a period from 1995 to 2002. Cross-SampEn (cross-sample entropy) method is used to compare the returns of every two exchange rate time series to assess their degree of asynchrony. The calculation method of confidence interval of SampEn is extended and applied to cross-SampEn. The cross-SampEn and its confidence interval for every two of the exchange rate time series in periods 1995-1998 (before the Asian currency crisis) and 1999-2002 (after the Asian currency crisis) are calculated. The results show that the cross-SampEn of every two of these exchange rates becomes higher after the Asian currency crisis, indicating a higher asynchrony between the exchange rates. Especially for Singapore, Thailand and Taiwan, the cross-SampEn values after the Asian currency crisis are significantly higher than those before the Asian currency crisis. Comparison with the correlation coefficient shows that cross-SampEn is superior to describe the correlation between time series.
An Operational Geodatabase Service for Disseminating Raster Time Series Data
NASA Astrophysics Data System (ADS)
Asante, K. O.
2009-12-01
The volume of raster time series data available for earth science applications is rapidly expanding with improvements in spatial and temporal resolution of earth imaging from remote sensing missions. Current dissemination systems are typically designed for mission efficiency rather than supporting the various needs of diverse user communities. This promotes the building of multiple archives of the same dataset by end users who acquire the skills needed to establish and maintain their own data streams. Such processing often becomes a barrier to the adoption of new datasets. This presentation describes the development of an operational geodatabase service for the dissemination of raster time series. The service combines innovative geocoding schemes with traditional database and geospatial capabilities to facilitate direct access to raster time series. It includes functionality such as search and retrieval, data segmentation, trend analysis and direct integration into third-party applications using predefined data schemas. The service allows end users to interact with data using simple web-based tools without the need for complex data processing skills. A live implementation of the service is demonstrated using sample global environmental datasets.
Clustering multivariate time series using Hidden Markov Models.
Ghassempour, Shima; Girosi, Federico; Maeder, Anthony
2014-03-06
In this paper we describe an algorithm for clustering multivariate time series with variables taking both categorical and continuous values. Time series of this type are frequent in health care, where they represent the health trajectories of individuals. The problem is challenging because categorical variables make it difficult to define a meaningful distance between trajectories. We propose an approach based on Hidden Markov Models (HMMs), where we first map each trajectory into an HMM, then define a suitable distance between HMMs and finally proceed to cluster the HMMs with a method based on a distance matrix. We test our approach on a simulated, but realistic, data set of 1,255 trajectories of individuals of age 45 and over, on a synthetic validation set with known clustering structure, and on a smaller set of 268 trajectories extracted from the longitudinal Health and Retirement Survey. The proposed method can be implemented quite simply using standard packages in R and Matlab and may be a good candidate for solving the difficult problem of clustering multivariate time series with categorical variables using tools that do not require advanced statistic knowledge, and therefore are accessible to a wide range of researchers.
Single event time-series analysis in a karst catchment evaluated using a groundwater model
NASA Astrophysics Data System (ADS)
Mayaud, Cyril; Wagner, Thomas; Birk, Steffen
2013-04-01
The Lurbach-Tanneben karst system (Styria, Austria) is drained by two major springs and replenished by both autogenic recharge from the karst massive itself and a sinking stream that originates in low permeable schists (allogenic recharge). Detailed data from two events recorded during a tracer experiment in 2008 (Oswald et al., EGU2009-9255) demonstrates that an overflow from one of the sub-catchment to the other is activated if the spring discharge exceeds a threshold. Time-series analysis (e.g., auto-correlation, cross-correlation) was applied to examine how far the various available methods support the identification of the transient inter-catchment flow observed in this karst system. As inter-catchment flow is intermittent, the evaluation was focused on single events. In order to support the interpretation of the results from the time-series analysis a simplified groundwater flow model was built using MODFLOW based on the current conceptual understanding of the karst system. The groundwater model represents a synthetic karst aquifer for which the same methods were applied. Using the wetting capability package of MODFLOW, the model simulated an overflow similar to what has been observed during the tracer experiment. Various options of recharge (e.g., allogenic versus autogenic) were used to generate synthetic discharge data for the time-series analysis. In addition, geometric and hydraulic properties of the karst system were varied in several model scenarios. This approach helps to identify effects of recharge and aquifer properties in the results from the time-series analysis. Comparing the results from the time-series analysis of the observed data with those of the synthetic data a good agreement was found. For instance, the cross-correlograms show similar patterns with respect to time lags and maximum cross-correlation coefficients if appropriate hydraulic parameters are assigned to the groundwater model. Thus, the heterogeneity of hydraulic aquifer
Metric emerging to massive modes in quantum cosmological space-times
NASA Astrophysics Data System (ADS)
Dapor, Andrea; Lewandowski, Jerzy
2013-03-01
We consider a massive quantum test Klein-Gordon field probing a homogeneous isotropic quantum cosmological space-time in the background. In particular, we derive a semiclassical space-time which emerges to a mode of the field. The method consists of a comparison between quantum field theory on a quantum background and quantum field theory on a classical curved space-time, giving rise to an emergent metric tensor (its components being computed from the equation of propagation of the quantum Klein-Gordon field in the test field approximation). If the field is massless the emergent metric is of the Friedmann-Robertson-Walker form, but if a mass term is considered it turns out that the simplest emergent metric that displays the symmetries of the system is of the Bianchi I type, deformed in the direction of propagation of the particle. This anisotropy is of a quantum nature: it is proportional to ℏ and “dresses” the isotropic classical space-time obtained in the classical limit.
