Directory of Open Access Journals (Sweden)
R. Caballero-Águila
2014-01-01
Full Text Available The optimal least-squares linear estimation problem is addressed for a class of discrete-time multisensor linear stochastic systems subject to randomly delayed measurements with different delay rates. For each sensor, a different binary sequence is used to model the delay process. The measured outputs are perturbed by both random parameter matrices and one-step autocorrelated and cross correlated noises. Using an innovation approach, computationally simple recursive algorithms are obtained for the prediction, filtering, and smoothing problems, without requiring full knowledge of the state-space model generating the signal process, but only the information provided by the delay probabilities and the mean and covariance functions of the processes (signal, random parameter matrices, and noises involved in the observation model. The accuracy of the estimators is measured by their error covariance matrices, which allow us to analyze the estimator performance in a numerical simulation example that illustrates the feasibility of the proposed algorithms.
A Robust Adaptive Unscented Kalman Filter for Nonlinear Estimation with Uncertain Noise Covariance.
Zheng, Binqi; Fu, Pengcheng; Li, Baoqing; Yuan, Xiaobing
2018-03-07
The Unscented Kalman filter (UKF) may suffer from performance degradation and even divergence while mismatch between the noise distribution assumed as a priori by users and the actual ones in a real nonlinear system. To resolve this problem, this paper proposes a robust adaptive UKF (RAUKF) to improve the accuracy and robustness of state estimation with uncertain noise covariance. More specifically, at each timestep, a standard UKF will be implemented first to obtain the state estimations using the new acquired measurement data. Then an online fault-detection mechanism is adopted to judge if it is necessary to update current noise covariance. If necessary, innovation-based method and residual-based method are used to calculate the estimations of current noise covariance of process and measurement, respectively. By utilizing a weighting factor, the filter will combine the last noise covariance matrices with the estimations as the new noise covariance matrices. Finally, the state estimations will be corrected according to the new noise covariance matrices and previous state estimations. Compared with the standard UKF and other adaptive UKF algorithms, RAUKF converges faster to the actual noise covariance and thus achieves a better performance in terms of robustness, accuracy, and computation for nonlinear estimation with uncertain noise covariance, which is demonstrated by the simulation results.
Noisy covariance matrices and portfolio optimization II
Pafka, Szilárd; Kondor, Imre
2003-03-01
Recent studies inspired by results from random matrix theory (Galluccio et al.: Physica A 259 (1998) 449; Laloux et al.: Phys. Rev. Lett. 83 (1999) 1467; Risk 12 (3) (1999) 69; Plerou et al.: Phys. Rev. Lett. 83 (1999) 1471) found that covariance matrices determined from empirical financial time series appear to contain such a high amount of noise that their structure can essentially be regarded as random. This seems, however, to be in contradiction with the fundamental role played by covariance matrices in finance, which constitute the pillars of modern investment theory and have also gained industry-wide applications in risk management. Our paper is an attempt to resolve this embarrassing paradox. The key observation is that the effect of noise strongly depends on the ratio r= n/ T, where n is the size of the portfolio and T the length of the available time series. On the basis of numerical experiments and analytic results for some toy portfolio models we show that for relatively large values of r (e.g. 0.6) noise does, indeed, have the pronounced effect suggested by Galluccio et al. (1998), Laloux et al. (1999) and Plerou et al. (1999) and illustrated later by Laloux et al. (Int. J. Theor. Appl. Finance 3 (2000) 391), Plerou et al. (Phys. Rev. E, e-print cond-mat/0108023) and Rosenow et al. (Europhys. Lett., e-print cond-mat/0111537) in a portfolio optimization context, while for smaller r (around 0.2 or below), the error due to noise drops to acceptable levels. Since the length of available time series is for obvious reasons limited in any practical application, any bound imposed on the noise-induced error translates into a bound on the size of the portfolio. In a related set of experiments we find that the effect of noise depends also on whether the problem arises in asset allocation or in a risk measurement context: if covariance matrices are used simply for measuring the risk of portfolios with a fixed composition rather than as inputs to optimization, the
MIMO-radar Waveform Covariance Matrices for High SINR and Low Side-lobe Levels
Ahmed, Sajid
2012-12-29
MIMO-radar has better parametric identifiability but compared to phased-array radar it shows loss in signal-to-noise ratio due to non-coherent processing. To exploit the benefits of both MIMO-radar and phased-array two transmit covariance matrices are found. Both of the covariance matrices yield gain in signal-to-interference-plus-noise ratio (SINR) compared to MIMO-radar and have lower side-lobe levels (SLL)\\'s compared to phased-array and MIMO-radar. Moreover, in contrast to recently introduced phased-MIMO scheme, where each antenna transmit different power, our proposed schemes allows same power transmission from each antenna. The SLL\\'s of the proposed first covariance matrix are higher than the phased-MIMO scheme while the SLL\\'s of the second proposed covariance matrix are lower than the phased-MIMO scheme. The first covariance matrix is generated using an auto-regressive process, which allow us to change the SINR and side lobe levels by changing the auto-regressive parameter, while to generate the second covariance matrix the values of sine function between 0 and $\\\\pi$ with the step size of $\\\\pi/n_T$ are used to form a positive-semidefinite Toeplitiz matrix, where $n_T$ is the number of transmit antennas. Simulation results validate our analytical results.
MIMO-radar Waveform Covariance Matrices for High SINR and Low Side-lobe Levels
Ahmed, Sajid; Alouini, Mohamed-Slim
2012-01-01
MIMO-radar has better parametric identifiability but compared to phased-array radar it shows loss in signal-to-noise ratio due to non-coherent processing. To exploit the benefits of both MIMO-radar and phased-array two transmit covariance matrices
Forecasting Covariance Matrices: A Mixed Frequency Approach
DEFF Research Database (Denmark)
Halbleib, Roxana; Voev, Valeri
This paper proposes a new method for forecasting covariance matrices of financial returns. The model mixes volatility forecasts from a dynamic model of daily realized volatilities estimated with high-frequency data with correlation forecasts based on daily data. This new approach allows for flexi......This paper proposes a new method for forecasting covariance matrices of financial returns. The model mixes volatility forecasts from a dynamic model of daily realized volatilities estimated with high-frequency data with correlation forecasts based on daily data. This new approach allows...... for flexible dependence patterns for volatilities and correlations, and can be applied to covariance matrices of large dimensions. The separate modeling of volatility and correlation forecasts considerably reduces the estimation and measurement error implied by the joint estimation and modeling of covariance...
Contributions to Large Covariance and Inverse Covariance Matrices Estimation
Kang, Xiaoning
2016-01-01
Estimation of covariance matrix and its inverse is of great importance in multivariate statistics with broad applications such as dimension reduction, portfolio optimization, linear discriminant analysis and gene expression analysis. However, accurate estimation of covariance or inverse covariance matrices is challenging due to the positive definiteness constraint and large number of parameters, especially in the high-dimensional cases. In this thesis, I develop several approaches for estimat...
Dimension from covariance matrices.
Carroll, T L; Byers, J M
2017-02-01
We describe a method to estimate embedding dimension from a time series. This method includes an estimate of the probability that the dimension estimate is valid. Such validity estimates are not common in algorithms for calculating the properties of dynamical systems. The algorithm described here compares the eigenvalues of covariance matrices created from an embedded signal to the eigenvalues for a covariance matrix of a Gaussian random process with the same dimension and number of points. A statistical test gives the probability that the eigenvalues for the embedded signal did not come from the Gaussian random process.
Flexible Bayesian Dynamic Modeling of Covariance and Correlation Matrices
Lan, Shiwei
2017-11-08
Modeling covariance (and correlation) matrices is a challenging problem due to the large dimensionality and positive-definiteness constraint. In this paper, we propose a novel Bayesian framework based on decomposing the covariance matrix into variance and correlation matrices. The highlight is that the correlations are represented as products of vectors on unit spheres. We propose a variety of distributions on spheres (e.g. the squared-Dirichlet distribution) to induce flexible prior distributions for covariance matrices that go beyond the commonly used inverse-Wishart prior. To handle the intractability of the resulting posterior, we introduce the adaptive $\\\\Delta$-Spherical Hamiltonian Monte Carlo. We also extend our structured framework to dynamic cases and introduce unit-vector Gaussian process priors for modeling the evolution of correlation among multiple time series. Using an example of Normal-Inverse-Wishart problem, a simulated periodic process, and an analysis of local field potential data (collected from the hippocampus of rats performing a complex sequence memory task), we demonstrated the validity and effectiveness of our proposed framework for (dynamic) modeling covariance and correlation matrices.
Physical properties of the Schur complement of local covariance matrices
International Nuclear Information System (INIS)
Haruna, L F; Oliveira, M C de
2007-01-01
General properties of global covariance matrices representing bipartite Gaussian states can be decomposed into properties of local covariance matrices and their Schur complements. We demonstrate that given a bipartite Gaussian state ρ 12 described by a 4 x 4 covariance matrix V, the Schur complement of a local covariance submatrix V 1 of it can be interpreted as a new covariance matrix representing a Gaussian operator of party 1 conditioned to local parity measurements on party 2. The connection with a partial parity measurement over a bipartite quantum state and the determination of the reduced Wigner function is given and an operational process of parity measurement is developed. Generalization of this procedure to an n-partite Gaussian state is given, and it is demonstrated that the n - 1 system state conditioned to a partial parity projection is given by a covariance matrix such that its 2 x 2 block elements are Schur complements of special local matrices
Hierarchical matrix approximation of large covariance matrices
Litvinenko, Alexander
2015-01-05
We approximate large non-structured covariance matrices in the H-matrix format with a log-linear computational cost and storage O(nlogn). We compute inverse, Cholesky decomposition and determinant in H-format. As an example we consider the class of Matern covariance functions, which are very popular in spatial statistics, geostatistics, machine learning and image analysis. Applications are: kriging and op- timal design.
Hierarchical matrix approximation of large covariance matrices
Litvinenko, Alexander; Genton, Marc G.; Sun, Ying; Tempone, Raul
2015-01-01
We approximate large non-structured covariance matrices in the H-matrix format with a log-linear computational cost and storage O(nlogn). We compute inverse, Cholesky decomposition and determinant in H-format. As an example we consider the class of Matern covariance functions, which are very popular in spatial statistics, geostatistics, machine learning and image analysis. Applications are: kriging and op- timal design.
Flexible Bayesian Dynamic Modeling of Covariance and Correlation Matrices
Lan, Shiwei; Holbrook, Andrew; Fortin, Norbert J.; Ombao, Hernando; Shahbaba, Babak
2017-01-01
Modeling covariance (and correlation) matrices is a challenging problem due to the large dimensionality and positive-definiteness constraint. In this paper, we propose a novel Bayesian framework based on decomposing the covariance matrix
Hierarchical matrix approximation of large covariance matrices
Litvinenko, Alexander
2015-01-07
We approximate large non-structured covariance matrices in the H-matrix format with a log-linear computational cost and storage O(n log n). We compute inverse, Cholesky decomposition and determinant in H-format. As an example we consider the class of Matern covariance functions, which are very popular in spatial statistics, geostatistics, machine learning and image analysis. Applications are: kriging and optimal design
Hierarchical matrix approximation of large covariance matrices
Litvinenko, Alexander; Genton, Marc G.; Sun, Ying; Tempone, Raul
2015-01-01
We approximate large non-structured covariance matrices in the H-matrix format with a log-linear computational cost and storage O(n log n). We compute inverse, Cholesky decomposition and determinant in H-format. As an example we consider the class of Matern covariance functions, which are very popular in spatial statistics, geostatistics, machine learning and image analysis. Applications are: kriging and optimal design
Some thoughts on positive definiteness in the consideration of nuclear data covariance matrices
Energy Technology Data Exchange (ETDEWEB)
Geraldo, L.P.; Smith, D.L.
1988-01-01
Some basic mathematical features of covariance matrices are reviewed, particularly as they relate to the property of positive difiniteness. Physical implications of positive definiteness are also discussed. Consideration is given to an examination of the origins of non-positive definite matrices, to procedures which encourage the generation of positive definite matrices and to the testing of covariance matrices for positive definiteness. Attention is also given to certain problems associated with the construction of covariance matrices using information which is obtained from evaluated data files recorded in the ENDF format. Examples are provided to illustrate key points pertaining to each of the topic areas covered.
Some thoughts on positive definiteness in the consideration of nuclear data covariance matrices
International Nuclear Information System (INIS)
Geraldo, L.P.; Smith, D.L.
1988-01-01
Some basic mathematical features of covariance matrices are reviewed, particularly as they relate to the property of positive difiniteness. Physical implications of positive definiteness are also discussed. Consideration is given to an examination of the origins of non-positive definite matrices, to procedures which encourage the generation of positive definite matrices and to the testing of covariance matrices for positive definiteness. Attention is also given to certain problems associated with the construction of covariance matrices using information which is obtained from evaluated data files recorded in the ENDF format. Examples are provided to illustrate key points pertaining to each of the topic areas covered
Spatiotemporal noise covariance estimation from limited empirical magnetoencephalographic data
International Nuclear Information System (INIS)
Jun, Sung C; Plis, Sergey M; Ranken, Doug M; Schmidt, David M
2006-01-01
The performance of parametric magnetoencephalography (MEG) and electroencephalography (EEG) source localization approaches can be degraded by the use of poor background noise covariance estimates. In general, estimation of the noise covariance for spatiotemporal analysis is difficult mainly due to the limited noise information available. Furthermore, its estimation requires a large amount of storage and a one-time but very large (and sometimes intractable) calculation or its inverse. To overcome these difficulties, noise covariance models consisting of one pair or a sum of multi-pairs of Kronecker products of spatial covariance and temporal covariance have been proposed. However, these approaches cannot be applied when the noise information is very limited, i.e., the amount of noise information is less than the degrees of freedom of the noise covariance models. A common example of this is when only averaged noise data are available for a limited prestimulus region (typically at most a few hundred milliseconds duration). For such cases, a diagonal spatiotemporal noise covariance model consisting of sensor variances with no spatial or temporal correlation has been the common choice for spatiotemporal analysis. In this work, we propose a different noise covariance model which consists of diagonal spatial noise covariance and Toeplitz temporal noise covariance. It can easily be estimated from limited noise information, and no time-consuming optimization and data-processing are required. Thus, it can be used as an alternative choice when one-pair or multi-pair noise covariance models cannot be estimated due to lack of noise information. To verify its capability we used Bayesian inference dipole analysis and a number of simulated and empirical datasets. We compared this covariance model with other existing covariance models such as conventional diagonal covariance, one-pair and multi-pair noise covariance models, when noise information is sufficient to estimate them. We
Data depth and rank-based tests for covariance and spectral density matrices
Chau, Joris
2017-06-26
In multivariate time series analysis, objects of primary interest to study cross-dependences in the time series are the autocovariance or spectral density matrices. Non-degenerate covariance and spectral density matrices are necessarily Hermitian and positive definite, and our primary goal is to develop new methods to analyze samples of such matrices. The main contribution of this paper is the generalization of the concept of statistical data depth for collections of covariance or spectral density matrices by exploiting the geometric properties of the space of Hermitian positive definite matrices as a Riemannian manifold. This allows one to naturally characterize most central or outlying matrices, but also provides a practical framework for rank-based hypothesis testing in the context of samples of covariance or spectral density matrices. First, the desired properties of a data depth function acting on the space of Hermitian positive definite matrices are presented. Second, we propose two computationally efficient pointwise and integrated data depth functions that satisfy each of these requirements. Several applications of the developed methodology are illustrated by the analysis of collections of spectral matrices in multivariate brain signal time series datasets.
Data depth and rank-based tests for covariance and spectral density matrices
Chau, Joris; Ombao, Hernando; Sachs, Rainer von
2017-01-01
In multivariate time series analysis, objects of primary interest to study cross-dependences in the time series are the autocovariance or spectral density matrices. Non-degenerate covariance and spectral density matrices are necessarily Hermitian and positive definite, and our primary goal is to develop new methods to analyze samples of such matrices. The main contribution of this paper is the generalization of the concept of statistical data depth for collections of covariance or spectral density matrices by exploiting the geometric properties of the space of Hermitian positive definite matrices as a Riemannian manifold. This allows one to naturally characterize most central or outlying matrices, but also provides a practical framework for rank-based hypothesis testing in the context of samples of covariance or spectral density matrices. First, the desired properties of a data depth function acting on the space of Hermitian positive definite matrices are presented. Second, we propose two computationally efficient pointwise and integrated data depth functions that satisfy each of these requirements. Several applications of the developed methodology are illustrated by the analysis of collections of spectral matrices in multivariate brain signal time series datasets.
Schur Complement Inequalities for Covariance Matrices and Monogamy of Quantum Correlations.
Lami, Ludovico; Hirche, Christoph; Adesso, Gerardo; Winter, Andreas
2016-11-25
We derive fundamental constraints for the Schur complement of positive matrices, which provide an operator strengthening to recently established information inequalities for quantum covariance matrices, including strong subadditivity. This allows us to prove general results on the monogamy of entanglement and steering quantifiers in continuous variable systems with an arbitrary number of modes per party. A powerful hierarchical relation for correlation measures based on the log-determinant of covariance matrices is further established for all Gaussian states, which has no counterpart among quantities based on the conventional von Neumann entropy.
Characteristic Polynomials of Sample Covariance Matrices: The Non-Square Case
Kösters, Holger
2009-01-01
We consider the sample covariance matrices of large data matrices which have i.i.d. complex matrix entries and which are non-square in the sense that the difference between the number of rows and the number of columns tends to infinity. We show that the second-order correlation function of the characteristic polynomial of the sample covariance matrix is asymptotically given by the sine kernel in the bulk of the spectrum and by the Airy kernel at the edge of the spectrum. Similar results are g...
Precomputing Process Noise Covariance for Onboard Sequential Filters
Olson, Corwin G.; Russell, Ryan P.; Carpenter, J. Russell
2017-01-01
Process noise is often used in estimation filters to account for unmodeled and mismodeled accelerations in the dynamics. The process noise covariance acts to inflate the state covariance over propagation intervals, increasing the uncertainty in the state. In scenarios where the acceleration errors change significantly over time, the standard process noise covariance approach can fail to provide effective representation of the state and its uncertainty. Consider covariance analysis techniques provide a method to precompute a process noise covariance profile along a reference trajectory using known model parameter uncertainties. The process noise covariance profile allows significantly improved state estimation and uncertainty representation over the traditional formulation. As a result, estimation performance on par with the consider filter is achieved for trajectories near the reference trajectory without the additional computational cost of the consider filter. The new formulation also has the potential to significantly reduce the trial-and-error tuning currently required of navigation analysts. A linear estimation problem as described in several previous consider covariance analysis studies is used to demonstrate the effectiveness of the precomputed process noise covariance, as well as a nonlinear descent scenario at the asteroid Bennu with optical navigation.
Hierarchical matrix approximation of large covariance matrices
Litvinenko, Alexander; Genton, Marc G.; Sun, Ying
2015-01-01
We approximate large non-structured Matérn covariance matrices of size n×n in the H-matrix format with a log-linear computational cost and storage O(kn log n), where rank k ≪ n is a small integer. Applications are: spatial statistics, machine learning and image analysis, kriging and optimal design.
Hierarchical matrix approximation of large covariance matrices
Litvinenko, Alexander
2015-11-30
We approximate large non-structured Matérn covariance matrices of size n×n in the H-matrix format with a log-linear computational cost and storage O(kn log n), where rank k ≪ n is a small integer. Applications are: spatial statistics, machine learning and image analysis, kriging and optimal design.
Estimation of Fuzzy Measures Using Covariance Matrices in Gaussian Mixtures
Directory of Open Access Journals (Sweden)
Nishchal K. Verma
2012-01-01
Full Text Available This paper presents a novel computational approach for estimating fuzzy measures directly from Gaussian mixtures model (GMM. The mixture components of GMM provide the membership functions for the input-output fuzzy sets. By treating consequent part as a function of fuzzy measures, we derived its coefficients from the covariance matrices found directly from GMM and the defuzzified output constructed from both the premise and consequent parts of the nonadditive fuzzy rules that takes the form of Choquet integral. The computational burden involved with the solution of λ-measure is minimized using Q-measure. The fuzzy model whose fuzzy measures were computed using covariance matrices found in GMM has been successfully applied on two benchmark problems and one real-time electric load data of Indian utility. The performance of the resulting model for many experimental studies including the above-mentioned application is found to be better and comparable to recent available fuzzy models. The main contribution of this paper is the estimation of fuzzy measures efficiently and directly from covariance matrices found in GMM, avoiding the computational burden greatly while learning them iteratively and solving polynomial equations of order of the number of input-output variables.
On spectral distribution of high dimensional covariation matrices
DEFF Research Database (Denmark)
Heinrich, Claudio; Podolskij, Mark
In this paper we present the asymptotic theory for spectral distributions of high dimensional covariation matrices of Brownian diffusions. More specifically, we consider N-dimensional Itô integrals with time varying matrix-valued integrands. We observe n equidistant high frequency data points...... of the underlying Brownian diffusion and we assume that N/n -> c in (0,oo). We show that under a certain mixed spectral moment condition the spectral distribution of the empirical covariation matrix converges in distribution almost surely. Our proof relies on method of moments and applications of graph theory....
International Nuclear Information System (INIS)
Roussin, R.W.; Drischler, J.D.; Marable, J.H.
1980-01-01
In recent years multigroup sensitivity profiles and covariance matrices have been added to the Radiation Shielding Information Center's Data Library Collection (DLC). Sensitivity profiles are available in a single package. DLC-45/SENPRO, and covariance matrices are found in two packages, DLC-44/COVERX and DLC-77/COVERV. The contents of these packages are described and their availability is discussed
Modeling and Forecasting Large Realized Covariance Matrices and Portfolio Choice
Callot, Laurent A.F.; Kock, Anders B.; Medeiros, Marcelo C.
2017-01-01
We consider modeling and forecasting large realized covariance matrices by penalized vector autoregressive models. We consider Lasso-type estimators to reduce the dimensionality and provide strong theoretical guarantees on the forecast capability of our procedure. We show that we can forecast
Performance of penalized maximum likelihood in estimation of genetic covariances matrices
Directory of Open Access Journals (Sweden)
Meyer Karin
2011-11-01
Full Text Available Abstract Background Estimation of genetic covariance matrices for multivariate problems comprising more than a few traits is inherently problematic, since sampling variation increases dramatically with the number of traits. This paper investigates the efficacy of regularized estimation of covariance components in a maximum likelihood framework, imposing a penalty on the likelihood designed to reduce sampling variation. In particular, penalties that "borrow strength" from the phenotypic covariance matrix are considered. Methods An extensive simulation study was carried out to investigate the reduction in average 'loss', i.e. the deviation in estimated matrices from the population values, and the accompanying bias for a range of parameter values and sample sizes. A number of penalties are examined, penalizing either the canonical eigenvalues or the genetic covariance or correlation matrices. In addition, several strategies to determine the amount of penalization to be applied, i.e. to estimate the appropriate tuning factor, are explored. Results It is shown that substantial reductions in loss for estimates of genetic covariance can be achieved for small to moderate sample sizes. While no penalty performed best overall, penalizing the variance among the estimated canonical eigenvalues on the logarithmic scale or shrinking the genetic towards the phenotypic correlation matrix appeared most advantageous. Estimating the tuning factor using cross-validation resulted in a loss reduction 10 to 15% less than that obtained if population values were known. Applying a mild penalty, chosen so that the deviation in likelihood from the maximum was non-significant, performed as well if not better than cross-validation and can be recommended as a pragmatic strategy. Conclusions Penalized maximum likelihood estimation provides the means to 'make the most' of limited and precious data and facilitates more stable estimation for multi-dimensional analyses. It should
Covariance matrices and applications to the field of nuclear data
International Nuclear Information System (INIS)
Smith, D.L.
1981-11-01
A student's introduction to covariance error analysis and least-squares evaluation of data is provided. It is shown that the basic formulas used in error propagation can be derived from a consideration of the geometry of curvilinear coordinates. Procedures for deriving covariances for scaler and vector functions of several variables are presented. Proper methods for reporting experimental errors and for deriving covariance matrices from these errors are indicated. The generalized least-squares method for evaluating experimental data is described. Finally, the use of least-squares techniques in data fitting applications is discussed. Specific examples of the various procedures are presented to clarify the concepts
Directory of Open Access Journals (Sweden)
James M. Cheverud
2007-03-01
Full Text Available Comparisons of covariance patterns are becoming more common as interest in the evolution of relationships between traits and in the evolutionary phenotypic diversification of clades have grown. We present parallel analyses of covariance matrix similarity for cranial traits in 14 New World Monkey genera using the Random Skewers (RS, T-statistics, and Common Principal Components (CPC approaches. We find that the CPC approach is very powerful in that with adequate sample sizes, it can be used to detect significant differences in matrix structure, even between matrices that are virtually identical in their evolutionary properties, as indicated by the RS results. We suggest that in many instances the assumption that population covariance matrices are identical be rejected out of hand. The more interesting and relevant question is, How similar are two covariance matrices with respect to their predicted evolutionary responses? This issue is addressed by the random skewers method described here.
Extreme eigenvalues of sample covariance and correlation matrices
DEFF Research Database (Denmark)
Heiny, Johannes
This thesis is concerned with asymptotic properties of the eigenvalues of high-dimensional sample covariance and correlation matrices under an infinite fourth moment of the entries. In the first part, we study the joint distributional convergence of the largest eigenvalues of the sample covariance...... matrix of a p-dimensional heavy-tailed time series when p converges to infinity together with the sample size n. We generalize the growth rates of p existing in the literature. Assuming a regular variation condition with tail index ... eigenvalues are essentially determined by the extreme order statistics from an array of iid random variables. The asymptotic behavior of the extreme eigenvalues is then derived routinely from classical extreme value theory. The resulting approximations are strikingly simple considering the high dimension...
Semiparametric estimation of covariance matrices for longitudinal data.
Fan, Jianqing; Wu, Yichao
2008-12-01
Estimation of longitudinal data covariance structure poses significant challenges because the data are usually collected at irregular time points. A viable semiparametric model for covariance matrices was proposed in Fan, Huang and Li (2007) that allows one to estimate the variance function nonparametrically and to estimate the correlation function parametrically via aggregating information from irregular and sparse data points within each subject. However, the asymptotic properties of their quasi-maximum likelihood estimator (QMLE) of parameters in the covariance model are largely unknown. In the current work, we address this problem in the context of more general models for the conditional mean function including parametric, nonparametric, or semi-parametric. We also consider the possibility of rough mean regression function and introduce the difference-based method to reduce biases in the context of varying-coefficient partially linear mean regression models. This provides a more robust estimator of the covariance function under a wider range of situations. Under some technical conditions, consistency and asymptotic normality are obtained for the QMLE of the parameters in the correlation function. Simulation studies and a real data example are used to illustrate the proposed approach.
Chang, Jinyuan; Zhou, Wen; Zhou, Wen-Xin; Wang, Lan
2017-03-01
Comparing large covariance matrices has important applications in modern genomics, where scientists are often interested in understanding whether relationships (e.g., dependencies or co-regulations) among a large number of genes vary between different biological states. We propose a computationally fast procedure for testing the equality of two large covariance matrices when the dimensions of the covariance matrices are much larger than the sample sizes. A distinguishing feature of the new procedure is that it imposes no structural assumptions on the unknown covariance matrices. Hence, the test is robust with respect to various complex dependence structures that frequently arise in genomics. We prove that the proposed procedure is asymptotically valid under weak moment conditions. As an interesting application, we derive a new gene clustering algorithm which shares the same nice property of avoiding restrictive structural assumptions for high-dimensional genomics data. Using an asthma gene expression dataset, we illustrate how the new test helps compare the covariance matrices of the genes across different gene sets/pathways between the disease group and the control group, and how the gene clustering algorithm provides new insights on the way gene clustering patterns differ between the two groups. The proposed methods have been implemented in an R-package HDtest and are available on CRAN. © 2016, The International Biometric Society.
Video based object representation and classification using multiple covariance matrices.
Zhang, Yurong; Liu, Quan
2017-01-01
Video based object recognition and classification has been widely studied in computer vision and image processing area. One main issue of this task is to develop an effective representation for video. This problem can generally be formulated as image set representation. In this paper, we present a new method called Multiple Covariance Discriminative Learning (MCDL) for image set representation and classification problem. The core idea of MCDL is to represent an image set using multiple covariance matrices with each covariance matrix representing one cluster of images. Firstly, we use the Nonnegative Matrix Factorization (NMF) method to do image clustering within each image set, and then adopt Covariance Discriminative Learning on each cluster (subset) of images. At last, we adopt KLDA and nearest neighborhood classification method for image set classification. Promising experimental results on several datasets show the effectiveness of our MCDL method.
ERRORJ, Multigroup covariance matrices generation from ENDF-6 format
International Nuclear Information System (INIS)
Chiba, Go
2007-01-01
1 - Description of program or function: ERRORJ produces multigroup covariance matrices from ENDF-6 format following mainly the methods of the ERRORR module in NJOY94.105. New version differs from previous version in the following features: Additional features in ERRORJ with respect to the NJOY94.105/ERRORR module: - expands processing for the covariance matrices of resolved and unresolved resonance parameters; - processes average cosine of scattering angle and fission spectrum; - treats cross-correlation between different materials and reactions; - accepts input of multigroup constants with various forms (user input, GENDF, etc.); - outputs files with various formats through utility NJOYCOVX (COVERX format, correlation matrix, relative error and standard deviation); - uses a 1% sensitivity method for processing of resonance parameters; - ERRORJ can process the JENDL-3.2 and 3.3 covariance matrices. Additional features of the version 2 with respect to the previous version of ERRORJ: - Since the release of version 2, ERRORJ has been modified to increase its reliability and stability, - calculation of the correlation coefficients in the resonance region, - Option for high-speed calculation is implemented, - Perturbation amount is optimised in a sensitivity calculation, - Effect of the resonance self-shielding can be considered, - a compact covariance format (LCOMP=2) proposed by N. M. Larson can be read. Additional features of the version 2.2.1 with respect to the previous version of ERRORJ: - Several routines were modified to reduce calculation time. The new one needs shorter calculation time (50-70%) than the old version without changing results. - In the U-233 and Pu-241 files of JENDL-3.3 an inconsistency between resonance parameters in MF=32 and those in MF=2 was corrected. NEA-1676/06: This version differs from the previous one (NEA-1676/05) in the following: ERRORJ2.2.1 was modified to treat the self-shielding effect accurately. NEA-1676/07: This version
Yang, Yang; DeGruttola, Victor
2012-06-22
Traditional resampling-based tests for homogeneity in covariance matrices across multiple groups resample residuals, that is, data centered by group means. These residuals do not share the same second moments when the null hypothesis is false, which makes them difficult to use in the setting of multiple testing. An alternative approach is to resample standardized residuals, data centered by group sample means and standardized by group sample covariance matrices. This approach, however, has been observed to inflate type I error when sample size is small or data are generated from heavy-tailed distributions. We propose to improve this approach by using robust estimation for the first and second moments. We discuss two statistics: the Bartlett statistic and a statistic based on eigen-decomposition of sample covariance matrices. Both statistics can be expressed in terms of standardized errors under the null hypothesis. These methods are extended to test homogeneity in correlation matrices. Using simulation studies, we demonstrate that the robust resampling approach provides comparable or superior performance, relative to traditional approaches, for single testing and reasonable performance for multiple testing. The proposed methods are applied to data collected in an HIV vaccine trial to investigate possible determinants, including vaccine status, vaccine-induced immune response level and viral genotype, of unusual correlation pattern between HIV viral load and CD4 count in newly infected patients.
Spatio-Temporal Audio Enhancement Based on IAA Noise Covariance Matrix Estimates
DEFF Research Database (Denmark)
Nørholm, Sidsel Marie; Jensen, Jesper Rindom; Christensen, Mads Græsbøll
2014-01-01
A method for estimating the noise covariance matrix in a mul- tichannel setup is proposed. The method is based on the iter- ative adaptive approach (IAA), which only needs short seg- ments of data to estimate the covariance matrix. Therefore, the method can be used for fast varying signals....... The method is based on an assumption of the desired signal being harmonic, which is used for estimating the noise covariance matrix from the covariance matrix of the observed signal. The noise co- variance estimate is used in the linearly constrained minimum variance (LCMV) filter and compared...
Litvinenko, Alexander
2017-09-26
The main goal of this article is to introduce the parallel hierarchical matrix library HLIBpro to the statistical community. We describe the HLIBCov package, which is an extension of the HLIBpro library for approximating large covariance matrices and maximizing likelihood functions. We show that an approximate Cholesky factorization of a dense matrix of size $2M\\\\times 2M$ can be computed on a modern multi-core desktop in few minutes. Further, HLIBCov is used for estimating the unknown parameters such as the covariance length, variance and smoothness parameter of a Mat\\\\\\'ern covariance function by maximizing the joint Gaussian log-likelihood function. The computational bottleneck here is expensive linear algebra arithmetics due to large and dense covariance matrices. Therefore covariance matrices are approximated in the hierarchical ($\\\\H$-) matrix format with computational cost $\\\\mathcal{O}(k^2n \\\\log^2 n/p)$ and storage $\\\\mathcal{O}(kn \\\\log n)$, where the rank $k$ is a small integer (typically $k<25$), $p$ the number of cores and $n$ the number of locations on a fairly general mesh. We demonstrate a synthetic example, where the true values of known parameters are known. For reproducibility we provide the C++ code, the documentation, and the synthetic data.
Litvinenko, Alexander
2017-09-24
The main goal of this article is to introduce the parallel hierarchical matrix library HLIBpro to the statistical community. We describe the HLIBCov package, which is an extension of the HLIBpro library for approximating large covariance matrices and maximizing likelihood functions. We show that an approximate Cholesky factorization of a dense matrix of size $2M\\\\times 2M$ can be computed on a modern multi-core desktop in few minutes. Further, HLIBCov is used for estimating the unknown parameters such as the covariance length, variance and smoothness parameter of a Mat\\\\\\'ern covariance function by maximizing the joint Gaussian log-likelihood function. The computational bottleneck here is expensive linear algebra arithmetics due to large and dense covariance matrices. Therefore covariance matrices are approximated in the hierarchical ($\\\\mathcal{H}$-) matrix format with computational cost $\\\\mathcal{O}(k^2n \\\\log^2 n/p)$ and storage $\\\\mathcal{O}(kn \\\\log n)$, where the rank $k$ is a small integer (typically $k<25$), $p$ the number of cores and $n$ the number of locations on a fairly general mesh. We demonstrate a synthetic example, where the true values of known parameters are known. For reproducibility we provide the C++ code, the documentation, and the synthetic data.
Perils of parsimony: properties of reduced-rank estimates of genetic covariance matrices.
Meyer, Karin; Kirkpatrick, Mark
2008-10-01
Eigenvalues and eigenvectors of covariance matrices are important statistics for multivariate problems in many applications, including quantitative genetics. Estimates of these quantities are subject to different types of bias. This article reviews and extends the existing theory on these biases, considering a balanced one-way classification and restricted maximum-likelihood estimation. Biases are due to the spread of sample roots and arise from ignoring selected principal components when imposing constraints on the parameter space, to ensure positive semidefinite estimates or to estimate covariance matrices of chosen, reduced rank. In addition, it is shown that reduced-rank estimators that consider only the leading eigenvalues and -vectors of the "between-group" covariance matrix may be biased due to selecting the wrong subset of principal components. In a genetic context, with groups representing families, this bias is inverse proportional to the degree of genetic relationship among family members, but is independent of sample size. Theoretical results are supplemented by a simulation study, demonstrating close agreement between predicted and observed bias for large samples. It is emphasized that the rank of the genetic covariance matrix should be chosen sufficiently large to accommodate all important genetic principal components, even though, paradoxically, this may require including a number of components with negligible eigenvalues. A strategy for rank selection in practical analyses is outlined.
MATXTST, Basic Operations for Covariance Matrices
International Nuclear Information System (INIS)
Geraldo, Luiz P.; Smith, Donald
1989-01-01
1 - Description of program or function: MATXTST and MATXTST1 perform the following operations for a covariance matrix: - test for singularity; - test for positive definiteness; - compute the inverse if the matrix is non-singular; - compute the determinant; - determine the number of positive, negative, and zero eigenvalues; - examine all possible 3 X 3 cross correlations within a sub-matrix corresponding to a leading principal minor which is non-positive definite. While the two programs utilize the same input, the calculational procedures employed are somewhat different and their functions are complementary. The available input options include: i) the full covariance matrix, ii) the basic variables plus the relative covariance matrix, or iii) uncertainties in the basic variables plus the correlation matrix. 2 - Method of solution: MATXTST employs LINPACK subroutines SPOFA and SPODI to test for positive definiteness and to perform further optional calculations. Subroutine SPOFA factors a symmetric matrix M using the Cholesky algorithm to determine the elements of a matrix R which satisfies the relation M=R'R, where R' is the transposed matrix of R. Each leading principal minor of M is tested until the first one is found which is not positive definite. MATXTST1 uses LINPACK subroutines SSICO, SSIFA, and SSIDI to estimate whether the matrix is near to singularity or not (SSICO), and to perform the matrix diagonalization process (SSIFA). The algorithm used in SSIFA is generalization of the Method of Lagrange Reduction. SSIDI is used to compute the determinant and inertia of the matrix. 3 - Restrictions on the complexity of the problem: Matrices of sizes up to 50 X 50 elements can be treated by present versions of the programs
Minimax Rate-optimal Estimation of High-dimensional Covariance Matrices with Incomplete Data.
Cai, T Tony; Zhang, Anru
2016-09-01
Missing data occur frequently in a wide range of applications. In this paper, we consider estimation of high-dimensional covariance matrices in the presence of missing observations under a general missing completely at random model in the sense that the missingness is not dependent on the values of the data. Based on incomplete data, estimators for bandable and sparse covariance matrices are proposed and their theoretical and numerical properties are investigated. Minimax rates of convergence are established under the spectral norm loss and the proposed estimators are shown to be rate-optimal under mild regularity conditions. Simulation studies demonstrate that the estimators perform well numerically. The methods are also illustrated through an application to data from four ovarian cancer studies. The key technical tools developed in this paper are of independent interest and potentially useful for a range of related problems in high-dimensional statistical inference with missing data.
Minimax Rate-optimal Estimation of High-dimensional Covariance Matrices with Incomplete Data*
Cai, T. Tony; Zhang, Anru
2016-01-01
Missing data occur frequently in a wide range of applications. In this paper, we consider estimation of high-dimensional covariance matrices in the presence of missing observations under a general missing completely at random model in the sense that the missingness is not dependent on the values of the data. Based on incomplete data, estimators for bandable and sparse covariance matrices are proposed and their theoretical and numerical properties are investigated. Minimax rates of convergence are established under the spectral norm loss and the proposed estimators are shown to be rate-optimal under mild regularity conditions. Simulation studies demonstrate that the estimators perform well numerically. The methods are also illustrated through an application to data from four ovarian cancer studies. The key technical tools developed in this paper are of independent interest and potentially useful for a range of related problems in high-dimensional statistical inference with missing data. PMID:27777471
Litvinenko, Alexander
2017-01-01
matrices. Therefore covariance matrices are approximated in the hierarchical ($\\H$-) matrix format with computational cost $\\mathcal{O}(k^2n \\log^2 n/p)$ and storage $\\mathcal{O}(kn \\log n)$, where the rank $k$ is a small integer (typically $k<25$), $p
Estimating correlation and covariance matrices by weighting of market similarity
Michael C. M\\"unnix; Rudi Sch\\"afer; Oliver Grothe
2010-01-01
We discuss a weighted estimation of correlation and covariance matrices from historical financial data. To this end, we introduce a weighting scheme that accounts for similarity of previous market conditions to the present one. The resulting estimators are less biased and show lower variance than either unweighted or exponentially weighted estimators. The weighting scheme is based on a similarity measure which compares the current correlation structure of the market to the structures at past ...
Nonlinear entanglement witnesses, covariance matrices and the geometry of separable states
Energy Technology Data Exchange (ETDEWEB)
Guehne, Otfried [Institut fuer Quantenoptik und Quanteninformation, Oesterreichische Akademie der Wissenschaften, A-6020 Innsbruck (Austria); Luetkenhaus, Norbert [Institute for Quantum Computing and Department of Physics and Astronomy, University of Waterloo, 200 University Avenue West, Waterloo, Ontario N2L 3G1 (Canada)
2007-05-15
Entanglement witnesses provide a standard tool for the analysis of entanglement in experiments. We investigate possible nonlinear entanglement witnesses from several perspectives. First, we demonstrate that they can be used to show that the set of separable states has no facets. Second, we give a new derivation of nonlinear witnesses based on covariance matrices. Finally, we investigate extensions to the multipartite case.
Integrated covariance estimation using high-frequency data in the presence of noise
DEFF Research Database (Denmark)
Voev, Valeri; Lunde, Asger
2007-01-01
We analyze the effects of nonsynchronicity and market microstructure noise on realized covariance type estimators. Hayashi and Yoshida (2005) propose a simple estimator that resolves the problem of nonsynchronicity and is unbiased and consistent for the integrated covariance in the absence of noise...
Universal correlations and power-law tails in financial covariance matrices
Akemann, G.; Fischmann, J.; Vivo, P.
2010-07-01
We investigate whether quantities such as the global spectral density or individual eigenvalues of financial covariance matrices can be best modelled by standard random matrix theory or rather by its generalisations displaying power-law tails. In order to generate individual eigenvalue distributions a chopping procedure is devised, which produces a statistical ensemble of asset-price covariances from a single instance of financial data sets. Local results for the smallest eigenvalue and individual spacings are very stable upon reshuffling the time windows and assets. They are in good agreement with the universal Tracy-Widom distribution and Wigner surmise, respectively. This suggests a strong degree of robustness especially in the low-lying sector of the spectra, most relevant for portfolio selections. Conversely, the global spectral density of a single covariance matrix as well as the average over all unfolded nearest-neighbour spacing distributions deviate from standard Gaussian random matrix predictions. The data are in fair agreement with a recently introduced generalised random matrix model, with correlations showing a power-law decay.
PUFF-IV, Code System to Generate Multigroup Covariance Matrices from ENDF/B-VI Uncertainty Files
International Nuclear Information System (INIS)
2007-01-01
1 - Description of program or function: The PUFF-IV code system processes ENDF/B-VI formatted nuclear cross section covariance data into multigroup covariance matrices. PUFF-IV is the newest release in this series of codes used to process ENDF uncertainty information and to generate the desired multi-group correlation matrix for the evaluation of interest. This version includes corrections and enhancements over previous versions. It is written in Fortran 90 and allows for a more modular design, thus facilitating future upgrades. PUFF-IV enhances support for resonance parameter covariance formats described in the ENDF standard and now handles almost all resonance parameter covariance information in the resolved region, with the exception of the long range covariance sub-subsections. PUFF-IV is normally used in conjunction with an AMPX master library containing group averaged cross section data. Two utility modules are included in this package to facilitate the data interface. The module SMILER allows one to use NJOY generated GENDF files containing group averaged cross section data in conjunction with PUFF-IV. The module COVCOMP allows one to compare two files written in COVERX format. 2 - Methods: Cross section and flux values on a 'super energy grid,' consisting of the union of the required energy group structure and the energy data points in the ENDF/B-V file, are interpolated from the input cross sections and fluxes. Covariance matrices are calculated for this grid and then collapsed to the required group structure. 3 - Restrictions on the complexity of the problem: PUFF-IV cannot process covariance information for energy and angular distributions of secondary particles. PUFF-IV does not process covariance information in Files 34 and 35; nor does it process covariance information in File 40. These new formats will be addressed in a future version of PUFF
Covariance matrices for nuclear cross sections derived from nuclear model calculations
International Nuclear Information System (INIS)
Smith, D. L.
2005-01-01
The growing need for covariance information to accompany the evaluated cross section data libraries utilized in contemporary nuclear applications is spurring the development of new methods to provide this information. Many of the current general purpose libraries of evaluated nuclear data used in applications are derived either almost entirely from nuclear model calculations or from nuclear model calculations benchmarked by available experimental data. Consequently, a consistent method for generating covariance information under these circumstances is required. This report discusses a new approach to producing covariance matrices for cross sections calculated using nuclear models. The present method involves establishing uncertainty information for the underlying parameters of nuclear models used in the calculations and then propagating these uncertainties through to the derived cross sections and related nuclear quantities by means of a Monte Carlo technique rather than the more conventional matrix error propagation approach used in some alternative methods. The formalism to be used in such analyses is discussed in this report along with various issues and caveats that need to be considered in order to proceed with a practical implementation of the methodology
Covariance measurement in the presence of non-synchronous trading and market microstructure noise
Griffin, J.E.; Oomen, R.C.A.
2011-01-01
This paper studies the problem of covariance estimation when prices are observed non-synchronously and contaminated by i.i.d. microstructure noise. We derive closed form expressions for the bias and variance of three popular covariance estimators, namely realised covariance, realised covariance plus
Bayesian estimation of covariance matrices: Application to market risk management at EDF
International Nuclear Information System (INIS)
Jandrzejewski-Bouriga, M.
2012-01-01
In this thesis, we develop new methods of regularized covariance matrix estimation, under the Bayesian setting. The regularization methodology employed is first related to shrinkage. We investigate a new Bayesian modeling of covariance matrix, based on hierarchical inverse-Wishart distribution, and then derive different estimators under standard loss functions. Comparisons between shrunk and empirical estimators are performed in terms of frequentist performance under different losses. It allows us to highlight the critical importance of the definition of cost function and show the persistent effect of the shrinkage-type prior on inference. In a second time, we consider the problem of covariance matrix estimation in Gaussian graphical models. If the issue is well treated for the decomposable case, it is not the case if you also consider non-decomposable graphs. We then describe a Bayesian and operational methodology to carry out the estimation of covariance matrix of Gaussian graphical models, decomposable or not. This procedure is based on a new and objective method of graphical-model selection, combined with a constrained and regularized estimation of the covariance matrix of the model chosen. The procedures studied effectively manage missing data. These estimation techniques were applied to calculate the covariance matrices involved in the market risk management for portfolios of EDF (Electricity of France), in particular for problems of calculating Value-at-Risk or in Asset Liability Management. (author)
Two-antenna GNSS Aided-INS Alignment Using Adaptive Control of Filter Noise Covariance
Directory of Open Access Journals (Sweden)
HAO Yushi
2018-04-01
Full Text Available This paper developed a theory of INS fine alignment in order to restrain the divergence of yaw angle,two antennas GNSS aided-INS integrated alignment algorithm was utilized.An attitude error measurement equation was conducted based on the relationship between baseline vectors calculated by two sensors and attitude error.The algorithm was executed by EKF using adaptive control of filter noise covariance.The experimental results showed that stability of the integrated system was improved under the system noise covariance adaptive control mechanism;The measurement noise covariance adaptive control mechanism can reduce the influence of measurement noise and improve the alignment absolute accuracy;Further improvement was achieved under the condition of minim bias of baseline length.The accuracy of roll and pitch was 0.02°,the accuracy of yaw was 0.04°.
Zeng, Rongping; Petrick, Nicholas; Gavrielides, Marios A; Myers, Kyle J
2011-10-07
Multi-slice computed tomography (MSCT) scanners have become popular volumetric imaging tools. Deterministic and random properties of the resulting CT scans have been studied in the literature. Due to the large number of voxels in the three-dimensional (3D) volumetric dataset, full characterization of the noise covariance in MSCT scans is difficult to tackle. However, as usage of such datasets for quantitative disease diagnosis grows, so does the importance of understanding the noise properties because of their effect on the accuracy of the clinical outcome. The goal of this work is to study noise covariance in the helical MSCT volumetric dataset. We explore possible approximations to the noise covariance matrix with reduced degrees of freedom, including voxel-based variance, one-dimensional (1D) correlation, two-dimensional (2D) in-plane correlation and the noise power spectrum (NPS). We further examine the effect of various noise covariance models on the accuracy of a prewhitening matched filter nodule size estimation strategy. Our simulation results suggest that the 1D longitudinal, 2D in-plane and NPS prewhitening approaches can improve the performance of nodule size estimation algorithms. When taking into account computational costs in determining noise characterizations, the NPS model may be the most efficient approximation to the MSCT noise covariance matrix.
International Nuclear Information System (INIS)
Akemann, Gernot; Checinski, Tomasz; Kieburg, Mario
2016-01-01
We compute the spectral statistics of the sum H of two independent complex Wishart matrices, each of which is correlated with a different covariance matrix. Random matrix theory enjoys many applications including sums and products of random matrices. Typically ensembles with correlations among the matrix elements are much more difficult to solve. Using a combination of supersymmetry, superbosonisation and bi-orthogonal functions we are able to determine all spectral k -point density correlation functions of H for arbitrary matrix size N . In the half-degenerate case, when one of the covariance matrices is proportional to the identity, the recent results by Kumar for the joint eigenvalue distribution of H serve as our starting point. In this case the ensemble has a bi-orthogonal structure and we explicitly determine its kernel, providing its exact solution for finite N . The kernel follows from computing the expectation value of a single characteristic polynomial. In the general non-degenerate case the generating function for the k -point resolvent is determined from a supersymmetric evaluation of the expectation value of k ratios of characteristic polynomials. Numerical simulations illustrate our findings for the spectral density at finite N and we also give indications how to do the asymptotic large- N analysis. (paper)
Treating Sample Covariances for Use in Strongly Coupled Atmosphere-Ocean Data Assimilation
Smith, Polly J.; Lawless, Amos S.; Nichols, Nancy K.
2018-01-01
Strongly coupled data assimilation requires cross-domain forecast error covariances; information from ensembles can be used, but limited sampling means that ensemble derived error covariances are routinely rank deficient and/or ill-conditioned and marred by noise. Thus, they require modification before they can be incorporated into a standard assimilation framework. Here we compare methods for improving the rank and conditioning of multivariate sample error covariance matrices for coupled atmosphere-ocean data assimilation. The first method, reconditioning, alters the matrix eigenvalues directly; this preserves the correlation structures but does not remove sampling noise. We show that it is better to recondition the correlation matrix rather than the covariance matrix as this prevents small but dynamically important modes from being lost. The second method, model state-space localization via the Schur product, effectively removes sample noise but can dampen small cross-correlation signals. A combination that exploits the merits of each is found to offer an effective alternative.
International Nuclear Information System (INIS)
Smith, D.L.
1988-01-01
The last decade has been a period of rapid development in the implementation of covariance-matrix methodology in nuclear data research. This paper offers some perspective on the progress which has been made, on some of the unresolved problems, and on the potential yet to be realized. These discussions address a variety of issues related to the development of nuclear data. Topics examined are: the importance of designing and conducting experiments so that error information is conveniently generated; the procedures for identifying error sources and quantifying their magnitudes and correlations; the combination of errors; the importance of consistent and well-characterized measurement standards; the role of covariances in data parameterization (fitting); the estimation of covariances for values calculated from mathematical models; the identification of abnormalities in covariance matrices and the analysis of their consequences; the problems encountered in representing covariance information in evaluated files; the role of covariances in the weighting of diverse data sets; the comparison of various evaluations; the influence of primary-data covariance in the analysis of covariances for derived quantities (sensitivity); and the role of covariances in the merging of the diverse nuclear data information. 226 refs., 2 tabs
Single-Channel Noise Reduction using Unified Joint Diagonalization and Optimal Filtering
DEFF Research Database (Denmark)
Nørholm, Sidsel Marie; Benesty, Jacob; Jensen, Jesper Rindom
2014-01-01
consider two cases, where, respectively, no distortion and distortion are incurred on the desired signal. The former can be achieved when the covariance matrix of the desired signal is rank deficient, which is the case, for example, for voiced speech. In the latter case, the covariance matrix......In this paper, the important problem of single-channel noise reduction is treated from a new perspective. The problem is posed as a filtering problem based on joint diagonalization of the covariance matrices of the desired and noise signals. More specifically, the eigenvectors from the joint...
PUFF-III: A Code for Processing ENDF Uncertainty Data Into Multigroup Covariance Matrices
International Nuclear Information System (INIS)
Dunn, M.E.
2000-01-01
PUFF-III is an extension of the previous PUFF-II code that was developed in the 1970s and early 1980s. The PUFF codes process the Evaluated Nuclear Data File (ENDF) covariance data and generate multigroup covariance matrices on a user-specified energy grid structure. Unlike its predecessor, PUFF-III can process the new ENDF/B-VI data formats. In particular, PUFF-III has the capability to process the spontaneous fission covariances for fission neutron multiplicity. With regard to the covariance data in File 33 of the ENDF system, PUFF-III has the capability to process short-range variance formats, as well as the lumped reaction covariance data formats that were introduced in ENDF/B-V. In addition to the new ENDF formats, a new directory feature is now available that allows the user to obtain a detailed directory of the uncertainty information in the data files without visually inspecting the ENDF data. Following the correlation matrix calculation, PUFF-III also evaluates the eigenvalues of each correlation matrix and tests each matrix for positive definiteness. Additional new features are discussed in the manual. PUFF-III has been developed for implementation in the AMPX code system, and several modifications were incorporated to improve memory allocation tasks and input/output operations. Consequently, the resulting code has a structure that is similar to other modules in the AMPX code system. With the release of PUFF-III, a new and improved covariance processing code is available to process ENDF covariance formats through Version VI
ZZ RRDF-98, Cross-sections and covariance matrices for 22 neutron induced dosimetry reactions
International Nuclear Information System (INIS)
Zolotarev, K.I.; Ignatyuk, A.V.; Mahokhin, V.N.; Pashchenko, A.B.
2005-01-01
1 - Description of program or function: Format: ENDF-6 format; Number of groups: Continuous energy; Dosimetry reactions: 6-C-12(n,2n), 8-O-16(n,2n), 9-F-19(n,2n), 12-Mg-24(n,p), 22-Ti-46(n,2n), 22-Ti-46(n,p), 22-Ti-47(n,x), 22-Ti-48(n,p), 22-Ti-48(n,x), 22-Ti-49(n,x), 23-V-51(n,alpha), 26-Fe-54(n,2n), 26-Fe-54(n,alpha), 26-Fe-56(n,p), 27-Co-59(n,alpha), 29-Cu-63(n,alpha), 33-As-75(n,2n), 41-Nb-93(n,2n), 41-Nb-93(n,n'), 45-Rh-103(n,n'), 49-In-115(n,n'), 59-Pr-141(n,2n); Origin: Russian Federation; Weighting spectrum: None. RRDF-98 contains original evaluations of cross section data performed at the Institute of Physics and Power Engineering, Obninsk, for 22 neutron induced dosimetry reactions. The dataset also contains the corresponding covariance matrices. 2 - Methods: The evaluation of excitation functions was performed on the basis of statistical analysis of corrected experimental data in the framework of generalized least squares method and taking into account the results of optical-statistical STAPRE and GNASH calculations. The experimental cross section data including the most recent results were critically reviewed and processed in this study. If necessary, the data were normalized in order to make adjustments in relevant cross sections and decay schemes. The covariance matrices were prepared and the evaluated cross section data are presented in ENDF-6 format (Files 3, 33). For estimation of correlations between experimental data the total uncertainties of measured cross sections have been separated into statistical and systematic parts and correlation coefficients between components of systematic parts were assigned according to information given in the original publications and EXFOR library. Then the correlation matrix of cross sections measured within one experiment was calculated and approximated by matrix with a constant (average) correlation coefficient. The overall correlation matrix was composed of such sub-matrices in the assumption that the cross
Zhu, Lingxue; Lei, Jing; Devlin, Bernie; Roeder, Kathryn
2017-09-01
Scientists routinely compare gene expression levels in cases versus controls in part to determine genes associated with a disease. Similarly, detecting case-control differences in co-expression among genes can be critical to understanding complex human diseases; however statistical methods have been limited by the high dimensional nature of this problem. In this paper, we construct a sparse-Leading-Eigenvalue-Driven (sLED) test for comparing two high-dimensional covariance matrices. By focusing on the spectrum of the differential matrix, sLED provides a novel perspective that accommodates what we assume to be common, namely sparse and weak signals in gene expression data, and it is closely related with Sparse Principal Component Analysis. We prove that sLED achieves full power asymptotically under mild assumptions, and simulation studies verify that it outperforms other existing procedures under many biologically plausible scenarios. Applying sLED to the largest gene-expression dataset obtained from post-mortem brain tissue from Schizophrenia patients and controls, we provide a novel list of genes implicated in Schizophrenia and reveal intriguing patterns in gene co-expression change for Schizophrenia subjects. We also illustrate that sLED can be generalized to compare other gene-gene "relationship" matrices that are of practical interest, such as the weighted adjacency matrices.
Covariance matrices of experimental data
International Nuclear Information System (INIS)
Perey, F.G.
1978-01-01
A complete statement of the uncertainties in data is given by its covariance matrix. It is shown how the covariance matrix of data can be generated using the information available to obtain their standard deviations. Determination of resonance energies by the time-of-flight method is used as an example. The procedure for combining data when the covariance matrix is non-diagonal is given. The method is illustrated by means of examples taken from the recent literature to obtain an estimate of the energy of the first resonance in carbon and for five resonances of 238 U
Bartz, Daniel; Hatrick, Kerr; Hesse, Christian W; Müller, Klaus-Robert; Lemm, Steven
2013-01-01
Robust and reliable covariance estimates play a decisive role in financial and many other applications. An important class of estimators is based on factor models. Here, we show by extensive Monte Carlo simulations that covariance matrices derived from the statistical Factor Analysis model exhibit a systematic error, which is similar to the well-known systematic error of the spectrum of the sample covariance matrix. Moreover, we introduce the Directional Variance Adjustment (DVA) algorithm, which diminishes the systematic error. In a thorough empirical study for the US, European, and Hong Kong stock market we show that our proposed method leads to improved portfolio allocation.
Spearing, Debra; Woehlke, Paula
To assess the effect on discriminant analysis in terms of correct classification into two groups, the following parameters were systematically altered using Monte Carlo techniques: sample sizes; proportions of one group to the other; number of independent variables; and covariance matrices. The pairing of the off diagonals (or covariances) with…
On estimating cosmology-dependent covariance matrices
International Nuclear Information System (INIS)
Morrison, Christopher B.; Schneider, Michael D.
2013-01-01
We describe a statistical model to estimate the covariance matrix of matter tracer two-point correlation functions with cosmological simulations. Assuming a fixed number of cosmological simulation runs, we describe how to build a 'statistical emulator' of the two-point function covariance over a specified range of input cosmological parameters. Because the simulation runs with different cosmological models help to constrain the form of the covariance, we predict that the cosmology-dependent covariance may be estimated with a comparable number of simulations as would be needed to estimate the covariance for fixed cosmology. Our framework is a necessary first step in planning a simulations campaign for analyzing the next generation of cosmological surveys
Bartz, Daniel; Hatrick, Kerr; Hesse, Christian W.; Müller, Klaus-Robert; Lemm, Steven
2013-01-01
Robust and reliable covariance estimates play a decisive role in financial and many other applications. An important class of estimators is based on factor models. Here, we show by extensive Monte Carlo simulations that covariance matrices derived from the statistical Factor Analysis model exhibit a systematic error, which is similar to the well-known systematic error of the spectrum of the sample covariance matrix. Moreover, we introduce the Directional Variance Adjustment (DVA) algorithm, which diminishes the systematic error. In a thorough empirical study for the US, European, and Hong Kong stock market we show that our proposed method leads to improved portfolio allocation. PMID:23844016
Directory of Open Access Journals (Sweden)
Daniel Bartz
Full Text Available Robust and reliable covariance estimates play a decisive role in financial and many other applications. An important class of estimators is based on factor models. Here, we show by extensive Monte Carlo simulations that covariance matrices derived from the statistical Factor Analysis model exhibit a systematic error, which is similar to the well-known systematic error of the spectrum of the sample covariance matrix. Moreover, we introduce the Directional Variance Adjustment (DVA algorithm, which diminishes the systematic error. In a thorough empirical study for the US, European, and Hong Kong stock market we show that our proposed method leads to improved portfolio allocation.
Beamforming using subspace estimation from a diagonally averaged sample covariance.
Quijano, Jorge E; Zurk, Lisa M
2017-08-01
The potential benefit of a large-aperture sonar array for high resolution target localization is often challenged by the lack of sufficient data required for adaptive beamforming. This paper introduces a Toeplitz-constrained estimator of the clairvoyant signal covariance matrix corresponding to multiple far-field targets embedded in background isotropic noise. The estimator is obtained by averaging along subdiagonals of the sample covariance matrix, followed by covariance extrapolation using the method of maximum entropy. The sample covariance is computed from limited data snapshots, a situation commonly encountered with large-aperture arrays in environments characterized by short periods of local stationarity. Eigenvectors computed from the Toeplitz-constrained covariance are used to construct signal-subspace projector matrices, which are shown to reduce background noise and improve detection of closely spaced targets when applied to subspace beamforming. Monte Carlo simulations corresponding to increasing array aperture suggest convergence of the proposed projector to the clairvoyant signal projector, thereby outperforming the classic projector obtained from the sample eigenvectors. Beamforming performance of the proposed method is analyzed using simulated data, as well as experimental data from the Shallow Water Array Performance experiment.
ESTIMATION OF FUNCTIONALS OF SPARSE COVARIANCE MATRICES.
Fan, Jianqing; Rigollet, Philippe; Wang, Weichen
High-dimensional statistical tests often ignore correlations to gain simplicity and stability leading to null distributions that depend on functionals of correlation matrices such as their Frobenius norm and other ℓ r norms. Motivated by the computation of critical values of such tests, we investigate the difficulty of estimation the functionals of sparse correlation matrices. Specifically, we show that simple plug-in procedures based on thresholded estimators of correlation matrices are sparsity-adaptive and minimax optimal over a large class of correlation matrices. Akin to previous results on functional estimation, the minimax rates exhibit an elbow phenomenon. Our results are further illustrated in simulated data as well as an empirical study of data arising in financial econometrics.
High-dimensional covariance estimation with high-dimensional data
Pourahmadi, Mohsen
2013-01-01
Methods for estimating sparse and large covariance matrices Covariance and correlation matrices play fundamental roles in every aspect of the analysis of multivariate data collected from a variety of fields including business and economics, health care, engineering, and environmental and physical sciences. High-Dimensional Covariance Estimation provides accessible and comprehensive coverage of the classical and modern approaches for estimating covariance matrices as well as their applications to the rapidly developing areas lying at the intersection of statistics and mac
ANL Critical Assembly Covariance Matrix Generation - Addendum
Energy Technology Data Exchange (ETDEWEB)
McKnight, Richard D. [Argonne National Lab. (ANL), Argonne, IL (United States); Grimm, Karl N. [Argonne National Lab. (ANL), Argonne, IL (United States)
2014-01-13
In March 2012, a report was issued on covariance matrices for Argonne National Laboratory (ANL) critical experiments. That report detailed the theory behind the calculation of covariance matrices and the methodology used to determine the matrices for a set of 33 ANL experimental set-ups. Since that time, three new experiments have been evaluated and approved. This report essentially updates the previous report by adding in these new experiments to the preceding covariance matrix structure.
Robust extended Kalman filter of discrete-time Markovian jump nonlinear system under uncertain noise
International Nuclear Information System (INIS)
Zhu, Jin; Park, Jun Hong; Lee, Kwan Soo; Spiryagin, Maksym
2008-01-01
This paper examines the problem of robust extended Kalman filter design for discrete -time Markovian jump nonlinear systems with noise uncertainty. Because of the existence of stochastic Markovian switching, the state and measurement equations of underlying system are subject to uncertain noise whose covariance matrices are time-varying or un-measurable instead of stationary. First, based on the expression of filtering performance deviation, admissible uncertainty of noise covariance matrix is given. Secondly, two forms of noise uncertainty are taken into account: Non- Structural and Structural. It is proved by applying game theory that this filter design is a robust mini-max filter. A numerical example shows the validity of the method
Shaw, Simon C.; Goldstein, Michael
2017-01-01
We explore the effect of finite population sampling in design problems with many variables cross-classified in many ways. In particular, we investigate designs where we wish to sample individuals belonging to different groups for which the underlying covariance matrices are separable between groups and variables. We exploit the generalised conditional independence structure of the model to show how the analysis of the full model can be reduced to an interpretable series of lower dimensional p...
Covariance matrix estimation for stationary time series
Xiao, Han; Wu, Wei Biao
2011-01-01
We obtain a sharp convergence rate for banded covariance matrix estimates of stationary processes. A precise order of magnitude is derived for spectral radius of sample covariance matrices. We also consider a thresholded covariance matrix estimator that can better characterize sparsity if the true covariance matrix is sparse. As our main tool, we implement Toeplitz [Math. Ann. 70 (1911) 351–376] idea and relate eigenvalues of covariance matrices to the spectral densities or Fourier transforms...
Institute of Scientific and Technical Information of China (English)
XIA Yuanqing; HAN Jingqing
2005-01-01
This paper concerns robust Kalman filtering for systems under norm bounded uncertainties in all the system matrices and error covariance constraints. Sufficient conditions are given for the existence of such filters in terms of Riccati equations. The solutions to the conditions can be used to design the filters. Finally, an illustrative example is given to demonstrate the effectiveness of the proposed design procedure.
Multi-compartment linear noise approximation
International Nuclear Information System (INIS)
Challenger, Joseph D; McKane, Alan J; Pahle, Jürgen
2012-01-01
The ability to quantify the stochastic fluctuations present in biochemical and other systems is becoming increasing important. Analytical descriptions of these fluctuations are attractive, as stochastic simulations are computationally expensive. Building on previous work, a linear noise approximation is developed for biochemical models with many compartments, for example cells. The procedure is then implemented in the software package COPASI. This technique is illustrated with two simple examples and is then applied to a more realistic biochemical model. Expressions for the noise, given in the form of covariance matrices, are presented. (paper)
Structural Analysis of Covariance and Correlation Matrices.
Joreskog, Karl G.
1978-01-01
A general approach to analysis of covariance structures is considered, in which the variances and covariances or correlations of the observed variables are directly expressed in terms of the parameters of interest. The statistical problems of identification, estimation and testing of such covariance or correlation structures are discussed.…
DEFF Research Database (Denmark)
Bingham, Rory J.; Tscherning, Christian; Knudsen, Per
2011-01-01
The availability of the full error variance-covariance matrices for the GOCE gravity field models is an important feature of the GOCE mission. Potentially, it will allow users to evaluate the accuracy of a geoid or mean dynamic topography (MDT) derived from the gravity field model at any particul...
Siren, J; Ovaskainen, O; Merilä, J
2017-10-01
The genetic variance-covariance matrix (G) is a quantity of central importance in evolutionary biology due to its influence on the rate and direction of multivariate evolution. However, the predictive power of empirically estimated G-matrices is limited for two reasons. First, phenotypes are high-dimensional, whereas traditional statistical methods are tuned to estimate and analyse low-dimensional matrices. Second, the stability of G to environmental effects and over time remains poorly understood. Using Bayesian sparse factor analysis (BSFG) designed to estimate high-dimensional G-matrices, we analysed levels variation and covariation in 10,527 expressed genes in a large (n = 563) half-sib breeding design of three-spined sticklebacks subject to two temperature treatments. We found significant differences in the structure of G between the treatments: heritabilities and evolvabilities were higher in the warm than in the low-temperature treatment, suggesting more and faster opportunity to evolve in warm (stressful) conditions. Furthermore, comparison of G and its phenotypic equivalent P revealed the latter is a poor substitute of the former. Most strikingly, the results suggest that the expected impact of G on evolvability-as well as the similarity among G-matrices-may depend strongly on the number of traits included into analyses. In our results, the inclusion of only few traits in the analyses leads to underestimation in the differences between the G-matrices and their predicted impacts on evolution. While the results highlight the challenges involved in estimating G, they also illustrate that by enabling the estimation of large G-matrices, the BSFG method can improve predicted evolutionary responses to selection. © 2017 John Wiley & Sons Ltd.
Exploiting Data Sparsity In Covariance Matrix Computations on Heterogeneous Systems
Charara, Ali M.
2018-05-24
Covariance matrices are ubiquitous in computational sciences, typically describing the correlation of elements of large multivariate spatial data sets. For example, covari- ance matrices are employed in climate/weather modeling for the maximum likelihood estimation to improve prediction, as well as in computational ground-based astronomy to enhance the observed image quality by filtering out noise produced by the adap- tive optics instruments and atmospheric turbulence. The structure of these covariance matrices is dense, symmetric, positive-definite, and often data-sparse, therefore, hier- archically of low-rank. This thesis investigates the performance limit of dense matrix computations (e.g., Cholesky factorization) on covariance matrix problems as the number of unknowns grows, and in the context of the aforementioned applications. We employ recursive formulations of some of the basic linear algebra subroutines (BLAS) to accelerate the covariance matrix computation further, while reducing data traffic across the memory subsystems layers. However, dealing with large data sets (i.e., covariance matrices of billions in size) can rapidly become prohibitive in memory footprint and algorithmic complexity. Most importantly, this thesis investigates the tile low-rank data format (TLR), a new compressed data structure and layout, which is valuable in exploiting data sparsity by approximating the operator. The TLR com- pressed data structure allows approximating the original problem up to user-defined numerical accuracy. This comes at the expense of dealing with tasks with much lower arithmetic intensities than traditional dense computations. In fact, this thesis con- solidates the two trends of dense and data-sparse linear algebra for HPC. Not only does the thesis leverage recursive formulations for dense Cholesky-based matrix al- gorithms, but it also implements a novel TLR-Cholesky factorization using batched linear algebra operations to increase hardware occupancy and
Introduction into Hierarchical Matrices
Litvinenko, Alexander
2013-01-01
Hierarchical matrices allow us to reduce computational storage and cost from cubic to almost linear. This technique can be applied for solving PDEs, integral equations, matrix equations and approximation of large covariance and precision matrices.
Introduction into Hierarchical Matrices
Litvinenko, Alexander
2013-12-05
Hierarchical matrices allow us to reduce computational storage and cost from cubic to almost linear. This technique can be applied for solving PDEs, integral equations, matrix equations and approximation of large covariance and precision matrices.
ACORNS, Covariance and Correlation Matrix Diagonalization
International Nuclear Information System (INIS)
Szondi, E.J.
1990-01-01
1 - Description of program or function: The program allows the user to verify the different types of covariance/correlation matrices used in the activation neutron spectrometry. 2 - Method of solution: The program performs the diagonalization of the input covariance/relative covariance/correlation matrices. The Eigen values are then analyzed to determine the rank of the matrices. If the Eigen vectors of the pertinent correlation matrix have also been calculated, the program can perform a complete factor analysis (generation of the factor matrix and its rotation in Kaiser's 'varimax' sense to select the origin of the correlations). 3 - Restrictions on the complexity of the problem: Matrix size is limited to 60 on PDP and to 100 on IBM PC/AT
The dependence of signal-to-noise ratio on number of scans in covariance spectroscopy.
Qian, Yi; Shen, Ming; Amoureux, Jean-Paul; Noda, Isao; Hu, Bingwen
2014-01-01
The dependence of signal-to-noise ratio on the number of scans in covariance spectroscopy has been systematically analyzed for the first time with the intriguing relationship of SNRcov∝n/2, which is different from that in FT2D spectrum with SNRFT∝n. This relationship guarantees the signal-to-noise ratio when increasing the number of scans. Copyright © 2014 Elsevier Inc. All rights reserved.
Computation of large covariance matrices by SAMMY on graphical processing units and multicore CPUs
International Nuclear Information System (INIS)
Arbanas, G.; Dunn, M.E.; Wiarda, D.
2011-01-01
Computational power of Graphical Processing Units and multicore CPUs was harnessed by the nuclear data evaluation code SAMMY to speed up computations of large Resonance Parameter Covariance Matrices (RPCMs). This was accomplished by linking SAMMY to vendor-optimized implementations of the matrix-matrix multiplication subroutine of the Basic Linear Algebra Library to compute the most time-consuming step. The 235 U RPCM computed previously using a triple-nested loop was re-computed using the NVIDIA implementation of the subroutine on a single Tesla Fermi Graphical Processing Unit, and also using the Intel's Math Kernel Library implementation on two different multicore CPU systems. A multiplication of two matrices of dimensions 16,000×20,000 that had previously taken days, took approximately one minute on the GPU. Comparable performance was achieved on a dual six-core CPU system. The magnitude of the speed-up suggests that these, or similar, combinations of hardware and libraries may be useful for large matrix operations in SAMMY. Uniform interfaces of standard linear algebra libraries make them a promising candidate for a programming framework of a new generation of SAMMY for the emerging heterogeneous computing platforms. (author)
Computation of large covariance matrices by SAMMY on graphical processing units and multicore CPUs
Energy Technology Data Exchange (ETDEWEB)
Arbanas, G.; Dunn, M.E.; Wiarda, D., E-mail: arbanasg@ornl.gov, E-mail: dunnme@ornl.gov, E-mail: wiardada@ornl.gov [Oak Ridge National Laboratory, Oak Ridge, TN (United States)
2011-07-01
Computational power of Graphical Processing Units and multicore CPUs was harnessed by the nuclear data evaluation code SAMMY to speed up computations of large Resonance Parameter Covariance Matrices (RPCMs). This was accomplished by linking SAMMY to vendor-optimized implementations of the matrix-matrix multiplication subroutine of the Basic Linear Algebra Library to compute the most time-consuming step. The {sup 235}U RPCM computed previously using a triple-nested loop was re-computed using the NVIDIA implementation of the subroutine on a single Tesla Fermi Graphical Processing Unit, and also using the Intel's Math Kernel Library implementation on two different multicore CPU systems. A multiplication of two matrices of dimensions 16,000×20,000 that had previously taken days, took approximately one minute on the GPU. Comparable performance was achieved on a dual six-core CPU system. The magnitude of the speed-up suggests that these, or similar, combinations of hardware and libraries may be useful for large matrix operations in SAMMY. Uniform interfaces of standard linear algebra libraries make them a promising candidate for a programming framework of a new generation of SAMMY for the emerging heterogeneous computing platforms. (author)
ANGELO-LAMBDA, Covariance matrix interpolation and mathematical verification
International Nuclear Information System (INIS)
Kodeli, Ivo
2007-01-01
1 - Description of program or function: The codes ANGELO-2.3 and LAMBDA-2.3 are used for the interpolation of the cross section covariance data from the original to a user defined energy group structure, and for the mathematical tests of the matrices, respectively. The LAMBDA-2.3 code calculates the eigenvalues of the matrices (both for the original or the converted) and lists them accordingly into positive and negative matrices. This verification is strongly recommended before using any covariance matrices. These versions of the two codes are the extended versions of the previous codes available in the Packages NEA-1264 - ZZ-VITAMIN-J/COVA. They were specifically developed for the purposes of the OECD LWR UAM benchmark, in particular for the processing of the ZZ-SCALE5.1/COVA-44G cross section covariance matrix library retrieved from the SCALE-5.1 package. Either the original SCALE-5.1 libraries or the libraries separated into several files by Nuclides can be (in principle) processed by ANGELO/LAMBDA codes, but the use of the one-nuclide data is strongly recommended. Due to large deviations of the correlation matrix terms from unity observed in some SCALE5.1 covariance matrices, the previous more severe acceptance condition in the ANGELO2.3 code was released. In case the correlation coefficients exceed 1.0, only a warning message is issued, and coefficients are replaced by 1.0. 2 - Methods: ANGELO-2.3 interpolates the covariance matrices to a union grid using flat weighting. LAMBDA-2.3 code includes the mathematical routines to calculate the eigenvalues of the covariance matrices. 3 - Restrictions on the complexity of the problem: The algorithm used in ANGELO is relatively simple, therefore the interpolations involving energy group structure which are very different from the original (e.g. large difference in the number of energy groups) may not be accurate. In particular in the case of the MT=1018 data (fission spectra covariances) the algorithm may not be
Position Error Covariance Matrix Validation and Correction
Frisbee, Joe, Jr.
2016-01-01
In order to calculate operationally accurate collision probabilities, the position error covariance matrices predicted at times of closest approach must be sufficiently accurate representations of the position uncertainties. This presentation will discuss why the Gaussian distribution is a reasonable expectation for the position uncertainty and how this assumed distribution type is used in the validation and correction of position error covariance matrices.
Li, Zheng; Zhang, Hai; Zhou, Qifan; Che, Huan
2017-09-05
The main objective of the introduced study is to design an adaptive Inertial Navigation System/Global Navigation Satellite System (INS/GNSS) tightly-coupled integration system that can provide more reliable navigation solutions by making full use of an adaptive Kalman filter (AKF) and satellite selection algorithm. To achieve this goal, we develop a novel redundant measurement noise covariance estimation (RMNCE) theorem, which adaptively estimates measurement noise properties by analyzing the difference sequences of system measurements. The proposed RMNCE approach is then applied to design both a modified weighted satellite selection algorithm and a type of adaptive unscented Kalman filter (UKF) to improve the performance of the tightly-coupled integration system. In addition, an adaptive measurement noise covariance expanding algorithm is developed to mitigate outliers when facing heavy multipath and other harsh situations. Both semi-physical simulation and field experiments were conducted to evaluate the performance of the proposed architecture and were compared with state-of-the-art algorithms. The results validate that the RMNCE provides a significant improvement in the measurement noise covariance estimation and the proposed architecture can improve the accuracy and reliability of the INS/GNSS tightly-coupled systems. The proposed architecture can effectively limit positioning errors under conditions of poor GNSS measurement quality and outperforms all the compared schemes.
Gaskins, J T; Daniels, M J
2016-01-02
The estimation of the covariance matrix is a key concern in the analysis of longitudinal data. When data consists of multiple groups, it is often assumed the covariance matrices are either equal across groups or are completely distinct. We seek methodology to allow borrowing of strength across potentially similar groups to improve estimation. To that end, we introduce a covariance partition prior which proposes a partition of the groups at each measurement time. Groups in the same set of the partition share dependence parameters for the distribution of the current measurement given the preceding ones, and the sequence of partitions is modeled as a Markov chain to encourage similar structure at nearby measurement times. This approach additionally encourages a lower-dimensional structure of the covariance matrices by shrinking the parameters of the Cholesky decomposition toward zero. We demonstrate the performance of our model through two simulation studies and the analysis of data from a depression study. This article includes Supplementary Material available online.
Massive data compression for parameter-dependent covariance matrices
Heavens, Alan F.; Sellentin, Elena; de Mijolla, Damien; Vianello, Alvise
2017-12-01
We show how the massive data compression algorithm MOPED can be used to reduce, by orders of magnitude, the number of simulated data sets which are required to estimate the covariance matrix required for the analysis of Gaussian-distributed data. This is relevant when the covariance matrix cannot be calculated directly. The compression is especially valuable when the covariance matrix varies with the model parameters. In this case, it may be prohibitively expensive to run enough simulations to estimate the full covariance matrix throughout the parameter space. This compression may be particularly valuable for the next generation of weak lensing surveys, such as proposed for Euclid and Large Synoptic Survey Telescope, for which the number of summary data (such as band power or shear correlation estimates) is very large, ∼104, due to the large number of tomographic redshift bins which the data will be divided into. In the pessimistic case where the covariance matrix is estimated separately for all points in an Monte Carlo Markov Chain analysis, this may require an unfeasible 109 simulations. We show here that MOPED can reduce this number by a factor of 1000, or a factor of ∼106 if some regularity in the covariance matrix is assumed, reducing the number of simulations required to a manageable 103, making an otherwise intractable analysis feasible.
Directory of Open Access Journals (Sweden)
Peng Fangfang
2014-01-01
Full Text Available This paper studies the fusion estimation problem of a class of multisensor multirate systems with observation multiplicative noises. The dynamic system is sampled uniformly. Sampling period of each sensor is uniform and the integer multiple of the state update period. Moreover, different sensors have the different sampling rates and observations of sensors are subject to the stochastic uncertainties of multiplicative noises. At first, local filters at the observation sampling points are obtained based on the observations of each sensor. Further, local estimators at the state update points are obtained by predictions of local filters at the observation sampling points. They have the reduced computational cost and a good real-time property. Then, the cross-covariance matrices between any two local estimators are derived at the state update points. At last, using the matrix weighted optimal fusion estimation algorithm in the linear minimum variance sense, the distributed optimal fusion estimator is obtained based on the local estimators and the cross-covariance matrices. An example shows the effectiveness of the proposed algorithms.