Earthquake forecasting studies using radon time series data in Taiwan
NASA Astrophysics Data System (ADS)
Walia, Vivek; Kumar, Arvind; Fu, Ching-Chou; Lin, Shih-Jung; Chou, Kuang-Wu; Wen, Kuo-Liang; Chen, Cheng-Hong
2017-04-01
For few decades, growing number of studies have shown usefulness of data in the field of seismogeochemistry interpreted as geochemical precursory signals for impending earthquakes and radon is idendified to be as one of the most reliable geochemical precursor. Radon is recognized as short-term precursor and is being monitored in many countries. This study is aimed at developing an effective earthquake forecasting system by inspecting long term radon time series data. The data is obtained from a network of radon monitoring stations eastblished along different faults of Taiwan. The continuous time series radon data for earthquake studies have been recorded and some significant variations associated with strong earthquakes have been observed. The data is also examined to evaluate earthquake precursory signals against environmental factors. An automated real-time database operating system has been developed recently to improve the data processing for earthquake precursory studies. In addition, the study is aimed at the appraisal and filtrations of these environmental parameters, in order to create a real-time database that helps our earthquake precursory study. In recent years, automatic operating real-time database has been developed using R, an open source programming language, to carry out statistical computation on the data. To integrate our data with our working procedure, we use the popular and famous open source web application solution, AMP (Apache, MySQL, and PHP), creating a website that could effectively show and help us manage the real-time database.
Cross-correlation dynamics in financial time series
NASA Astrophysics Data System (ADS)
Conlon, T.; Ruskin, H. J.; Crane, M.
2009-03-01
The dynamics of the equal-time cross-correlation matrix of multivariate financial time series is explored by examination of the eigenvalue spectrum over sliding time windows. Empirical results for the S&P 500 and the Dow Jones Euro Stoxx 50 indices reveal that the dynamics of the small eigenvalues of the cross-correlation matrix, over these time windows, oppose those of the largest eigenvalue. This behaviour is shown to be independent of the size of the time window and the number of stocks examined. A basic one-factor model is then proposed, which captures the main dynamical features of the eigenvalue spectrum of the empirical data. Through the addition of perturbations to the one-factor model, (leading to a ‘market plus sectors’ model), additional sectoral features are added, resulting in an Inverse Participation Ratio comparable to that found for empirical data. By partitioning the eigenvalue time series, we then show that negative index returns, ( drawdowns), are associated with periods where the largest eigenvalue is greatest, while positive index returns, ( drawups), are associated with periods where the largest eigenvalue is smallest. The study of correlation dynamics provides some insight on the collective behaviour of traders with varying strategies.
Hydroxyl time series and recirculation in turbulent nonpremixed swirling flames
Guttenfelder, Walter A.; Laurendeau, Normand M.; Ji, Jun; King, Galen B.; Gore, Jay P.; Renfro, Michael W.
2006-10-15
Time-series measurements of OH, as related to accompanying flow structures, are reported using picosecond time-resolved laser-induced fluorescence (PITLIF) and particle-imaging velocimetry (PIV) for turbulent, swirling, nonpremixed methane-air flames. The [OH] data portray a primary reaction zone surrounding the internal recirculation zone, with residual OH in the recirculation zone approaching chemical equilibrium. Modeling of the OH electronic quenching environment, when compared to fluorescence lifetime measurements, offers additional evidence that the reaction zone burns as a partially premixed flame. A time-series analysis affirms the presence of thin flamelet-like regions based on the relation between swirl-induced turbulence and fluctuations of [OH] in the reaction and recirculation zones. The OH integral time-scales are found to correspond qualitatively to local mean velocities. Furthermore, quantitative dependencies can be established with respect to axial position, Reynolds number, and global equivalence ratio. Given these relationships, the OH time-scales, and thus the primary reaction zone, appear to be dominated by convection-driven fluctuations. Surprisingly, the OH time-scales for these nominally swirling flames demonstrate significant similarities to previous PITLIF results in nonpremixed jet flames. (author)
Robust, automatic GPS station velocities and velocity time series
NASA Astrophysics Data System (ADS)
Blewitt, G.; Kreemer, C.; Hammond, W. C.
2014-12-01
Automation in GPS coordinate time series analysis makes results more objective and reproducible, but not necessarily as robust as the human eye to detect problems. Moreover, it is not a realistic option to manually scan our current load of >20,000 time series per day. This motivates us to find an automatic way to estimate station velocities that is robust to outliers, discontinuities, seasonality, and noise characteristics (e.g., heteroscedasticity). Here we present a non-parametric method based on the Theil-Sen estimator, defined as the median of velocities vij=(xj-xi)/(tj-ti) computed between all pairs (i, j). Theil-Sen estimators produce statistically identical solutions to ordinary least squares for normally distributed data, but they can tolerate up to 29% of data being problematic. To mitigate seasonality, our proposed estimator only uses pairs approximately separated by an integer number of years (N-δt)<(tj-ti )<(N+δt), where δt is chosen to be small enough to capture seasonality, yet large enough to reduce random error. We fix N=1 to maximally protect against discontinuities. In addition to estimating an overall velocity, we also use these pairs to estimate velocity time series. To test our methods, we process real data sets that have already been used with velocities published in the NA12 reference frame. Accuracy can be tested by the scatter of horizontal velocities in the North American plate interior, which is known to be stable to ~0.3 mm/yr. This presents new opportunities for time series interpretation. For example, the pattern of velocity variations at the interannual scale can help separate tectonic from hydrological processes. Without any step detection, velocity estimates prove to be robust for stations affected by the Mw7.2 2010 El Mayor-Cucapah earthquake, and velocity time series show a clear change after the earthquake, without any of the usual parametric constraints, such as relaxation of postseismic velocities to their preseismic values.
Analyzing Exoplanet Time-Series Data with the VARTOOLS program
NASA Astrophysics Data System (ADS)
Hartman, Joel D.
2015-08-01
VARTOOLS is a publicly available command-line tool for analyzing astronomical time series data. Its primary use is in batch processing light curves from transit surveys. It includes commands for detecting transit signals and other periodic phenomena, for filtering light curves, simulating light curves with time-correlated noise, simulating transit light curves, fitting transit models (or other generic models) to light curves, calculating variability statistics, and many other features. A mechanism is available for users to incorporate their own commands into the program. Examples will be presented of using the program to search light curves for transiting planets, and to determine the detection efficiency of a transit survey.
Optimal model-free prediction from multivariate time series
NASA Astrophysics Data System (ADS)
Runge, Jakob; Donner, Reik V.; Kurths, Jürgen
2015-04-01
Forecasting a complex system's time evolution constitutes a challenging problem, especially if the governing physical equations are unknown or too complex to be simulated with first-principle models. Here a model-free prediction scheme based on the observed multivariate time series is discussed. It efficiently overcomes the curse of dimensionality in finding good predictors from large data sets and yields information-theoretically optimal predictors. The practical performance of the prediction scheme is demonstrated on multivariate nonlinear stochastic delay processes and in an application to an index of El Nino-Southern Oscillation.
Time-series animation techniques for visualizing urban growth
Acevedo, W.; Masuoka, P.
1997-01-01
Time-series animation is a visually intuitive way to display urban growth. Animations of landuse change for the Baltimore-Washington region were generated by showing a series of images one after the other in sequential order. Before creating an animation, various issues which will affect the appearance of the animation should be considered, including the number of original data frames to use, the optimal animation display speed, the number of intermediate frames to create between the known frames, and the output media on which the animations will be displayed. To create new frames between the known years of data, the change in each theme (i.e. urban development, water bodies, transportation routes) must be characterized and an algorithm developed to create the in-between frames. Example time-series animations were created using a temporal GIS database of the Baltimore-Washington area. Creating the animations involved generating raster images of the urban development, water bodies, and principal transportation routes; overlaying the raster images on a background image; and importing the frames to a movie file. Three-dimensional perspective animations were created by draping each image over digital elevation data prior to importing the frames to a movie file. ?? 1997 Elsevier Science Ltd.
Nonlinear time-series-based adaptive control applications
NASA Technical Reports Server (NTRS)
Mohler, R. R.; Rajkumar, V.; Zakrzewski, R. R.
1991-01-01
A control design methodology based on a nonlinear time-series reference model is presented. It is indicated by highly nonlinear simulations that such designs successfully stabilize troublesome aircraft maneuvers undergoing large changes in angle of attack as well as large electric power transients due to line faults. In both applications, the nonlinear controller was significantly better than the corresponding linear adaptive controller. For the electric power network, a flexible AC transmission system with series capacitor power feedback control is studied. A bilinear autoregressive moving average reference model is identified from system data, and the feedback control is manipulated according to a desired reference state. The control is optimized according to a predictive one-step quadratic performance index. A similar algorithm is derived for control of rapid changes in aircraft angle of attack over a normally unstable flight regime. In the latter case, however, a generalization of a bilinear time-series model reference includes quadratic and cubic terms in angle of attack.
Unraveling the cause-effect relation between time series.
Liang, X San
2014-11-01
Given two time series, can one faithfully tell, in a rigorous and quantitative way, the cause and effect between them? Based on a recently rigorized physical notion, namely, information flow, we solve an inverse problem and give this important and challenging question, which is of interest in a wide variety of disciplines, a positive answer. Here causality is measured by the time rate of information flowing from one series to the other. The resulting formula is tight in form, involving only commonly used statistics, namely, sample covariances; an immediate corollary is that causation implies correlation, but correlation does not imply causation. It has been validated with touchstone linear and nonlinear series, purportedly generated with one-way causality that evades the traditional approaches. It has also been applied successfully to the investigation of real-world problems; an example presented here is the cause-and-effect relation between the two climate modes, El Niño and the Indian Ocean Dipole (IOD), which have been linked to hazards in far-flung regions of the globe. In general, the two modes are mutually causal, but the causality is asymmetric: El Niño tends to stabilize IOD, while IOD functions to make El Niño more uncertain. To El Niño, the information flowing from IOD manifests itself as a propagation of uncertainty from the Indian Ocean.