The covariance matrix of neutron spectra used in the REAL 84 exercise
International Nuclear Information System (INIS)
Matzke, M.
1986-08-01
Covariance matrices of continuous functions are discussed. It is pointed out that the number of non-vanishing eigenvalues corresponds to the number of random variables (parameters) involved in the construction of the continuous functions. The covariance matrices used in the REAL 84 international intercomparison of unfolding methods of neutron spectra are investigated. It is shown that a small rank of these covariance matrices leads to a restriction of the possible solution spectra. (orig.) [de
Covariance as input to and output from resonance analyses
International Nuclear Information System (INIS)
Larson, N.M.
1992-01-01
Accurate data analysis requires understanding of the roles played by both data and parameter covariance matrices. In this paper the entire data reduction/analysis process is examined, for neutron-induced reactions in the resonance region. Interrelationships between data and parameter covariance matrices are examined and alternative reduction/analysis methods discussed
Bazzani, Armando; Castellani, Gastone C; Cooper, Leon N
2010-05-01
We analyze the effects of noise correlations in the input to, or among, Bienenstock-Cooper-Munro neurons using the Wigner semicircular law to construct random, positive-definite symmetric correlation matrices and compute their eigenvalue distributions. In the finite dimensional case, we compare our analytic results with numerical simulations and show the effects of correlations on the lifetimes of synaptic strengths in various visual environments. These correlations can be due either to correlations in the noise from the input lateral geniculate nucleus neurons, or correlations in the variability of lateral connections in a network of neurons. In particular, we find that for fixed dimensionality, a large noise variance can give rise to long lifetimes of synaptic strengths. This may be of physiological significance.
On the covariance matrices in the evaluated nuclear data
International Nuclear Information System (INIS)
Corcuera, R.P.
1983-05-01
The implications of the uncertainties of nuclear data on reactor calculations are shown. The concept of variance, covariance and correlation are expressed first by intuitive definitions and then through statistical theory. The format of the covariance data for ENDF/B is explained and the formulas to obtain the multigroup covariances are given. (Author) [pt
Lorentz Covariance of Langevin Equation
International Nuclear Information System (INIS)
Koide, T.; Denicol, G.S.; Kodama, T.
2008-01-01
Relativistic covariance of a Langevin type equation is discussed. The requirement of Lorentz invariance generates an entanglement between the force and noise terms so that the noise itself should not be a covariant quantity. (author)
Klees, R.; Slobbe, D. C.; Farahani, H. H.
2018-03-01
The posed question arises for instance in regional gravity field modelling using weighted least-squares techniques if the gravity field functionals are synthesised from the spherical harmonic coefficients of a satellite-only global gravity model (GGM), and are used as one of the noisy datasets. The associated noise covariance matrix, appeared to be extremely ill-conditioned with a singular value spectrum that decayed gradually to zero without any noticeable gap. We analysed three methods to deal with the ill-conditioned noise covariance matrix: Tihonov regularisation of the noise covariance matrix in combination with the standard formula for the weighted least-squares estimator, a formula of the weighted least-squares estimator, which does not involve the inverse noise covariance matrix, and an estimator based on Rao's unified theory of least-squares. Our analysis was based on a numerical experiment involving a set of height anomalies synthesised from the GGM GOCO05s, which is provided with a full noise covariance matrix. We showed that the three estimators perform similar, provided that the two regularisation parameters each method knows were chosen properly. As standard regularisation parameter choice rules do not apply here, we suggested a new parameter choice rule, and demonstrated its performance. Using this rule, we found that the differences between the three least-squares estimates were within noise. For the standard formulation of the weighted least-squares estimator with regularised noise covariance matrix, this required an exceptionally strong regularisation, much larger than one expected from the condition number of the noise covariance matrix. The preferred method is the inversion-free formulation of the weighted least-squares estimator, because of its simplicity with respect to the choice of the two regularisation parameters.
Earth Observing System Covariance Realism
Zaidi, Waqar H.; Hejduk, Matthew D.
2016-01-01
The purpose of covariance realism is to properly size a primary object's covariance in order to add validity to the calculation of the probability of collision. The covariance realism technique in this paper consists of three parts: collection/calculation of definitive state estimates through orbit determination, calculation of covariance realism test statistics at each covariance propagation point, and proper assessment of those test statistics. An empirical cumulative distribution function (ECDF) Goodness-of-Fit (GOF) method is employed to determine if a covariance is properly sized by comparing the empirical distribution of Mahalanobis distance calculations to the hypothesized parent 3-DoF chi-squared distribution. To realistically size a covariance for collision probability calculations, this study uses a state noise compensation algorithm that adds process noise to the definitive epoch covariance to account for uncertainty in the force model. Process noise is added until the GOF tests pass a group significance level threshold. The results of this study indicate that when outliers attributed to persistently high or extreme levels of solar activity are removed, the aforementioned covariance realism compensation method produces a tuned covariance with up to 80 to 90% of the covariance propagation timespan passing (against a 60% minimum passing threshold) the GOF tests-a quite satisfactory and useful result.
Selection of noise parameters for Kalman filter
Institute of Scientific and Technical Information of China (English)
Ka-Veng Yuen; Ka-In Hoi; Kai-Meng Mok
2007-01-01
The Bayesian probabilistic approach is proposed to estimate the process noise and measurement noise parameters for a Kalman filter. With state vectors and covariance matrices estimated by the Kalman filter, the likehood of the measurements can be constructed as a function of the process noise and measurement noise parameters. By maximizing the likklihood function with respect to these noise parameters, the optimal values can be obtained. Furthermore, the Bayesian probabilistic approach allows the associated uncertainty to be quantified. Examples using a single-degree-of-freedom system and a ten-story building illustrate the proposed method. The effect on the performance of the Kalman filter due to the selection of the process noise and measurement noise parameters was demonstrated. The optimal values of the noise parameters were found to be close to the actual values in the sense that the actual parameters were in the region with significant probability density. Through these examples, the Bayesian approach was shown to have the capability to provide accurate estimates of the noise parameters of the Kalman filter, and hence for state estimation.
Generalized Linear Covariance Analysis
Carpenter, James R.; Markley, F. Landis
2014-01-01
This talk presents a comprehensive approach to filter modeling for generalized covariance analysis of both batch least-squares and sequential estimators. We review and extend in two directions the results of prior work that allowed for partitioning of the state space into solve-for'' and consider'' parameters, accounted for differences between the formal values and the true values of the measurement noise, process noise, and textita priori solve-for and consider covariances, and explicitly partitioned the errors into subspaces containing only the influence of the measurement noise, process noise, and solve-for and consider covariances. In this work, we explicitly add sensitivity analysis to this prior work, and relax an implicit assumption that the batch estimator's epoch time occurs prior to the definitive span. We also apply the method to an integrated orbit and attitude problem, in which gyro and accelerometer errors, though not estimated, influence the orbit determination performance. We illustrate our results using two graphical presentations, which we call the variance sandpile'' and the sensitivity mosaic,'' and we compare the linear covariance results to confidence intervals associated with ensemble statistics from a Monte Carlo analysis.
Likelihood Approximation With Hierarchical Matrices For Large Spatial Datasets
Litvinenko, Alexander
2017-09-03
We use available measurements to estimate the unknown parameters (variance, smoothness parameter, and covariance length) of a covariance function by maximizing the joint Gaussian log-likelihood function. To overcome cubic complexity in the linear algebra, we approximate the discretized covariance function in the hierarchical (H-) matrix format. The H-matrix format has a log-linear computational cost and storage O(kn log n), where the rank k is a small integer and n is the number of locations. The H-matrix technique allows us to work with general covariance matrices in an efficient way, since H-matrices can approximate inhomogeneous covariance functions, with a fairly general mesh that is not necessarily axes-parallel, and neither the covariance matrix itself nor its inverse have to be sparse. We demonstrate our method with Monte Carlo simulations and an application to soil moisture data. The C, C++ codes and data are freely available.
Summary of the benchmark test on artificial noise data
Energy Technology Data Exchange (ETDEWEB)
Hoogenboom, J.E.; Ciftcioglu, O.; Dam, H. van
1988-01-01
A survey is given of the SMORN-V artificial noise benchmark test for checking autoregressive modelling of noise and testing anomaly detection methods. A detailed description of the system used to generate the signals is given. Contributions from 7 participants have been received. Not all participants executed both the tests on the stationary data and the anomaly data. Comparison of plots of transfer functions, noise contribution ratios and the spectrum of a noise source obtained from AR-analysis partly shows satisfactory agreement (except for normalization), partly distinct disagreement. This was also the case for the several parameters to be determined numerically. The covariance matrices of the intrinsic noise sources showed considerable differences. Participants dealing with the anomaly data used very different methods for anomaly detection. Two of them detected both anomalies present in the signals. One participant the first anomaly and the other participant the second anomaly only.
Summary of the benchmark test on artificial noise data
International Nuclear Information System (INIS)
Hoogenboom, J.E.; Ciftcioglu, O.; Dam, H. van
1988-01-01
A survey is given of the SMORN-V artificial noise benchmark test for checking autoregressive modelling of noise and testing anomaly detection methods. A detailed description of the system used to generate the signals is given. Contributions from 7 participants have been received. Not all participants executed both the tests on the stationary data and the anomaly data. Comparison of plots of transfer functions, noise contribution ratios and the spectrum of a noise source obtained from AR-analysis partly shows satisfactory agreement (except for normalization), partly distinct disagreement. This was also the case for the several parameters to be determined numerically. The covariance matrices of the intrinsic noise sources showed considerable differences. Participants dealing with the anomaly data used very different methods for anomaly detection. Two of them detected both anomalies present in the signals. One participant the first anomaly and the other participant the second anomaly only. (author)
Caballero-Águila, R.; Hermoso-Carazo, A.; Linares-Pérez, J.
2017-07-01
This paper studies the distributed fusion estimation problem from multisensor measured outputs perturbed by correlated noises and uncertainties modelled by random parameter matrices. Each sensor transmits its outputs to a local processor over a packet-erasure channel and, consequently, random losses may occur during transmission. Different white sequences of Bernoulli variables are introduced to model the transmission losses. For the estimation, each lost output is replaced by its estimator based on the information received previously, and only the covariances of the processes involved are used, without requiring the signal evolution model. First, a recursive algorithm for the local least-squares filters is derived by using an innovation approach. Then, the cross-correlation matrices between any two local filters is obtained. Finally, the distributed fusion filter weighted by matrices is obtained from the local filters by applying the least-squares criterion. The performance of the estimators and the influence of both sensor uncertainties and transmission losses on the estimation accuracy are analysed in a numerical example.
Updated Covariance Processing Capabilities in the AMPX Code System
International Nuclear Information System (INIS)
Wiarda, Dorothea; Dunn, Michael E.
2007-01-01
A concerted effort is in progress within the nuclear data community to provide new cross-section covariance data evaluations to support sensitivity/uncertainty analyses of fissionable systems. The objective of this work is to update processing capabilities of the AMPX library to process the latest Evaluated Nuclear Data File (ENDF)/B formats to generate covariance data libraries for radiation transport software such as SCALE. The module PUFF-IV was updated to allow processing of new ENDF covariance formats in the resolved resonance region. In the resolved resonance region, covariance matrices are given in terms of resonance parameters, which need to be processed into covariance matrices with respect to the group-averaged cross-section data. The parameter covariance matrix can be quite large if the evaluation has many resonances. The PUFF-IV code has recently been used to process an evaluation of 235U, which was prepared in collaboration between Oak Ridge National Laboratory and Los Alamos National Laboratory.
Multilevel maximum likelihood estimation with application to covariance matrices
Czech Academy of Sciences Publication Activity Database
Turčičová, Marie; Mandel, J.; Eben, Kryštof
Published online: 23 January ( 2018 ) ISSN 0361-0926 R&D Projects: GA ČR GA13-34856S Institutional support: RVO:67985807 Keywords : Fisher information * High dimension * Hierarchical maximum likelihood * Nested parameter spaces * Spectral diagonal covariance model * Sparse inverse covariance model Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 0.311, year: 2016
Recent Advances with the AMPX Covariance Processing Capabilities in PUFF-IV
International Nuclear Information System (INIS)
Wiarda, Dorothea; Arbanas, Goran; Leal, Luiz C.; Dunn, Michael E.
2008-01-01
The program PUFF-IV is used to process resonance parameter covariance information given in ENDF/B File 32 and point-wise covariance matrices given in ENDF/B File 33 into group-averaged covariances matrices on a user-supplied group structure. For large resonance covariance matrices, found for example in 235U, the execution time of PUFF-IV can be quite long. Recently the code was modified to take advandage of Basic Linear Algebra Subprograms (BLAS) routines for the most time-consuming matrix multiplications. This led to a substantial decrease in execution time. This faster processing capability allowed us to investigate the conversion of File 32 data into File 33 data using a larger number of user-defined groups. While conversion substantially reduces the ENDF/B file size requirements for evaluations with a large number of resonances, a trade-off is made between the number of groups used to represent the resonance parameter covariance as a point-wise covariance matrix and the file size. We are also investigating a hybrid version of the conversion, in which the low-energy part of the File 32 resonance parameter covariances matrix is retained and the correlations with higher energies as well as the high energy part are given in File 33.
Directory of Open Access Journals (Sweden)
Janiga-Ćmiel Anna
2016-12-01
Full Text Available The paper looks at the issues related to the research on and assessment of the contagion effect. Based on several examinations of two selected EU countries, Poland paired with one of the EU member states; it presents the interaction between their economic development. A DCC-GARCH model constructed for the purpose of the study was used to generate a covariance matrix Ht, which enabled the calculation of correlation matrices Rt. The resulting variance vectors were used to present a linear correlation model on which a further analysis of the contagion effect was based. The aim of the study was to test a contagion effect among selected EU countries in the years 2000–2014. The transmission channel under study was the GDP of a selected country. The empirical studies confirmed the existence of the contagion effect between the economic development of the Polish and selected EU economies.
A simple procedure to estimate reactivity with good noise filtering characteristics
International Nuclear Information System (INIS)
Shimazu, Yoichiro
2014-01-01
Highlights: • A new and simple on-line reactivity estimation method is proposed. • The estimator has robust noise filtering characteristics. • The noise filtering is equivalent to those of conventional reactivity meters. • The new estimator eliminates the burden of selecting optimum filter constants. • The new estimation performance is assessed without and with measurement noise. - Abstract: A new and simple on-line reactivity estimation method is proposed. The estimator has robust noise filtering characteristics without the use of complex filters. The noise filtering capability is equivalent to or better than that of a conventional estimator based on Inverse Point Kinetics (IPK). The new estimator can also eliminate the burden of selecting optimum filter time constants, such as would be required for the IPK-based estimator, or noise covariance matrices, which are needed if the extended Kalman filter (EKF) technique is used. In this paper, the new estimation method is introduced and its performance assessed without and with measurement noise
More on Estimation of Banded and Banded Toeplitz Covariance Matrices
Berntsson, Fredrik; Ohlson, Martin
2017-01-01
In this paper we consider two different linear covariance structures, e.g., banded and bended Toeplitz, and how to estimate them using different methods, e.g., by minimizing different norms. One way to estimate the parameters in a linear covariance structure is to use tapering, which has been shown to be the solution to a universal least squares problem. We know that tapering not always guarantee the positive definite constraints on the estimated covariance matrix and may not be a suitable me...
Undesirable effects of covariance matrix techniques for error analysis
International Nuclear Information System (INIS)
Seibert, D.
1994-01-01
Regression with χ 2 constructed from covariance matrices should not be used for some combinations of covariance matrices and fitting functions. Using the technique for unsuitable combinations can amplify systematic errors. This amplification is uncontrolled, and can produce arbitrarily inaccurate results that might not be ruled out by a χ 2 test. In addition, this technique can give incorrect (artificially small) errors for fit parameters. I give a test for this instability and a more robust (but computationally more intensive) method for fitting correlated data
Online updating and uncertainty quantification using nonstationary output-only measurement
Yuen, Ka-Veng; Kuok, Sin-Chi
2016-01-01
Extended Kalman filter (EKF) is widely adopted for state estimation and parametric identification of dynamical systems. In this algorithm, it is required to specify the covariance matrices of the process noise and measurement noise based on prior knowledge. However, improper assignment of these noise covariance matrices leads to unreliable estimation and misleading uncertainty estimation on the system state and model parameters. Furthermore, it may induce diverging estimation. To resolve these problems, we propose a Bayesian probabilistic algorithm for online estimation of the noise parameters which are used to characterize the noise covariance matrices. There are three major appealing features of the proposed approach. First, it resolves the divergence problem in the conventional usage of EKF due to improper choice of the noise covariance matrices. Second, the proposed approach ensures the reliability of the uncertainty quantification. Finally, since the noise parameters are allowed to be time-varying, nonstationary process noise and/or measurement noise are explicitly taken into account. Examples using stationary/nonstationary response of linear/nonlinear time-varying dynamical systems are presented to demonstrate the efficacy of the proposed approach. Furthermore, comparison with the conventional usage of EKF will be provided to reveal the necessity of the proposed approach for reliable model updating and uncertainty quantification.
Likelihood Approximation With Parallel Hierarchical Matrices For Large Spatial Datasets
Litvinenko, Alexander; Sun, Ying; Genton, Marc G.; Keyes, David E.
2017-01-01
The main goal of this article is to introduce the parallel hierarchical matrix library HLIBpro to the statistical community. We describe the HLIBCov package, which is an extension of the HLIBpro library for approximating large covariance matrices and maximizing likelihood functions. We show that an approximate Cholesky factorization of a dense matrix of size $2M\\times 2M$ can be computed on a modern multi-core desktop in few minutes. Further, HLIBCov is used for estimating the unknown parameters such as the covariance length, variance and smoothness parameter of a Matérn covariance function by maximizing the joint Gaussian log-likelihood function. The computational bottleneck here is expensive linear algebra arithmetics due to large and dense covariance matrices. Therefore covariance matrices are approximated in the hierarchical ($\\H$-) matrix format with computational cost $\\mathcal{O}(k^2n \\log^2 n/p)$ and storage $\\mathcal{O}(kn \\log n)$, where the rank $k$ is a small integer (typically $k<25$), $p$ the number of cores and $n$ the number of locations on a fairly general mesh. We demonstrate a synthetic example, where the true values of known parameters are known. For reproducibility we provide the C++ code, the documentation, and the synthetic data.
Likelihood Approximation With Parallel Hierarchical Matrices For Large Spatial Datasets
Litvinenko, Alexander
2017-11-01
The main goal of this article is to introduce the parallel hierarchical matrix library HLIBpro to the statistical community. We describe the HLIBCov package, which is an extension of the HLIBpro library for approximating large covariance matrices and maximizing likelihood functions. We show that an approximate Cholesky factorization of a dense matrix of size $2M\\\\times 2M$ can be computed on a modern multi-core desktop in few minutes. Further, HLIBCov is used for estimating the unknown parameters such as the covariance length, variance and smoothness parameter of a Matérn covariance function by maximizing the joint Gaussian log-likelihood function. The computational bottleneck here is expensive linear algebra arithmetics due to large and dense covariance matrices. Therefore covariance matrices are approximated in the hierarchical ($\\\\H$-) matrix format with computational cost $\\\\mathcal{O}(k^2n \\\\log^2 n/p)$ and storage $\\\\mathcal{O}(kn \\\\log n)$, where the rank $k$ is a small integer (typically $k<25$), $p$ the number of cores and $n$ the number of locations on a fairly general mesh. We demonstrate a synthetic example, where the true values of known parameters are known. For reproducibility we provide the C++ code, the documentation, and the synthetic data.
Neutron spectrum adjustment. The role of covariances
International Nuclear Information System (INIS)
Remec, I.
1992-01-01
Neutron spectrum adjustment method is shortly reviewed. Practical example dealing with power reactor pressure vessel exposure rates determination is analysed. Adjusted exposure rates are found only slightly affected by the covariances of measured reaction rates and activation cross sections, while the multigroup spectra covariances were found important. Approximate spectra covariance matrices, as suggested in Astm E944-89, were found useful but care is advised if they are applied in adjustments of spectra at locations without dosimetry. (author) [sl
Non-evaluation applications for covariance matrices
Energy Technology Data Exchange (ETDEWEB)
Smith, D.L.
1982-05-01
The possibility for application of covariance matrix techniques to a variety of common research problems other than formal data evaluation are demonstrated by means of several examples. These examples deal with such matters as fitting spectral data, deriving uncertainty estimates for results calculated from experimental data, obtaining the best values for plurally-measured quantities, and methods for analysis of cross section errors based on properties of the experiment. The examples deal with realistic situations encountered in the laboratory, and they are treated in sufficient detail to enable a careful reader to extrapolate the methods to related problems.
Relativistic covariant wave equations and acausality in external fields
International Nuclear Information System (INIS)
Pijlgroms, R.B.J.
1980-01-01
The author considers linear, finite dimensional, first order relativistic wave equations: (βsup(μ)ideltasub(μ)-β)PSI(x) = 0 with βsup(μ) and β constant matrices. Firstly , the question of the relativistic covariance conditions on these equations is considered. Then the theory of these equations with β non-singular is summarized. Theories with βsup(μ), β square matrices and β singular are also discussed. Non-square systems of covariant relativistic wave equations for arbitrary spin > 1 are then considered. Finally, the interaction with external fields and the acausality problem are discussed. (G.T.H.)
Evaluating functions of positive-definite matrices using colored-noise thermostats
Nava, Marco; Ceriotti, Michele; Dryzun, Chaim; Parrinello, Michele
2014-02-01
Many applications in computational science require computing the elements of a function of a large matrix. A commonly used approach is based on the the evaluation of the eigenvalue decomposition, a task that, in general, involves a computing time that scales with the cube of the size of the matrix. We present here a method that can be used to evaluate the elements of a function of a positive-definite matrix with a scaling that is linear for sparse matrices and quadratic in the general case. This methodology is based on the properties of the dynamics of a multidimensional harmonic potential coupled with colored-noise, generalized Langevin equation thermostats. This "f-thermostat" approach allows us to calculate directly elements of functions of a positive-definite matrix by carefully tailoring the properties of the stochastic dynamics. We demonstrate the scaling and the accuracy of this approach for both dense and sparse problems and compare the results with other established methodologies.
The application of sparse estimation of covariance matrix to quadratic discriminant analysis
Sun, Jiehuan; Zhao, Hongyu
2015-01-01
Background Although Linear Discriminant Analysis (LDA) is commonly used for classification, it may not be directly applied in genomics studies due to the large p, small n problem in these studies. Different versions of sparse LDA have been proposed to address this significant challenge. One implicit assumption of various LDA-based methods is that the covariance matrices are the same across different classes. However, rewiring of genetic networks (therefore different covariance matrices) acros...
Application of Parallel Hierarchical Matrices in Spatial Statistics and Parameter Identification
Litvinenko, Alexander
2018-04-20
Parallel H-matrices in spatial statistics 1. Motivation: improve statistical model 2. Tools: Hierarchical matrices [Hackbusch 1999] 3. Matern covariance function and joint Gaussian likelihood 4. Identification of unknown parameters via maximizing Gaussian log-likelihood 5. Implementation with HLIBPro
Transformation of covariant quark Wigner operator to noncovariant one
International Nuclear Information System (INIS)
Selikhov, A.V.
1989-01-01
The gauge in which covariant and noncovariant quark Wigner operators coincide has been found. In this gauge the representations of vector potential via field strength tensor is valid. The system of equations for the coefficients of covariant Wigner operator expansion in the basis γ-matrices algebra is obtained. 12 refs.; 3 figs
Criteria of the validation of experimental and evaluated covariance data
International Nuclear Information System (INIS)
Badikov, S.
2008-01-01
The criteria of the validation of experimental and evaluated covariance data are reviewed. In particular: a) the criterion of the positive definiteness for covariance matrices, b) the relationship between the 'integral' experimental and estimated uncertainties, c) the validity of the statistical invariants, d) the restrictions imposed to correlations between experimental errors, are described. Applying these criteria in nuclear data evaluation was considered and 4 particular points have been examined. First preserving positive definiteness of covariance matrices in case of arbitrary transformation of a random vector was considered, properties of the covariance matrices in operations widely used in neutron and reactor physics (splitting and collapsing energy groups, averaging the physical values over energy groups, estimation parameters on the basis of measurements by means of generalized least squares method) were studied. Secondly, an algorithm for comparison of experimental and estimated 'integral' uncertainties was developed, square root of determinant of a covariance matrix is recommended for use in nuclear data evaluation as a measure of 'integral' uncertainty for vectors of experimental and estimated values. Thirdly, a set of statistical invariants-values which are preserved in statistical processing was presented. And fourthly, the inequality that signals a correlation between experimental errors that leads to unphysical values is given. An application is given concerning the cross-section of the (n,t) reaction on Li 6 with a neutron incident energy comprised between 1 and 100 keV
Uncertainty covariances in robotics applications
International Nuclear Information System (INIS)
Smith, D.L.
1984-01-01
The application of uncertainty covariance matrices in the analysis of robot trajectory errors is explored. First, relevant statistical concepts are reviewed briefly. Then, a simple, hypothetical robot model is considered to illustrate methods for error propagation and performance test data evaluation. The importance of including error correlations is emphasized
International Nuclear Information System (INIS)
Bachoc, Francois
2014-01-01
Covariance parameter estimation of Gaussian processes is analyzed in an asymptotic framework. The spatial sampling is a randomly perturbed regular grid and its deviation from the perfect regular grid is controlled by a single scalar regularity parameter. Consistency and asymptotic normality are proved for the Maximum Likelihood and Cross Validation estimators of the covariance parameters. The asymptotic covariance matrices of the covariance parameter estimators are deterministic functions of the regularity parameter. By means of an exhaustive study of the asymptotic covariance matrices, it is shown that the estimation is improved when the regular grid is strongly perturbed. Hence, an asymptotic confirmation is given to the commonly admitted fact that using groups of observation points with small spacing is beneficial to covariance function estimation. Finally, the prediction error, using a consistent estimator of the covariance parameters, is analyzed in detail. (authors)
Impact of the 235U Covariance Data in Benchmark Calculations
International Nuclear Information System (INIS)
Leal, Luiz C.; Mueller, D.; Arbanas, G.; Wiarda, D.; Derrien, H.
2008-01-01
The error estimation for calculated quantities relies on nuclear data uncertainty information available in the basic nuclear data libraries such as the U.S. Evaluated Nuclear Data File (ENDF/B). The uncertainty files (covariance matrices) in the ENDF/B library are generally obtained from analysis of experimental data. In the resonance region, the computer code SAMMY is used for analyses of experimental data and generation of resonance parameters. In addition to resonance parameters evaluation, SAMMY also generates resonance parameter covariance matrices (RPCM). SAMMY uses the generalized least-squares formalism (Bayes method) together with the resonance formalism (R-matrix theory) for analysis of experimental data. Two approaches are available for creation of resonance-parameter covariance data. (1) During the data-evaluation process, SAMMY generates both a set of resonance parameters that fit the experimental data and the associated resonance-parameter covariance matrix. (2) For existing resonance-parameter evaluations for which no resonance-parameter covariance data are available, SAMMY can retroactively create a resonance-parameter covariance matrix. The retroactive method was used to generate covariance data for 235U. The resulting 235U covariance matrix was then used as input to the PUFF-IV code, which processed the covariance data into multigroup form, and to the TSUNAMI code, which calculated the uncertainty in the multiplication factor due to uncertainty in the experimental cross sections. The objective of this work is to demonstrate the use of the 235U covariance data in calculations of critical benchmark systems
Impact of the 235U covariance data in benchmark calculations
International Nuclear Information System (INIS)
Leal, Luiz; Mueller, Don; Arbanas, Goran; Wiarda, Dorothea; Derrien, Herve
2008-01-01
The error estimation for calculated quantities relies on nuclear data uncertainty information available in the basic nuclear data libraries such as the U.S. Evaluated Nuclear Data File (ENDF/B). The uncertainty files (covariance matrices) in the ENDF/B library are generally obtained from analysis of experimental data. In the resonance region, the computer code SAMMY is used for analyses of experimental data and generation of resonance parameters. In addition to resonance parameters evaluation, SAMMY also generates resonance parameter covariance matrices (RPCM). SAMMY uses the generalized least-squares formalism (Bayes' method) together with the resonance formalism (R-matrix theory) for analysis of experimental data. Two approaches are available for creation of resonance-parameter covariance data. (1) During the data-evaluation process, SAMMY generates both a set of resonance parameters that fit the experimental data and the associated resonance-parameter covariance matrix. (2) For existing resonance-parameter evaluations for which no resonance-parameter covariance data are available, SAMMY can retroactively create a resonance-parameter covariance matrix. The retroactive method was used to generate covariance data for 235 U. The resulting 235 U covariance matrix was then used as input to the PUFF-IV code, which processed the covariance data into multigroup form, and to the TSUNAMI code, which calculated the uncertainty in the multiplication factor due to uncertainty in the experimental cross sections. The objective of this work is to demonstrate the use of the 235 U covariance data in calculations of critical benchmark systems. (authors)
International Nuclear Information System (INIS)
Smith, D.L.
1987-03-01
Attention is called to the considerable sensitivity of many uncertainty calculations to the magnitude of the long-ranged correlations which appear in covariance matrices. If such correlations do exist, they must be included in order to properly assess the impact of the uncertainties in the data. If, however, certain assumed long-range correlations are unrealistic, then analyses involving such correlation information are almost certain to produce misleading results. The issue is discussed in general terms, and its importance is illustrated by examples based in part on recent work from this laboratory. Some practical suggestions are offered for dealing with the matter of correlations in instances where the available information is incomplete. 23 refs., 2 figs., 1 tab
ERRORJ. Covariance processing code. Version 2.2
International Nuclear Information System (INIS)
Chiba, Go
2004-07-01
ERRORJ is the covariance processing code that can produce covariance data of multi-group cross sections, which are essential for uncertainty analyses of nuclear parameters, such as neutron multiplication factor. The ERRORJ code can process the covariance data of cross sections including resonance parameters, angular and energy distributions of secondary neutrons. Those covariance data cannot be processed by the other covariance processing codes. ERRORJ has been modified and the version 2.2 has been developed. This document describes the modifications and how to use. The main topics of the modifications are as follows. Non-diagonal elements of covariance matrices are calculated in the resonance energy region. Option for high-speed calculation is implemented. Perturbation amount is optimized in a sensitivity calculation. Effect of the resonance self-shielding on covariance of multi-group cross section can be considered. It is possible to read a compact covariance format proposed by N.M. Larson. (author)
A Generalized Autocovariance Least-Squares Method for Covariance Estimation
DEFF Research Database (Denmark)
Åkesson, Bernt Magnus; Jørgensen, John Bagterp; Poulsen, Niels Kjølstad
2007-01-01
A generalization of the autocovariance least- squares method for estimating noise covariances is presented. The method can estimate mutually correlated system and sensor noise and can be used with both the predicting and the filtering form of the Kalman filter.......A generalization of the autocovariance least- squares method for estimating noise covariances is presented. The method can estimate mutually correlated system and sensor noise and can be used with both the predicting and the filtering form of the Kalman filter....
Multivariate covariance generalized linear models
DEFF Research Database (Denmark)
Bonat, W. H.; Jørgensen, Bent
2016-01-01
are fitted by using an efficient Newton scoring algorithm based on quasi-likelihood and Pearson estimating functions, using only second-moment assumptions. This provides a unified approach to a wide variety of types of response variables and covariance structures, including multivariate extensions......We propose a general framework for non-normal multivariate data analysis called multivariate covariance generalized linear models, designed to handle multivariate response variables, along with a wide range of temporal and spatial correlation structures defined in terms of a covariance link...... function combined with a matrix linear predictor involving known matrices. The method is motivated by three data examples that are not easily handled by existing methods. The first example concerns multivariate count data, the second involves response variables of mixed types, combined with repeated...
Extensive set of low-fidelity cross sections covariances in fast neutron region
International Nuclear Information System (INIS)
Pigni, M.T.; Herman, M.; Oblozinsky, P.
2008-01-01
We produced a large set of neutron cross section covariances in the energy range of 5 keV - 20 MeV. The covariance matrices were calculated for 307 isotopes divided into three major regions: structural materials, fission products, and heavy nuclei. These results have been developed to provide initial, but consistent estimates of covariance data for nuclear criticality safety applications. The methodology for the determination of such covariance matrices is presented. It combines the nuclear reaction model code EMPIRE which calculates sensitivity of cross sections to nuclear reaction model parameters, and the Bayesian code KALMAN that propagates uncertainties of the model parameters to cross sections. Taking into account large number of materials, only marginal reference to experimental data was made. The covariances were derived from the perturbation of several key model parameters selected by the sensitivity analysis. These parameters refer to the optical model potential, the level densities and the strength of the pre-equilibrium emission. This work represents the first try ever to generate nuclear data covariances on such a large scale. (authors)
On the regularity of the covariance matrix of a discretized scalar field on the sphere
Energy Technology Data Exchange (ETDEWEB)
Bilbao-Ahedo, J.D. [Departamento de Física Moderna, Universidad de Cantabria, Av. los Castros s/n, 39005 Santander (Spain); Barreiro, R.B.; Herranz, D.; Vielva, P.; Martínez-González, E., E-mail: bilbao@ifca.unican.es, E-mail: barreiro@ifca.unican.es, E-mail: herranz@ifca.unican.es, E-mail: vielva@ifca.unican.es, E-mail: martinez@ifca.unican.es [Instituto de Física de Cantabria (CSIC-UC), Av. los Castros s/n, 39005 Santander (Spain)
2017-02-01
We present a comprehensive study of the regularity of the covariance matrix of a discretized field on the sphere. In a particular situation, the rank of the matrix depends on the number of pixels, the number of spherical harmonics, the symmetries of the pixelization scheme and the presence of a mask. Taking into account the above mentioned components, we provide analytical expressions that constrain the rank of the matrix. They are obtained by expanding the determinant of the covariance matrix as a sum of determinants of matrices made up of spherical harmonics. We investigate these constraints for five different pixelizations that have been used in the context of Cosmic Microwave Background (CMB) data analysis: Cube, Icosahedron, Igloo, GLESP and HEALPix, finding that, at least in the considered cases, the HEALPix pixelization tends to provide a covariance matrix with a rank closer to the maximum expected theoretical value than the other pixelizations. The effect of the propagation of numerical errors in the regularity of the covariance matrix is also studied for different computational precisions, as well as the effect of adding a certain level of noise in order to regularize the matrix. In addition, we investigate the application of the previous results to a particular example that requires the inversion of the covariance matrix: the estimation of the CMB temperature power spectrum through the Quadratic Maximum Likelihood algorithm. Finally, some general considerations in order to achieve a regular covariance matrix are also presented.
ℋ-matrix techniques for approximating large covariance matrices and estimating its parameters
Litvinenko, Alexander; Genton, Marc G.; Sun, Ying; Keyes, David E.
2016-01-01
In this work the task is to use the available measurements to estimate unknown hyper-parameters (variance, smoothness parameter and covariance length) of the covariance function. We do it by maximizing the joint log-likelihood function. This is a non-convex and non-linear problem. To overcome cubic complexity in linear algebra, we approximate the discretised covariance function in the hierarchical (ℋ-) matrix format. The ℋ-matrix format has a log-linear computational cost and storage O(knlogn), where rank k is a small integer. On each iteration step of the optimization procedure the covariance matrix itself, its determinant and its Cholesky decomposition are recomputed within ℋ-matrix format. (© 2016 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)
ℋ-matrix techniques for approximating large covariance matrices and estimating its parameters
Litvinenko, Alexander
2016-10-25
In this work the task is to use the available measurements to estimate unknown hyper-parameters (variance, smoothness parameter and covariance length) of the covariance function. We do it by maximizing the joint log-likelihood function. This is a non-convex and non-linear problem. To overcome cubic complexity in linear algebra, we approximate the discretised covariance function in the hierarchical (ℋ-) matrix format. The ℋ-matrix format has a log-linear computational cost and storage O(knlogn), where rank k is a small integer. On each iteration step of the optimization procedure the covariance matrix itself, its determinant and its Cholesky decomposition are recomputed within ℋ-matrix format. (© 2016 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)
New perspective in covariance evaluation for nuclear data
International Nuclear Information System (INIS)
Kanda, Y.
1992-01-01
Methods of nuclear data evaluation have been highly developed during the past decade, especially after introducing the concept of covariance. This makes it utmost important how to evaluate covariance matrices for nuclear data. It can be said that covariance evaluation is just the nuclear data evaluation, because the covariance matrix has quantitatively decisive function in current evaluation methods. The covariance primarily represents experimental uncertainties. However, correlation of individual uncertainties between different data must be taken into account and it can not be conducted without detailed physical considerations on experimental conditions. This procedure depends on the evaluator and the estimated covariance does also. The mathematical properties of the covariance have been intensively discussed. Their physical properties should be studied to apply it to the nuclear data evaluation, and then, in this report, are reviewed to give the base for further development of the covariance application. (orig.)
EQUIVALENT MODELS IN COVARIANCE STRUCTURE-ANALYSIS
LUIJBEN, TCW
1991-01-01
Defining equivalent models as those that reproduce the same set of covariance matrices, necessary and sufficient conditions are stated for the local equivalence of two expanded identified models M1 and M2 when fitting the more restricted model M0. Assuming several regularity conditions, the rank
Quality Quantification of Evaluated Cross Section Covariances
International Nuclear Information System (INIS)
Varet, S.; Dossantos-Uzarralde, P.; Vayatis, N.
2015-01-01
Presently, several methods are used to estimate the covariance matrix of evaluated nuclear cross sections. Because the resulting covariance matrices can be different according to the method used and according to the assumptions of the method, we propose a general and objective approach to quantify the quality of the covariance estimation for evaluated cross sections. The first step consists in defining an objective criterion. The second step is computation of the criterion. In this paper the Kullback-Leibler distance is proposed for the quality quantification of a covariance matrix estimation and its inverse. It is based on the distance to the true covariance matrix. A method based on the bootstrap is presented for the estimation of this criterion, which can be applied with most methods for covariance matrix estimation and without the knowledge of the true covariance matrix. The full approach is illustrated on the 85 Rb nucleus evaluations and the results are then used for a discussion on scoring and Monte Carlo approaches for covariance matrix estimation of the cross section evaluations
International Nuclear Information System (INIS)
Kodeli, Ivan-Alexander
2005-01-01
The new cross-section covariance matrix library ZZ-VITAMIN-J/COVA/EFF3 intended to simplify and encourage sensitivity and uncertainty analysis was prepared and is available from the NEA Data Bank. The library is organised in a ready-to-use form including both the covariance matrix data as well as processing tools:-Cross-section covariance matrices from the EFF-3 evaluation for five materials: 9 Be, 28 Si, 56 Fe, 58 Ni and 60 Ni. Other data will be included when available. -FORTRAN program ANGELO-2 to extrapolate/interpolate the covariance matrices to a users' defined energy group structure. -FORTRAN program LAMBDA to verify the mathematical properties of the covariance matrices, like symmetry, positive definiteness, etc. The preparation, testing and use of the covariance matrix library are presented. The uncertainties based on the cross-section covariance data were compared with those based on other evaluations, like ENDF/B-VI. The collapsing procedure used in the ANGELO-2 code was compared and validated with the one used in the NJOY system
Runcie, Daniel E; Mukherjee, Sayan
2013-07-01
Quantitative genetic studies that model complex, multivariate phenotypes are important for both evolutionary prediction and artificial selection. For example, changes in gene expression can provide insight into developmental and physiological mechanisms that link genotype and phenotype. However, classical analytical techniques are poorly suited to quantitative genetic studies of gene expression where the number of traits assayed per individual can reach many thousand. Here, we derive a Bayesian genetic sparse factor model for estimating the genetic covariance matrix (G-matrix) of high-dimensional traits, such as gene expression, in a mixed-effects model. The key idea of our model is that we need consider only G-matrices that are biologically plausible. An organism's entire phenotype is the result of processes that are modular and have limited complexity. This implies that the G-matrix will be highly structured. In particular, we assume that a limited number of intermediate traits (or factors, e.g., variations in development or physiology) control the variation in the high-dimensional phenotype, and that each of these intermediate traits is sparse - affecting only a few observed traits. The advantages of this approach are twofold. First, sparse factors are interpretable and provide biological insight into mechanisms underlying the genetic architecture. Second, enforcing sparsity helps prevent sampling errors from swamping out the true signal in high-dimensional data. We demonstrate the advantages of our model on simulated data and in an analysis of a published Drosophila melanogaster gene expression data set.