Connectionist Architectures for Time Series Prediction of Dynamical Systems
NASA Astrophysics Data System (ADS)
Weigend, Andreas Sebastian
We investigate the effectiveness of connectionist networks for predicting the future continuation of temporal sequences. The problem of overfitting, particularly serious for short records of noisy data, is addressed by the method of weight-elimination: a term penalizing network complexity is added to the usual cost function in back-propagation. We describe the dynamics of the procedure and clarify the meaning of the parameters involved. From a Bayesian perspective, the complexity term can be usefully interpreted as an assumption about prior distribution of the weights. We analyze three time series. On the benchmark sunspot series, the networks outperform traditional statistical approaches. We show that the network performance does not deteriorate when there are more input units than needed. In the second example, the notoriously noisy foreign exchange rates series, we pick one weekday and one currency (DM vs. US). Given exchange rate information up to and including a Monday, the task is to predict the rate for the following Tuesday. Weight-elimination manages to extract a significant part of the dynamics and makes the solution interpretable. In the third example, the networks predict the resource utilization of a chaotic computational ecosystem for hundreds of steps forward in time.
Physical Database Design for Efficient Time-Series Similarity Search
NASA Astrophysics Data System (ADS)
Kim, Sang-Wook; Kim, Jinho; Park, Sanghyun
Similarity search in time-series databases finds such data sequences whose changing patterns are similar to that of a query sequence. For efficient processing, it normally employs a multi-dimensional index. In order to alleviate the well-known dimensionality curse, the previous methods for similarity search apply the Discrete Fourier Transform (DFT) to data sequences, and take only the first two or three DFT coefficients as organizing attributes. Other than this ad-hoc approach, there have been no research efforts on devising a systematic guideline for choosing the best organizing attributes. This paper first points out the problems occurring in the previous methods, and proposes a novel solution to construct optimal multi-dimensional indexes. The proposed method analyzes the characteristics of a target time-series database, and identifies the organizing attributes having the best discrimination power. It also determines the optimal number of organizing attributes for efficient similarity search by using a cost model. Through a series of experiments, we show that the proposed method outperforms the previous ones significantly.
Studies in Astronomical Time Series Analysis. VI. Bayesian Block Representations
NASA Technical Reports Server (NTRS)
Scargle, Jeffrey D.; Norris, Jay P.; Jackson, Brad; Chiang, James
2013-01-01
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it-an improved and generalized version of Bayesian Blocks [Scargle 1998]-that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piece- wise linear and piecewise exponential representations, multivariate time series data, analysis of variance, data on the circle, other data modes, and dispersed data. Simulations provide evidence that the detection efficiency for weak signals is close to a theoretical asymptotic limit derived by [Arias-Castro, Donoho and Huo 2003]. In the spirit of Reproducible Research [Donoho et al. (2008)] all of the code and data necessary to reproduce all of the figures in this paper are included as auxiliary material.
STUDIES IN ASTRONOMICAL TIME SERIES ANALYSIS. VI. BAYESIAN BLOCK REPRESENTATIONS
Scargle, Jeffrey D.; Norris, Jay P.; Jackson, Brad; Chiang, James
2013-02-20
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it-an improved and generalized version of Bayesian Blocks-that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piecewise linear and piecewise exponential representations, multivariate time series data, analysis of variance, data on the circle, other data modes, and dispersed data. Simulations provide evidence that the detection efficiency for weak signals is close to a theoretical asymptotic limit derived by Arias-Castro et al. In the spirit of Reproducible Research all of the code and data necessary to reproduce all of the figures in this paper are included as supplementary material.
Time-Series Analysis of Supergranule Characterstics at Solar Minimum
NASA Technical Reports Server (NTRS)
Williams, Peter E.; Pesnell, W. Dean
2013-01-01
Sixty days of Doppler images from the Solar and Heliospheric Observatory (SOHO) / Michelson Doppler Imager (MDI) investigation during the 1996 and 2008 solar minima have been analyzed to show that certain supergranule characteristics (size, size range, and horizontal velocity) exhibit fluctuations of three to five days. Cross-correlating parameters showed a good, positive correlation between supergranulation size and size range, and a moderate, negative correlation between size range and velocity. The size and velocity do exhibit a moderate, negative correlation, but with a small time lag (less than 12 hours). Supergranule sizes during five days of co-temporal data from MDI and the Solar Dynamics Observatory (SDO) / Helioseismic Magnetic Imager (HMI) exhibit similar fluctuations with a high level of correlation between them. This verifies the solar origin of the fluctuations, which cannot be caused by instrumental artifacts according to these observations. Similar fluctuations are also observed in data simulations that model the evolution of the MDI Doppler pattern over a 60-day period. Correlations between the supergranule size and size range time-series derived from the simulated data are similar to those seen in MDI data. A simple toy-model using cumulative, uncorrelated exponential growth and decay patterns at random emergence times produces a time-series similar to the data simulations. The qualitative similarities between the simulated and the observed time-series suggest that the fluctuations arise from stochastic processes occurring within the solar convection zone. This behavior, propagating to surface manifestations of supergranulation, may assist our understanding of magnetic-field-line advection, evolution, and interaction.