How (not) to teach Lorentz covariance of the Dirac equation
International Nuclear Information System (INIS)
Nikolić, Hrvoje
2014-01-01
In the textbook proofs of the Lorentz covariance of the Dirac equation, one treats the wave function as a spinor and gamma matrices as scalars, leading to a quite complicated formalism with several pedagogic drawbacks. As an alternative, I propose to teach the Dirac equation and its Lorentz covariance by using a much simpler, but physically equivalent formalism, in which these drawbacks do not appear. In this alternative formalism, the wave function transforms as a scalar and gamma matrices as components of a vector, such that the standard physically relevant bilinear combinations do not change their transformation properties. The alternative formalism allows also a natural construction of some additional non-standard bilinear combinations with well-defined transformation properties. (paper)
Robust Covariance Estimators Based on Information Divergences and Riemannian Manifold
Directory of Open Access Journals (Sweden)
Xiaoqiang Hua
2018-03-01
Full Text Available This paper proposes a class of covariance estimators based on information divergences in heterogeneous environments. In particular, the problem of covariance estimation is reformulated on the Riemannian manifold of Hermitian positive-definite (HPD matrices. The means associated with information divergences are derived and used as the estimators. Without resorting to the complete knowledge of the probability distribution of the sample data, the geometry of the Riemannian manifold of HPD matrices is considered in mean estimators. Moreover, the robustness of mean estimators is analyzed using the influence function. Simulation results indicate the robustness and superiority of an adaptive normalized matched filter with our proposed estimators compared with the existing alternatives.
Inference for High-dimensional Differential Correlation Matrices.
Cai, T Tony; Zhang, Anru
2016-01-01
Motivated by differential co-expression analysis in genomics, we consider in this paper estimation and testing of high-dimensional differential correlation matrices. An adaptive thresholding procedure is introduced and theoretical guarantees are given. Minimax rate of convergence is established and the proposed estimator is shown to be adaptively rate-optimal over collections of paired correlation matrices with approximately sparse differences. Simulation results show that the procedure significantly outperforms two other natural methods that are based on separate estimation of the individual correlation matrices. The procedure is also illustrated through an analysis of a breast cancer dataset, which provides evidence at the gene co-expression level that several genes, of which a subset has been previously verified, are associated with the breast cancer. Hypothesis testing on the differential correlation matrices is also considered. A test, which is particularly well suited for testing against sparse alternatives, is introduced. In addition, other related problems, including estimation of a single sparse correlation matrix, estimation of the differential covariance matrices, and estimation of the differential cross-correlation matrices, are also discussed.
High-Dimensional Multivariate Repeated Measures Analysis with Unequal Covariance Matrices
Harrar, Solomon W.; Kong, Xiaoli
2015-01-01
In this paper, test statistics for repeated measures design are introduced when the dimension is large. By large dimension is meant the number of repeated measures and the total sample size grow together but either one could be larger than the other. Asymptotic distribution of the statistics are derived for the equal as well as unequal covariance cases in the balanced as well as unbalanced cases. The asymptotic framework considered requires proportional growth of the sample sizes and the dimension of the repeated measures in the unequal covariance case. In the equal covariance case, one can grow at much faster rate than the other. The derivations of the asymptotic distributions mimic that of Central Limit Theorem with some important peculiarities addressed with sufficient rigor. Consistent and unbiased estimators of the asymptotic variances, which make efficient use of all the observations, are also derived. Simulation study provides favorable evidence for the accuracy of the asymptotic approximation under the null hypothesis. Power simulations have shown that the new methods have comparable power with a popular method known to work well in low-dimensional situation but the new methods have shown enormous advantage when the dimension is large. Data from Electroencephalograph (EEG) experiment is analyzed to illustrate the application of the results. PMID:26778861
TRANSPOSABLE REGULARIZED COVARIANCE MODELS WITH AN APPLICATION TO MISSING DATA IMPUTATION.
Allen, Genevera I; Tibshirani, Robert
2010-06-01
Missing data estimation is an important challenge with high-dimensional data arranged in the form of a matrix. Typically this data matrix is transposable , meaning that either the rows, columns or both can be treated as features. To model transposable data, we present a modification of the matrix-variate normal, the mean-restricted matrix-variate normal , in which the rows and columns each have a separate mean vector and covariance matrix. By placing additive penalties on the inverse covariance matrices of the rows and columns, these so called transposable regularized covariance models allow for maximum likelihood estimation of the mean and non-singular covariance matrices. Using these models, we formulate EM-type algorithms for missing data imputation in both the multivariate and transposable frameworks. We present theoretical results exploiting the structure of our transposable models that allow these models and imputation methods to be applied to high-dimensional data. Simulations and results on microarray data and the Netflix data show that these imputation techniques often outperform existing methods and offer a greater degree of flexibility.
Dark matter statistics for large galaxy catalogs: power spectra and covariance matrices
Klypin, Anatoly; Prada, Francisco
2018-06-01
Large-scale surveys of galaxies require accurate theoretical predictions of the dark matter clustering for thousands of mock galaxy catalogs. We demonstrate that this goal can be achieve with the new Parallel Particle-Mesh (PM) N-body code GLAM at a very low computational cost. We run ˜22, 000 simulations with ˜2 billion particles that provide ˜1% accuracy of the dark matter power spectra P(k) for wave-numbers up to k ˜ 1hMpc-1. Using this large data-set we study the power spectrum covariance matrix. In contrast to many previous analytical and numerical results, we find that the covariance matrix normalised to the power spectrum C(k, k΄)/P(k)P(k΄) has a complex structure of non-diagonal components: an upturn at small k, followed by a minimum at k ≈ 0.1 - 0.2 hMpc-1, and a maximum at k ≈ 0.5 - 0.6 hMpc-1. The normalised covariance matrix strongly evolves with redshift: C(k, k΄)∝δα(t)P(k)P(k΄), where δ is the linear growth factor and α ≈ 1 - 1.25, which indicates that the covariance matrix depends on cosmological parameters. We also show that waves longer than 1h-1Gpc have very little impact on the power spectrum and covariance matrix. This significantly reduces the computational costs and complexity of theoretical predictions: relatively small volume ˜(1h-1Gpc)3 simulations capture the necessary properties of dark matter clustering statistics. As our results also indicate, achieving ˜1% errors in the covariance matrix for k < 0.50 hMpc-1 requires a resolution better than ɛ ˜ 0.5h-1Mpc.
Covariance structure in the skull of Catarrhini: a case of pattern stasis and magnitude evolution.
de Oliveira, Felipe Bandoni; Porto, Arthur; Marroig, Gabriel
2009-04-01
The study of the genetic variance/covariance matrix (G-matrix) is a recent and fruitful approach in evolutionary biology, providing a window of investigating for the evolution of complex characters. Although G-matrix studies were originally conducted for microevolutionary timescales, they could be extrapolated to macroevolution as long as the G-matrix remains relatively constant, or proportional, along the period of interest. A promising approach to investigating the constancy of G-matrices is to compare their phenotypic counterparts (P-matrices) in a large group of related species; if significant similarity is found among several taxa, it is very likely that the underlying G-matrices are also equivalent. Here we study the similarity of covariance and correlation structure in a broad sample of Old World monkeys and apes (Catarrhini). We made phylogenetically structured comparisons of correlation and covariance matrices derived from 39 skull traits, ranging from between species to the superfamily level. We also compared the overall magnitude of integration between skull traits (r2) for all Catarrhini genera. Our results show that P-matrices were not strictly constant among catarrhines, but the amount of divergence observed among taxa was generally low. There was significant and positive correlation between the amount of divergence in correlation and covariance patterns among the 30 genera and their phylogenetic distances derived from a recently proposed phylogenetic hypothesis. Our data demonstrate that the P-matrices remained relatively similar along the evolutionary history of catarrhines, and comparisons with the G-matrix available for a New World monkey genus (Saguinus) suggests that the same holds for all anthropoids. The magnitude of integration, in contrast, varied considerably among genera, indicating that evolution of the magnitude, rather than the pattern of inter-trait correlations, might have played an important role in the diversification of the
Westgate, Philip M
2016-01-01
When generalized estimating equations (GEE) incorporate an unstructured working correlation matrix, the variances of regression parameter estimates can inflate due to the estimation of the correlation parameters. In previous work, an approximation for this inflation that results in a corrected version of the sandwich formula for the covariance matrix of regression parameter estimates was derived. Use of this correction for correlation structure selection also reduces the over-selection of the unstructured working correlation matrix. In this manuscript, we conduct a simulation study to demonstrate that an increase in variances of regression parameter estimates can occur when GEE incorporates structured working correlation matrices as well. Correspondingly, we show the ability of the corrected version of the sandwich formula to improve the validity of inference and correlation structure selection. We also study the relative influences of two popular corrections to a different source of bias in the empirical sandwich covariance estimator.
The utility of covariance of combining ability in plant breeding.
Arunachalam, V
1976-11-01
The definition of covariances of half- and full sibs, and hence that of variances of general and specific combining ability with regard to a quantitative character, is extended to take into account the respective covariances between a pair of characters. The interpretation of the dispersion and correlation matrices of general and specific combining ability is discussed by considering a set of single, three- and four-way crosses, made using diallel and line × tester mating systems in Pennisetum typhoides. The general implications of the concept of covariance of combining ability in plant breeding are discussed.
Congedo, Marco; Barachant, Alexandre
2015-01-01
Currently the Riemannian geometry of symmetric positive definite (SPD) matrices is gaining momentum as a powerful tool in a wide range of engineering applications such as image, radar and biomedical data signal processing. If the data is not natively represented in the form of SPD matrices, typically we may summarize them in such form by estimating covariance matrices of the data. However once we manipulate such covariance matrices on the Riemannian manifold we lose the representation in the original data space. For instance, we can evaluate the geometric mean of a set of covariance matrices, but not the geometric mean of the data generating the covariance matrices, the space of interest in which the geometric mean can be interpreted. As a consequence, Riemannian information geometry is often perceived by non-experts as a "black-box" tool and this perception prevents a wider adoption in the scientific community. Hereby we show that we can overcome this limitation by constructing a special form of SPD matrix embedding both the covariance structure of the data and the data itself. Incidentally, whenever the original data can be represented in the form of a generic data matrix (not even square), this special SPD matrix enables an exhaustive and unique description of the data up to second-order statistics. This is achieved embedding the covariance structure of both the rows and columns of the data matrix, allowing naturally a wide range of possible applications and bringing us over and above just an interpretability issue. We demonstrate the method by manipulating satellite images (pansharpening) and event-related potentials (ERPs) of an electroencephalography brain-computer interface (BCI) study. The first example illustrates the effect of moving along geodesics in the original data space and the second provides a novel estimation of ERP average (geometric mean), showing that, in contrast to the usual arithmetic mean, this estimation is robust to outliers. In
Prewhitening for Rank-Deficient Noise in Subspace Methods for Noise Reduction
DEFF Research Database (Denmark)
Hansen, Per Christian; Jensen, Søren Holdt
2005-01-01
A fundamental issue in connection with subspace methods for noise reduction is that the covariance matrix for the noise is required to have full rank, in order for the prewhitening step to be defined. However, there are important cases where this requirement is not fulfilled, e.g., when the noise...... has narrow-band characteristics, or in the case of tonal noise. We extend the concept of prewhitening to include the case when the noise covariance matrix is rank deficient, using a weighted pseudoinverse and the quotient SVD, and we show how to formulate a general rank-reduction algorithm that works...... also for rank deficient noise. We also demonstrate how to formulate this algorithm by means of a quotient ULV decomposition, which allows for faster computation and updating. Finally we apply our algorithm to a problem involving a speech signal contaminated by narrow-band noise....
HIGH DIMENSIONAL COVARIANCE MATRIX ESTIMATION IN APPROXIMATE FACTOR MODELS.
Fan, Jianqing; Liao, Yuan; Mincheva, Martina
2011-01-01
The variance covariance matrix plays a central role in the inferential theories of high dimensional factor models in finance and economics. Popular regularization methods of directly exploiting sparsity are not directly applicable to many financial problems. Classical methods of estimating the covariance matrices are based on the strict factor models, assuming independent idiosyncratic components. This assumption, however, is restrictive in practical applications. By assuming sparse error covariance matrix, we allow the presence of the cross-sectional correlation even after taking out common factors, and it enables us to combine the merits of both methods. We estimate the sparse covariance using the adaptive thresholding technique as in Cai and Liu (2011), taking into account the fact that direct observations of the idiosyncratic components are unavailable. The impact of high dimensionality on the covariance matrix estimation based on the factor structure is then studied.
Shepherd, Daniel; Dirks, Kim; Welch, David; McBride, David; Landon, Jason
2016-08-06
Air pollution originating from road traffic is a known risk factor of respiratory and cardiovascular disease (both in terms of chronic and acute effects). While adverse effects on cardiovascular health have also been linked with noise (after controlling for air pollution), noise exposure has been commonly linked to sleep impairment and negative emotional reactions. Health is multi-faceted, both conceptually and operationally; Health-Related Quality of Life (HRQOL) is one of many measures capable of probing health. In this study, we examine pre-collected data from postal surveys probing HRQOL obtained from a variety of urban, suburban, and rural contexts across the North Island of New Zealand. Analyses focus on the covariance between air pollution annoyance and noise annoyances, and their independent and combined effects on HRQOL. Results indicate that the highest ratings of air pollution annoyance and noise annoyances were for residents living close to the motorway, while the lowest were for rural residents. Most of the city samples indicated no significant difference between air pollution- and noise-annoyance ratings, and of all of the correlations between air pollution- and noise-annoyance, the highest were found in the city samples. These findings suggest that annoyance is driven by exposure to environmental factors and not personality characteristics. Analysis of HRQOL indicated that air pollution annoyance predicts greater variability in the physical HRQOL domain while noise annoyance predicts greater variability in the psychological, social and environmental domains. The lack of an interaction effect between air pollution annoyance and noise annoyance suggests that air pollution and noise impact on health independently. These results echo those obtained from objective measures of health and suggest that mitigation of traffic effects should address both air and noise pollution.
Shepherd, Daniel; Dirks, Kim; Welch, David; McBride, David; Landon, Jason
2016-01-01
Air pollution originating from road traffic is a known risk factor of respiratory and cardiovascular disease (both in terms of chronic and acute effects). While adverse effects on cardiovascular health have also been linked with noise (after controlling for air pollution), noise exposure has been commonly linked to sleep impairment and negative emotional reactions. Health is multi-faceted, both conceptually and operationally; Health-Related Quality of Life (HRQOL) is one of many measures capable of probing health. In this study, we examine pre-collected data from postal surveys probing HRQOL obtained from a variety of urban, suburban, and rural contexts across the North Island of New Zealand. Analyses focus on the covariance between air pollution annoyance and noise annoyances, and their independent and combined effects on HRQOL. Results indicate that the highest ratings of air pollution annoyance and noise annoyances were for residents living close to the motorway, while the lowest were for rural residents. Most of the city samples indicated no significant difference between air pollution- and noise-annoyance ratings, and of all of the correlations between air pollution- and noise-annoyance, the highest were found in the city samples. These findings suggest that annoyance is driven by exposure to environmental factors and not personality characteristics. Analysis of HRQOL indicated that air pollution annoyance predicts greater variability in the physical HRQOL domain while noise annoyance predicts greater variability in the psychological, social and environmental domains. The lack of an interaction effect between air pollution annoyance and noise annoyance suggests that air pollution and noise impact on health independently. These results echo those obtained from objective measures of health and suggest that mitigation of traffic effects should address both air and noise pollution. PMID:27509512
Covariant differential calculus on quantum Minkowski space and the q-analogue of Dirac equation
International Nuclear Information System (INIS)
Song Xingchang; Academia Sinica, Beijing
1992-01-01
The covariant differential calculus on the quantum Minkowski space is presented with the help of the generalized Wess-Zumino method and the quantum Pauli matrices and quantum Dirac matrices are constructed parallel to those in the classical case. Combining these two aspects a q-analogue of Dirac equation follows directly. (orig.)
Positive semidefinite integrated covariance estimation, factorizations and asynchronicity
DEFF Research Database (Denmark)
Boudt, Kris; Laurent, Sébastien; Lunde, Asger
2017-01-01
An estimator of the ex-post covariation of log-prices under asynchronicity and microstructure noise is proposed. It uses the Cholesky factorization of the covariance matrix in order to exploit the heterogeneity in trading intensities to estimate the different parameters sequentially with as many...
Paragrassmann analysis and covariant quantum algebras
International Nuclear Information System (INIS)
Filippov, A.T.; Isaev, A.P.; Kurdikov, A.B.; Pyatov, P.N.
1993-01-01
This report is devoted to the consideration from the algebraic point of view the paragrassmann algebras with one and many paragrassmann generators Θ i , Θ p+1 i = 0. We construct the paragrassmann versions of the Heisenberg algebra. For the special case, this algebra is nothing but the algebra for coordinates and derivatives considered in the context of covariant differential calculus on quantum hyperplane. The parameter of deformation q in our case is (p+1)-root of unity. Our construction is nondegenerate only for even p. Taking bilinear combinations of paragrassmann derivatives and coordinates we realize generators for the covariant quantum algebras as tensor products of (p+1) x (p+1) matrices. (orig./HSI)
Litvinenko, Alexander
2018-03-12
Part 1: Parallel H-matrices in spatial statistics 1. Motivation: improve statistical model 2. Tools: Hierarchical matrices 3. Matern covariance function and joint Gaussian likelihood 4. Identification of unknown parameters via maximizing Gaussian log-likelihood 5. Implementation with HLIBPro. Part 2: Low-rank Tucker tensor methods in spatial statistics
A Concise Method for Storing and Communicating the Data Covariance Matrix
Energy Technology Data Exchange (ETDEWEB)
Larson, Nancy M [ORNL
2008-10-01
The covariance matrix associated with experimental cross section or transmission data consists of several components. Statistical uncertainties on the measured quantity (counts) provide a diagonal contribution. Off-diagonal components arise from uncertainties on the parameters (such as normalization or background) that figure into the data reduction process; these are denoted systematic or common uncertainties, since they affect all data points. The full off-diagonal data covariance matrix (DCM) can be extremely large, since the size is the square of the number of data points. Fortunately, it is not necessary to explicitly calculate, store, or invert the DCM. Likewise, it is not necessary to explicitly calculate, store, or use the inverse of the DCM. Instead, it is more efficient to accomplish the same results using only the various component matrices that appear in the definition of the DCM. Those component matrices are either diagonal or small (the number of data points times the number of data-reduction parameters); hence, this implicit data covariance method requires far less array storage and far fewer computations while producing more accurate results.
A three domain covariance framework for EEG/MEG data.
Roś, Beata P; Bijma, Fetsje; de Gunst, Mathisca C M; de Munck, Jan C
2015-10-01
In this paper we introduce a covariance framework for the analysis of single subject EEG and MEG data that takes into account observed temporal stationarity on small time scales and trial-to-trial variations. We formulate a model for the covariance matrix, which is a Kronecker product of three components that correspond to space, time and epochs/trials, and consider maximum likelihood estimation of the unknown parameter values. An iterative algorithm that finds approximations of the maximum likelihood estimates is proposed. Our covariance model is applicable in a variety of cases where spontaneous EEG or MEG acts as source of noise and realistic noise covariance estimates are needed, such as in evoked activity studies, or where the properties of spontaneous EEG or MEG are themselves the topic of interest, like in combined EEG-fMRI experiments in which the correlation between EEG and fMRI signals is investigated. We use a simulation study to assess the performance of the estimator and investigate the influence of different assumptions about the covariance factors on the estimated covariance matrix and on its components. We apply our method to real EEG and MEG data sets. Copyright © 2015 Elsevier Inc. All rights reserved.
Ros, B.P.; Bijma, F.; de Munck, J.C.; de Gunst, M.C.M.
2016-01-01
This paper deals with multivariate Gaussian models for which the covariance matrix is a Kronecker product of two matrices. We consider maximum likelihood estimation of the model parameters, in particular of the covariance matrix. There is no explicit expression for the maximum likelihood estimator
International Nuclear Information System (INIS)
Nuamah, N.N.N.N.
1991-01-01
This paper postulates the assumptions underlying the Mean Approach model and recasts the re-expressions of the normal equations of this model in partitioned matrices of covariances. These covariance structures have been analysed. (author). 16 refs
International Nuclear Information System (INIS)
Fiorito, L.; Diez, C.J.; Cabellos, O.; Stankovskiy, A.; Van den Eynde, G.; Labeau, P.E.
2014-01-01
Highlights: • Fission yield data and uncertainty comparison between major nuclear data libraries. • Fission yield covariance generation through Bayesian technique. • Study of the effect of fission yield correlations on decay heat calculations. • Covariance information contribute to reduce fission pulse decay heat uncertainty. - Abstract: Fission product yields are fundamental parameters in burnup/activation calculations and the impact of their uncertainties was widely studied in the past. Evaluations of these uncertainties were released, still without covariance data. Therefore, the nuclear community expressed the need of full fission yield covariance matrices to be able to produce inventory calculation results that take into account the complete uncertainty data. State-of-the-art fission yield data and methodologies for fission yield covariance generation were researched in this work. Covariance matrices were generated and compared to the original data stored in the library. Then, we focused on the effect of fission yield covariance information on fission pulse decay heat results for thermal fission of 235 U. Calculations were carried out using different libraries and codes (ACAB and ALEPH-2) after introducing the new covariance values. Results were compared with those obtained with the uncertainty data currently provided by the libraries. The uncertainty quantification was performed first with Monte Carlo sampling and then compared with linear perturbation. Indeed, correlations between fission yields strongly affect the uncertainty of decay heat. Eventually, a sensitivity analysis of fission product yields to fission pulse decay heat was performed in order to provide a full set of the most sensitive nuclides for such a calculation
Moeyaert, Mariola; Ugille, Maaike; Ferron, John M.; Beretvas, S. Natasha; Van den Noortgate, Wim
2016-01-01
The impact of misspecifying covariance matrices at the second and third levels of the three-level model is evaluated. Results indicate that ignoring existing covariance has no effect on the treatment effect estimate. In addition, the between-case variance estimates are unbiased when covariance is either modeled or ignored. If the research interest…
Estimation of covariance matrix on the experimental data for nuclear data evaluation
International Nuclear Information System (INIS)
Murata, T.
1985-01-01
In order to evaluate fission and capture cross sections of some U and Pu isotopes for JENDL-3, we have a plan for evaluating them simultaneously with a least-squares method. For the simultaneous evaluation, the covariance matrix is required for each experimental data set. In the present work, we have studied the procedures for deriving the covariance matrix from the error data given in the experimental papers. The covariance matrices were obtained using the partial errors and estimated correlation coefficients between the same type partial errors for different neutron energy. Some examples of the covariance matrix estimation are explained and the preliminary results of the simultaneous evaluation are presented. (author)
An Empirical State Error Covariance Matrix Orbit Determination Example
Frisbee, Joseph H., Jr.
2015-01-01
State estimation techniques serve effectively to provide mean state estimates. However, the state error covariance matrices provided as part of these techniques suffer from some degree of lack of confidence in their ability to adequately describe the uncertainty in the estimated states. A specific problem with the traditional form of state error covariance matrices is that they represent only a mapping of the assumed observation error characteristics into the state space. Any errors that arise from other sources (environment modeling, precision, etc.) are not directly represented in a traditional, theoretical state error covariance matrix. First, consider that an actual observation contains only measurement error and that an estimated observation contains all other errors, known and unknown. Then it follows that a measurement residual (the difference between expected and observed measurements) contains all errors for that measurement. Therefore, a direct and appropriate inclusion of the actual measurement residuals in the state error covariance matrix of the estimate will result in an empirical state error covariance matrix. This empirical state error covariance matrix will fully include all of the errors in the state estimate. The empirical error covariance matrix is determined from a literal reinterpretation of the equations involved in the weighted least squares estimation algorithm. It is a formally correct, empirical state error covariance matrix obtained through use of the average form of the weighted measurement residual variance performance index rather than the usual total weighted residual form. Based on its formulation, this matrix will contain the total uncertainty in the state estimate, regardless as to the source of the uncertainty and whether the source is anticipated or not. It is expected that the empirical error covariance matrix will give a better, statistical representation of the state error in poorly modeled systems or when sensor performance
Convex Banding of the Covariance Matrix.
Bien, Jacob; Bunea, Florentina; Xiao, Luo
2016-01-01
We introduce a new sparse estimator of the covariance matrix for high-dimensional models in which the variables have a known ordering. Our estimator, which is the solution to a convex optimization problem, is equivalently expressed as an estimator which tapers the sample covariance matrix by a Toeplitz, sparsely-banded, data-adaptive matrix. As a result of this adaptivity, the convex banding estimator enjoys theoretical optimality properties not attained by previous banding or tapered estimators. In particular, our convex banding estimator is minimax rate adaptive in Frobenius and operator norms, up to log factors, over commonly-studied classes of covariance matrices, and over more general classes. Furthermore, it correctly recovers the bandwidth when the true covariance is exactly banded. Our convex formulation admits a simple and efficient algorithm. Empirical studies demonstrate its practical effectiveness and illustrate that our exactly-banded estimator works well even when the true covariance matrix is only close to a banded matrix, confirming our theoretical results. Our method compares favorably with all existing methods, in terms of accuracy and speed. We illustrate the practical merits of the convex banding estimator by showing that it can be used to improve the performance of discriminant analysis for classifying sound recordings.
Joint Estimation of Multiple Precision Matrices with Common Structures.
Lee, Wonyul; Liu, Yufeng
Estimation of inverse covariance matrices, known as precision matrices, is important in various areas of statistical analysis. In this article, we consider estimation of multiple precision matrices sharing some common structures. In this setting, estimating each precision matrix separately can be suboptimal as it ignores potential common structures. This article proposes a new approach to parameterize each precision matrix as a sum of common and unique components and estimate multiple precision matrices in a constrained l 1 minimization framework. We establish both estimation and selection consistency of the proposed estimator in the high dimensional setting. The proposed estimator achieves a faster convergence rate for the common structure in certain cases. Our numerical examples demonstrate that our new estimator can perform better than several existing methods in terms of the entropy loss and Frobenius loss. An application to a glioblastoma cancer data set reveals some interesting gene networks across multiple cancer subtypes.
Condition Number Regularized Covariance Estimation.
Won, Joong-Ho; Lim, Johan; Kim, Seung-Jean; Rajaratnam, Bala
2013-06-01
Estimation of high-dimensional covariance matrices is known to be a difficult problem, has many applications, and is of current interest to the larger statistics community. In many applications including so-called the "large p small n " setting, the estimate of the covariance matrix is required to be not only invertible, but also well-conditioned. Although many regularization schemes attempt to do this, none of them address the ill-conditioning problem directly. In this paper, we propose a maximum likelihood approach, with the direct goal of obtaining a well-conditioned estimator. No sparsity assumption on either the covariance matrix or its inverse are are imposed, thus making our procedure more widely applicable. We demonstrate that the proposed regularization scheme is computationally efficient, yields a type of Steinian shrinkage estimator, and has a natural Bayesian interpretation. We investigate the theoretical properties of the regularized covariance estimator comprehensively, including its regularization path, and proceed to develop an approach that adaptively determines the level of regularization that is required. Finally, we demonstrate the performance of the regularized estimator in decision-theoretic comparisons and in the financial portfolio optimization setting. The proposed approach has desirable properties, and can serve as a competitive procedure, especially when the sample size is small and when a well-conditioned estimator is required.
Galaxy-galaxy lensing estimators and their covariance properties
Singh, Sukhdeep; Mandelbaum, Rachel; Seljak, Uroš; Slosar, Anže; Vazquez Gonzalez, Jose
2017-11-01
We study the covariance properties of real space correlation function estimators - primarily galaxy-shear correlations, or galaxy-galaxy lensing - using SDSS data for both shear catalogues and lenses (specifically the BOSS LOWZ sample). Using mock catalogues of lenses and sources, we disentangle the various contributions to the covariance matrix and compare them with a simple analytical model. We show that not subtracting the lensing measurement around random points from the measurement around the lens sample is equivalent to performing the measurement using the lens density field instead of the lens overdensity field. While the measurement using the lens density field is unbiased (in the absence of systematics), its error is significantly larger due to an additional term in the covariance. Therefore, this subtraction should be performed regardless of its beneficial effects on systematics. Comparing the error estimates from data and mocks for estimators that involve the overdensity, we find that the errors are dominated by the shape noise and lens clustering, which empirically estimated covariances (jackknife and standard deviation across mocks) that are consistent with theoretical estimates, and that both the connected parts of the four-point function and the supersample covariance can be neglected for the current levels of noise. While the trade-off between different terms in the covariance depends on the survey configuration (area, source number density), the diagnostics that we use in this work should be useful for future works to test their empirically determined covariances.
Galaxy–galaxy lensing estimators and their covariance properties
International Nuclear Information System (INIS)
Singh, Sukhdeep; Mandelbaum, Rachel; Seljak, Uros; Slosar, Anze; Gonzalez, Jose Vazquez
2017-01-01
Here, we study the covariance properties of real space correlation function estimators – primarily galaxy–shear correlations, or galaxy–galaxy lensing – using SDSS data for both shear catalogues and lenses (specifically the BOSS LOWZ sample). Using mock catalogues of lenses and sources, we disentangle the various contributions to the covariance matrix and compare them with a simple analytical model. We show that not subtracting the lensing measurement around random points from the measurement around the lens sample is equivalent to performing the measurement using the lens density field instead of the lens overdensity field. While the measurement using the lens density field is unbiased (in the absence of systematics), its error is significantly larger due to an additional term in the covariance. Therefore, this subtraction should be performed regardless of its beneficial effects on systematics. Comparing the error estimates from data and mocks for estimators that involve the overdensity, we find that the errors are dominated by the shape noise and lens clustering, which empirically estimated covariances (jackknife and standard deviation across mocks) that are consistent with theoretical estimates, and that both the connected parts of the four-point function and the supersample covariance can be neglected for the current levels of noise. While the trade-off between different terms in the covariance depends on the survey configuration (area, source number density), the diagnostics that we use in this work should be useful for future works to test their empirically determined covariances.
Accelerating Matrix-Vector Multiplication on Hierarchical Matrices Using Graphical Processing Units
Boukaram, W.
2015-03-25
Large dense matrices arise from the discretization of many physical phenomena in computational sciences. In statistics very large dense covariance matrices are used for describing random fields and processes. One can, for instance, describe distribution of dust particles in the atmosphere, concentration of mineral resources in the earth\\'s crust or uncertain permeability coefficient in reservoir modeling. When the problem size grows, storing and computing with the full dense matrix becomes prohibitively expensive both in terms of computational complexity and physical memory requirements. Fortunately, these matrices can often be approximated by a class of data sparse matrices called hierarchical matrices (H-matrices) where various sub-blocks of the matrix are approximated by low rank matrices. These matrices can be stored in memory that grows linearly with the problem size. In addition, arithmetic operations on these H-matrices, such as matrix-vector multiplication, can be completed in almost linear time. Originally the H-matrix technique was developed for the approximation of stiffness matrices coming from partial differential and integral equations. Parallelizing these arithmetic operations on the GPU has been the focus of this work and we will present work done on the matrix vector operation on the GPU using the KSPARSE library.
Noise removal in multichannel image data by a parametric maximum noise fraction estimator
DEFF Research Database (Denmark)
Conradsen, Knut; Ersbøll, Bjarne Kjær; Nielsen, Allan Aasbjerg
1991-01-01
Some approaches to noise removal in multispectral imagery are presented. The primary contribution of the present work is the establishment of several ways of estimating the noise covariance matrix from image data and a comparison of the noise separation performances. A case study with Landsat MSS...
A Geometrical Framework for Covariance Matrices of Continuous and Categorical Variables
Vernizzi, Graziano; Nakai, Miki
2015-01-01
It is well known that a categorical random variable can be represented geometrically by a simplex. Accordingly, several measures of association between categorical variables have been proposed and discussed in the literature. Moreover, the standard definitions of covariance and correlation coefficient for continuous random variables have been…
Robust sequential learning of feedforward neural networks in the presence of heavy-tailed noise.
Vuković, Najdan; Miljković, Zoran
2015-03-01
Feedforward neural networks (FFNN) are among the most used neural networks for modeling of various nonlinear problems in engineering. In sequential and especially real time processing all neural networks models fail when faced with outliers. Outliers are found across a wide range of engineering problems. Recent research results in the field have shown that to avoid overfitting or divergence of the model, new approach is needed especially if FFNN is to run sequentially or in real time. To accommodate limitations of FFNN when training data contains a certain number of outliers, this paper presents new learning algorithm based on improvement of conventional extended Kalman filter (EKF). Extended Kalman filter robust to outliers (EKF-OR) is probabilistic generative model in which measurement noise covariance is not constant; the sequence of noise measurement covariance is modeled as stochastic process over the set of symmetric positive-definite matrices in which prior is modeled as inverse Wishart distribution. In each iteration EKF-OR simultaneously estimates noise estimates and current best estimate of FFNN parameters. Bayesian framework enables one to mathematically derive expressions, while analytical intractability of the Bayes' update step is solved by using structured variational approximation. All mathematical expressions in the paper are derived using the first principles. Extensive experimental study shows that FFNN trained with developed learning algorithm, achieves low prediction error and good generalization quality regardless of outliers' presence in training data. Copyright © 2014 Elsevier Ltd. All rights reserved.
The Bayesian Covariance Lasso.
Khondker, Zakaria S; Zhu, Hongtu; Chu, Haitao; Lin, Weili; Ibrahim, Joseph G
2013-04-01
Estimation of sparse covariance matrices and their inverse subject to positive definiteness constraints has drawn a lot of attention in recent years. The abundance of high-dimensional data, where the sample size ( n ) is less than the dimension ( d ), requires shrinkage estimation methods since the maximum likelihood estimator is not positive definite in this case. Furthermore, when n is larger than d but not sufficiently larger, shrinkage estimation is more stable than maximum likelihood as it reduces the condition number of the precision matrix. Frequentist methods have utilized penalized likelihood methods, whereas Bayesian approaches rely on matrix decompositions or Wishart priors for shrinkage. In this paper we propose a new method, called the Bayesian Covariance Lasso (BCLASSO), for the shrinkage estimation of a precision (covariance) matrix. We consider a class of priors for the precision matrix that leads to the popular frequentist penalties as special cases, develop a Bayes estimator for the precision matrix, and propose an efficient sampling scheme that does not precalculate boundaries for positive definiteness. The proposed method is permutation invariant and performs shrinkage and estimation simultaneously for non-full rank data. Simulations show that the proposed BCLASSO performs similarly as frequentist methods for non-full rank data.
Theory of Covariance Equivalent ARMAV Models of Civil Engineering Structures
DEFF Research Database (Denmark)
Andersen, P.; Brincker, Rune; Kirkegaard, Poul Henning
1996-01-01
In this paper the theoretical background for using covariance equivalent ARMAV models in modal analysis is discussed. It is shown how to obtain a covariance equivalent ARMA model for a univariate linear second order continous-time system excited by Gaussian white noise. This result is generalized...
Theory of Covariance Equivalent ARMAV Models of Civil Engineering Structures
DEFF Research Database (Denmark)
Andersen, P.; Brincker, Rune; Kirkegaard, Poul Henning
In this paper the theoretical background for using covariance equivalent ARMAV models in modal analysis is discussed. It is shown how to obtain a covariance equivalent ARMA model for a univariate linear second order continuous-time system excited by Gaussian white noise. This result is generalize...
Condition Number Regularized Covariance Estimation*
Won, Joong-Ho; Lim, Johan; Kim, Seung-Jean; Rajaratnam, Bala
2012-01-01
Estimation of high-dimensional covariance matrices is known to be a difficult problem, has many applications, and is of current interest to the larger statistics community. In many applications including so-called the “large p small n” setting, the estimate of the covariance matrix is required to be not only invertible, but also well-conditioned. Although many regularization schemes attempt to do this, none of them address the ill-conditioning problem directly. In this paper, we propose a maximum likelihood approach, with the direct goal of obtaining a well-conditioned estimator. No sparsity assumption on either the covariance matrix or its inverse are are imposed, thus making our procedure more widely applicable. We demonstrate that the proposed regularization scheme is computationally efficient, yields a type of Steinian shrinkage estimator, and has a natural Bayesian interpretation. We investigate the theoretical properties of the regularized covariance estimator comprehensively, including its regularization path, and proceed to develop an approach that adaptively determines the level of regularization that is required. Finally, we demonstrate the performance of the regularized estimator in decision-theoretic comparisons and in the financial portfolio optimization setting. The proposed approach has desirable properties, and can serve as a competitive procedure, especially when the sample size is small and when a well-conditioned estimator is required. PMID:23730197
Signal and noise in financial correlation matrices
Burda, Zdzisław; Jurkiewicz, Jerzy
2004-12-01
Using Random Matrix Theory one can derive exact relations between the eigenvalue spectrum of the covariance matrix and the eigenvalue spectrum of its estimator (experimentally measured correlation matrix). These relations will be used to analyze a particular case of the correlations in financial series and to show that contrary to earlier claims, correlations can be measured also in the “random” part of the spectrum. Implications for the portfolio optimization are briefly discussed.
On covariance structure in noisy, big data
Paffenroth, Randy C.; Nong, Ryan; Du Toit, Philip C.
2013-09-01
Herein we describe theory and algorithms for detecting covariance structures in large, noisy data sets. Our work uses ideas from matrix completion and robust principal component analysis to detect the presence of low-rank covariance matrices, even when the data is noisy, distorted by large corruptions, and only partially observed. In fact, the ability to handle partial observations combined with ideas from randomized algorithms for matrix decomposition enables us to produce asymptotically fast algorithms. Herein we will provide numerical demonstrations of the methods and their convergence properties. While such methods have applicability to many problems, including mathematical finance, crime analysis, and other large-scale sensor fusion problems, our inspiration arises from applying these methods in the context of cyber network intrusion detection.
Delahaie, B; Charmantier, A; Chantepie, S; Garant, D; Porlier, M; Teplitsky, C
2017-08-01
The genetic variance-covariance matrix (G-matrix) summarizes the genetic architecture of multiple traits. It has a central role in the understanding of phenotypic divergence and the quantification of the evolutionary potential of populations. Laboratory experiments have shown that G-matrices can vary rapidly under divergent selective pressures. However, because of the demanding nature of G-matrix estimation and comparison in wild populations, the extent of its spatial variability remains largely unknown. In this study, we investigate spatial variation in G-matrices for morphological and life-history traits using long-term data sets from one continental and three island populations of blue tit (Cyanistes caeruleus) that have experienced contrasting population history and selective environment. We found no evidence for differences in G-matrices among populations. Interestingly, the phenotypic variance-covariance matrices (P) were divergent across populations, suggesting that using P as a substitute for G may be inadequate. These analyses also provide the first evidence in wild populations for additive genetic variation in the incubation period (that is, the period between last egg laid and hatching) in all four populations. Altogether, our results suggest that G-matrices may be stable across populations inhabiting contrasted environments, therefore challenging the results of previous simulation studies and laboratory experiments.
The application of sparse estimation of covariance matrix to quadratic discriminant analysis.
Sun, Jiehuan; Zhao, Hongyu
2015-02-18
Although Linear Discriminant Analysis (LDA) is commonly used for classification, it may not be directly applied in genomics studies due to the large p, small n problem in these studies. Different versions of sparse LDA have been proposed to address this significant challenge. One implicit assumption of various LDA-based methods is that the covariance matrices are the same across different classes. However, rewiring of genetic networks (therefore different covariance matrices) across different diseases has been observed in many genomics studies, which suggests that LDA and its variations may be suboptimal for disease classifications. However, it is not clear whether considering differing genetic networks across diseases can improve classification in genomics studies. We propose a sparse version of Quadratic Discriminant Analysis (SQDA) to explicitly consider the differences of the genetic networks across diseases. Both simulation and real data analysis are performed to compare the performance of SQDA with six commonly used classification methods. SQDA provides more accurate classification results than other methods for both simulated and real data. Our method should prove useful for classification in genomics studies and other research settings, where covariances differ among classes.
Modelling the Covariance Structure in Marginal Multivariate Count Models
DEFF Research Database (Denmark)
Bonat, W. H.; Olivero, J.; Grande-Vega, M.
2017-01-01
The main goal of this article is to present a flexible statistical modelling framework to deal with multivariate count data along with longitudinal and repeated measures structures. The covariance structure for each response variable is defined in terms of a covariance link function combined...... be used to indicate whether there was statistical evidence of a decline in blue duikers and other species hunted during the study period. Determining whether observed drops in the number of animals hunted are indeed true is crucial to assess whether species depletion effects are taking place in exploited...... with a matrix linear predictor involving known matrices. In order to specify the joint covariance matrix for the multivariate response vector, the generalized Kronecker product is employed. We take into account the count nature of the data by means of the power dispersion function associated with the Poisson...
Image covariance and lesion detectability in direct fan-beam x-ray computed tomography.
Wunderlich, Adam; Noo, Frédéric
2008-05-21
We consider noise in computed tomography images that are reconstructed using the classical direct fan-beam filtered backprojection algorithm, from both full- and short-scan data. A new, accurate method for computing image covariance is presented. The utility of the new covariance method is demonstrated by its application to the implementation of a channelized Hotelling observer for a lesion detection task. Results from the new covariance method and its application to the channelized Hotelling observer are compared with results from Monte Carlo simulations. In addition, the impact of a bowtie filter and x-ray tube current modulation on reconstruction noise and lesion detectability are explored for full-scan reconstruction.
Image covariance and lesion detectability in direct fan-beam x-ray computed tomography
International Nuclear Information System (INIS)
Wunderlich, Adam; Noo, Frederic
2008-01-01
We consider noise in computed tomography images that are reconstructed using the classical direct fan-beam filtered backprojection algorithm, from both full- and short-scan data. A new, accurate method for computing image covariance is presented. The utility of the new covariance method is demonstrated by its application to the implementation of a channelized Hotelling observer for a lesion detection task. Results from the new covariance method and its application to the channelized Hotelling observer are compared with results from Monte Carlo simulations. In addition, the impact of a bowtie filter and x-ray tube current modulation on reconstruction noise and lesion detectability are explored for full-scan reconstruction
Davies, Christopher E; Glonek, Gary Fv; Giles, Lynne C
2017-08-01
One purpose of a longitudinal study is to gain a better understanding of how an outcome of interest changes among a given population over time. In what follows, a trajectory will be taken to mean the series of measurements of the outcome variable for an individual. Group-based trajectory modelling methods seek to identify subgroups of trajectories within a population, such that trajectories that are grouped together are more similar to each other than to trajectories in distinct groups. Group-based trajectory models generally assume a certain structure in the covariances between measurements, for example conditional independence, homogeneous variance between groups or stationary variance over time. Violations of these assumptions could be expected to result in poor model performance. We used simulation to investigate the effect of covariance misspecification on misclassification of trajectories in commonly used models under a range of scenarios. To do this we defined a measure of performance relative to the ideal Bayesian correct classification rate. We found that the more complex models generally performed better over a range of scenarios. In particular, incorrectly specified covariance matrices could significantly bias the results but using models with a correct but more complicated than necessary covariance matrix incurred little cost.
Agnostic Estimation of Mean and Covariance
Lai, Kevin A.; Rao, Anup B.; Vempala, Santosh
2016-01-01
We consider the problem of estimating the mean and covariance of a distribution from iid samples in $\\mathbb{R}^n$, in the presence of an $\\eta$ fraction of malicious noise; this is in contrast to much recent work where the noise itself is assumed to be from a distribution of known type. The agnostic problem includes many interesting special cases, e.g., learning the parameters of a single Gaussian (or finding the best-fit Gaussian) when $\\eta$ fraction of data is adversarially corrupted, agn...
Construction and use of gene expression covariation matrix
Directory of Open Access Journals (Sweden)
Bellis Michel
2009-07-01
Full Text Available Abstract Background One essential step in the massive analysis of transcriptomic profiles is the calculation of the correlation coefficient, a value used to select pairs of genes with similar or inverse transcriptional profiles across a large fraction of the biological conditions examined. Until now, the choice between the two available methods for calculating the coefficient has been dictated mainly by technological considerations. Specifically, in analyses based on double-channel techniques, researchers have been required to use covariation correlation, i.e. the correlation between gene expression changes measured between several pairs of biological conditions, expressed for example as fold-change. In contrast, in analyses of single-channel techniques scientists have been restricted to the use of coexpression correlation, i.e. correlation between gene expression levels. To our knowledge, nobody has ever examined the possible benefits of using covariation instead of coexpression in massive analyses of single channel microarray results. Results We describe here how single-channel techniques can be treated like double-channel techniques and used to generate both gene expression changes and covariation measures. We also present a new method that allows the calculation of both positive and negative correlation coefficients between genes. First, we perform systematic comparisons between two given biological conditions and classify, for each comparison, genes as increased (I, decreased (D, or not changed (N. As a result, the original series of n gene expression level measures assigned to each gene is replaced by an ordered string of n(n-1/2 symbols, e.g. IDDNNIDID....DNNNNNNID, with the length of the string corresponding to the number of comparisons. In a second step, positive and negative covariation matrices (CVM are constructed by calculating statistically significant positive or negative correlation scores for any pair of genes by comparing their
Treatment of Nuclear Data Covariance Information in Sample Generation
Energy Technology Data Exchange (ETDEWEB)
Swiler, Laura Painton [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Adams, Brian M. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Wieselquist, William [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Reactor and Nuclear Systems Division
2017-10-01
This report summarizes a NEAMS (Nuclear Energy Advanced Modeling and Simulation) project focused on developing a sampling capability that can handle the challenges of generating samples from nuclear cross-section data. The covariance information between energy groups tends to be very ill-conditioned and thus poses a problem using traditional methods for generated correlated samples. This report outlines a method that addresses the sample generation from cross-section matrices.
Treatment of Nuclear Data Covariance Information in Sample Generation
International Nuclear Information System (INIS)
Swiler, Laura Painton; Adams, Brian M.; Wieselquist, William
2017-01-01
This report summarizes a NEAMS (Nuclear Energy Advanced Modeling and Simulation) project focused on developing a sampling capability that can handle the challenges of generating samples from nuclear cross-section data. The covariance information between energy groups tends to be very ill-conditioned and thus poses a problem using traditional methods for generated correlated samples. This report outlines a method that addresses the sample generation from cross-section matrices.
Mikosch, Jochen; Patchkovskii, Serguei
2013-10-01
We use an analytical theory of noisy Poisson processes, developed in the preceding companion publication, to compare coincidence and covariance measurement approaches in photoelectron and -ion spectroscopy. For non-unit detection efficiencies, coincidence data acquisition (DAQ) suffers from false coincidences. The rate of false coincidences grows quadratically with the rate of elementary ionization events. To minimize false coincidences for rare event outcomes, very low event rates may hence be required. Coincidence measurements exhibit high tolerance to noise introduced by unstable experimental conditions. Covariance DAQ on the other hand is free of systematic errors as long as stable experimental conditions are maintained. In the presence of noise, all channels in a covariance measurement become correlated. Under favourable conditions, covariance DAQ may allow orders of magnitude reduction in measurement times. Finally, we use experimental data for strong-field ionization of 1,3-butadiene to illustrate how fluctuations in experimental conditions can contaminate a covariance measurement, and how such contamination can be detected.
Ziyatdinov, Andrey; Vázquez-Santiago, Miquel; Brunel, Helena; Martinez-Perez, Angel; Aschard, Hugues; Soria, Jose Manuel
2018-02-27
Quantitative trait locus (QTL) mapping in genetic data often involves analysis of correlated observations, which need to be accounted for to avoid false association signals. This is commonly performed by modeling such correlations as random effects in linear mixed models (LMMs). The R package lme4 is a well-established tool that implements major LMM features using sparse matrix methods; however, it is not fully adapted for QTL mapping association and linkage studies. In particular, two LMM features are lacking in the base version of lme4: the definition of random effects by custom covariance matrices; and parameter constraints, which are essential in advanced QTL models. Apart from applications in linkage studies of related individuals, such functionalities are of high interest for association studies in situations where multiple covariance matrices need to be modeled, a scenario not covered by many genome-wide association study (GWAS) software. To address the aforementioned limitations, we developed a new R package lme4qtl as an extension of lme4. First, lme4qtl contributes new models for genetic studies within a single tool integrated with lme4 and its companion packages. Second, lme4qtl offers a flexible framework for scenarios with multiple levels of relatedness and becomes efficient when covariance matrices are sparse. We showed the value of our package using real family-based data in the Genetic Analysis of Idiopathic Thrombophilia 2 (GAIT2) project. Our software lme4qtl enables QTL mapping models with a versatile structure of random effects and efficient computation for sparse covariances. lme4qtl is available at https://github.com/variani/lme4qtl .
Chen, Fei; Loizou, Philipos C
2010-12-01
The normalized covariance measure (NCM) has been shown previously to predict reliably the intelligibility of noise-suppressed speech containing non-linear distortions. This study analyzes a simplified NCM measure that requires only a small number of bands (not necessarily contiguous) and uses simple binary (1 or 0) weighting functions. The rationale behind the use of a small number of bands is to account for the fact that the spectral information contained in contiguous or nearby bands is correlated and redundant. The modified NCM measure was evaluated with speech intelligibility scores obtained by normal-hearing listeners in 72 noisy conditions involving noise-suppressed speech corrupted by four different types of maskers (car, babble, train, and street interferences). High correlation (r = 0.8) was obtained with the modified NCM measure even when only one band was used. Further analysis revealed a masker-specific pattern of correlations when only one band was used, and bands with low correlation signified the corresponding envelopes that have been severely distorted by the noise-suppression algorithm and/or the masker. Correlation improved to r = 0.84 when only two disjoint bands (centered at 325 and 1874 Hz) were used. Even further improvements in correlation (r = 0.85) were obtained when three or four lower-frequency (<700 Hz) bands were selected.
Phenotypic covariance at species' borders.
Caley, M Julian; Cripps, Edward; Game, Edward T
2013-05-28
Understanding the evolution of species limits is important in ecology, evolution, and conservation biology. Despite its likely importance in the evolution of these limits, little is known about phenotypic covariance in geographically marginal populations, and the degree to which it constrains, or facilitates, responses to selection. We investigated phenotypic covariance in morphological traits at species' borders by comparing phenotypic covariance matrices (P), including the degree of shared structure, the distribution of strengths of pair-wise correlations between traits, the degree of morphological integration of traits, and the ranks of matricies, between central and marginal populations of three species-pairs of coral reef fishes. Greater structural differences in P were observed between populations close to range margins and conspecific populations toward range centres, than between pairs of conspecific populations that were both more centrally located within their ranges. Approximately 80% of all pair-wise trait correlations within populations were greater in the north, but these differences were unrelated to the position of the sampled population with respect to the geographic range of the species. Neither the degree of morphological integration, nor ranks of P, indicated greater evolutionary constraint at range edges. Characteristics of P observed here provide no support for constraint contributing to the formation of these species' borders, but may instead reflect structural change in P caused by selection or drift, and their potential to evolve in the future.
Institute of Scientific and Technical Information of China (English)
Xiaogu ZHENG
2009-01-01
An adaptive estimation of forecast error covariance matrices is proposed for Kalman filtering data assimilation. A forecast error covariance matrix is initially estimated using an ensemble of perturbation forecasts. This initially estimated matrix is then adjusted with scale parameters that are adaptively estimated by minimizing -2log-likelihood of observed-minus-forecast residuals. The proposed approach could be applied to Kalman filtering data assimilation with imperfect models when the model error statistics are not known. A simple nonlinear model (Burgers' equation model) is used to demonstrate the efficacy of the proposed approach.
DANTE, Activation Analysis Neutron Spectra Unfolding by Covariance Matrix Method
International Nuclear Information System (INIS)
Petilli, M.
1981-01-01
1 - Description of problem or function: The program evaluates activation measurements of reactor neutron spectra and unfolds the results for dosimetry purposes. Different evaluation options are foreseen: absolute or relative fluxes and different iteration algorithms. 2 - Method of solution: A least-square fit method is used. A correlation between available data and their uncertainties has been introduced by means of flux and activity variance-covariance matrices. Cross sections are assumed to be constant, i.e. with variance-covariance matrix equal to zero. The Lagrange multipliers method has been used for calculating the solution. 3 - Restrictions on the complexity of the problem: 9 activation experiments can be analyzed. 75 energy groups are accepted
Phenotypic Covariation and Morphological Diversification in the Ruminant Skull.
Haber, Annat
2016-05-01
Differences among clades in their diversification patterns result from a combination of extrinsic and intrinsic factors. In this study, I examined the role of intrinsic factors in the morphological diversification of ruminants, in general, and in the differences between bovids and cervids, in particular. Using skull morphology, which embodies many of the adaptations that distinguish bovids and cervids, I examined 132 of the 200 extant ruminant species. As a proxy for intrinsic constraints, I quantified different aspects of the phenotypic covariation structure within species and compared them with the among-species divergence patterns, using phylogenetic comparative methods. My results show that for most species, divergence is well aligned with their phenotypic covariance matrix and that those that are better aligned have diverged further away from their ancestor. Bovids have dispersed into a wider range of directions in morphospace than cervids, and their overall disparity is higher. This difference is best explained by the lower eccentricity of bovids' within-species covariance matrices. These results are consistent with the role of intrinsic constraints in determining amount, range, and direction of dispersion and demonstrate that intrinsic constraints can influence macroevolutionary patterns even as the covariance structure evolves.
International Nuclear Information System (INIS)
Geraldo, L.P.; Smith, D.L.
1989-01-01
The methodology of covariance matrix and square methods have been applied in the relative efficiency calibration for a Ge(Li) detector apllied in the relative efficiency calibration for a Ge(Li) detector. Procedures employed to generate, manipulate and test covariance matrices which serve to properly represent uncertainties of experimental data are discussed. Calibration data fitting using least square methods has been performed for a particular experimental data set. (author) [pt
Linear Covariance Analysis and Epoch State Estimators
Markley, F. Landis; Carpenter, J. Russell
2014-01-01
This paper extends in two directions the results of prior work on generalized linear covariance analysis of both batch least-squares and sequential estimators. The first is an improved treatment of process noise in the batch, or epoch state, estimator with an epoch time that may be later than some or all of the measurements in the batch. The second is to account for process noise in specifying the gains in the epoch state estimator. We establish the conditions under which the latter estimator is equivalent to the Kalman filter.
Asymmetric correlation matrices: an analysis of financial data
Livan, G.; Rebecchi, L.
2012-06-01
We analyse the spectral properties of correlation matrices between distinct statistical systems. Such matrices are intrinsically non-symmetric, and lend themselves to extend the spectral analyses usually performed on standard Pearson correlation matrices to the realm of complex eigenvalues. We employ some recent random matrix theory results on the average eigenvalue density of this type of matrix to distinguish between noise and non-trivial correlation structures, and we focus on financial data as a case study. Namely, we employ daily prices of stocks belonging to the American and British stock exchanges, and look for the emergence of correlations between two such markets in the eigenvalue spectrum of their non-symmetric correlation matrix. We find several non trivial results when considering time-lagged correlations over short lags, and we corroborate our findings by additionally studying the asymmetric correlation matrix of the principal components of our datasets.
Inverse m-matrices and ultrametric matrices
Dellacherie, Claude; San Martin, Jaime
2014-01-01
The study of M-matrices, their inverses and discrete potential theory is now a well-established part of linear algebra and the theory of Markov chains. The main focus of this monograph is the so-called inverse M-matrix problem, which asks for a characterization of nonnegative matrices whose inverses are M-matrices. We present an answer in terms of discrete potential theory based on the Choquet-Deny Theorem. A distinguished subclass of inverse M-matrices is ultrametric matrices, which are important in applications such as taxonomy. Ultrametricity is revealed to be a relevant concept in linear algebra and discrete potential theory because of its relation with trees in graph theory and mean expected value matrices in probability theory. Remarkable properties of Hadamard functions and products for the class of inverse M-matrices are developed and probabilistic insights are provided throughout the monograph.
Positive Semidefinite Integrated Covariance Estimation, Factorizations and Asynchronicity
DEFF Research Database (Denmark)
Boudt, Kris; Laurent, Sébastien; Lunde, Asger
An estimator of the ex-post covariation of log-prices under asynchronicity and microstructure noise is proposed. It uses the Cholesky factorization on the correlation matrix in order to exploit the heterogeneity in trading intensity to estimate the different parameters sequentially with as many...
von Cramon-Taubadel, Noreen; Schroeder, Lauren
2016-10-01
Estimation of the variance-covariance (V/CV) structure of fragmentary bioarchaeological populations requires the use of proxy extant V/CV parameters. However, it is currently unclear whether extant human populations exhibit equivalent V/CV structures. Random skewers (RS) and hierarchical analyses of common principal components (CPC) were applied to a modern human cranial dataset. Cranial V/CV similarity was assessed globally for samples of individual populations (jackknifed method) and for pairwise population sample contrasts. The results were examined in light of potential explanatory factors for covariance difference, such as geographic region, among-group distance, and sample size. RS analyses showed that population samples exhibited highly correlated multivariate responses to selection, and that differences in RS results were primarily a consequence of differences in sample size. The CPC method yielded mixed results, depending upon the statistical criterion used to evaluate the hierarchy. The hypothesis-testing (step-up) approach was deemed problematic due to sensitivity to low statistical power and elevated Type I errors. In contrast, the model-fitting (lowest AIC) approach suggested that V/CV matrices were proportional and/or shared a large number of CPCs. Pairwise population sample CPC results were correlated with cranial distance, suggesting that population history explains some of the variability in V/CV structure among groups. The results indicate that patterns of covariance in human craniometric samples are broadly similar but not identical. These findings have important implications for choosing extant covariance matrices to use as proxy V/CV parameters in evolutionary analyses of past populations. © 2016 Wiley Periodicals, Inc.
Luo, Xiaodong; Hoteit, Ibrahim
2013-01-01
This article examines the influence of covariance inflation on the distance between the measured observation and the simulated (or predicted) observation with respect to the state estimate. In order for the aforementioned distance to be bounded in a certain interval, some sufficient conditions are derived, indicating that the covariance inflation factor should be bounded in a certain interval, and that the inflation bounds are related to the maximum and minimum eigenvalues of certain matrices. Implications of these analytic results are discussed, and a numerical experiment is presented to verify the validity of the analysis conducted.
Luo, Xiaodong
2013-10-01
This article examines the influence of covariance inflation on the distance between the measured observation and the simulated (or predicted) observation with respect to the state estimate. In order for the aforementioned distance to be bounded in a certain interval, some sufficient conditions are derived, indicating that the covariance inflation factor should be bounded in a certain interval, and that the inflation bounds are related to the maximum and minimum eigenvalues of certain matrices. Implications of these analytic results are discussed, and a numerical experiment is presented to verify the validity of the analysis conducted.
Anomaly detection in OECD Benchmark data using co-variance methods
International Nuclear Information System (INIS)
Srinivasan, G.S.; Krinizs, K.; Por, G.
1993-02-01
OECD Benchmark data distributed for the SMORN VI Specialists Meeting in Reactor Noise were investigated for anomaly detection in artificially generated reactor noise benchmark analysis. It was observed that statistical features extracted from covariance matrix of frequency components are very sensitive in terms of the anomaly detection level. It is possible to create well defined alarm levels. (R.P.) 5 refs.; 23 figs.; 1 tab
Does occupational noise cause asymmetric hearing loss?
Dobie, Robert A
2014-01-01
Determine whether occupational noise exposure increases audiometric asymmetry. Audiograms were performed on 2044 men from the Occupational Noise and Hearing Survey, representing four groups based on preliminary screening (for previous noise exposure, otologic history, and otoscopy) and current occupational noise exposure. The effects of current noise exposure on audiometric asymmetry were tested using ANCOVA, with binaural average thresholds as covariates. There were no significant differences in asymmetry attributable to current occupational noise exposure. Occupational noise exposure does not usually cause or exacerbate audiometric asymmetry.
[Occupational noise exposure and work accidents].
Dias, Adriano; Cordeiro, Ricardo; Gonçalves, Cláudia Giglio de Oliveira
2006-10-01
The purpose of this study was to verify whether occupational noise exposure is a significant risk factor for work accidents in the city of Piracicaba, São Paulo State, Brazil. This hospital-based case-control study included 600 workers aged 15-60 who suffered typical occupational accidents between May and October 2004 and were seen at the Piracicaba Orthopedics and Trauma Center. The control group comprised 822 workers, aged 15-60, who were also seen at the Center, and either had a non-occupational accident or were accompanying someone who had suffered an accident. A multiple logistic regression model was adjusted with work accident as an independent variable, controlled by covariables of interest such as noise exposure. The risk of having a work accident was about twice as high among workers exposed to noise, after controlling for several covariables. Occupational noise exposure not only affected auditory health status but was also a risk factor for work accidents.
Generalisations of Fisher Matrices
Directory of Open Access Journals (Sweden)
Alan Heavens
2016-06-01
Full Text Available Fisher matrices play an important role in experimental design and in data analysis. Their primary role is to make predictions for the inference of model parameters—both their errors and covariances. In this short review, I outline a number of extensions to the simple Fisher matrix formalism, covering a number of recent developments in the field. These are: (a situations where the data (in the form of ( x , y pairs have errors in both x and y; (b modifications to parameter inference in the presence of systematic errors, or through fixing the values of some model parameters; (c Derivative Approximation for LIkelihoods (DALI - higher-order expansions of the likelihood surface, going beyond the Gaussian shape approximation; (d extensions of the Fisher-like formalism, to treat model selection problems with Bayesian evidence.
Analytical Derivation of the Inverse Moments of One-Sided Correlated Gram Matrices With Applications
Elkhalil, Khalil
2016-02-03
This paper addresses the development of analytical tools for the computation of the inverse moments of random Gram matrices with one side correlation. Such a question is mainly driven by applications in signal processing and wireless communications wherein such matrices naturally arise. In particular, we derive closed-form expressions for the inverse moments and show that the obtained results can help approximate several performance metrics such as the average estimation error corresponding to the Best Linear Unbiased Estimator (BLUE) and the Linear Minimum Mean Square Error (LMMSE) estimator or also other loss functions used to measure the accuracy of covariance matrix estimates.
An Empirical State Error Covariance Matrix for Batch State Estimation
Frisbee, Joseph H., Jr.
2011-01-01
State estimation techniques serve effectively to provide mean state estimates. However, the state error covariance matrices provided as part of these techniques suffer from some degree of lack of confidence in their ability to adequately describe the uncertainty in the estimated states. A specific problem with the traditional form of state error covariance matrices is that they represent only a mapping of the assumed observation error characteristics into the state space. Any errors that arise from other sources (environment modeling, precision, etc.) are not directly represented in a traditional, theoretical state error covariance matrix. Consider that an actual observation contains only measurement error and that an estimated observation contains all other errors, known and unknown. It then follows that a measurement residual (the difference between expected and observed measurements) contains all errors for that measurement. Therefore, a direct and appropriate inclusion of the actual measurement residuals in the state error covariance matrix will result in an empirical state error covariance matrix. This empirical state error covariance matrix will fully account for the error in the state estimate. By way of a literal reinterpretation of the equations involved in the weighted least squares estimation algorithm, it is possible to arrive at an appropriate, and formally correct, empirical state error covariance matrix. The first specific step of the method is to use the average form of the weighted measurement residual variance performance index rather than its usual total weighted residual form. Next it is helpful to interpret the solution to the normal equations as the average of a collection of sample vectors drawn from a hypothetical parent population. From here, using a standard statistical analysis approach, it directly follows as to how to determine the standard empirical state error covariance matrix. This matrix will contain the total uncertainty in the
A Phylogenetic Analysis of Shape Covariance Structure in the Anthropoid Skull
De Oliveira, Felipe; Marroig, Gabriel; Garcia, Guilherme
2016-01-01
Phenotypic traits evolve in a coordinated manner due to developmental and functional interactions, mediated by the dynamics of natural selection; the dependence between traits arising from these three factors is captured by genetic ( G ) and phenotypic ( P ) covariance matrices. Mammalian skull development produces an intricate pattern of tissue organization and mutual signaling that integrates this structure, although the set of functions it performs is quite disparate. Therefore, the interp...
Optimal Filtering in Mass Transport Modeling From Satellite Gravimetry Data
Ditmar, P.; Hashemi Farahani, H.; Klees, R.
2011-12-01
Monitoring natural mass transport in the Earth's system, which has marked a new era in Earth observation, is largely based on the data collected by the GRACE satellite mission. Unfortunately, this mission is not free from certain limitations, two of which are especially critical. Firstly, its sensitivity is strongly anisotropic: it senses the north-south component of the mass re-distribution gradient much better than the east-west component. Secondly, it suffers from a trade-off between temporal and spatial resolution: a high (e.g., daily) temporal resolution is only possible if the spatial resolution is sacrificed. To make things even worse, the GRACE satellites enter occasionally a phase when their orbit is characterized by a short repeat period, which makes it impossible to reach a high spatial resolution at all. A way to mitigate limitations of GRACE measurements is to design optimal data processing procedures, so that all available information is fully exploited when modeling mass transport. This implies, in particular, that an unconstrained model directly derived from satellite gravimetry data needs to be optimally filtered. In principle, this can be realized with a Wiener filter, which is built on the basis of covariance matrices of noise and signal. In practice, however, a compilation of both matrices (and, therefore, of the filter itself) is not a trivial task. To build the covariance matrix of noise in a mass transport model, it is necessary to start from a realistic model of noise in the level-1B data. Furthermore, a routine satellite gravimetry data processing includes, in particular, the subtraction of nuisance signals (for instance, associated with atmosphere and ocean), for which appropriate background models are used. Such models are not error-free, which has to be taken into account when the noise covariance matrix is constructed. In addition, both signal and noise covariance matrices depend on the type of mass transport processes under
Effectual switching filter for removing impulse noise using a SCM detector
Yuan, Jin-xia; Zhang, Hong-juan; Ma, Yi-de
2012-03-01
An effectual method is proposed to remove impulse noise from corrupted color images. The spiking cortical model (SCM) is adopted as a noise detector to identify noisy pixels in each channel of color images, and detected noise pixels are saved in three marking matrices. According to the three marking matrices, the detected noisy pixels are divided into two types (type I and type II). They are filtered differently: an adaptive median filter is used for type I and an adaptive vector median for type II. Noise-free pixels are left unchanged. Extensive experiments show that the proposed method outperforms most of the other well-known filters in the aspects of both visual and objective quality measures, and this method can also reduce the possibility of generating color artifacts while preserving image details.
Are Low-order Covariance Estimates Useful in Error Analyses?
Baker, D. F.; Schimel, D.
2005-12-01
Atmospheric trace gas inversions, using modeled atmospheric transport to infer surface sources and sinks from measured concentrations, are most commonly done using least-squares techniques that return not only an estimate of the state (the surface fluxes) but also the covariance matrix describing the uncertainty in that estimate. Besides allowing one to place error bars around the estimate, the covariance matrix may be used in simulation studies to learn what uncertainties would be expected from various hypothetical observing strategies. This error analysis capability is routinely used in designing instrumentation, measurement campaigns, and satellite observing strategies. For example, Rayner, et al (2002) examined the ability of satellite-based column-integrated CO2 measurements to constrain monthly-average CO2 fluxes for about 100 emission regions using this approach. Exact solutions for both state vector and covariance matrix become computationally infeasible, however, when the surface fluxes are solved at finer resolution (e.g., daily in time, under 500 km in space). It is precisely at these finer scales, however, that one would hope to be able to estimate fluxes using high-density satellite measurements. Non-exact estimation methods such as variational data assimilation or the ensemble Kalman filter could be used, but they achieve their computational savings by obtaining an only approximate state estimate and a low-order approximation of the true covariance. One would like to be able to use this covariance matrix to do the same sort of error analyses as are done with the full-rank covariance, but is it correct to do so? Here we compare uncertainties and `information content' derived from full-rank covariance matrices obtained from a direct, batch least squares inversion to those from the incomplete-rank covariance matrices given by a variational data assimilation approach solved with a variable metric minimization technique (the Broyden-Fletcher- Goldfarb
Institute of Scientific and Technical Information of China (English)
QI Wen-Juan; ZHANG Peng; DENG Zi-Li
2014-01-01
This paper deals with the problem of designing robust sequential covariance intersection (SCI) fusion Kalman filter for the clustering multi-agent sensor network system with measurement delays and uncertain noise variances. The sensor network is partitioned into clusters by the nearest neighbor rule. Using the minimax robust estimation principle, based on the worst-case conservative sensor network system with conservative upper bounds of noise variances, and applying the unbiased linear minimum variance (ULMV) optimal estimation rule, we present the two-layer SCI fusion robust steady-state Kalman filter which can reduce communication and computation burdens and save energy sources, and guarantee that the actual filtering error variances have a less-conservative upper-bound. A Lyapunov equation method for robustness analysis is proposed, by which the robustness of the local and fused Kalman filters is proved. The concept of the robust accuracy is presented and the robust accuracy relations of the local and fused robust Kalman filters are proved. It is proved that the robust accuracy of the global SCI fuser is higher than those of the local SCI fusers and the robust accuracies of all SCI fusers are higher than that of each local robust Kalman filter. A simulation example for a tracking system verifies the robustness and robust accuracy relations.
Shokravi, H.; Bakhary, NH
2017-11-01
Subspace System Identification (SSI) is considered as one of the most reliable tools for identification of system parameters. Performance of a SSI scheme is considerably affected by the structure of the associated identification algorithm. Weight matrix is a variable in SSI that is used to reduce the dimensionality of the state-space equation. Generally one of the weight matrices of Principle Component (PC), Unweighted Principle Component (UPC) and Canonical Variate Analysis (CVA) are used in the structure of a SSI algorithm. An increasing number of studies in the field of structural health monitoring are using SSI for damage identification. However, studies that evaluate the performance of the weight matrices particularly in association with accuracy, noise resistance, and time complexity properties are very limited. In this study, the accuracy, noise-robustness, and time-efficiency of the weight matrices are compared using different qualitative and quantitative metrics. Three evaluation metrics of pole analysis, fit values and elapsed time are used in the assessment process. A numerical model of a mass-spring-dashpot and operational data is used in this research paper. It is observed that the principal components obtained using PC algorithms are more robust against noise uncertainty and give more stable results for the pole distribution. Furthermore, higher estimation accuracy is achieved using UPC algorithm. CVA had the worst performance for pole analysis and time efficiency analysis. The superior performance of the UPC algorithm in the elapsed time is attributed to using unit weight matrices. The obtained results demonstrated that the process of reducing dimensionality in CVA and PC has not enhanced the time efficiency but yield an improved modal identification in PC.
Noise estimation for remote sensing image data analysis
Du, Qian
2004-01-01
Noise estimation does not receive much attention in remote sensing society. It may be because normally noise is not large enough to impair image analysis result. Noise estimation is also very challenging due to the randomness nature of the noise (for random noise) and the difficulty of separating the noise component from the signal in each specific location. We review and propose seven different types of methods to estimate noise variance and noise covariance matrix in a remotely sensed image. In the experiment, it is demonstrated that a good noise estimate can improve the performance of an algorithm via noise whitening if this algorithm assumes white noise.
Covariances for measured activation and fission ratios data
International Nuclear Information System (INIS)
Smith, D.L.; Meadows, J.W.; Watanabe, Y.
1986-01-01
Methods which are routinely used in the determination of covariance matrices for both integral and differential activation and fission-ratios data acquired at the Argonne National Laboratory Fast-Neutron Generator Facility (FNG) are discussed. Special consideration is given to problems associated with the estimation of correlations between various identified sources of experimental error. Approximation methods which are commonly used to reduce the labor involved in this analysis to manageable levels are described. Results from some experiments which have been recently carried out in this laboratory are presented to illustrate these procedures. 13 refs., 1 fig., 5 tabs
Identification of multivariate models for noise analysis of nuclear plant
International Nuclear Information System (INIS)
Zwingelstein, G.C.; Upadhyaya, B.R.
1979-01-01
During the normal operation of a pressurized water reactor, neutron noise analysis with multivariate autoregressive procedures in a valuable diagnostic tool to extract dynamic characteristics for incipient failure detection. The first part of the paper will describe in details the equations for estimating the multivariate autoregressive model matrices and the structure of various matrices. The matrices are estimated by solving a set of matrix operations, called Yule-Walker equations. The selection of optimal model order will also be discussed. Once the optimal parameter set is obtained, simple and fast calculations are used to determine the auto power spectral density, cross spectra, coherence function, phase. In addition the spectra may be decomposed into components being contributed from different noise sources. An application using neutron flux data collected on a nuclear plant will illustrate the efficiency of the method
Generation of integral experiment covariance data and their impact on criticality safety validation
Energy Technology Data Exchange (ETDEWEB)
Stuke, Maik; Peters, Elisabeth; Sommer, Fabian
2016-11-15
The quantification of statistical dependencies in data of critical experiments and how to account for them properly in validation procedures has been discussed in the literature by various groups. However, these subjects are still an active topic in the Expert Group on Uncertainty Analysis for Criticality Safety Assessment (UACSA) of the OECDNEA Nuclear Science Committee. The latter compiles and publishes the freely available experimental data collection, the International Handbook of Evaluated Criticality Safety Benchmark Experiments, ICSBEP. Most of the experiments were performed as series and share parts of experimental setups, consequently leading to correlation effects in the results. The correct consideration of correlated data seems to be inevitable if the experimental data in a validation procedure is limited or one cannot rely on a sufficient number of uncorrelated data sets, e.g. from different laboratories using different setups. The general determination of correlations and the underlying covariance data as well as the consideration of them in a validation procedure is the focus of the following work. We discuss and demonstrate possible effects on calculated k{sub eff}'s, their uncertainties, and the corresponding covariance matrices due to interpretation of evaluated experimental data and its translation into calculation models. The work shows effects of various modeling approaches, varying distribution functions of parameters and compares and discusses results from the applied Monte-Carlo sampling method with available data on correlations. Our findings indicate that for the reliable determination of integral experimental covariance matrices or the correlation coefficients a detailed study of the underlying experimental data, the modeling approach and assumptions made, and the resulting sensitivity analysis seems to be inevitable. Further, a Bayesian method is discussed to include integral experimental covariance data when estimating an
Generation of integral experiment covariance data and their impact on criticality safety validation
International Nuclear Information System (INIS)
Stuke, Maik; Peters, Elisabeth; Sommer, Fabian
2016-11-01
The quantification of statistical dependencies in data of critical experiments and how to account for them properly in validation procedures has been discussed in the literature by various groups. However, these subjects are still an active topic in the Expert Group on Uncertainty Analysis for Criticality Safety Assessment (UACSA) of the OECDNEA Nuclear Science Committee. The latter compiles and publishes the freely available experimental data collection, the International Handbook of Evaluated Criticality Safety Benchmark Experiments, ICSBEP. Most of the experiments were performed as series and share parts of experimental setups, consequently leading to correlation effects in the results. The correct consideration of correlated data seems to be inevitable if the experimental data in a validation procedure is limited or one cannot rely on a sufficient number of uncorrelated data sets, e.g. from different laboratories using different setups. The general determination of correlations and the underlying covariance data as well as the consideration of them in a validation procedure is the focus of the following work. We discuss and demonstrate possible effects on calculated k eff 's, their uncertainties, and the corresponding covariance matrices due to interpretation of evaluated experimental data and its translation into calculation models. The work shows effects of various modeling approaches, varying distribution functions of parameters and compares and discusses results from the applied Monte-Carlo sampling method with available data on correlations. Our findings indicate that for the reliable determination of integral experimental covariance matrices or the correlation coefficients a detailed study of the underlying experimental data, the modeling approach and assumptions made, and the resulting sensitivity analysis seems to be inevitable. Further, a Bayesian method is discussed to include integral experimental covariance data when estimating an application
Autism-specific covariation in perceptual performances: "g" or "p" factor?
Meilleur, Andrée-Anne S; Berthiaume, Claude; Bertone, Armando; Mottron, Laurent
2014-01-01
Autistic perception is characterized by atypical and sometimes exceptional performance in several low- (e.g., discrimination) and mid-level (e.g., pattern matching) tasks in both visual and auditory domains. A factor that specifically affects perceptive abilities in autistic individuals should manifest as an autism-specific association between perceptual tasks. The first purpose of this study was to explore how perceptual performances are associated within or across processing levels and/or modalities. The second purpose was to determine if general intelligence, the major factor that accounts for covariation in task performances in non-autistic individuals, equally controls perceptual abilities in autistic individuals. We asked 46 autistic individuals and 46 typically developing controls to perform four tasks measuring low- or mid-level visual or auditory processing. Intelligence was measured with the Wechsler's Intelligence Scale (FSIQ) and Raven Progressive Matrices (RPM). We conducted linear regression models to compare task performances between groups and patterns of covariation between tasks. The addition of either Wechsler's FSIQ or RPM in the regression models controlled for the effects of intelligence. In typically developing individuals, most perceptual tasks were associated with intelligence measured either by RPM or Wechsler FSIQ. The residual covariation between unimodal tasks, i.e. covariation not explained by intelligence, could be explained by a modality-specific factor. In the autistic group, residual covariation revealed the presence of a plurimodal factor specific to autism. Autistic individuals show exceptional performance in some perceptual tasks. Here, we demonstrate the existence of specific, plurimodal covariation that does not dependent on general intelligence (or "g" factor). Instead, this residual covariation is accounted for by a common perceptual process (or "p" factor), which may drive perceptual abilities differently in autistic and
Autism-specific covariation in perceptual performances: "g" or "p" factor?
Directory of Open Access Journals (Sweden)
Andrée-Anne S Meilleur
Full Text Available Autistic perception is characterized by atypical and sometimes exceptional performance in several low- (e.g., discrimination and mid-level (e.g., pattern matching tasks in both visual and auditory domains. A factor that specifically affects perceptive abilities in autistic individuals should manifest as an autism-specific association between perceptual tasks. The first purpose of this study was to explore how perceptual performances are associated within or across processing levels and/or modalities. The second purpose was to determine if general intelligence, the major factor that accounts for covariation in task performances in non-autistic individuals, equally controls perceptual abilities in autistic individuals.We asked 46 autistic individuals and 46 typically developing controls to perform four tasks measuring low- or mid-level visual or auditory processing. Intelligence was measured with the Wechsler's Intelligence Scale (FSIQ and Raven Progressive Matrices (RPM. We conducted linear regression models to compare task performances between groups and patterns of covariation between tasks. The addition of either Wechsler's FSIQ or RPM in the regression models controlled for the effects of intelligence.In typically developing individuals, most perceptual tasks were associated with intelligence measured either by RPM or Wechsler FSIQ. The residual covariation between unimodal tasks, i.e. covariation not explained by intelligence, could be explained by a modality-specific factor. In the autistic group, residual covariation revealed the presence of a plurimodal factor specific to autism.Autistic individuals show exceptional performance in some perceptual tasks. Here, we demonstrate the existence of specific, plurimodal covariation that does not dependent on general intelligence (or "g" factor. Instead, this residual covariation is accounted for by a common perceptual process (or "p" factor, which may drive perceptual abilities differently in
Covariance specification and estimation to improve top-down Green House Gas emission estimates
Ghosh, S.; Lopez-Coto, I.; Prasad, K.; Whetstone, J. R.