Root System Water Consumption Pattern Identification on Time Series Data.
Figueroa, Manuel; Pope, Christopher
2017-06-16
In agriculture, soil and meteorological sensors are used along low power networks to capture data, which allows for optimal resource usage and minimizing environmental impact. This study uses time series analysis methods for outliers' detection and pattern recognition on soil moisture sensor data to identify irrigation and consumption patterns and to improve a soil moisture prediction and irrigation system. This study compares three new algorithms with the current detection technique in the project; the results greatly decrease the number of false positives detected. The best result is obtained by the Series Strings Comparison (SSC) algorithm averaging a precision of 0.872 on the testing sets, vastly improving the current system's 0.348 precision.
Inverse sequential procedures for the monitoring of time series
NASA Technical Reports Server (NTRS)
Radok, Uwe; Brown, Timothy J.
1995-01-01
When one or more new values are added to a developing time series, they change its descriptive parameters (mean, variance, trend, coherence). A 'change index (CI)' is developed as a quantitative indicator that the changed parameters remain compatible with the existing 'base' data. CI formulate are derived, in terms of normalized likelihood ratios, for small samples from Poisson, Gaussian, and Chi-Square distributions, and for regression coefficients measuring linear or exponential trends. A substantial parameter change creates a rapid or abrupt CI decrease which persists when the length of the bases is changed. Except for a special Gaussian case, the CI has no simple explicit regions for tests of hypotheses. However, its design ensures that the series sampled need not conform strictly to the distribution form assumed for the parameter estimates. The use of the CI is illustrated with both constructed and observed data samples, processed with a Fortran code 'Sequitor'.
AQUAdexIM: highly efficient in-memory indexing and querying of astronomy time series images
NASA Astrophysics Data System (ADS)
Hong, Zhi; Yu, Ce; Wang, Jie; Xiao, Jian; Cui, Chenzhou; Sun, Jizhou
2016-12-01
Astronomy has always been, and will continue to be, a data-based science, and astronomers nowadays are faced with increasingly massive datasets, one key problem of which is to efficiently retrieve the desired cup of data from the ocean. AQUAdexIM, an innovative spatial indexing and querying method, performs highly efficient on-the-fly queries under users' request to search for Time Series Images from existing observation data on the server side and only return the desired FITS images to users, so users no longer need to download entire datasets to their local machines, which will only become more and more impractical as the data size keeps increasing. Moreover, AQUAdexIM manages to keep a very low storage space overhead and its specially designed in-memory index structure enables it to search for Time Series Images of a given area of the sky 10 times faster than using Redis, a state-of-the-art in-memory database.
Characterizing weak chaos using time series of Lyapunov exponents.
da Silva, R M; Manchein, C; Beims, M W; Altmann, E G
2015-06-01
We investigate chaos in mixed-phase-space Hamiltonian systems using time series of the finite-time Lyapunov exponents. The methodology we propose uses the number of Lyapunov exponents close to zero to define regimes of ordered (stickiness), semiordered (or semichaotic), and strongly chaotic motion. The dynamics is then investigated looking at the consecutive time spent in each regime, the transition between different regimes, and the regions in the phase space associated to them. Applying our methodology to a chain of coupled standard maps we obtain (i) that it allows for an improved numerical characterization of stickiness in high-dimensional Hamiltonian systems, when compared to the previous analyses based on the distribution of recurrence times; (ii) that the transition probabilities between different regimes are determined by the phase-space volume associated to the corresponding regions; and (iii) the dependence of the Lyapunov exponents with the coupling strength.
Monitoring Forest Regrowth Using a Multi-Platform Time Series
NASA Technical Reports Server (NTRS)
Sabol, Donald E., Jr.; Smith, Milton O.; Adams, John B.; Gillespie, Alan R.; Tucker, Compton J.
1996-01-01
Over the past 50 years, the forests of western Washington and Oregon have been extensively harvested for timber. This has resulted in a heterogeneous mosaic of remaining mature forests, clear-cuts, new plantations, and second-growth stands that now occur in areas that formerly were dominated by extensive old-growth forests and younger forests resulting from fire disturbance. Traditionally, determination of seral stage and stand condition have been made using aerial photography and spot field observations, a methodology that is not only time- and resource-intensive, but falls short of providing current information on a regional scale. These limitations may be solved, in part, through the use of multispectral images which can cover large areas at spatial resolutions in the order of tens of meters. The use of multiple images comprising a time series potentially can be used to monitor land use (e.g. cutting and replanting), and to observe natural processes such as regeneration, maturation and phenologic change. These processes are more likely to be spectrally observed in a time series composed of images taken during different seasons over a long period of time. Therefore, for many areas, it may be necessary to use a variety of images taken with different imaging systems. A common framework for interpretation is needed that reduces topographic, atmospheric, instrumental, effects as well as differences in lighting geometry between images. The present state of remote-sensing technology in general use does not realize the full potential of the multispectral data in areas of high topographic relief. For example, the primary method for analyzing images of forested landscapes in the Northwest has been with statistical classifiers (e.g. parallelepiped, nearest-neighbor, maximum likelihood, etc.), often applied to uncalibrated multispectral data. Although this approach has produced useful information from individual images in some areas, landcover classes defined by these
Monitoring Forest Regrowth Using a Multi-Platform Time Series
NASA Technical Reports Server (NTRS)
Sabol, Donald E., Jr.; Smith, Milton O.; Adams, John B.; Gillespie, Alan R.; Tucker, Compton J.
1996-01-01
Over the past 50 years, the forests of western Washington and Oregon have been extensively harvested for timber. This has resulted in a heterogeneous mosaic of remaining mature forests, clear-cuts, new plantations, and second-growth stands that now occur in areas that formerly were dominated by extensive old-growth forests and younger forests resulting from fire disturbance. Traditionally, determination of seral stage and stand condition have been made using aerial photography and spot field observations, a methodology that is not only time- and resource-intensive, but falls short of providing current information on a regional scale. These limitations may be solved, in part, through the use of multispectral images which can cover large areas at spatial resolutions in the order of tens of meters. The use of multiple images comprising a time series potentially can be used to monitor land use (e.g. cutting and replanting), and to observe natural processes such as regeneration, maturation and phenologic change. These processes are more likely to be spectrally observed in a time series composed of images taken during different seasons over a long period of time. Therefore, for many areas, it may be necessary to use a variety of images taken with different imaging systems. A common framework for interpretation is needed that reduces topographic, atmospheric, instrumental, effects as well as differences in lighting geometry between images. The present state of remote-sensing technology in general use does not realize the full potential of the multispectral data in areas of high topographic relief. For example, the primary method for analyzing images of forested landscapes in the Northwest has been with statistical classifiers (e.g. parallelepiped, nearest-neighbor, maximum likelihood, etc.), often applied to uncalibrated multispectral data. Although this approach has produced useful information from individual images in some areas, landcover classes defined by these
ERIC Educational Resources Information Center
Ngan, Chun-Kit
2013-01-01
Making decisions over multivariate time series is an important topic which has gained significant interest in the past decade. A time series is a sequence of data points which are measured and ordered over uniform time intervals. A multivariate time series is a set of multiple, related time series in a particular domain in which domain experts…
ERIC Educational Resources Information Center
Ngan, Chun-Kit
2013-01-01
Making decisions over multivariate time series is an important topic which has gained significant interest in the past decade. A time series is a sequence of data points which are measured and ordered over uniform time intervals. A multivariate time series is a set of multiple, related time series in a particular domain in which domain experts…
Remote-Sensing Time Series Analysis, a Vegetation Monitoring Tool
NASA Technical Reports Server (NTRS)
McKellip, Rodney; Prados, Donald; Ryan, Robert; Ross, Kenton; Spruce, Joseph; Gasser, Gerald; Greer, Randall
2008-01-01
The Time Series Product Tool (TSPT) is software, developed in MATLAB , which creates and displays high signal-to- noise Vegetation Indices imagery and other higher-level products derived from remotely sensed data. This tool enables automated, rapid, large-scale regional surveillance of crops, forests, and other vegetation. TSPT temporally processes high-revisit-rate satellite imagery produced by the Moderate Resolution Imaging Spectroradiometer (MODIS) and by other remote-sensing systems. Although MODIS imagery is acquired daily, cloudiness and other sources of noise can greatly reduce the effective temporal resolution. To improve cloud statistics, the TSPT combines MODIS data from multiple satellites (Aqua and Terra). The TSPT produces MODIS products as single time-frame and multitemporal change images, as time-series plots at a selected location, or as temporally processed image videos. Using the TSPT program, MODIS metadata is used to remove and/or correct bad and suspect data. Bad pixel removal, multiple satellite data fusion, and temporal processing techniques create high-quality plots and animated image video sequences that depict changes in vegetation greenness. This tool provides several temporal processing options not found in other comparable imaging software tools. Because the framework to generate and use other algorithms is established, small modifications to this tool will enable the use of a large range of remotely sensed data types. An effective remote-sensing crop monitoring system must be able to detect subtle changes in plant health in the earliest stages, before the effects of a disease outbreak or other adverse environmental conditions can become widespread and devastating. The integration of the time series analysis tool with ground-based information, soil types, crop types, meteorological data, and crop growth models in a Geographic Information System, could provide the foundation for a large-area crop-surveillance system that could identify
Homogenization of historical time series on a subdaily scale
NASA Astrophysics Data System (ADS)
Kocen, Renate; Brönnimann, Stefan; Breda, Leila; Spadin, Reto; Begert, Michael; Füllemann, Christine
2010-05-01
Homogeneous long-term climatological time series provide useful information on climate back to the preindustrial era. High temporal resolution of climate data is desirable to address trends and variability in the mean climate and in climatic extremes. For Switzerland, three long (~250 yrs) historical time series (Basel, Geneva, Gr. St. Bernhard) that were hitherto available in the form of monthly means only have recently been digitized (in cooperation with MeteoSwiss) on a subdaily scale. The digitized time series contain subdaily data (varies from 2-5 daily measurements) on temperature, precipitation/snow height, pressure and humidity, as subdaily descriptions on wind direction, wind speeds and cloud cover. Long-term climatological records often contain inhomogeneities due to non climatic changes such as station relocations, changes in instrumentation and instrument exposure, changes in observing schedules/practices and environmental changes in the proximity of the observation site. Those disturbances can distort or hide the true climatic signal and could seriously affect the correct assessment and analysis of climate trends, variability and climatic extremes. It is therefore crucial to detect and eliminate artificial shifts and trends, to the extent possible, in the climate data prior to its application. Detailed information of the station history and instruments (metadata) can be of fundamental importance in the process of homogenization in order to support the determination of the exact time of inhomogeneities and the interpretation of statistical test results. While similar methods can be used for the detection of inhomogeneities in subdaily or monthly mean data, quite different correction methods can be chosen. The wealth of information in a high temporal resolution allows more physics-based correction methods. For instance, a detected radiation error in temperature can be corrected with an error model that incorporates radiation and ventilation terms using
Loading effects in GPS vertical displacement time series
NASA Astrophysics Data System (ADS)
Memin, A.; Boy, J. P.; Santamaría-Gómez, A.; Watson, C.; Gravelle, M.; Tregoning, P.