2015-12-01
The National Institute of Standards and Technology (NIST) operates the North-East Corridor (NEC) project and the Indianapolis Flux Experiment (INFLUX) in order to develop measurement methods to quantify sources of Greenhouse Gas (GHG) emissions as well as their uncertainties in urban domains using a top down inversion method. Top down inversion updates prior knowledge using observations in a Bayesian way. One primary consideration in a Bayesian inversion framework is the covariance structure of (1) the emission prior residuals and (2) the observation residuals (i.e. the difference between observations and model predicted observations). These covariance matrices are respectively referred to as the prior covariance matrix and the model-data mismatch covariance matrix. It is known that the choice of these covariances can have large effect on estimates. The main objective of this work is to determine the impact of different covariance models on inversion estimates and their associated uncertainties in urban domains. We use a pseudo-data Bayesian inversion framework using footprints (i.e. sensitivities of tower measurements of GHGs to surface emissions) and emission priors (based on Hestia project to quantify fossil-fuel emissions) to estimate posterior emissions using different covariance schemes. The posterior emission estimates and uncertainties are compared to the hypothetical truth. We find that, if we correctly specify spatial variability and spatio-temporal variability in prior and model-data mismatch covariances respectively, then we can compute more accurate posterior estimates. We discuss few covariance models to introduce space-time interacting mismatches along with estimation of the involved parameters. We then compare several candidate prior spatial covariance models from the Matern covariance class and estimate their parameters with specified mismatches. We find that best-fitted prior covariances are not always best in recovering the truth. To achieve
Development of a perceptually calibrated objective metric of noise
Keelan, Brian W.; Jin, Elaine W.; Prokushkin, Sergey
2011-01-01
A system simulation model was used to create scene-dependent noise masks that reflect current performance of mobile phone cameras. Stimuli with different overall magnitudes of noise and with varying mixtures of red, green, blue, and luminance noises were included in the study. Eleven treatments in each of ten pictorial scenes were evaluated by twenty observers using the softcopy ruler method. In addition to determining the quality loss function in just noticeable differences (JNDs) for the average observer and scene, transformations for different combinations of observer sensitivity and scene susceptibility were derived. The psychophysical results were used to optimize an objective metric of isotropic noise based on system noise power spectra (NPS), which were integrated over a visual frequency weighting function to yield perceptually relevant variances and covariances in CIE L*a*b* space. Because the frequency weighting function is expressed in terms of cycles per degree at the retina, it accounts for display pixel size and viewing distance effects, so application-specific predictions can be made. Excellent results were obtained using only L* and a* variances and L*a* covariance, with relative weights of 100, 5, and 12, respectively. The positive a* weight suggests that the luminance (photopic) weighting is slightly narrow on the long wavelength side for predicting perceived noisiness. The L*a* covariance term, which is normally negative, reflects masking between L* and a* noise, as confirmed in informal evaluations. Test targets in linear sRGB and rendered L*a*b* spaces for each treatment are available at http://www.aptina.com/ImArch/ to enable other researchers to test metrics of their own design and calibrate them to JNDs of quality loss without performing additional observer experiments. Such JND-calibrated noise metrics are particularly valuable for comparing the impact of noise and other attributes, and for computing overall image quality.
MIMO Radar Transmit Beampattern Design Without Synthesising the Covariance Matrix
Ahmed, Sajid
2013-10-28
Compared to phased-array, multiple-input multiple-output (MIMO) radars provide more degrees-offreedom (DOF) that can be exploited for improved spatial resolution, better parametric identifiability, lower side-lobe levels at the transmitter/receiver, and design variety of transmit beampatterns. The design of the transmit beampattern generally requires the waveforms to have arbitrary auto- and crosscorrelation properties. The generation of such waveforms is a two step complicated process. In the first step a waveform covariance matrix is synthesised, which is a constrained optimisation problem. In the second step, to realise this covariance matrix actual waveforms are designed, which is also a constrained optimisation problem. Our proposed scheme converts this two step constrained optimisation problem into a one step unconstrained optimisation problem. In the proposed scheme, in contrast to synthesising the covariance matrix for the desired beampattern, nT independent finite-alphabet constantenvelope waveforms are generated and pre-processed, with weight matrix W, before transmitting from the antennas. In this work, two weight matrices are proposed that can be easily optimised for the desired symmetric and non-symmetric beampatterns and guarantee equal average power transmission from each antenna. Simulation results validate our claims.
Tensor Dictionary Learning for Positive Definite Matrices.
Sivalingam, Ravishankar; Boley, Daniel; Morellas, Vassilios; Papanikolopoulos, Nikolaos
2015-11-01
Sparse models have proven to be extremely successful in image processing and computer vision. However, a majority of the effort has been focused on sparse representation of vectors and low-rank models for general matrices. The success of sparse modeling, along with popularity of region covariances, has inspired the development of sparse coding approaches for these positive definite descriptors. While in earlier work, the dictionary was formed from all, or a random subset of, the training signals, it is clearly advantageous to learn a concise dictionary from the entire training set. In this paper, we propose a novel approach for dictionary learning over positive definite matrices. The dictionary is learned by alternating minimization between sparse coding and dictionary update stages, and different atom update methods are described. A discriminative version of the dictionary learning approach is also proposed, which simultaneously learns dictionaries for different classes in classification or clustering. Experimental results demonstrate the advantage of learning dictionaries from data both from reconstruction and classification viewpoints. Finally, a software library is presented comprising C++ binaries for all the positive definite sparse coding and dictionary learning approaches presented here.
Tian, Wei; Cai, Li; Thissen, David; Xin, Tao
2013-01-01
In item response theory (IRT) modeling, the item parameter error covariance matrix plays a critical role in statistical inference procedures. When item parameters are estimated using the EM algorithm, the parameter error covariance matrix is not an automatic by-product of item calibration. Cai proposed the use of Supplemented EM algorithm for…
Workman, Eli Joseph
We present a single-station method for the determination of Rayleigh wave ellipticity, or Rayleigh wave horizontal to vertical amplitude ratio (H/V) using Frequency Dependent Polarization Analysis (FDPA). This procedure uses singular value decomposition of 3-by-3 spectral covariance matrices over 1-hr time windows to determine properties of the ambient seismic noise field such as particle motion and dominant wave-type. In FPDA, if the noise is mostly dominated by a primary singular value and the phase difference is roughly 90° between the major horizontal axis and the vertical axis of the corresponding singular vector, we infer that Rayleigh waves are dominant and measure an H/V ratio for that hour and frequency bin. We perform this analysis for all available data from the Earthscope Transportable Array between 2004 and 2014. We compare the observed Rayleigh wave H/V ratios with those previously measured by multicomponent, multistation noise cross-correlation (NCC), as well as classical noise spectrum H/V ratio analysis (NSHV). At 8 sec the results from all three methods agree, suggesting that the ambient seismic noise field is Rayleigh wave dominated. Between 10 and 30 sec, while the general pattern agrees well, the results from FDPA and NSHV are persistently slightly higher ( 2%) and significantly higher (>20%), respectively, than results from the array-based NCC. This is likely caused by contamination from other wave types (i.e., Love waves, body waves, and tilt noise) in the single station methods, but it could also reflect a small, persistent error in NCC. Additionally, we find that the single station method has difficulty retrieving robust Rayleigh wave H/V ratios within major sedimentary basins, such as the Williston Basin and Mississippi Embayment, where the noise field is likely dominated by reverberating Love waves.
Separation of Correlated Astrophysical Sources Using Multiple-Lag Data Covariance Matrices
Directory of Open Access Journals (Sweden)
Baccigalupi C
2005-01-01
Full Text Available This paper proposes a new strategy to separate astrophysical sources that are mutually correlated. This strategy is based on second-order statistics and exploits prior information about the possible structure of the mixing matrix. Unlike ICA blind separation approaches, where the sources are assumed mutually independent and no prior knowledge is assumed about the mixing matrix, our strategy allows the independence assumption to be relaxed and performs the separation of even significantly correlated sources. Besides the mixing matrix, our strategy is also capable to evaluate the source covariance functions at several lags. Moreover, once the mixing parameters have been identified, a simple deconvolution can be used to estimate the probability density functions of the source processes. To benchmark our algorithm, we used a database that simulates the one expected from the instruments that will operate onboard ESA's Planck Surveyor Satellite to measure the CMB anisotropies all over the celestial sphere.
A Noise Robust Statistical Texture Model
DEFF Research Database (Denmark)
Hilger, Klaus Baggesen; Stegmann, Mikkel Bille; Larsen, Rasmus
2002-01-01
Appearance Models segmentation framework. This is accomplished by augmenting the model with an estimate of the covariance of the noise present in the training data. This results in a more compact model maximising the signal-to-noise ratio, thus favouring subspaces rich on signal, but low on noise......This paper presents a novel approach to the problem of obtaining a low dimensional representation of texture (pixel intensity) variation present in a training set after alignment using a Generalised Procrustes analysis.We extend the conventional analysis of training textures in the Active...
Covariance expressions for eigenvalue and eigenvector problems
Liounis, Andrew J.
There are a number of important scientific and engineering problems whose solutions take the form of an eigenvalue--eigenvector problem. Some notable examples include solutions to linear systems of ordinary differential equations, controllability of linear systems, finite element analysis, chemical kinetics, fitting ellipses to noisy data, and optimal estimation of attitude from unit vectors. In many of these problems, having knowledge of the eigenvalue and eigenvector Jacobians is either necessary or is nearly as important as having the solution itself. For instance, Jacobians are necessary to find the uncertainty in a computed eigenvalue or eigenvector estimate. This uncertainty, which is usually represented as a covariance matrix, has been well studied for problems similar to the eigenvalue and eigenvector problem, such as singular value decomposition. There has been substantially less research on the covariance of an optimal estimate originating from an eigenvalue-eigenvector problem. In this thesis we develop two general expressions for the Jacobians of eigenvalues and eigenvectors with respect to the elements of their parent matrix. The expressions developed make use of only the parent matrix and the eigenvalue and eigenvector pair under consideration. In addition, they are applicable to any general matrix (including complex valued matrices, eigenvalues, and eigenvectors) as long as the eigenvalues are simple. Alongside this, we develop expressions that determine the uncertainty in a vector estimate obtained from an eigenvalue-eigenvector problem given the uncertainty of the terms of the matrix. The Jacobian expressions developed are numerically validated with forward finite, differencing and the covariance expressions are validated using Monte Carlo analysis. Finally, the results from this work are used to determine covariance expressions for a variety of estimation problem examples and are also applied to the design of a dynamical system.
Nonlinear consider covariance analysis using a sigma-point filter formulation
Lisano, Michael E.
2006-01-01
The research reported here extends the mathematical formulation of nonlinear, sigma-point estimators to enable consider covariance analysis for dynamical systems. This paper presents a novel sigma-point consider filter algorithm, for consider-parameterized nonlinear estimation, following the unscented Kalman filter (UKF) variation on the sigma-point filter formulation, which requires no partial derivatives of dynamics models or measurement models with respect to the parameter list. It is shown that, consistent with the attributes of sigma-point estimators, a consider-parameterized sigma-point estimator can be developed entirely without requiring the derivation of any partial-derivative matrices related to the dynamical system, the measurements, or the considered parameters, which appears to be an advantage over the formulation of a linear-theory sequential consider estimator. It is also demonstrated that a consider covariance analysis performed with this 'partial-derivative-free' formulation yields equivalent results to the linear-theory consider filter, for purely linear problems.
DEFF Research Database (Denmark)
Kinnebrock, Silja; Podolskij, Mark
This paper introduces a new estimator to measure the ex-post covariation between high-frequency financial time series under market microstructure noise. We provide an asymptotic limit theory (including feasible central limit theorems) for standard methods such as regression, correlation analysis...... process can be relaxed and how our method can be applied to non-synchronous observations. We also present an empirical study of how high-frequency correlations, regressions and covariances change through time....
Averaging operations on matrices
Indian Academy of Sciences (India)
2014-07-03
Jul 3, 2014 ... Role of Positive Definite Matrices. • Diffusion Tensor Imaging: 3 × 3 pd matrices model water flow at each voxel of brain scan. • Elasticity: 6 × 6 pd matrices model stress tensors. • Machine Learning: n × n pd matrices occur as kernel matrices. Tanvi Jain. Averaging operations on matrices ...
MIMO Radar Transceiver Design for High Signal-to-Interference-Plus-Noise Ratio
Lipor, John
2013-05-12
Multiple-input multiple-output (MIMO) radar employs orthogonal or partially correlated transmit signals to achieve performance benefits over its phased-array counterpart. It has been shown that MIMO radar can achieve greater spatial resolution, improved signal-to-noise ratio (SNR) and target localization, and greater clutter resolution using space-time adaptive processing (STAP). This thesis explores various methods to improve the signal-to-interference-plus-noise ratio (SINR) via transmit and receive beamforming. In MIMO radar settings, it is often desirable to transmit power only to a given location or set of locations defined by a beampattern. Current methods involve a two- step process of designing the transmit covariance matrix R via iterative solutions and then using R to generate waveforms that fulfill practical constraints such as having a constant-envelope or drawing from a finite alphabet. In this document, a closed- form method to design R is proposed that utilizes the discrete Fourier transform (DFT) coefficients and Toeplitz matrices. The resulting covariance matrix fulfills the practical constraints such as positive semidefiniteness and the uniform elemental power constraint and provides performance similar to that of iterative methods, which require a much greater computation time. Next, a transmit architecture is presented that exploits the orthogonality of frequencies at discrete DFT values to transmit a sum of orthogonal signals from each antenna. The resulting waveforms provide a lower mean-square error than current methods at a much lower computational cost, and a simulated detection scenario demonstrates the performance advantages achieved. It is also desirable to receive signal power only from a given set of directions defined by a beampattern. In a later chapter of this document, the problem of receive beampattern matching is formulated and three solutions to this problem are demonstrated. We show that partitioning the received data vector
Autism-Specific Covariation in Perceptual Performances: “g” or “p” Factor?
Meilleur, Andrée-Anne S.; Berthiaume, Claude; Bertone, Armando; Mottron, Laurent
2014-01-01
Background Autistic perception is characterized by atypical and sometimes exceptional performance in several low- (e.g., discrimination) and mid-level (e.g., pattern matching) tasks in both visual and auditory domains. A factor that specifically affects perceptive abilities in autistic individuals should manifest as an autism-specific association between perceptual tasks. The first purpose of this study was to explore how perceptual performances are associated within or across processing levels and/or modalities. The second purpose was to determine if general intelligence, the major factor that accounts for covariation in task performances in non-autistic individuals, equally controls perceptual abilities in autistic individuals. Methods We asked 46 autistic individuals and 46 typically developing controls to perform four tasks measuring low- or mid-level visual or auditory processing. Intelligence was measured with the Wechsler's Intelligence Scale (FSIQ) and Raven Progressive Matrices (RPM). We conducted linear regression models to compare task performances between groups and patterns of covariation between tasks. The addition of either Wechsler's FSIQ or RPM in the regression models controlled for the effects of intelligence. Results In typically developing individuals, most perceptual tasks were associated with intelligence measured either by RPM or Wechsler FSIQ. The residual covariation between unimodal tasks, i.e. covariation not explained by intelligence, could be explained by a modality-specific factor. In the autistic group, residual covariation revealed the presence of a plurimodal factor specific to autism. Conclusions Autistic individuals show exceptional performance in some perceptual tasks. Here, we demonstrate the existence of specific, plurimodal covariation that does not dependent on general intelligence (or “g” factor). Instead, this residual covariation is accounted for by a common perceptual process (or “p” factor), which may drive
Evaluation of covariance data for chromium, iron and nickel contained in JENDL-3.2
International Nuclear Information System (INIS)
Oh, Soo-Youl; Shibata, Keiichi.
1998-01-01
An evaluation has been made for the covariances of neutron cross sections of 52 Cr, 56 Fe, 58 Ni and 60 Ni contained in JENDL-3.2. Reactions considered were the threshold reactions such as (n, 2n), (n, nα), (n, np), (n, p), (n, d), (n, t) and (n, α), the radiative capture reaction above the resonance region, and the inelastic scattering to discrete and continuum levels. Evaluation guidelines and procedures were established during the work. A generalized least-squares fitting code GMA was used in estimating covariances for reactions of which JENDL-3.2 cross sections had been evaluated by taking account of many measured data. For cross sections that had been evaluated by nuclear reaction model calculations, the KALMAN code, which yields covariances of cross sections and of associated model parameters on the basis of the Bayesian statistics, was used in conjunction with reaction model codes EGNASH and CASTHY. The evaluated uncertainties of a few percent to 30% in the cross sections look reasonable, and the correlation matrices show understandable trends. Even though there is no strict way to confirm the validity of the evaluated covariances, tools and procedures adopted in the present work are appropriate for producing covariance files based on JENDL-3.2. The covariances obtained will be compiled into JENDL in the near future. Meanwhile, new sets of optical model and level density parameters were proposed as one of byproducts obtained from the KALMAN calculations. (author)
Directory of Open Access Journals (Sweden)
Yasuhiro Nakamura
2012-07-01
Full Text Available The present study introduces the four-component scattering power decomposition (4-CSPD algorithm with rotation of covariance matrix, and presents an experimental proof of the equivalence between the 4-CSPD algorithms based on rotation of covariance matrix and coherency matrix. From a theoretical point of view, the 4-CSPD algorithms with rotation of the two matrices are identical. Although it seems obvious, no experimental evidence has yet been presented. In this paper, using polarimetric synthetic aperture radar (POLSAR data acquired by Phased Array L-band SAR (PALSAR on board of Advanced Land Observing Satellite (ALOS, an experimental proof is presented to show that both algorithms indeed produce identical results.
Porta, Tiffany; Grivet, Chantal; Knochenmuss, Richard; Varesio, Emmanuel; Hopfgartner, Gérard
2011-02-01
Analysis of low molecular weight compounds (LMWC) in complex matrices by vacuum matrix-assisted laser desorption/ionization (MALDI) often suffers from matrix interferences, which can severely degrade limits of quantitation. It is, therefore, useful to have available a range of suitable matrices, which exhibit complementary regions of interference. Two newly synthesized α-cyanocinnamic acid derivatives are reported here; (E)-2-cyano-3-(naphthalen-2-yl)acrylic acid (NpCCA) and (2E)-3-(anthracen-9-yl)-2-cyanoprop-2enoic acid (AnCCA). Along with the commonly used α-cyano-4-hydroxycinnamic acid (CHCA), and the recently developed 4-chloro-α-cyanocinnamic acid (Cl-CCA) matrices, these constitute a chemically similar series of matrices covering a range of molecular weights, and with correspondingly differing ranges of spectral interference. Their performance was compared by measuring the signal-to-noise ratios (S/N) of 47 analytes, mostly pharmaceuticals, with the different matrices using the selected reaction monitoring (SRM) mode on a triple quadrupole instrument equipped with a vacuum MALDI source. AnCCA, NpCCA and Cl-CCA were found to offer better signal-to-noise ratios in SRM mode than CHCA, but Cl-CCA yielded the best results for 60% of the compounds tested. To better understand the relative performance of this matrix series, the proton affinities (PAs) were measured using the kinetic method. Their relative values were: AnCCA > CHCA > NpCCA > Cl-CCA. This ordering is consistent with the performance data. The synthesis of the new matrices is straightforward and they provide (1) tunability of matrix background interfering ions and (2) enhanced analyte response for certain classes of compounds. Copyright © 2011 John Wiley & Sons, Ltd.
Simulation-based hypothesis testing of high dimensional means under covariance heterogeneity.
Chang, Jinyuan; Zheng, Chao; Zhou, Wen-Xin; Zhou, Wen
2017-12-01
In this article, we study the problem of testing the mean vectors of high dimensional data in both one-sample and two-sample cases. The proposed testing procedures employ maximum-type statistics and the parametric bootstrap techniques to compute the critical values. Different from the existing tests that heavily rely on the structural conditions on the unknown covariance matrices, the proposed tests allow general covariance structures of the data and therefore enjoy wide scope of applicability in practice. To enhance powers of the tests against sparse alternatives, we further propose two-step procedures with a preliminary feature screening step. Theoretical properties of the proposed tests are investigated. Through extensive numerical experiments on synthetic data sets and an human acute lymphoblastic leukemia gene expression data set, we illustrate the performance of the new tests and how they may provide assistance on detecting disease-associated gene-sets. The proposed methods have been implemented in an R-package HDtest and are available on CRAN. © 2017, The International Biometric Society.
On the Kalman Filter error covariance collapse into the unstable subspace
Directory of Open Access Journals (Sweden)
A. Trevisan
2011-03-01
Full Text Available When the Extended Kalman Filter is applied to a chaotic system, the rank of the error covariance matrices, after a sufficiently large number of iterations, reduces to N^{+} + N^{0} where N^{+} and N^{0} are the number of positive and null Lyapunov exponents. This is due to the collapse into the unstable and neutral tangent subspace of the solution of the full Extended Kalman Filter. Therefore the solution is the same as the solution obtained by confining the assimilation to the space spanned by the Lyapunov vectors with non-negative Lyapunov exponents. Theoretical arguments and numerical verification are provided to show that the asymptotic state and covariance estimates of the full EKF and of its reduced form, with assimilation in the unstable and neutral subspace (EKF-AUS are the same. The consequences of these findings on applications of Kalman type Filters to chaotic models are discussed.
Globally covering a-priori regional gravity covariance models
Directory of Open Access Journals (Sweden)
D. Arabelos
2003-01-01
Full Text Available Gravity anomaly data generated using Wenzel’s GPM98A model complete to degree 1800, from which OSU91A has been subtracted, have been used to estimate covariance functions for a set of globally covering equal-area blocks of size 22.5° × 22.5° at Equator, having a 2.5° overlap. For each block an analytic covariance function model was determined. The models are based on 4 parameters: the depth to the Bjerhammar sphere (determines correlation, the free-air gravity anomaly variance, a scale factor of the OSU91A error degree-variances and a maximal summation index, N, of the error degree-variances. The depth of Bjerhammar-sphere varies from -134km to nearly zero, N varies from 360 to 40, the scale factor from 0.03 to 38.0 and the gravity variance from 1081 to 24(10µms-22. The parameters are interpreted in terms of the quality of the data used to construct OSU91A and GPM98A and general conditions such as the occurrence of mountain chains. The variation of the parameters show that it is necessary to use regional covariance models in order to obtain a realistic signal to noise ratio in global applications.Key words. GOCE mission, Covariance function, Spacewise approach`
VanderLaan Circulant Type Matrices
Directory of Open Access Journals (Sweden)
Hongyan Pan
2015-01-01
Full Text Available Circulant matrices have become a satisfactory tools in control methods for modern complex systems. In the paper, VanderLaan circulant type matrices are presented, which include VanderLaan circulant, left circulant, and g-circulant matrices. The nonsingularity of these special matrices is discussed by the surprising properties of VanderLaan numbers. The exact determinants of VanderLaan circulant type matrices are given by structuring transformation matrices, determinants of well-known tridiagonal matrices, and tridiagonal-like matrices. The explicit inverse matrices of these special matrices are obtained by structuring transformation matrices, inverses of known tridiagonal matrices, and quasi-tridiagonal matrices. Three kinds of norms and lower bound for the spread of VanderLaan circulant and left circulant matrix are given separately. And we gain the spectral norm of VanderLaan g-circulant matrix.
Power law deformation of Wishart–Laguerre ensembles of random matrices
International Nuclear Information System (INIS)
Akemann, Gernot; Vivo, Pierpaolo
2008-01-01
We introduce a one-parameter deformation of the Wishart–Laguerre or chiral ensembles of positive definite random matrices with Dyson index β = 1,2 and 4. Our generalized model has a fat-tailed distribution while preserving the invariance under orthogonal, unitary or symplectic transformations. The spectral properties are derived analytically for finite matrix size N × M for all three values of β, in terms of the orthogonal polynomials of the standard Wishart–Laguerre ensembles. For large N in a certain double-scaling limit we obtain a generalized Marčenko–Pastur distribution on the macroscopic scale, and a generalized Bessel law at the hard edge which is shown to be universal. Both macroscopic and microscopic correlations exhibit power law tails, where the microscopic limit depends on β and the difference M−N. In the limit where our parameter governing the power law goes to infinity we recover the correlations of the Wishart–Laguerre ensembles. To illustrate these findings, the generalized Marčenko–Pastur distribution is shown to be in very good agreement with empirical data from financial covariance matrices
Approximate joint diagonalization and geometric mean of symmetric positive definite matrices.
Congedo, Marco; Afsari, Bijan; Barachant, Alexandre; Moakher, Maher
2014-01-01
We explore the connection between two problems that have arisen independently in the signal processing and related fields: the estimation of the geometric mean of a set of symmetric positive definite (SPD) matrices and their approximate joint diagonalization (AJD). Today there is a considerable interest in estimating the geometric mean of a SPD matrix set in the manifold of SPD matrices endowed with the Fisher information metric. The resulting mean has several important invariance properties and has proven very useful in diverse engineering applications such as biomedical and image data processing. While for two SPD matrices the mean has an algebraic closed form solution, for a set of more than two SPD matrices it can only be estimated by iterative algorithms. However, none of the existing iterative algorithms feature at the same time fast convergence, low computational complexity per iteration and guarantee of convergence. For this reason, recently other definitions of geometric mean based on symmetric divergence measures, such as the Bhattacharyya divergence, have been considered. The resulting means, although possibly useful in practice, do not satisfy all desirable invariance properties. In this paper we consider geometric means of covariance matrices estimated on high-dimensional time-series, assuming that the data is generated according to an instantaneous mixing model, which is very common in signal processing. We show that in these circumstances we can approximate the Fisher information geometric mean by employing an efficient AJD algorithm. Our approximation is in general much closer to the Fisher information geometric mean as compared to its competitors and verifies many invariance properties. Furthermore, convergence is guaranteed, the computational complexity is low and the convergence rate is quadratic. The accuracy of this new geometric mean approximation is demonstrated by means of simulations.
Approximate joint diagonalization and geometric mean of symmetric positive definite matrices.
Directory of Open Access Journals (Sweden)
Marco Congedo
Full Text Available We explore the connection between two problems that have arisen independently in the signal processing and related fields: the estimation of the geometric mean of a set of symmetric positive definite (SPD matrices and their approximate joint diagonalization (AJD. Today there is a considerable interest in estimating the geometric mean of a SPD matrix set in the manifold of SPD matrices endowed with the Fisher information metric. The resulting mean has several important invariance properties and has proven very useful in diverse engineering applications such as biomedical and image data processing. While for two SPD matrices the mean has an algebraic closed form solution, for a set of more than two SPD matrices it can only be estimated by iterative algorithms. However, none of the existing iterative algorithms feature at the same time fast convergence, low computational complexity per iteration and guarantee of convergence. For this reason, recently other definitions of geometric mean based on symmetric divergence measures, such as the Bhattacharyya divergence, have been considered. The resulting means, although possibly useful in practice, do not satisfy all desirable invariance properties. In this paper we consider geometric means of covariance matrices estimated on high-dimensional time-series, assuming that the data is generated according to an instantaneous mixing model, which is very common in signal processing. We show that in these circumstances we can approximate the Fisher information geometric mean by employing an efficient AJD algorithm. Our approximation is in general much closer to the Fisher information geometric mean as compared to its competitors and verifies many invariance properties. Furthermore, convergence is guaranteed, the computational complexity is low and the convergence rate is quadratic. The accuracy of this new geometric mean approximation is demonstrated by means of simulations.
Chitanda, Jackson M.; Zhang, Haixia; Pahl, Erica; Purves, Randy W.; El-Aneed, Anas
2016-10-01
The utility of novel functionalized nanodiamonds (NDs) as matrices for matrix-assisted laser desorption ionization-mass spectrometry (MALDI-MS) is described herein. MALDI-MS analysis of small organic compounds (<1000 Da) is typically complex because of interferences from numerous cluster ions formed when using conventional matrices. To expand the use of MALDI for the analysis of small molecules, novel matrices were designed by covalently linking conventional matrices (or a lysine moiety) to detonated NDs. Four new functionalized NDs were evaluated for their ionization capabilities using five pharmaceuticals with varying molecular structures. Two ND matrices were able to ionize all tested pharmaceuticals in the negative ion mode, producing the deprotonated ions [M - H]-. Ion intensity for target analytes was generally strong with enhanced signal-to-noise ratios compared with conventional matrices. The negative ion mode is of great importance for biological samples as interference from endogenous compounds is inherently minimized in the negative ion mode. Since the molecular structures of the tested pharmaceuticals did not suggest that negative ion mode would be preferable, this result magnifies the importance of these findings. On the other hand, conventional matrices primarily facilitated the ionization as expected in the positive ion mode, producing either the protonated molecules [M + H]+ or cationic adducts (typically producing complex spectra with numerous adduct peaks). The data presented in this study suggests that these matrices may offer advantages for the analysis of low molecular weight pharmaceuticals/metabolites.
Generation of covariance files for the isotopes of Cr, Fe, Ni, Cu, and Pb in ENDF/B-VI
International Nuclear Information System (INIS)
Hetrick, D.M.; Larson, D.C.; Fu, C.Y.
1991-02-01
The considerations that governed the development of the uncertainty files for the isotopes of Cr, Fe, Ni, Cu, and Pb in ENDF/B-VI are summarized. Four different approaches were used in providing the covariance information. Some examples are given which show the standard deviations as a function of incident energy and the corresponding correlation matrices. 11 refs., 5 tabs
Directory of Open Access Journals (Sweden)
Ryan Louise
2007-11-01
Full Text Available Abstract Background The Conditional Autoregressive (CAR model is widely used in many small-area ecological studies to analyse outcomes measured at an areal level. There has been little evaluation of the influence of different neighbourhood weight matrix structures on the amount of smoothing performed by the CAR model. We examined this issue in detail. Methods We created several neighbourhood weight matrices and applied them to a large dataset of births and birth defects in New South Wales (NSW, Australia within 198 Statistical Local Areas. Between the years 1995–2003, there were 17,595 geocoded birth defects and 770,638 geocoded birth records with available data. Spatio-temporal models were developed with data from 1995–2000 and their fit evaluated within the following time period: 2001–2003. Results We were able to create four adjacency-based weight matrices, seven distance-based weight matrices and one matrix based on similarity in terms of a key covariate (i.e. maternal age. In terms of agreement between observed and predicted relative risks, categorised in epidemiologically relevant groups, generally the distance-based matrices performed better than the adjacency-based neighbourhoods. In terms of recovering the underlying risk structure, the weight-7 model (smoothing by maternal-age 'Covariate model' was able to correctly classify 35/47 high-risk areas (sensitivity 74% with a specificity of 47%, and the 'Gravity' model had sensitivity and specificity values of 74% and 39% respectively. Conclusion We found considerable differences in the smoothing properties of the CAR model, depending on the type of neighbours specified. This in turn had an effect on the models' ability to recover the observed risk in an area. Prior to risk mapping or ecological modelling, an exploratory analysis of the neighbourhood weight matrix to guide the choice of a suitable weight matrix is recommended. Alternatively, the weight matrix can be chosen a priori
2015-03-01
biometrics for physiological characteristics, hyperspectral remote sensing for detecting signals buried in noise and clutter, and medical genetics for...s); %approximate bounds on the eigenvalues used in Eq. (8) that are derived %from the Marcenko- Pastur law k=p./n; %band
Gene regulation and noise reduction by coupling of stochastic processes
Ramos, Alexandre F.; Hornos, José Eduardo M.; Reinitz, John
2015-02-01
Here we characterize the low-noise regime of a stochastic model for a negative self-regulating binary gene. The model has two stochastic variables, the protein number and the state of the gene. Each state of the gene behaves as a protein source governed by a Poisson process. The coupling between the two gene states depends on protein number. This fact has a very important implication: There exist protein production regimes characterized by sub-Poissonian noise because of negative covariance between the two stochastic variables of the model. Hence the protein numbers obey a probability distribution that has a peak that is sharper than those of the two coupled Poisson processes that are combined to produce it. Biochemically, the noise reduction in protein number occurs when the switching of the genetic state is more rapid than protein synthesis or degradation. We consider the chemical reaction rates necessary for Poisson and sub-Poisson processes in prokaryotes and eucaryotes. Our results suggest that the coupling of multiple stochastic processes in a negative covariance regime might be a widespread mechanism for noise reduction.
Gene regulation and noise reduction by coupling of stochastic processes.
Ramos, Alexandre F; Hornos, José Eduardo M; Reinitz, John
2015-02-01
Here we characterize the low-noise regime of a stochastic model for a negative self-regulating binary gene. The model has two stochastic variables, the protein number and the state of the gene. Each state of the gene behaves as a protein source governed by a Poisson process. The coupling between the two gene states depends on protein number. This fact has a very important implication: There exist protein production regimes characterized by sub-Poissonian noise because of negative covariance between the two stochastic variables of the model. Hence the protein numbers obey a probability distribution that has a peak that is sharper than those of the two coupled Poisson processes that are combined to produce it. Biochemically, the noise reduction in protein number occurs when the switching of the genetic state is more rapid than protein synthesis or degradation. We consider the chemical reaction rates necessary for Poisson and sub-Poisson processes in prokaryotes and eucaryotes. Our results suggest that the coupling of multiple stochastic processes in a negative covariance regime might be a widespread mechanism for noise reduction.
Holmes, John B; Dodds, Ken G; Lee, Michael A
2017-03-02
An important issue in genetic evaluation is the comparability of random effects (breeding values), particularly between pairs of animals in different contemporary groups. This is usually referred to as genetic connectedness. While various measures of connectedness have been proposed in the literature, there is general agreement that the most appropriate measure is some function of the prediction error variance-covariance matrix. However, obtaining the prediction error variance-covariance matrix is computationally demanding for large-scale genetic evaluations. Many alternative statistics have been proposed that avoid the computational cost of obtaining the prediction error variance-covariance matrix, such as counts of genetic links between contemporary groups, gene flow matrices, and functions of the variance-covariance matrix of estimated contemporary group fixed effects. In this paper, we show that a correction to the variance-covariance matrix of estimated contemporary group fixed effects will produce the exact prediction error variance-covariance matrix averaged by contemporary group for univariate models in the presence of single or multiple fixed effects and one random effect. We demonstrate the correction for a series of models and show that approximations to the prediction error matrix based solely on the variance-covariance matrix of estimated contemporary group fixed effects are inappropriate in certain circumstances. Our method allows for the calculation of a connectedness measure based on the prediction error variance-covariance matrix by calculating only the variance-covariance matrix of estimated fixed effects. Since the number of fixed effects in genetic evaluation is usually orders of magnitudes smaller than the number of random effect levels, the computational requirements for our method should be reduced.
Flavonoids as matrices for MALDI-TOF mass spectrometric analysis of transition metal complexes
Petkovic, Marijana; Petrovic, Biljana; Savic, Jasmina; Bugarcic, Zivadin D.; Dimitric-Markovic, Jasmina; Momic, Tatjana; Vasic, Vesna
2010-02-01
Matrix-assisted laser desorption and ionization time-of-flight mass spectrometry (MALDI-TOF MS) is a suitable method for the analysis of inorganic and organic compounds and biomolecules. This makes MALDI-TOF MS convenient for monitoring the interaction of metallo-drugs with biomolecules. Results presented in this manuscript demonstrate that flavonoids such as apigenin, kaempferol and luteolin are suitable for MALDI-TOF MS analysis of Pt(II), Pd(II), Pt(IV) and Ru(III) complexes, giving different signal-to-noise ratios of the analyte peak. The MALDI-TOF mass spectra of inorganic complexes acquired with these flavonoid matrices are easy to interpret and have some advantages over the application of other commonly used matrices: a low number of matrix peaks are detectable and the coordinative metal-ligand bond is, in most cases, preserved. On the other hand, flavonoids do not act as typical matrices, as their excess is not required for the acquisition of MALDI-TOF mass spectra of inorganic complexes.
Estimated 55Mn and 90Zr cross section covariances in the fast neutron energy region
International Nuclear Information System (INIS)
Pigni, M.T.; Herman, M.; Oblozinsky, P.
2008-01-01
We completed estimates of neutron cross section covariances for 55 Mn and 90 Zr, from keV range to 25 MeV, considering the most important reaction channels, total, elastic, inelastic, capture, and (n,2n). The nuclear reaction model code EMPIRE was used to calculate sensitivity to model parameters by perturbation of parameters that define the optical model potential, nuclear level densities and strength of the pre-equilibrium emission. The sensitivity analysis was performed with the set of parameters which reproduces the ENDF/B-VII.0 cross sections. The experimental data were analyzed and both statistical and systematic uncertainties were extracted from almost 30 selected experiments. Then, the Bayesian code KALMAN was used to combine the sensitivity analysis and the experiments to obtain the evaluated covariance matrices
Estimated 55Mn and 90Zr cross section covariances in the fast neutron energy region
Energy Technology Data Exchange (ETDEWEB)
Pigni,M.T.; Herman, M.; Oblozinsky, P.
2008-06-24
We completed estimates of neutron cross section covariances for {sup 55}Mn and {sup 90}Zr, from keV range to 25 MeV, considering the most important reaction channels, total, elastic, inelastic, capture, and (n,2n). The nuclear reaction model code EMPIRE was used to calculate sensitivity to model parameters by perturbation of parameters that define the optical model potential, nuclear level densities and strength of the pre-equilibrium emission. The sensitivity analysis was performed with the set of parameters which reproduces the ENDF/B-VII.0 cross sections. The experimental data were analyzed and both statistical and systematic uncertainties were extracted from almost 30 selected experiments. Then, the Bayesian code KALMAN was used to combine the sensitivity analysis and the experiments to obtain the evaluated covariance matrices.
Directory of Open Access Journals (Sweden)
Githure John I
2009-09-01
Full Text Available Abstract Background Autoregressive regression coefficients for Anopheles arabiensis aquatic habitat models are usually assessed using global error techniques and are reported as error covariance matrices. A global statistic, however, will summarize error estimates from multiple habitat locations. This makes it difficult to identify where there are clusters of An. arabiensis aquatic habitats of acceptable prediction. It is therefore useful to conduct some form of spatial error analysis to detect clusters of An. arabiensis aquatic habitats based on uncertainty residuals from individual sampled habitats. In this research, a method of error estimation for spatial simulation models was demonstrated using autocorrelation indices and eigenfunction spatial filters to distinguish among the effects of parameter uncertainty on a stochastic simulation of ecological sampled Anopheles aquatic habitat covariates. A test for diagnostic checking error residuals in an An. arabiensis aquatic habitat model may enable intervention efforts targeting productive habitats clusters, based on larval/pupal productivity, by using the asymptotic distribution of parameter estimates from a residual autocovariance matrix. The models considered in this research extends a normal regression analysis previously considered in the literature. Methods Field and remote-sampled data were collected during July 2006 to December 2007 in Karima rice-village complex in Mwea, Kenya. SAS 9.1.4® was used to explore univariate statistics, correlations, distributions, and to generate global autocorrelation statistics from the ecological sampled datasets. A local autocorrelation index was also generated using spatial covariance parameters (i.e., Moran's Indices in a SAS/GIS® database. The Moran's statistic was decomposed into orthogonal and uncorrelated synthetic map pattern components using a Poisson model with a gamma-distributed mean (i.e. negative binomial regression. The eigenfunction
Bayesian source term determination with unknown covariance of measurements
Belal, Alkomiet; Tichý, Ondřej; Šmídl, Václav
2017-04-01
Determination of a source term of release of a hazardous material into the atmosphere is a very important task for emergency response. We are concerned with the problem of estimation of the source term in the conventional linear inverse problem, y = Mx, where the relationship between the vector of observations y is described using the source-receptor-sensitivity (SRS) matrix M and the unknown source term x. Since the system is typically ill-conditioned, the problem is recast as an optimization problem minR,B(y - Mx)TR-1(y - Mx) + xTB-1x. The first term minimizes the error of the measurements with covariance matrix R, and the second term is a regularization of the source term. There are different types of regularization arising for different choices of matrices R and B, for example, Tikhonov regularization assumes covariance matrix B as the identity matrix multiplied by scalar parameter. In this contribution, we adopt a Bayesian approach to make inference on the unknown source term x as well as unknown R and B. We assume prior on x to be a Gaussian with zero mean and unknown diagonal covariance matrix B. The covariance matrix of the likelihood R is also unknown. We consider two potential choices of the structure of the matrix R. First is the diagonal matrix and the second is a locally correlated structure using information on topology of the measuring network. Since the inference of the model is intractable, iterative variational Bayes algorithm is used for simultaneous estimation of all model parameters. The practical usefulness of our contribution is demonstrated on an application of the resulting algorithm to real data from the European Tracer Experiment (ETEX). This research is supported by EEA/Norwegian Financial Mechanism under project MSMT-28477/2014 Source-Term Determination of Radionuclide Releases by Inverse Atmospheric Dispersion Modelling (STRADI).