2015-12-01
Surface deformations due to loading, with yet no comprehensive representation, account for a significant part of the variability in geodetic time series. We assess effects of loading in GPS vertical displacement time series at several frequency bands. We compare displacement derived from up-to-date loading models to two global sets of positioning time series, and investigate how they are reduced looking at interannual periods (> 2 months), intermediate periods (> 7 days) and the whole spectrum (> 1day). We assess the impact of interannual loading on estimating velocities. We compute atmospheric loading effects using surface pressure fields from the ECMWF. We use the inverted barometer (IB) hypothesis valid for periods exceeding a week to describe the ocean response to the pressure forcing. We used general circulation ocean model (ECCO and GLORYS) to account for wind, heat and fresh water flux. We separately use the Toulouse Unstructured Grid Ocean model (TUGO-m), forced by air pressure and winds, to represent the dynamics of the ocean response at high frequencies. The continental water storage is described using GLDAS/Noah and MERRA-land models. Non-hydrology loading reduces the variability of the observed vertical displacement differently according to the frequency band. The hydrology loading leads to a further reduction mostly at annual periods. ECMWF+TUGO-m better agrees with vertical surface motion than the ECMWF+IB model at all frequencies. The interannual deformation is time-correlated at most of the locations. It is adequately described by a power-law process of spectral index varying from -1.5 to -0.2. Depending on the power-law parameters, the predicted non-linear deformation due to mass loading variations leads to vertical velocity biases up to 0.7 mm/yr when estimated from 5 years of continuous observations. The maximum velocity bias can reach up to 1 mm/yr in regions around the southern Tropical band.
Discovering significant evolution patterns from satellite image time series.
Petitjean, François; Masseglia, Florent; Gançarski, Pierre; Forestier, Germain
2011-12-01
Satellite Image Time Series (SITS) provide us with precious information on land cover evolution. By studying these series of images we can both understand the changes of specific areas and discover global phenomena that spread over larger areas. Changes that can occur throughout the sensing time can spread over very long periods and may have different start time and end time depending on the location, which complicates the mining and the analysis of series of images. This work focuses on frequent sequential pattern mining (FSPM) methods, since this family of methods fits the above-mentioned issues. This family of methods consists of finding the most frequent evolution behaviors, and is actually able to extract long-term changes as well as short term ones, whenever the change may start and end. However, applying FSPM methods to SITS implies confronting two main challenges, related to the characteristics of SITS and the domain's constraints. First, satellite images associate multiple measures with a single pixel (the radiometric levels of different wavelengths corresponding to infra-red, red, etc.), which makes the search space multi-dimensional and thus requires specific mining algorithms. Furthermore, the non evolving regions, which are the vast majority and overwhelm the evolving ones, challenge the discovery of these patterns. We propose a SITS mining framework that enables discovery of these patterns despite these constraints and characteristics. Our proposal is inspired from FSPM and provides a relevant visualization principle. Experiments carried out on 35 images sensed over 20 years show the proposed approach makes it possible to extract relevant evolution behaviors.
Detecting switching and intermittent causalities in time series
NASA Astrophysics Data System (ADS)
Zanin, Massimiliano; Papo, David
2017-04-01
During the last decade, complex network representations have emerged as a powerful instrument for describing the cross-talk between different brain regions both at rest and as subjects are carrying out cognitive tasks, in healthy brains and neurological pathologies. The transient nature of such cross-talk has nevertheless by and large been neglected, mainly due to the inherent limitations of some metrics, e.g., causality ones, which require a long time series in order to yield statistically significant results. Here, we present a methodology to account for intermittent causal coupling in neural activity, based on the identification of non-overlapping windows within the original time series in which the causality is strongest. The result is a less coarse-grained assessment of the time-varying properties of brain interactions, which can be used to create a high temporal resolution time-varying network. We apply the proposed methodology to the analysis of the brain activity of control subjects and alcoholic patients performing an image recognition task. Our results show that short-lived, intermittent, local-scale causality is better at discriminating both groups than global network metrics. These results highlight the importance of the transient nature of brain activity, at least under some pathological conditions.
Long-term time series prediction using OP-ELM.
Grigorievskiy, Alexander; Miche, Yoan; Ventelä, Anne-Mari; Séverin, Eric; Lendasse, Amaury
2014-03-01
In this paper, an Optimally Pruned Extreme Learning Machine (OP-ELM) is applied to the problem of long-term time series prediction. Three known strategies for the long-term time series prediction i.e. Recursive, Direct and DirRec are considered in combination with OP-ELM and compared with a baseline linear least squares model and Least-Squares Support Vector Machines (LS-SVM). Among these three strategies DirRec is the most time consuming and its usage with nonlinear models like LS-SVM, where several hyperparameters need to be adjusted, leads to relatively heavy computations. It is shown that OP-ELM, being also a nonlinear model, allows reasonable computational time for the DirRec strategy. In all our experiments, except one, OP-ELM with DirRec strategy outperforms the linear model with any strategy. In contrast to the proposed algorithm, LS-SVM behaves unstably without variable selection. It is also shown that there is no superior strategy for OP-ELM: any of three can be the best. In addition, the prediction accuracy of an ensemble of OP-ELM is studied and it is shown that averaging predictions of the ensemble can improve the accuracy (Mean Square Error) dramatically. Copyright © 2013 Elsevier Ltd. All rights reserved.
Improvement in global forecast for chaotic time series
NASA Astrophysics Data System (ADS)
Alves, P. R. L.; Duarte, L. G. S.; da Mota, L. A. C. P.
2016-10-01
In the Polynomial Global Approach to Time Series Analysis, the most costly (computationally speaking) step is the finding of the fitting polynomial. Here we present two routines that improve the forecasting. In the first, an algorithm that greatly improves this situation is introduced and implemented. The heart of this procedure is implemented on the specific routine which performs a mapping with great efficiency. In comparison with the similar procedure of the TimeS package developed by Carli et al. (2014), an enormous gain in efficiency and an increasing in accuracy are obtained. Another development in this work is the establishment of a level of confidence in global prediction with a statistical test for evaluating if the minimization performed is suitable or not. The other program presented in this article applies the Shapiro-Wilk test for checking the normality of the distribution of errors and calculates the expected deviation. The development is employed in observed and simulated time series to illustrate the performance obtained.
Weighted statistical parameters for irregularly sampled time series
NASA Astrophysics Data System (ADS)
Rimoldini, Lorenzo
2014-01-01
Unevenly spaced time series are common in astronomy because of the day-night cycle, weather conditions, dependence on the source position in the sky, allocated telescope time and corrupt measurements, for example, or inherent to the scanning law of satellites like Hipparcos and the forthcoming Gaia. Irregular sampling often causes clumps of measurements and gaps with no data which can severely disrupt the values of estimators. This paper aims at improving the accuracy of common statistical parameters when linear interpolation (in time or phase) can be considered an acceptable approximation of a deterministic signal. A pragmatic solution is formulated in terms of a simple weighting scheme, adapting to the sampling density and noise level, applicable to large data volumes at minimal computational cost. Tests on time series from the Hipparcos periodic catalogue led to significant improvements in the overall accuracy and precision of the estimators with respect to the unweighted counterparts and those weighted by inverse-squared uncertainties. Automated classification procedures employing statistical parameters weighted by the suggested scheme confirmed the benefits of the improved input attributes. The classification of eclipsing binaries, Mira, RR Lyrae, Delta Cephei and Alpha2 Canum Venaticorum stars employing exclusively weighted descriptive statistics achieved an overall accuracy of 92 per cent, about 6 per cent higher than with unweighted estimators.
NASA Astrophysics Data System (ADS)
Prasia, P.; Kuriakose, V. C.
2017-01-01
In this work we study the Quasi-Normal Modes (QNMs) under massless scalar perturbations and the thermodynamics of linearly charged BTZ black holes in massive gravity in the (Anti)de Sitter ((A)dS) space-time. It is found that the behavior of QNMs changes with the massive parameter of the graviton and also with the charge of the black hole. The thermodynamics of such black holes in the (A)dS space-time is also analyzed in detail. The behavior of specific heat with temperature for such black holes gives an indication of a phase transition that depends on the massive parameter of the graviton and also on the charge of the black hole.
Connecting real-time properties of the massless Schwinger model to the massive case
NASA Astrophysics Data System (ADS)
Hebenstreit, F.; Berges, J.
2014-08-01
Quantum electrodynamics in 1+1 space-time dimensions is analytically solvable for massless fermions, while no solution is known for massive fermions. Employing the classical-statistical approach, we simulate the real-time dynamics on a lattice using Wilson fermions with mass m at gauge coupling g. It is shown that quantitative properties of the massless Schwinger model are emerging in the limit of large g/m. We investigate two scenarios corresponding to opposite charges which are either held fixed or moving back-to-back along the light cone, as employed in effective descriptions for jet energy loss and photon production in the context of heavy-ion collisions. Remarkably, we find that the dynamics is rather well described by the massless limit for a wide range of mass values at fixed coupling. Moreover, our study shows that previous approximate scenarios with external charges on the light cone rather accurately capture the self-consistent dynamics of the energy conserving simulation.