A method to construct covariance files in ENDF/B format for criticality safety applications
International Nuclear Information System (INIS)
Naberejnev, D.G.; Smith, D.L.
1999-01-01
Argonne National Laboratory is providing support for a criticality safety analysis project that is being performed at Oak Ridge National Laboratory. The ANL role is to provide the covariance information needed by ORNL for this project. The ENDF/B-V evaluation is being used for this particular criticality analysis. In this evaluation, covariance information for several isotopes or elements of interest to this analysis is either not given or needs to be reconsidered. For some required materials, covariance information does not exist in ENDF/B-V: 233 U, 236 U, Zr, Mg, Gd, and Hf. For others, existing covariance information may need to be re-examined in light of the newer ENDF/B-V evaluation and recent experimental data. In this category are the following materials: 235 U, 238 U, 239 Pu, 240 Pu, 241 Pu, Fe, H, C, N, O, Al, Si, and B. A reasonable estimation of the fractional errors for various evaluated neutron cross sections from ENDF/B-V can be based on the comparisons between the major more recent evaluations including ENDF/B-VI, JENDL3.2, BROND2.2, and JEF2.2, as well as a careful examination of experimental data. A reasonable method to construct correlation matrices is proposed here. Coupling both of these considerations suggests a method to construct covariances files in ENDF/B format that can be used to express uncertainties for specific ENDF/B-V cross sections
Weak lensing of the cosmic microwave background: Power spectrum covariance
International Nuclear Information System (INIS)
Cooray, Asantha
2002-01-01
We discuss the non-Gaussian contribution to the power spectrum covariance of cosmic microwave background (CMB) anisotropies resulting through weak gravitational lensing angular deflections and the correlation of deflections with secondary sources of temperature fluctuations generated by the large scale structure, such as the integrated Sachs-Wolfe effect and the Sunyaev-Zel'dovich effect. This additional contribution to the covariance of binned angular power spectrum, beyond the well known cosmic variance and any associated instrumental noise, results from a trispectrum, or a four point correlation function, in temperature anisotropy data. With substantially wide bins in multipole space, the resulting non-Gaussian contribution from lensing to the binned power spectrum variance is insignificant out to multipoles of a few thousand and is not likely to affect the cosmological parameter estimation with acoustic peaks and the damping tail. The non-Gaussian contribution to covariance, however, should be considered when interpreting binned CMB power spectrum measurements at multipoles of a few thousand corresponding to angular scales of few arcminutes and less
Fluctuations of Wigner-type random matrices associated with symmetric spaces of class DIII and CI
Stolz, Michael
2018-02-01
Wigner-type randomizations of the tangent spaces of classical symmetric spaces can be thought of as ordinary Wigner matrices on which additional symmetries have been imposed. In particular, they fall within the scope of a framework, due to Schenker and Schulz-Baldes, for the study of fluctuations of Wigner matrices with additional dependencies among their entries. In this contribution, we complement the results of these authors by explicit calculations of the asymptotic covariances for symmetry classes DIII and CI and thus obtain explicit CLTs for these classes. On the technical level, the present work is an exercise in controlling the cumulative effect of systematically occurring sign factors in an involved sum of products by setting up a suitable combinatorial model for the summands. This aspect may be of independent interest. Research supported by Deutsche Forschungsgemeinschaft (DFG) via SFB 878.
Lee, Paul H
2016-08-01
This study aims to show that under several assumptions, in randomized controlled trials (RCTs), unadjusted, crude analysis will underestimate the Cohen's d effect size of the treatment, and an unbiased estimate of effect size can be obtained only by adjusting for all predictors of the outcome. Four simulations were performed to examine the effects of adjustment on the estimated effect size of the treatment and power of the analysis. In addition, we analyzed data from the Advanced Cognitive Training for Independent and Vital Elderly (ACTIVE) study (older adults aged 65-94), an RCT with three treatment arms and one control arm. We showed that (1) the number of unadjusted covariates was associated with the effect size of the treatment; (2) the biasedness of effect size estimation was minimized if all covariates were adjusted for; (3) the power of the statistical analysis slightly decreased with the number of adjusted noise variables; and (4) exhaustively searching the covariates and noise variables adjusted for can lead to exaggeration of the true effect size. Analysis of the ACTIVE study data showed that the effect sizes adjusting for covariates of all three treatments were 7.39-24.70% larger than their unadjusted counterparts, whereas the effect size would be elevated by at most 57.92% by exhaustively searching the variables adjusted for. All covariates of the outcome in RCTs should be adjusted for, and if the effect of a particular variable on the outcome is unknown, adjustment will do more good than harm. Copyright © 2016 Elsevier Inc. All rights reserved.
Progress on Nuclear Data Covariances: AFCI-1.2 Covariance Library
International Nuclear Information System (INIS)
Oblozinsky, P.; Oblozinsky, P.; Mattoon, C.M.; Herman, M.; Mughabghab, S.F.; Pigni, M.T.; Talou, P.; Hale, G.M.; Kahler, A.C.; Kawano, T.; Little, R.C.; Young, P.G
2009-01-01
Improved neutron cross section covariances were produced for 110 materials including 12 light nuclei (coolants and moderators), 78 structural materials and fission products, and 20 actinides. Improved covariances were organized into AFCI-1.2 covariance library in 33-energy groups, from 10 -5 eV to 19.6 MeV. BNL contributed improved covariance data for the following materials: 23 Na and 55 Mn where more detailed evaluation was done; improvements in major structural materials 52 Cr, 56 Fe and 58 Ni; improved estimates for remaining structural materials and fission products; improved covariances for 14 minor actinides, and estimates of mubar covariances for 23 Na and 56 Fe. LANL contributed improved covariance data for 235 U and 239 Pu including prompt neutron fission spectra and completely new evaluation for 240 Pu. New R-matrix evaluation for 16 O including mubar covariances is under completion. BNL assembled the library and performed basic testing using improved procedures including inspection of uncertainty and correlation plots for each material. The AFCI-1.2 library was released to ANL and INL in August 2009.
Directory of Open Access Journals (Sweden)
Friederike Hammersen
2016-09-01
Full Text Available The health implications of environmental noise, especially cardiovascular effects, have been studied intensively. Research on associations between noise and mental health, however, has shown contradictory results. The present study examined associations between individual levels of noise annoyance due to noise from various sources in the living environment and mental health of adults in Germany. It evaluated whether these associations persisted after adjusting for potential covariates. Data were obtained from the cross-sectional “German Health Update” study 2012 (GEDA 2012, a national health interview survey among adults in Germany conducted by the Robert Koch Institute (n = 19,294. Noise annoyance questions referred to overall noise and that from road traffic, neighbours, and air traffic. Mental health was measured with the five-item Mental Health Inventory. Bivariate analysis showed associations between high levels of noise annoyance and impaired mental health for all noise sources except air traffic. After adjusting for covariates (sociodemographic factors, chronic disease, and social support, both men and women who reported high overall noise annoyance showed more than doubled odds of impaired mental health compared to those who were not annoyed. The odds of impaired mental health in the highest noise annoyance category from road traffic and neighbours were also significantly increased. These findings indicate that high noise annoyance is associated with impaired mental health and that this association can vary with the source of environmental noise. Further research on covariates of this association is necessary. Particularly, longitudinal data are required to establish the direction of associations and to address questions of causality.
Changes in Southern Hemisphere circulation variability in climate change modelling experiments
International Nuclear Information System (INIS)
Grainger, Simon; Frederiksen, Carsten; Zheng, Xiaogu
2007-01-01
Full text: The seasonal mean of a climate variable can be considered as a statistical random variable, consisting of a signal and noise components (Madden 1976). The noise component consists of internal intraseasonal variability, and is not predictable on time-scales of a season or more ahead. The signal consists of slowly varying external and internal variability, and is potentially predictable on seasonal time-scales. The method of Zheng and Frederiksen (2004) has been applied to monthly time series of 500hPa Geopotential height from models submitted to the Coupled Model Intercomparison Project (CMIP3) experiment to obtain covariance matrices of the intraseasonal and slow components of covariability for summer and winter. The Empirical Orthogonal Functions (EOFs) of the intraseasonal and slow covariance matrices for the second half of the 20th century are compared with those observed by Frederiksen and Zheng (2007). The leading EOF in summer and winter for both the intraseasonal and slow components of covariability is the Southern Annular Mode (see, e.g. Kiladis and Mo 1998). This is generally reproduced by the CMIP3 models, although with different variance amounts. The observed secondary intraseasonal covariability modes of wave 4 patterns in summer and wave 3 or blocking in winter are also generally seen in the models, although the actual spatial pattern is different. For the slow covariabilty, the models are less successful in reproducing the two observed ENSO modes, with generally only one of them being represented among the leading EOFs. However, most models reproduce the observed South Pacific wave pattern. The intraseasonal and slow covariances matrices of 500hPa geopotential height under three climate change scenarios are also analysed and compared with those found for the second half of the 20th century. Through aggregating the results from a number of CMIP3 models, a consensus estimate of the changes in Southern Hemisphere variability, and their
Infinite matrices and sequence spaces
Cooke, Richard G
2014-01-01
This clear and correct summation of basic results from a specialized field focuses on the behavior of infinite matrices in general, rather than on properties of special matrices. Three introductory chapters guide students to the manipulation of infinite matrices, covering definitions and preliminary ideas, reciprocals of infinite matrices, and linear equations involving infinite matrices.From the fourth chapter onward, the author treats the application of infinite matrices to the summability of divergent sequences and series from various points of view. Topics include consistency, mutual consi
Complex Wedge-Shaped Matrices: A Generalization of Jacobi Matrices
Czech Academy of Sciences Publication Activity Database
Hnětynková, Iveta; Plešinger, M.
2015-01-01
Roč. 487, 15 December (2015), s. 203-219 ISSN 0024-3795 R&D Projects: GA ČR GA13-06684S Keywords : eigenvalues * eigenvector * wedge-shaped matrices * generalized Jacobi matrices * band (or block) Krylov subspace methods Subject RIV: BA - General Mathematics Impact factor: 0.965, year: 2015
Directory of Open Access Journals (Sweden)
Changgan SHU
2014-09-01
Full Text Available In the standard root multiple signal classification algorithm, the performance of direction of arrival estimation will reduce and even lose effect in circumstances that a low signal noise ratio and a small signals interval. By reconstructing and weighting the covariance matrix of received signal, the modified algorithm can provide more accurate estimation results. The computer simulation and performance analysis are given next, which show that under the condition of lower signal noise ratio and stronger correlation between signals, the proposed modified algorithm could provide preferable azimuth estimating performance than the standard method.
A Small Guide to Generating Covariances of Experimental Data
International Nuclear Information System (INIS)
Mannhart, Wolf
2011-05-01
A complete description of the uncertainties of an experiment can only be realized by a detailed list of all the uncertainty components, their value and a specification of existing correlations between the data. Based on such information the covariance matrix can be generated, which is necessary for any further proceeding with the experimental data. It is not necessary, and not recommended, that an experimenter evaluates this covariance matrix. The reason for this is that a incorrectly evaluated final covariance matrix can never be corrected if the details are not given. (Such obviously wrong covariance matrices have recently occasionally been found in the literature). Hence quotation of a covariance matrix is an additional step which should not occur without quoting a detailed list of the various uncertainty components and their correlations as well. It must be hoped that editors of journals will understand these necessary requirements. The generalized least squares procedure shown permits an easy way of interchanging data D 0 with parameter estimates P. This means new data can easily be combined with an earlier evaluation. However, it must be mentioned that this is only valid as long as the new data have no correlation with any of the older data of the prior evaluation. Otherwise the old data which show correlation with new data have to be extracted from the evaluation and then, together with the new data and taking account of the correlation, have again to be added to the reduced evaluation. In most cases this step cannot be performed and the evaluation has to be completely redone. A partial way out is given if the evaluation is performed step by step and the results of each step are stored. Then the evaluation need only be repeated from the step which contains correlated data for the first time while all earlier steps remain unchanged. Finally it should be noted that the addition of a small set of new data to a prior evaluation consisting of a large number of
On reflectionless equi-transmitting matrices
Directory of Open Access Journals (Sweden)
Pavel Kurasov
2014-01-01
Full Text Available Reflectionless equi-transmitting unitary matrices are studied in connection to matching conditions in quantum graphs. All possible such matrices of size 6 are described explicitly. It is shown that such matrices form 30 six-parameter families intersected along 12 five-parameter families closely connected to conference matrices.
Dispersion curve estimation via a spatial covariance method with ultrasonic wavefield imaging.
Chong, See Yenn; Todd, Michael D
2018-05-01
Numerous Lamb wave dispersion curve estimation methods have been developed to support damage detection and localization strategies in non-destructive evaluation/structural health monitoring (NDE/SHM) applications. In this paper, the covariance matrix is used to extract features from an ultrasonic wavefield imaging (UWI) scan in order to estimate the phase and group velocities of S0 and A0 modes. A laser ultrasonic interrogation method based on a Q-switched laser scanning system was used to interrogate full-field ultrasonic signals in a 2-mm aluminum plate at five different frequencies. These full-field ultrasonic signals were processed in three-dimensional space-time domain. Then, the time-dependent covariance matrices of the UWI were obtained based on the vector variables in Cartesian and polar coordinate spaces for all time samples. A spatial covariance map was constructed to show spatial correlations within the full wavefield. It was observed that the variances may be used as a feature for S0 and A0 mode properties. The phase velocity and the group velocity were found using a variance map and an enveloped variance map, respectively, at five different frequencies. This facilitated the estimation of Lamb wave dispersion curves. The estimated dispersion curves of the S0 and A0 modes showed good agreement with the theoretical dispersion curves. Copyright © 2018 Elsevier B.V. All rights reserved.
Kisil, Vladimir V.
2010-01-01
The paper develops theory of covariant transform, which is inspired by the wavelet construction. It was observed that many interesting types of wavelets (or coherent states) arise from group representations which are not square integrable or vacuum vectors which are not admissible. Covariant transform extends an applicability of the popular wavelets construction to classic examples like the Hardy space H_2, Banach spaces, covariant functional calculus and many others. Keywords: Wavelets, cohe...
Directory of Open Access Journals (Sweden)
Pablo Gregori
2014-03-01
Full Text Available This paper represents a survey of recent advances in modeling of space or space-time Gaussian Random Fields (GRF, tools of Geostatistics at hand for the understanding of special cases of noise in image analysis. They can be used when stationarity or isotropy are unrealistic assumptions, or even when negative covariance between some couples of locations are evident. We show some strategies in order to escape from these restrictions, on the basis of rich classes of well known stationary or isotropic non negative covariance models, and through suitable operations, like linear combinations, generalized means, or with particular Fourier transforms.
Improving the sensitivity of LISA
International Nuclear Information System (INIS)
Nayak, K Rajesh; Pai, A; Dhurandhar, S V; Vinet, J-Y
2003-01-01
It has been shown in several recent papers that the six Doppler data streams obtained from a triangular LISA configuration can be combined by appropriately delaying the data streams for cancelling the laser frequency noise. Raw laser noise is several orders of magnitude above the other noises and thus it is essential to bring it down to the level of other noises such as shot, acceleration, etc. A rigorous and systematic formalism using the powerful techniques of computational commutative algebra was developed, which generates in principle all the data combinations cancelling the laser frequency noise. The relevant data combinations form a first module of syzygies. In this paper, we use this formalism to advantage for optimizing the sensitivity of LISA by analysing the noise and signal covariance matrices. The signal covariance matrix is calculated for binaries whose frequency changes at most adiabatically and the signal is averaged over polarizations and directions. We then present the extremal SNR curves for all the data combinations in the module. They correspond to the eigenvectors of the noise and signal covariance matrices. A LISA 'network' SNR is also computed by combining the outputs of the eigenvectors. We show that substantial gains in sensitivity can be obtained by employing these strategies. The maximum SNR curve can yield an improvement up to 70% over the Michelson, mainly at high frequencies, while the improvement using the network SNR ranges from 40% to over 100%. Finally, we describe a simple toy model, in which LISA rotates in a plane. In this analysis, we estimate the improvement in the LISA sensitivity, if one switches from one data combination to another as it rotates. Here the improvement in sensitivity, if one switches optimally over three cyclic data combinations of the eigenvector, is about 55% on average over the LISA bandwidth. The corresponding SNR improvement increases to 60%, if one maximizes over the module
Time-Distance Helioseismology: Noise Estimation
Gizon, L.; Birch, A. C.
2004-10-01
As in global helioseismology, the dominant source of noise in time-distance helioseismology measurements is realization noise due to the stochastic nature of the excitation mechanism of solar oscillations. Characterizing noise is important for the interpretation and inversion of time-distance measurements. In this paper we introduce a robust definition of travel time that can be applied to very noisy data. We then derive a simple model for the full covariance matrix of the travel-time measurements. This model depends only on the expectation value of the filtered power spectrum and assumes that solar oscillations are stationary and homogeneous on the solar surface. The validity of the model is confirmed through comparison with SOHO MDI measurements in a quiet-Sun region. We show that the correlation length of the noise in the travel times is about half the dominant wavelength of the filtered power spectrum. We also show that the signal-to-noise ratio in quiet-Sun travel-time maps increases roughly as the square root of the observation time and is at maximum for a distance near half the length scale of supergranulation.
Solid-state NMR covariance of homonuclear correlation spectra.
Hu, Bingwen; Amoureux, Jean-Paul; Trebosc, Julien; Deschamps, Michael; Tricot, Gregory
2008-04-07
Direct covariance NMR spectroscopy, which does not involve a Fourier transformation along the indirect dimension, is demonstrated to obtain homonuclear correlation two-dimensional (2D) spectra in the solid state. In contrast to the usual 2D Fourier transform (2D-FT) NMR, in a 2D covariance (2D-Cov) spectrum the spectral resolution in the indirect dimension is determined by the resolution along the detection dimension, thereby largely reducing the time-consuming indirect sampling requirement. The covariance method does not need any separate phase correction or apodization along the indirect dimension because it uses those applied in the detection dimension. We compare in detail the specifications obtained with 2D-FT and 2D-Cov, for narrow and broad resonances. The efficiency of the covariance data treatment is demonstrated in organic and inorganic samples that are both well crystallized and amorphous, for spin -1/2 nuclei with 13C, 29Si, and 31P through-space or through-bond homonuclear 2D correlation spectra. In all cases, the experimental time has been reduced by at least a factor of 10, without any loss of resolution and signal to noise ratio, with respect to what is necessary with the 2D-FT NMR. According to this method, we have been able to study the silicate network of glasses by 2D NMR within reasonable experimental time despite the very long relaxation time of the 29Si nucleus. The main limitation of the 2D-Cov data treatment is related to the introduction of autocorrelated peaks onto the diagonal, which does not represent any actual connectivity.
Are your covariates under control? How normalization can re-introduce covariate effects.
Pain, Oliver; Dudbridge, Frank; Ronald, Angelica
2018-04-30
Many statistical tests rely on the assumption that the residuals of a model are normally distributed. Rank-based inverse normal transformation (INT) of the dependent variable is one of the most popular approaches to satisfy the normality assumption. When covariates are included in the analysis, a common approach is to first adjust for the covariates and then normalize the residuals. This study investigated the effect of regressing covariates against the dependent variable and then applying rank-based INT to the residuals. The correlation between the dependent variable and covariates at each stage of processing was assessed. An alternative approach was tested in which rank-based INT was applied to the dependent variable before regressing covariates. Analyses based on both simulated and real data examples demonstrated that applying rank-based INT to the dependent variable residuals after regressing out covariates re-introduces a linear correlation between the dependent variable and covariates, increasing type-I errors and reducing power. On the other hand, when rank-based INT was applied prior to controlling for covariate effects, residuals were normally distributed and linearly uncorrelated with covariates. This latter approach is therefore recommended in situations were normality of the dependent variable is required.
Portfolio management using realized covariances: Evidence from Brazil
Directory of Open Access Journals (Sweden)
João F. Caldeira
2017-09-01
Full Text Available It is often argued that intraday returns can be used to construct covariance estimates that are more accurate than those based on daily returns. However, it is still unclear whether high frequency data provide more precise covariance estimates in markets more contaminated from microstructure noise such as higher bid-ask spreads and lower liquidity. We address this question by investigating the benefits of using high frequency data in the Brazilian equities market to construct optimal minimum variance portfolios. We implement alternative realized covariance estimators based on intraday returns sampled at alternative frequencies and obtain their dynamic versions using a multivariate GARCH framework. Our evidence based on a high-dimensional data set suggests that realized covariance estimators performed significantly better from an economic point of view in comparison to standard estimators based on low-frequency (close-to-close data as they delivered less risky portfolios. Resumo: Argumenta-se frequentemente que retornos intradiários podem ser usados para construir estimativas de covariâncias mais precisas em relação àquelas obtidas com retornos diários. No entanto, ainda não está claro se os dados de alta freqüência fornecem estimativas de covariância mais precisas em mercados mais contaminados pelo ruído da microestrutura, como maiores spreads entre ofertas de compra e venda e baixa liquidez. Abordamos essa questão investigando os benefícios do uso de dados de alta freqüência no mercado de ações brasileiro através da construção de portfólios ótimos de variância mínima. Implementamos diversos estimadores de covariâncias realizadas com base em retornos intradiários amostrados em diferentes frequências e obtemos suas versões dinâmicas usando uma estrutura GARCH multivariada. Nossa evidência baseada em um conjunto de dados de alta dimensão sugere que os estimadores de covariâncias realizadas obtiveram um desempenho
International Nuclear Information System (INIS)
Plevnik, Lucijan; Žerovnik, Gašper
2016-01-01
Highlights: • Methods for random sampling of correlated parameters. • Link to open-source code for sampling of resonance parameters in ENDF-6 format. • Validation of the code on realistic and artificial data. • Validation of covariances in three major contemporary nuclear data libraries. - Abstract: Methods for random sampling of correlated parameters are presented. The methods are implemented for sampling of resonance parameters in ENDF-6 format and a link to the open-source code ENDSAM is given. The code has been validated on realistic data. Additionally, consistency of covariances of resonance parameters of three major contemporary nuclear data libraries (JEFF-3.2, ENDF/B-VII.1 and JENDL-4.0u2) has been checked.
International Nuclear Information System (INIS)
Kawano, Toshihiko; Shibata, Keiichi.
1997-09-01
A covariance evaluation system for the evaluated nuclear data library was established. The parameter estimation method and the least squares method with a spline function are used to generate the covariance data. Uncertainties of nuclear reaction model parameters are estimated from experimental data uncertainties, then the covariance of the evaluated cross sections is calculated by means of error propagation. Computer programs ELIESE-3, EGNASH4, ECIS, and CASTHY are used. Covariances of 238 U reaction cross sections were calculated with this system. (author)
Asymptotic theory for the sample covariance matrix of a heavy-tailed multivariate time series
DEFF Research Database (Denmark)
Davis, Richard A.; Mikosch, Thomas Valentin; Pfaffel, Olivier
2016-01-01
In this paper we give an asymptotic theory for the eigenvalues of the sample covariance matrix of a multivariate time series. The time series constitutes a linear process across time and between components. The input noise of the linear process has regularly varying tails with index α∈(0,4) in...... particular, the time series has infinite fourth moment. We derive the limiting behavior for the largest eigenvalues of the sample covariance matrix and show point process convergence of the normalized eigenvalues. The limiting process has an explicit form involving points of a Poisson process and eigenvalues...... of a non-negative definite matrix. Based on this convergence we derive limit theory for a host of other continuous functionals of the eigenvalues, including the joint convergence of the largest eigenvalues, the joint convergence of the largest eigenvalue and the trace of the sample covariance matrix...
Waller, Niels G
2016-01-01
For a fixed set of standardized regression coefficients and a fixed coefficient of determination (R-squared), an infinite number of predictor correlation matrices will satisfy the implied quadratic form. I call such matrices fungible correlation matrices. In this article, I describe an algorithm for generating positive definite (PD), positive semidefinite (PSD), or indefinite (ID) fungible correlation matrices that have a random or fixed smallest eigenvalue. The underlying equations of this algorithm are reviewed from both algebraic and geometric perspectives. Two simulation studies illustrate that fungible correlation matrices can be profitably used in Monte Carlo research. The first study uses PD fungible correlation matrices to compare penalized regression algorithms. The second study uses ID fungible correlation matrices to compare matrix-smoothing algorithms. R code for generating fungible correlation matrices is presented in the supplemental materials.
On the algebraic structure of covariant anomalies and covariant Schwinger terms
International Nuclear Information System (INIS)
Kelnhofer, G.
1992-01-01
A cohomological characterization of covariant anomalies and covariant Schwinger terms in an anomalous Yang-Mills theory is formulated and w ill be geometrically interpreted. The BRS and anti-BRS transformations are defined as purely differential geometric objects. Finally the covariant descent equations are formulated within this context. (author)
Preconditioner-free Wiener filtering with a dense noise matrix
Huffenberger, Kevin M.
2018-05-01
This work extends the Elsner & Wandelt (2013) iterative method for efficient, preconditioner-free Wiener filtering to cases in which the noise covariance matrix is dense, but can be decomposed into a sum whose parts are sparse in convenient bases. The new method, which uses multiple messenger fields, reproduces Wiener-filter solutions for test problems, and we apply it to a case beyond the reach of the Elsner & Wandelt (2013) method. We compute the Wiener-filter solution for a simulated Cosmic Microwave Background (CMB) map that contains spatially varying, uncorrelated noise, isotropic 1/f noise, and large-scale horizontal stripes (like those caused by atmospheric noise). We discuss simple extensions that can filter contaminated modes or inverse-noise-filter the data. These techniques help to address complications in the noise properties of maps from current and future generations of ground-based Microwave Background experiments, like Advanced ACTPol, Simons Observatory, and CMB-S4.
A class of covariate-dependent spatiotemporal covariance functions
Reich, Brian J; Eidsvik, Jo; Guindani, Michele; Nail, Amy J; Schmidt, Alexandra M.
2014-01-01
In geostatistics, it is common to model spatially distributed phenomena through an underlying stationary and isotropic spatial process. However, these assumptions are often untenable in practice because of the influence of local effects in the correlation structure. Therefore, it has been of prolonged interest in the literature to provide flexible and effective ways to model non-stationarity in the spatial effects. Arguably, due to the local nature of the problem, we might envision that the correlation structure would be highly dependent on local characteristics of the domain of study, namely the latitude, longitude and altitude of the observation sites, as well as other locally defined covariate information. In this work, we provide a flexible and computationally feasible way for allowing the correlation structure of the underlying processes to depend on local covariate information. We discuss the properties of the induced covariance functions and discuss methods to assess its dependence on local covariate information by means of a simulation study and the analysis of data observed at ozone-monitoring stations in the Southeast United States. PMID:24772199
Double stochastic matrices in quantum mechanics
International Nuclear Information System (INIS)
Louck, J.D.
1997-01-01
The general set of doubly stochastic matrices of order n corresponding to ordinary nonrelativistic quantum mechanical transition probability matrices is given. Lande's discussion of the nonquantal origin of such matrices is noted. Several concrete examples are presented for elementary and composite angular momentum systems with the focus on the unitary symmetry associated with such systems in the spirit of the recent work of Bohr and Ulfbeck. Birkhoff's theorem on doubly stochastic matrices of order n is reformulated in a geometrical language suitable for application to the subset of quantum mechanical doubly stochastic matrices. Specifically, it is shown that the set of points on the unit sphere in cartesian n'-space is subjective with the set of doubly stochastic matrices of order n. The question is raised, but not answered, as to what is the subset of points of this unit sphere that correspond to the quantum mechanical transition probability matrices, and what is the symmetry group of this subset of matrices
ENDF-6 File 30: Data covariances obtained from parameter covariances and sensitivities
International Nuclear Information System (INIS)
Muir, D.W.
1989-01-01
File 30 is provided as a means of describing the covariances of tabulated cross sections, multiplicities, and energy-angle distributions that result from propagating the covariances of a set of underlying parameters (for example, the input parameters of a nuclear-model code), using an evaluator-supplied set of parameter covariances and sensitivities. Whenever nuclear data are evaluated primarily through the application of nuclear models, the covariances of the resulting data can be described very adequately, and compactly, by specifying the covariance matrix for the underlying nuclear parameters, along with a set of sensitivity coefficients giving the rate of change of each nuclear datum of interest with respect to each of the model parameters. Although motivated primarily by these applications of nuclear theory, use of File 30 is not restricted to any one particular evaluation methodology. It can be used to describe data covariances of any origin, so long as they can be formally separated into a set of parameters with specified covariances and a set of data sensitivities
Deterministic matrices matching the compressed sensing phase transitions of Gaussian random matrices
Monajemi, Hatef; Jafarpour, Sina; Gavish, Matan; Donoho, David L.; Ambikasaran, Sivaram; Bacallado, Sergio; Bharadia, Dinesh; Chen, Yuxin; Choi, Young; Chowdhury, Mainak; Chowdhury, Soham; Damle, Anil; Fithian, Will; Goetz, Georges; Grosenick, Logan; Gross, Sam; Hills, Gage; Hornstein, Michael; Lakkam, Milinda; Lee, Jason; Li, Jian; Liu, Linxi; Sing-Long, Carlos; Marx, Mike; Mittal, Akshay; Monajemi, Hatef; No, Albert; Omrani, Reza; Pekelis, Leonid; Qin, Junjie; Raines, Kevin; Ryu, Ernest; Saxe, Andrew; Shi, Dai; Siilats, Keith; Strauss, David; Tang, Gary; Wang, Chaojun; Zhou, Zoey; Zhu, Zhen
2013-01-01
In compressed sensing, one takes samples of an N-dimensional vector using an matrix A, obtaining undersampled measurements . For random matrices with independent standard Gaussian entries, it is known that, when is k-sparse, there is a precisely determined phase transition: for a certain region in the (,)-phase diagram, convex optimization typically finds the sparsest solution, whereas outside that region, it typically fails. It has been shown empirically that the same property—with the same phase transition location—holds for a wide range of non-Gaussian random matrix ensembles. We report extensive experiments showing that the Gaussian phase transition also describes numerous deterministic matrices, including Spikes and Sines, Spikes and Noiselets, Paley Frames, Delsarte-Goethals Frames, Chirp Sensing Matrices, and Grassmannian Frames. Namely, for each of these deterministic matrices in turn, for a typical k-sparse object, we observe that convex optimization is successful over a region of the phase diagram that coincides with the region known for Gaussian random matrices. Our experiments considered coefficients constrained to for four different sets , and the results establish our finding for each of the four associated phase transitions. PMID:23277588
Energy Technology Data Exchange (ETDEWEB)
Greco, Johnny P. [Department of Astrophysical Sciences, Princeton University, Princeton, NJ (United States); Brandt, Timothy D. [Institute for Advanced Study, Princeton, NJ (United States)
2016-12-20
The recovery of an exoplanet’s atmospheric parameters from its spectrum requires accurate knowledge of the spectral errors and covariances. Unfortunately, the complex image processing used in high-contrast integral-field spectrograph (IFS) observations generally produces spectral covariances that are poorly understood and often ignored. In this work, we show how to measure the spectral errors and covariances and include them self-consistently in parameter retrievals. By combining model exoplanet spectra with a realistic noise model generated from the Gemini Planet Imager (GPI) early science data, we show that ignoring spectral covariance in high-contrast IFS data can both bias inferred parameters and lead to unreliable confidence regions on those parameters. This problem is made worse by the common practice of scaling the χ {sup 2} per degree of freedom to unity; the input parameters then fall outside the 95% confidence regions in as many as ∼80% of noise realizations. The biases we observe can approach the typical levels of precision achieved in high-contrast spectroscopy. Accounting for realistic priors in fully Bayesian retrievals can also have a significant impact on the inferred parameters. Plausible priors on effective temperature and surface gravity can vary by an order of magnitude across the confidence regions appropriate for objects with weak age constraints; priors for objects with good age constraints are dominated by modeling uncertainties. Our methods are directly applicable to existing high-contrast IFSs including GPI and SPHERE, as well as upcoming instruments like CHARIS and, ultimately, WFIRST-AFTA.
Matrices and linear transformations
Cullen, Charles G
1990-01-01
""Comprehensive . . . an excellent introduction to the subject."" - Electronic Engineer's Design Magazine.This introductory textbook, aimed at sophomore- and junior-level undergraduates in mathematics, engineering, and the physical sciences, offers a smooth, in-depth treatment of linear algebra and matrix theory. The major objects of study are matrices over an arbitrary field. Contents include Matrices and Linear Systems; Vector Spaces; Determinants; Linear Transformations; Similarity: Part I and Part II; Polynomials and Polynomial Matrices; Matrix Analysis; and Numerical Methods. The first
Pairwise registration of TLS point clouds using covariance descriptors and a non-cooperative game
Zai, Dawei; Li, Jonathan; Guo, Yulan; Cheng, Ming; Huang, Pengdi; Cao, Xiaofei; Wang, Cheng
2017-12-01
It is challenging to automatically register TLS point clouds with noise, outliers and varying overlap. In this paper, we propose a new method for pairwise registration of TLS point clouds. We first generate covariance matrix descriptors with an adaptive neighborhood size from point clouds to find candidate correspondences, we then construct a non-cooperative game to isolate mutual compatible correspondences, which are considered as true positives. The method was tested on three models acquired by two different TLS systems. Experimental results demonstrate that our proposed adaptive covariance (ACOV) descriptor is invariant to rigid transformation and robust to noise and varying resolutions. The average registration errors achieved on three models are 0.46 cm, 0.32 cm and 1.73 cm, respectively. The computational times cost on these models are about 288 s, 184 s and 903 s, respectively. Besides, our registration framework using ACOV descriptors and a game theoretic method is superior to the state-of-the-art methods in terms of both registration error and computational time. The experiment on a large outdoor scene further demonstrates the feasibility and effectiveness of our proposed pairwise registration framework.
Livan, Giacomo; Alfarano, Simone; Scalas, Enrico
2011-07-01
We study some properties of eigenvalue spectra of financial correlation matrices. In particular, we investigate the nature of the large eigenvalue bulks which are observed empirically, and which have often been regarded as a consequence of the supposedly large amount of noise contained in financial data. We challenge this common knowledge by acting on the empirical correlation matrices of two data sets with a filtering procedure which highlights some of the cluster structure they contain, and we analyze the consequences of such filtering on eigenvalue spectra. We show that empirically observed eigenvalue bulks emerge as superpositions of smaller structures, which in turn emerge as a consequence of cross correlations between stocks. We interpret and corroborate these findings in terms of factor models, and we compare empirical spectra to those predicted by random matrix theory for such models.
Livan, Giacomo; Alfarano, Simone; Scalas, Enrico
2011-07-01
We study some properties of eigenvalue spectra of financial correlation matrices. In particular, we investigate the nature of the large eigenvalue bulks which are observed empirically, and which have often been regarded as a consequence of the supposedly large amount of noise contained in financial data. We challenge this common knowledge by acting on the empirical correlation matrices of two data sets with a filtering procedure which highlights some of the cluster structure they contain, and we analyze the consequences of such filtering on eigenvalue spectra. We show that empirically observed eigenvalue bulks emerge as superpositions of smaller structures, which in turn emerge as a consequence of cross correlations between stocks. We interpret and corroborate these findings in terms of factor models, and we compare empirical spectra to those predicted by random matrix theory for such models.
Brier, Matthew R; Mitra, Anish; McCarthy, John E; Ances, Beau M; Snyder, Abraham Z
2015-11-01
Functional connectivity refers to shared signals among brain regions and is typically assessed in a task free state. Functional connectivity commonly is quantified between signal pairs using Pearson correlation. However, resting-state fMRI is a multivariate process exhibiting a complicated covariance structure. Partial covariance assesses the unique variance shared between two brain regions excluding any widely shared variance, hence is appropriate for the analysis of multivariate fMRI datasets. However, calculation of partial covariance requires inversion of the covariance matrix, which, in most functional connectivity studies, is not invertible owing to rank deficiency. Here we apply Ledoit-Wolf shrinkage (L2 regularization) to invert the high dimensional BOLD covariance matrix. We investigate the network organization and brain-state dependence of partial covariance-based functional connectivity. Although RSNs are conventionally defined in terms of shared variance, removal of widely shared variance, surprisingly, improved the separation of RSNs in a spring embedded graphical model. This result suggests that pair-wise unique shared variance plays a heretofore unrecognized role in RSN covariance organization. In addition, application of partial correlation to fMRI data acquired in the eyes open vs. eyes closed states revealed focal changes in uniquely shared variance between the thalamus and visual cortices. This result suggests that partial correlation of resting state BOLD time series reflect functional processes in addition to structural connectivity. Copyright © 2015 Elsevier Inc. All rights reserved.
Székely, Gábor J.; Rizzo, Maria L.
2010-01-01
Distance correlation is a new class of multivariate dependence coefficients applicable to random vectors of arbitrary and not necessarily equal dimension. Distance covariance and distance correlation are analogous to product-moment covariance and correlation, but generalize and extend these classical bivariate measures of dependence. Distance correlation characterizes independence: it is zero if and only if the random vectors are independent. The notion of covariance with...
Irgens-Hansen, Kaja; Gundersen, Hilde; Sunde, Erlend; Baste, Valborg; Harris, Anette; Bråtveit, Magne; Moen, Bente E
2015-01-01
Prior research shows that work on board vessels of the Royal Norwegian Navy (RNoN) is associated with noise exposure levels above recommended standards. Further, noise exposure has been found to impair cognitive performance in environmental, occupational, and experimental settings, although prior research in naval and maritime settings is sparse. The aim of this study was to evaluate cognitive performance after exposure to noise among personnel working on board vessels in the RNoN. Altogether 87 Navy personnel (80 men, 7 women; 31 ± 9 years) from 24 RNoN vessels were included. Noise exposure was recorded by personal noise dosimeters at a minimum of 4 h prior to testing, and categorized into 4 groups for the analysis: 85.2 dB(A). The participants performed a visual attention test based on the Posner cue-target paradigm. Multivariable general linear model (GLM) analyses were performed to analyze whether noise exposure was associated with response time (RT) when adjusting for the covariates age, alertness, workload, noise exposure in test location, sleep the night before testing, use of hearing protection device (HPD), and percentage of errors. When adjusting for covariates, RT was significantly increased among personnel exposed to >85.2 dB(A) and 77.1-85.2 dB(A) compared to personnel exposed to <72.6 dB(A).
Noise exposure and cognitive performance: A study on personnel on board Royal Norwegian Navy vessels
Directory of Open Access Journals (Sweden)
Kaja Irgens-Hansen
2015-01-01
Full Text Available Prior research shows that work on board vessels of the Royal Norwegian Navy (RNoN is associated with noise exposure levels above recommended standards. Further, noise exposure has been found to impair cognitive performance in environmental, occupational, and experimental settings, although prior research in naval and maritime settings is sparse. The aim of this study was to evaluate cognitive performance after exposure to noise among personnel working on board vessels in the RNoN. Altogether 87 Navy personnel (80 men, 7 women; 31 ± 9 years from 24 RNoN vessels were included. Noise exposure was recorded by personal noise dosimeters at a minimum of 4 h prior to testing, and categorized into 4 groups for the analysis: 85.2 dB(A. The participants performed a visual attention test based on the Posner cue-target paradigm. Multivariable general linear model (GLM analyses were performed to analyze whether noise exposure was associated with response time (RT when adjusting for the covariates age, alertness, workload, noise exposure in test location, sleep the night before testing, use of hearing protection device (HPD, and percentage of errors. When adjusting for covariates, RT was significantly increased among personnel exposed to >85.2 dB(A and 77.1-85.2 dB(A compared to personnel exposed to <72.6 dB(A.
Lambda-matrices and vibrating systems
Lancaster, Peter; Stark, M; Kahane, J P
1966-01-01
Lambda-Matrices and Vibrating Systems presents aspects and solutions to problems concerned with linear vibrating systems with a finite degrees of freedom and the theory of matrices. The book discusses some parts of the theory of matrices that will account for the solutions of the problems. The text starts with an outline of matrix theory, and some theorems are proved. The Jordan canonical form is also applied to understand the structure of square matrices. Classical theorems are discussed further by applying the Jordan canonical form, the Rayleigh quotient, and simple matrix pencils with late
Manin matrices and Talalaev's formula
International Nuclear Information System (INIS)
Chervov, A; Falqui, G
2008-01-01
In this paper we study properties of Lax and transfer matrices associated with quantum integrable systems. Our point of view stems from the fact that their elements satisfy special commutation properties, considered by Yu I Manin some 20 years ago at the beginning of quantum group theory. These are the commutation properties of matrix elements of linear homomorphisms between polynomial rings; more explicitly these read: (1) elements of the same column commute; (2) commutators of the cross terms are equal: [M ij , M kl ] [M kj , M il ] (e.g. [M 11 , M 22 ] = [M 21 , M 12 ]). The main aim of this paper is twofold: on the one hand we observe and prove that such matrices (which we call Manin matrices in short) behave almost as well as matrices with commutative elements. Namely, the theorems of linear algebra (e.g., a natural definition of the determinant, the Cayley-Hamilton theorem, the Newton identities and so on and so forth) have a straightforward counterpart in the case of Manin matrices. On the other hand, we remark that such matrices are somewhat ubiquitous in the theory of quantum integrability. For instance, Manin matrices (and their q-analogs) include matrices satisfying the Yang-Baxter relation 'RTT=TTR' and the so-called Cartier-Foata matrices. Also, they enter Talalaev's remarkable formulae: det(∂ z -L gaudin (z)), det(1-e -∂z T Yangian (z)) for the 'quantum spectral curve', and appear in the separation of variables problem and Capelli identities. We show that theorems of linear algebra, after being established for such matrices, have various applications to quantum integrable systems and Lie algebras, e.g. in the construction of new generators in Z(U crit (gl-hat n )) (and, in general, in the construction of quantum conservation laws), in the Knizhnik-Zamolodchikov equation, and in the problem of Wick ordering. We propose, in the appendix, a construction of quantum separated variables for the XXX-Heisenberg system
Two-stage sparse coding of region covariance via Log-Euclidean kernels to detect saliency.
Zhang, Ying-Ying; Yang, Cai; Zhang, Ping
2017-05-01
In this paper, we present a novel bottom-up saliency detection algorithm from the perspective of covariance matrices on a Riemannian manifold. Each superpixel is described by a region covariance matrix on Riemannian Manifolds. We carry out a two-stage sparse coding scheme via Log-Euclidean kernels to extract salient objects efficiently. In the first stage, given background dictionary on image borders, sparse coding of each region covariance via Log-Euclidean kernels is performed. The reconstruction error on the background dictionary is regarded as the initial saliency of each superpixel. In the second stage, an improvement of the initial result is achieved by calculating reconstruction errors of the superpixels on foreground dictionary, which is extracted from the first stage saliency map. The sparse coding in the second stage is similar to the first stage, but is able to effectively highlight the salient objects uniformly from the background. Finally, three post-processing methods-highlight-inhibition function, context-based saliency weighting, and the graph cut-are adopted to further refine the saliency map. Experiments on four public benchmark datasets show that the proposed algorithm outperforms the state-of-the-art methods in terms of precision, recall and mean absolute error, and demonstrate the robustness and efficiency of the proposed method. Copyright © 2017 Elsevier Ltd. All rights reserved.
Covariant representations of nuclear *-algebras
International Nuclear Information System (INIS)
Moore, S.M.
1978-01-01
Extensions of the Csup(*)-algebra theory for covariant representations to nuclear *-algebra are considered. Irreducible covariant representations are essentially unique, an invariant state produces a covariant representation with stable vacuum, and the usual relation between ergodic states and covariant representations holds. There exist construction and decomposition theorems and a possible relation between derivations and covariant representations
MERSENNE AND HADAMARD MATRICES CALCULATION BY SCARPIS METHOD
Directory of Open Access Journals (Sweden)
N. A. Balonin
2014-05-01
Full Text Available Purpose. The paper deals with the problem of basic generalizations of Hadamard matrices associated with maximum determinant matrices or not optimal by determinant matrices with orthogonal columns (weighing matrices, Mersenne and Euler matrices, ets.; calculation methods for the quasi-orthogonal local maximum determinant Mersenne matrices are not studied enough sufficiently. The goal of this paper is to develop the theory of Mersenne and Hadamard matrices on the base of generalized Scarpis method research. Methods. Extreme solutions are found in general by minimization of maximum for absolute values of the elements of studied matrices followed by their subsequent classification according to the quantity of levels and their values depending on orders. Less universal but more effective methods are based on structural invariants of quasi-orthogonal matrices (Silvester, Paley, Scarpis methods, ets.. Results. Generalizations of Hadamard and Belevitch matrices as a family of quasi-orthogonal matrices of odd orders are observed; they include, in particular, two-level Mersenne matrices. Definitions of section and layer on the set of generalized matrices are proposed. Calculation algorithms for matrices of adjacent layers and sections by matrices of lower orders are described. Approximation examples of the Belevitch matrix structures up to 22-nd critical order by Mersenne matrix of the third order are given. New formulation of the modified Scarpis method to approximate Hadamard matrices of high orders by lower order Mersenne matrices is proposed. Williamson method is described by example of one modular level matrices approximation by matrices with a small number of levels. Practical relevance. The efficiency of developing direction for the band-pass filters creation is justified. Algorithms for Mersenne matrices design by Scarpis method are used in developing software of the research program complex. Mersenne filters are based on the suboptimal by
International Nuclear Information System (INIS)
Oliver, J; Budzevich, M; Moros, E; Zhang, G; Hunt, D
2015-01-01
Purpose: To investigate the relationship between quantitative image features (i.e. radiomics) and statistical fluctuations (i.e. electronic noise) in clinical Computed Tomography (CT) using the standardized American College of Radiology (ACR) CT accreditation phantom and patient images. Methods: Three levels of uncorrelated Gaussian noise were added to CT images of phantom and patients (20) acquired in static mode and respiratory tracking mode. We calculated the noise-power spectrum (NPS) of the original CT images of the phantom, and of the phantom images with added Gaussian noise with means of 50, 80, and 120 HU. Concurrently, on patient images (original and noise-added images), image features were calculated: 14 shape, 19 intensity (1st order statistics from intensity volume histograms), 18 GLCM features (2nd order statistics from grey level co-occurrence matrices) and 11 RLM features (2nd order statistics from run-length matrices). These features provide the underlying structural information of the images. GLCM (size 128x128) was calculated with a step size of 1 voxel in 13 directions and averaged. RLM feature calculation was performed in 13 directions with grey levels binning into 128 levels. Results: Adding the electronic noise to the images modified the quality of the NPS, shifting the noise from mostly correlated to mostly uncorrelated voxels. The dramatic increase in noise texture did not affect image structure/contours significantly for patient images. However, it did affect the image features and textures significantly as demonstrated by GLCM differences. Conclusion: Image features are sensitive to acquisition factors (simulated by adding uncorrelated Gaussian noise). We speculate that image features will be more difficult to detect in the presence of electronic noise (an uncorrelated noise contributor) or, for that matter, any other highly correlated image noise. This work focuses on the effect of electronic, uncorrelated, noise and future work shall
Small, Robert J.; Brost, Brian M.; Hooten, Mevin B.; Castellote, Manuel; Mondragon, Jeffrey
2017-01-01
The population of beluga whales in Cook Inlet, Alaska, USA, declined by nearly half in the mid-1990s, primarily from an unsustainable harvest, and was listed as endangered in 2008. In 2014, abundance was ~340 whales, and the population trend during 1999-2014 was -1.3% yr-1. Cook Inlet beluga whales are particularly vulnerable to anthropogenic impacts, and noise that has the potential to reduce communication and echolocation range considerably has been documented in critical habitat; thus, noise was ranked as a high potential threat in the Cook Inlet beluga Recovery Plan. The current recovery strategy includes research on effects of threats potentially limiting recovery, and thus we examined the potential impact of anthropogenic noise in critical habitat, specifically, spatial displacement. Using a subset of data on anthropogenic noise and beluga detections from a 5 yr acoustic study, we evaluated the influence of noise events on beluga occupancy probability. We used occupancy models, which account for factors that affect detection probability when estimating occupancy, the first application of these models to examine the potential impacts of anthropogenic noise on marine mammal behavior. Results were inconclusive, primarily because beluga detections were relatively infrequent. Even though noise metrics (sound pressure level and noise duration) appeared in high-ranking models as covariates for occupancy probability, the data were insufficient to indicate better predictive ability beyond those models that only included environmental covariates. Future studies that implement protocols designed specifically for beluga occupancy will be most effective for accurately estimating the effect of noise on beluga displacement.
Wang, Jun-Sheng; Yang, Guang-Hong
2017-07-25
This paper studies the optimal output-feedback control problem for unknown linear discrete-time systems with stochastic measurement and process noise. A dithered Bellman equation with the innovation covariance matrix is constructed via the expectation operator given in the form of a finite summation. On this basis, an output-feedback-based approximate dynamic programming method is developed, where the terms depending on the innovation covariance matrix are available with the aid of the innovation covariance matrix identified beforehand. Therefore, by iterating the Bellman equation, the resulting value function can converge to the optimal one in the presence of the aforementioned noise, and the nearly optimal control laws are delivered. To show the effectiveness and the advantages of the proposed approach, a simulation example and a velocity control experiment on a dc machine are employed.
Chen, Peng; Yang, Yixin; Wang, Yong; Ma, Yuanliang
2018-05-08
When sensor position errors exist, the performance of recently proposed interference-plus-noise covariance matrix (INCM)-based adaptive beamformers may be severely degraded. In this paper, we propose a weighted subspace fitting-based INCM reconstruction algorithm to overcome sensor displacement for linear arrays. By estimating the rough signal directions, we construct a novel possible mismatched steering vector (SV) set. We analyze the proximity of the signal subspace from the sample covariance matrix (SCM) and the space spanned by the possible mismatched SV set. After solving an iterative optimization problem, we reconstruct the INCM using the estimated sensor position errors. Then we estimate the SV of the desired signal by solving an optimization problem with the reconstructed INCM. The main advantage of the proposed algorithm is its robustness against SV mismatches dominated by unknown sensor position errors. Numerical examples show that even if the position errors are up to half of the assumed sensor spacing, the output signal-to-interference-plus-noise ratio is only reduced by 4 dB. Beam patterns plotted using experiment data show that the interference suppression capability of the proposed beamformer outperforms other tested beamformers.
Intrinsic character of Stokes matrices
Gagnon, Jean-François; Rousseau, Christiane
2017-02-01
Two germs of linear analytic differential systems x k + 1Y‧ = A (x) Y with a non-resonant irregular singularity are analytically equivalent if and only if they have the same eigenvalues and equivalent collections of Stokes matrices. The Stokes matrices are the transition matrices between sectors on which the system is analytically equivalent to its formal normal form. Each sector contains exactly one separating ray for each pair of eigenvalues. A rotation in S allows supposing that R+ lies in the intersection of two sectors. Reordering of the coordinates of Y allows ordering the real parts of the eigenvalues, thus yielding triangular Stokes matrices. However, the choice of the rotation in x is not canonical. In this paper we establish how the collection of Stokes matrices depends on this rotation, and hence on a chosen order of the projection of the eigenvalues on a line through the origin.
Hierarchical matrices algorithms and analysis
Hackbusch, Wolfgang
2015-01-01
This self-contained monograph presents matrix algorithms and their analysis. The new technique enables not only the solution of linear systems but also the approximation of matrix functions, e.g., the matrix exponential. Other applications include the solution of matrix equations, e.g., the Lyapunov or Riccati equation. The required mathematical background can be found in the appendix. The numerical treatment of fully populated large-scale matrices is usually rather costly. However, the technique of hierarchical matrices makes it possible to store matrices and to perform matrix operations approximately with almost linear cost and a controllable degree of approximation error. For important classes of matrices, the computational cost increases only logarithmically with the approximation error. The operations provided include the matrix inversion and LU decomposition. Since large-scale linear algebra problems are standard in scientific computing, the subject of hierarchical matrices is of interest to scientists ...
Small fluctuations in epitaxial growth via conservative noise
International Nuclear Information System (INIS)
Patrone, Paul N; Wang Rongrong; Margetis, Dionisios
2011-01-01
We study the combined effect of growth (material deposition from above) and nearest-neighbor entropic and force-dipole interactions in a stochastically perturbed system of N line defects (steps) on a vicinal crystal surface in 1+1 dimensions. First, we formulate a general model of conservative white noise and derive simplified formulas for the terrace width distribution and terrace width correlations in the limit N → ∞ for small step fluctuations. Our general result expresses terrace width correlations as an interplay of noise covariance and step interaction strength. Second, we apply our formalism to two specific noise models which stem, respectively, from (i) the fluctuation-dissipation theorem for diffusion of adsorbed atoms; and (ii) the phenomenological consideration of deposition-flux-induced asymmetric attachment and detachment of atoms at step edges. In both cases of noise, we find that terrace width correlations decay exponentially with the step number difference; this behavior leads to vanishing correlations in the macroscopic limit. Our analysis may be used to (i) determine the noise in quasi-one-dimensional surfaces and (ii) assess the validity of previous mean field approximations.
DEFF Research Database (Denmark)
Jensen, Jesper Rindom; Benesty, Jacob; Christensen, Mads Græsbøll
2013-01-01
In this paper, we introduce a new class of op- timal rectangular filtering matrices for single-channel speech enhancement. The new class of filters exploits the fact that the dimension of the signal subspace is lower than that of the full space. By doing this, extra degrees of freedom...... in the filters, that are otherwise reserved for preserving the signal subspace, can be used for achieving an improved output signal-to-noise ratio (SNR). Moreover, the filters allow for explicit control of the tradeoff between noise reduction and speech distortion via the chosen rank of the signal subspace...... and real signals. The results show a number of interesting things. Firstly, they show how speech distortion can be traded for noise reduction and vice versa in a seamless manner. Moreover, the introduced filter designs are capable of achieving both the upper and lower bounds for the output SNR via...
Knospe, Steffen H G
2010-04-01
We study anisotropic spatial autocorrelation in differential synthetic aperture radar interferometric (dInSAR) measurements and its impact on geophysical parameter estimations. The dInSAR phase acquired by the satellite sensor is a superposition of different contributions, and when studying geophysical processes, we are usually only interested in the surface deformation part of the signal. Therefore, to obtain high-quality results, we would like to characterize and/or remove other phase components. A stochastic model has been found to be appropriate to describe atmospheric phase delay in dInSAR images. However, these phase delays are usually modeled as being isotropic, which is a simplification, because InSAR images often show directional atmospheric anomalies. Here, we analyze anisotropic structures and show validation results using both real and simulated data. We calculate experimental semivariograms of the dInSAR phase in several European Remote Sensing satellite-1/2 tandem interferograms. Based on the theory of random functions (RFs), we then fit anisotropic variogram models in the spatial domain, employing Matérn-and Bessel-family correlation functions in nested models to represent complex dInSAR covariance structures. The presented covariance function types, in the statistical framework of stationary RFs, are consistent with tropospheric delay models. We find that by using anisotropic data covariance information to weight dInSAR measurements, we can significantly improve both the precision and accuracy of geophysical parameter estimations. Furthermore, the improvement is dependent on how similar the deformation pattern is to the dominant structure of the anisotropic atmospheric signals. © 2009 IEEE.
Special matrices of mathematical physics stochastic, circulant and Bell matrices
Aldrovandi, R
2001-01-01
This book expounds three special kinds of matrices that are of physical interest, centering on physical examples. Stochastic matrices describe dynamical systems of many different types, involving (or not) phenomena like transience, dissipation, ergodicity, nonequilibrium, and hypersensitivity to initial conditions. The main characteristic is growth by agglomeration, as in glass formation. Circulants are the building blocks of elementary Fourier analysis and provide a natural gateway to quantum mechanics and noncommutative geometry. Bell polynomials offer closed expressions for many formulas co
Covariant field equations in supergravity
Energy Technology Data Exchange (ETDEWEB)
Vanhecke, Bram [KU Leuven, Institute for Theoretical Physics, Leuven (Belgium); Ghent University, Faculty of Physics, Gent (Belgium); Proeyen, Antoine van [KU Leuven, Institute for Theoretical Physics, Leuven (Belgium)
2017-12-15
Covariance is a useful property for handling supergravity theories. In this paper, we prove a covariance property of supergravity field equations: under reasonable conditions, field equations of supergravity are covariant modulo other field equations. We prove that for any supergravity there exist such covariant equations of motion, other than the regular equations of motion, that are equivalent to the latter. The relations that we find between field equations and their covariant form can be used to obtain multiplets of field equations. In practice, the covariant field equations are easily found by simply covariantizing the ordinary field equations. (copyright 2017 WILEY-VCH Verlag GmbH and Co. KGaA, Weinheim)
Covariant field equations in supergravity
International Nuclear Information System (INIS)
Vanhecke, Bram; Proeyen, Antoine van
2017-01-01
Covariance is a useful property for handling supergravity theories. In this paper, we prove a covariance property of supergravity field equations: under reasonable conditions, field equations of supergravity are covariant modulo other field equations. We prove that for any supergravity there exist such covariant equations of motion, other than the regular equations of motion, that are equivalent to the latter. The relations that we find between field equations and their covariant form can be used to obtain multiplets of field equations. In practice, the covariant field equations are easily found by simply covariantizing the ordinary field equations. (copyright 2017 WILEY-VCH Verlag GmbH and Co. KGaA, Weinheim)
Analysis of fMRI data using noise-diffusion network models: a new covariance-coding perspective.
Gilson, Matthieu
2018-04-01
Since the middle of the 1990s, studies of resting-state fMRI/BOLD data have explored the correlation patterns of activity across the whole brain, which is referred to as functional connectivity (FC). Among the many methods that have been developed to interpret FC, a recently proposed model-based approach describes the propagation of fluctuating BOLD activity within the recurrently connected brain network by inferring the effective connectivity (EC). In this model, EC quantifies the strengths of directional interactions between brain regions, viewed from the proxy of BOLD activity. In addition, the tuning procedure for the model provides estimates for the local variability (input variances) to explain how the observed FC is generated. Generalizing, the network dynamics can be studied in the context of an input-output mapping-determined by EC-for the second-order statistics of fluctuating nodal activities. The present paper focuses on the following detection paradigm: observing output covariances, how discriminative is the (estimated) network model with respect to various input covariance patterns? An application with the model fitted to experimental fMRI data-movie viewing versus resting state-illustrates that changes in local variability and changes in brain coordination go hand in hand.
Automatic physiological waveform processing for FMRI noise correction and analysis.
Directory of Open Access Journals (Sweden)
Daniel J Kelley
2008-03-01
Full Text Available Functional MRI resting state and connectivity studies of brain focus on neural fluctuations at low frequencies which share power with physiological fluctuations originating from lung and heart. Due to the lack of automated software to process physiological signals collected at high magnetic fields, a gap exists in the processing pathway between the acquisition of physiological data and its use in fMRI software for both physiological noise correction and functional analyses of brain activation and connectivity. To fill this gap, we developed an open source, physiological signal processing program, called PhysioNoise, in the python language. We tested its automated processing algorithms and dynamic signal visualization on resting monkey cardiac and respiratory waveforms. PhysioNoise consistently identifies physiological fluctuations for fMRI noise correction and also generates covariates for subsequent analyses of brain activation and connectivity.
A special covariance structure for random coefficient models with both between and within covariates
International Nuclear Information System (INIS)
Riedel, K.S.
1990-07-01
We review random coefficient (RC) models in linear regression and propose a bias correction to the maximum likelihood (ML) estimator. Asymmptotic expansion of the ML equations are given when the between individual variance is much larger or smaller than the variance from within individual fluctuations. The standard model assumes all but one covariate varies within each individual, (we denote the within covariates by vector χ 1 ). We consider random coefficient models where some of the covariates do not vary in any single individual (we denote the between covariates by vector χ 0 ). The regression coefficients, vector β k , can only be estimated in the subspace X k of X. Thus the number of individuals necessary to estimate vector β and the covariance matrix Δ of vector β increases significantly in the presence of more than one between covariate. When the number of individuals is sufficient to estimate vector β but not the entire matrix Δ , additional assumptions must be imposed on the structure of Δ. A simple reduced model is that the between component of vector β is fixed and only the within component varies randomly. This model fails because it is not invariant under linear coordinate transformations and it can significantly overestimate the variance of new observations. We propose a covariance structure for Δ without these difficulties by first projecting the within covariates onto the space perpendicular to be between covariates. (orig.)
The effects of railway noise on sleep medication intake: Results from the ALPNAP-study
Directory of Open Access Journals (Sweden)
P Lercher
2010-01-01
Full Text Available In the 1980s/90s, a number of socio-acoustic surveys and laboratory studies on railway noise effects have observed less reported disturbance/interference with sleep at the same exposure level compared with other modes of transportation. This lower grade of disturbance has received the label "railway bonus", was implemented in noise legislation in a number of European countries and was applied in planning and environmental impact assessments. However, majority of the studies investigating physiological outcomes did not find the bespoke difference. In a telephone survey (N=1643 we investigated the relationship between railway noise and sleep medication intake and the impact of railway noise events on motility parameters during night was assessed with contact-free high resolution actimetry devices. Multiple logistic regression analysis with cubic splines was applied to assess the probability of sleep medication use based on railway sound level and nine covariates. The non-linear exposure-response curve showed a statistically significant leveling off around 60 dB (A, Lden. Age, health status and trauma history were the most important covariates. The results were supported also by a similar analysis based on the indicator "night time noise annoyance". No railway bonus could be observed above 55 dB(A, Lden. In the actimetry study, the slope of rise of train noise events proved to be almost as important a predictor for motility reactions as was the maximum sound pressure level - an observation which confirms similar findings from laboratory experiments and field studies on aircraft noise and sleep disturbance. Legislation using a railway bonus will underestimate the noise impact by about 10 dB (A, Lden under the conditions comparable with those in the survey study. The choice of the noise calculation method may influence the threshold for guideline setting.
The effects of railway noise on sleep medication intake: results from the ALPNAP-study.
Lercher, P; Brink, M; Rudisser, J; Van Renterghem, T; Botteldooren, D; Baulac, M; Defrance, J
2010-01-01
In the 1980s/90s, a number of socio-acoustic surveys and laboratory studies on railway noise effects have observed less reported disturbance/interference with sleep at the same exposure level compared with other modes of transportation. This lower grade of disturbance has received the label "railway bonus", was implemented in noise legislation in a number of European countries and was applied in planning and environmental impact assessments. However, majority of the studies investigating physiological outcomes did not find the bespoke difference. In a telephone survey (N=1643) we investigated the relationship between railway noise and sleep medication intake and the impact of railway noise events on motility parameters during night was assessed with contact-free high resolution actimetry devices. Multiple logistic regression analysis with cubic splines was applied to assess the probability of sleep medication use based on railway sound level and nine covariates. The non-linear exposure-response curve showed a statistically significant leveling off around 60 dB (A), Lden. Age, health status and trauma history were the most important covariates. The results were supported also by a similar analysis based on the indicator "night time noise annoyance". No railway bonus could be observed above 55 dB(A), Lden. In the actimetry study, the slope of rise of train noise events proved to be almost as important a predictor for motility reactions as was the maximum sound pressure level - an observation which confirms similar findings from laboratory experiments and field studies on aircraft noise and sleep disturbance. Legislation using a railway bonus will underestimate the noise impact by about 10 dB (A), Lden under the conditions comparable with those in the survey study. The choice of the noise calculation method may influence the threshold for guideline setting.
Planck 2013 results. II. The Low Frequency Instrument data processing
DEFF Research Database (Denmark)
Aghanim, N.; Armitage-Caplan, C.; Arnaud, M.
2013-01-01
We describe the data processing pipeline of the Planck Low Frequency Instrument (LFI) data processing centre (DPC) to create and characterize full-sky maps based on the first 15.5 months of operations at 30, 44, and 70 GHz. In particular, we discuss the various steps involved in reducing the data......) is employed to combine radiometric data and pointing information into sky maps, minimizing the variance of correlated noise. Noise covariance matrices, required to compute statistical uncertainties on LFI and Planck products, are also produced. Main beams are estimated down to the approximate to-20 dB level...
Bergshoeff, E.; Pope, C.N.; Stelle, K.S.
1990-01-01
We discuss the notion of higher-spin covariance in w∞ gravity. We show how a recently proposed covariant w∞ gravity action can be obtained from non-chiral w∞ gravity by making field redefinitions that introduce new gauge-field components with corresponding new gauge transformations.
Energy Technology Data Exchange (ETDEWEB)
Wagner, C.
1996-12-31
In 1992, Wittum introduced the frequency filtering decompositions (FFD), which yield a fast method for the iterative solution of large systems of linear equations. Based on this method, the tangential frequency filtering decompositions (TFFD) have been developed. The TFFD allow the robust and efficient treatment of matrices with strongly varying coefficients. The existence and the convergence of the TFFD can be shown for symmetric and positive definite matrices. For a large class of matrices, it is possible to prove that the convergence rate of the TFFD and of the FFD is independent of the number of unknowns. For both methods, schemes for the construction of frequency filtering decompositions for unsymmetric matrices have been developed. Since, in contrast to Wittums`s FFD, the TFFD needs only one test vector, an adaptive test vector can be used. The TFFD with respect to the adaptive test vector can be combined with other iterative methods, e.g. multi-grid methods, in order to improve the robustness of these methods. The frequency filtering decompositions have been successfully applied to the problem of the decontamination of a heterogeneous porous medium by flushing.
New parameters in adaptive testing of ferromagnetic materials utilizing magnetic Barkhausen noise
International Nuclear Information System (INIS)
Pal’a, Jozef; Ušák, Elemír
2016-01-01
A new method of magnetic Barkhausen noise (MBN) measurement and optimization of the measured data processing with respect to non-destructive evaluation of ferromagnetic materials was tested. Using this method we tried to found, if it is possible to enhance sensitivity and stability of measurement results by replacing the traditional MBN parameter (root mean square) with some new parameter. In the tested method, a complex set of the MBN from minor hysteresis loops is measured. Afterward, the MBN data are collected into suitably designed matrices and optimal parameters of MBN with respect to maximum sensitivity to the evaluated variable are searched. The method was verified on plastically deformed steel samples. It was shown that the proposed measuring method and measured data processing bring an improvement of the sensitivity to the evaluated variable when comparing with measuring traditional MBN parameter. Moreover, we found a parameter of MBN, which is highly resistant to the changes of applied field amplitude and at the same time it is noticeably more sensitive to the evaluated variable. - Highlights: • We test an adaptive magnetic Barkhausen noise method. • The method utilizes measuring a complex set of Barkhausen noise signals. • We define new matrices of parameters for this method. • The pulse density is highly resistant to changes in applied field amplitude.
Analysis and Extension of the PCA Method, Estimating a Noise Curve from a Single Image
Directory of Open Access Journals (Sweden)
Miguel Colom
2016-12-01
Full Text Available In the article 'Image Noise Level Estimation by Principal Component Analysis', S. Pyatykh, J. Hesser, and L. Zheng propose a new method to estimate the variance of the noise in an image from the eigenvalues of the covariance matrix of the overlapping blocks of the noisy image. Instead of using all the patches of the noisy image, the authors propose an iterative strategy to adaptively choose the optimal set containing the patches with lowest variance. Although the method measures uniform Gaussian noise, it can be easily adapted to deal with signal-dependent noise, which is realistic with the Poisson noise model obtained by a CMOS or CCD device in a digital camera.
International Nuclear Information System (INIS)
Putter, Roland de; Wagner, Christian; Verde, Licia; Mena, Olga; Percival, Will J.
2012-01-01
Accurate power spectrum (or correlation function) covariance matrices are a crucial requirement for cosmological parameter estimation from large scale structure surveys. In order to minimize reliance on computationally expensive mock catalogs, it is important to have a solid analytic understanding of the different components that make up a covariance matrix. Considering the matter power spectrum covariance matrix, it has recently been found that there is a potentially dominant effect on mildly non-linear scales due to power in modes of size equal to and larger than the survey volume. This beat coupling effect has been derived analytically in perturbation theory and while it has been tested with simulations, some questions remain unanswered. Moreover, there is an additional effect of these large modes, which has so far not been included in analytic studies, namely the effect on the estimated average density which enters the power spectrum estimate. In this article, we work out analytic, perturbation theory based expressions including both the beat coupling and this local average effect and we show that while, when isolated, beat coupling indeed causes large excess covariance in agreement with the literature, in a realistic scenario this is compensated almost entirely by the local average effect, leaving only ∼ 10% of the excess. We test our analytic expressions by comparison to a suite of large N-body simulations, using both full simulation boxes and subboxes thereof to study cases without beat coupling, with beat coupling and with both beat coupling and the local average effect. For the variances, we find excellent agreement with the analytic expressions for k −1 at z = 0.5, while the correlation coefficients agree to beyond k = 0.4 hMpc −1 . As expected, the range of agreement increases towards higher redshift and decreases slightly towards z = 0. We finish by including the large-mode effects in a full covariance matrix description for arbitrary survey
Introduction to matrices and vectors
Schwartz, Jacob T
2001-01-01
In this concise undergraduate text, the first three chapters present the basics of matrices - in later chapters the author shows how to use vectors and matrices to solve systems of linear equations. 1961 edition.
Sensitivity of PPI analysis to differences in noise reduction strategies.
Barton, M; Marecek, R; Rektor, I; Filip, P; Janousova, E; Mikl, M
2015-09-30
In some fields of fMRI data analysis, using correct methods for dealing with noise is crucial for achieving meaningful results. This paper provides a quantitative assessment of the effects of different preprocessing and noise filtering strategies on psychophysiological interactions (PPI) methods for analyzing fMRI data where noise management has not yet been established. Both real and simulated fMRI data were used to assess these effects. Four regions of interest (ROIs) were chosen for the PPI analysis on the basis of their engagement during two tasks. PPI analysis was performed for 32 different preprocessing and analysis settings, which included data filtering with RETROICOR or no such filtering; different filtering of the ROI "seed" signal with a nuisance data-driven time series; and the involvement of these data-driven time series in the subsequent PPI GLM analysis. The extent of the statistically significant results was quantified at the group level using simple descriptive statistics. Simulated data were generated to assess statistical improvement of different filtering strategies. We observed that different approaches for dealing with noise in PPI analysis yield differing results in real data. In simulated data, we found RETROICOR, seed signal filtering and the addition of data-driven covariates to the PPI design matrix significantly improves results. We recommend the use of RETROICOR, and data-driven filtering of the whole data, or alternatively, seed signal filtering with data-driven signals and the addition of data-driven covariates to the PPI design matrix. Copyright © 2015 Elsevier B.V. All rights reserved.
Impact of noise and air pollution on pregnancy outcomes.
Gehring, Ulrike; Tamburic, Lillian; Sbihi, Hind; Davies, Hugh W; Brauer, Michael
2014-05-01
Motorized traffic is an important source of both air pollution and community noise. While there is growing evidence for an adverse effect of ambient air pollution on reproductive health, little is known about the association between traffic noise and pregnancy outcomes. We evaluated the impact of residential noise exposure on small size for gestational age, preterm birth, term birth weight, and low birth weight at term in a population-based cohort study, for which we previously reported associations between air pollution and pregnancy outcomes. We also evaluated potential confounding of air pollution effects by noise and vice versa. Linked administrative health data sets were used to identify 68,238 singleton births (1999-2002) in Vancouver, British Columbia, Canada, with complete covariate data (sex, ethnicity, parity, birth month and year, income, and education) and maternal residential history. We estimated exposure to noise with a deterministic model (CadnaA) and exposure to air pollution using temporally adjusted land-use regression models and inverse distance weighting of stationary monitors for the entire pregnancy. Noise exposure was negatively associated with term birth weight (mean difference = -19 [95% confidence interval = -23 to -15] g per 6 dB(A)). In joint air pollution-noise models, associations between noise and term birth weight remained largely unchanged, whereas associations decreased for all air pollutants. Traffic may affect birth weight through exposure to both air pollution and noise.
Zhang, Ying-Ying; Yang, Cai; Zhang, Ping
2017-08-01
In this paper, we present a novel bottom-up saliency detection algorithm from the perspective of covariance matrices on a Riemannian manifold. Each superpixel is described by a region covariance matrix on Riemannian Manifolds. We carry out a two-stage sparse coding scheme via Log-Euclidean kernels to extract salient objects efficiently. In the first stage, given background dictionary on image borders, sparse coding of each region covariance via Log-Euclidean kernels is performed. The reconstruction error on the background dictionary is regarded as the initial saliency of each superpixel. In the second stage, an improvement of the initial result is achieved by calculating reconstruction errors of the superpixels on foreground dictionary, which is extracted from the first stage saliency map. The sparse coding in the second stage is similar to the first stage, but is able to effectively highlight the salient objects uniformly from the background. Finally, three post-processing methods-highlight-inhibition function, context-based saliency weighting, and the graph cut-are adopted to further refine the saliency map. Experiments on four public benchmark datasets show that the proposed algorithm outperforms the state-of-the-art methods in terms of precision, recall and mean absolute error, and demonstrate the robustness and efficiency of the proposed method. Copyright © 2017 Elsevier Ltd. All rights reserved.
Evaluation and processing of covariance data
International Nuclear Information System (INIS)
Wagner, M.
1993-01-01
These proceedings of a specialists'meeting on evaluation and processing of covariance data is divided into 4 parts bearing on: part 1- Needs for evaluated covariance data (2 Papers), part 2- generation of covariance data (15 Papers), part 3- Processing of covariance files (2 Papers), part 4-Experience in the use of evaluated covariance data (2 Papers)
Covariance data processing code. ERRORJ
International Nuclear Information System (INIS)
Kosako, Kazuaki
2001-01-01
The covariance data processing code, ERRORJ, was developed to process the covariance data of JENDL-3.2. ERRORJ has the processing functions of covariance data for cross sections including resonance parameters, angular distribution and energy distribution. (author)
Pathological rate matrices: from primates to pathogens
Directory of Open Access Journals (Sweden)
Knight Rob
2008-12-01
Full Text Available Abstract Background Continuous-time Markov models allow flexible, parametrically succinct descriptions of sequence divergence. Non-reversible forms of these models are more biologically realistic but are challenging to develop. The instantaneous rate matrices defined for these models are typically transformed into substitution probability matrices using a matrix exponentiation algorithm that employs eigendecomposition, but this algorithm has characteristic vulnerabilities that lead to significant errors when a rate matrix possesses certain 'pathological' properties. Here we tested whether pathological rate matrices exist in nature, and consider the suitability of different algorithms to their computation. Results We used concatenated protein coding gene alignments from microbial genomes, primate genomes and independent intron alignments from primate genomes. The Taylor series expansion and eigendecomposition matrix exponentiation algorithms were compared to the less widely employed, but more robust, Padé with scaling and squaring algorithm for nucleotide, dinucleotide, codon and trinucleotide rate matrices. Pathological dinucleotide and trinucleotide matrices were evident in the microbial data set, affecting the eigendecomposition and Taylor algorithms respectively. Even using a conservative estimate of matrix error (occurrence of an invalid probability, both Taylor and eigendecomposition algorithms exhibited substantial error rates: ~100% of all exonic trinucleotide matrices were pathological to the Taylor algorithm while ~10% of codon positions 1 and 2 dinucleotide matrices and intronic trinucleotide matrices, and ~30% of codon matrices were pathological to eigendecomposition. The majority of Taylor algorithm errors derived from occurrence of multiple unobserved states. A small number of negative probabilities were detected from the Pad�� algorithm on trinucleotide matrices that were attributable to machine precision. Although the Pad
ORACLS: A system for linear-quadratic-Gaussian control law design
Armstrong, E. S.
1978-01-01
A modern control theory design package (ORACLS) for constructing controllers and optimal filters for systems modeled by linear time-invariant differential or difference equations is described. Numerical linear-algebra procedures are used to implement the linear-quadratic-Gaussian (LQG) methodology of modern control theory. Algorithms are included for computing eigensystems of real matrices, the relative stability of a matrix, factored forms for nonnegative definite matrices, the solutions and least squares approximations to the solutions of certain linear matrix algebraic equations, the controllability properties of a linear time-invariant system, and the steady state covariance matrix of an open-loop stable system forced by white noise. Subroutines are provided for solving both the continuous and discrete optimal linear regulator problems with noise free measurements and the sampled-data optimal linear regulator problem. For measurement noise, duality theory and the optimal regulator algorithms are used to solve the continuous and discrete Kalman-Bucy filter problems. Subroutines are also included which give control laws causing the output of a system to track the output of a prescribed model.
Zhu, Peijuan; Ding, Wei; Tong, Wei; Ghosal, Anima; Alton, Kevin; Chowdhury, Swapan
2009-06-01
A retention-time-shift-tolerant background subtraction and noise reduction algorithm (BgS-NoRA) is implemented using the statistical programming language R to remove non-drug-related ion signals from accurate mass liquid chromatography/mass spectrometry (LC/MS) data. The background-subtraction part of the algorithm is similar to a previously published procedure (Zhang H and Yang Y. J. Mass Spectrom. 2008, 43: 1181-1190). The noise reduction algorithm (NoRA) is an add-on feature to help further clean up the residual matrix ion noises after background subtraction. It functions by removing ion signals that are not consistent across many adjacent scans. The effectiveness of BgS-NoRA was examined in biological matrices by spiking blank plasma extract, bile and urine with diclofenac and ibuprofen that have been pre-metabolized by microsomal incubation. Efficient removal of background ions permitted the detection of drug-related ions in in vivo samples (plasma, bile, urine and feces) obtained from rats orally dosed with (14)C-loratadine with minimal interference. Results from these experiments demonstrate that BgS-NoRA is more effective in removing analyte-unrelated ions than background subtraction alone. NoRA is shown to be particularly effective in the early retention region for urine samples and middle retention region for bile samples, where the matrix ion signals still dominate the total ion chromatograms (TICs) after background subtraction. In most cases, the TICs after BgS-NoRA are in excellent qualitative correlation to the radiochromatograms. BgS-NoRA will be a very useful tool in metabolite detection and identification work, especially in first-in-human (FIH) studies and multiple dose toxicology studies where non-radio-labeled drugs are administered. Data from these types of studies are critical to meet the latest FDA guidance on Metabolite in Safety Testing (MIST). Copyright (c) 2009 John Wiley & Sons, Ltd.
Spectra of sparse random matrices
International Nuclear Information System (INIS)
Kuehn, Reimer
2008-01-01
We compute the spectral density for ensembles of sparse symmetric random matrices using replica. Our formulation of the replica-symmetric ansatz shares the symmetries of that suggested in a seminal paper by Rodgers and Bray (symmetry with respect to permutation of replica and rotation symmetry in the space of replica), but uses a different representation in terms of superpositions of Gaussians. It gives rise to a pair of integral equations which can be solved by a stochastic population-dynamics algorithm. Remarkably our representation allows us to identify pure-point contributions to the spectral density related to the existence of normalizable eigenstates. Our approach is not restricted to matrices defined on graphs with Poissonian degree distribution. Matrices defined on regular random graphs or on scale-free graphs, are easily handled. We also look at matrices with row constraints such as discrete graph Laplacians. Our approach naturally allows us to unfold the total density of states into contributions coming from vertices of different local coordinations and an example of such an unfolding is presented. Our results are well corroborated by numerical diagonalization studies of large finite random matrices
Dynamic visual noise interferes with storage in visual working memory.
Dean, Graham M; Dewhurst, Stephen A; Whittaker, Annalise
2008-01-01
Several studies have demonstrated that dynamic visual noise (DVN) does not interfere with memory for random matrices. This has led to suggestions that (a) visual working memory is distinct from imagery, and (b) visual working memory is not a gateway between sensory input and long-term storage. A comparison of the interference effects of DVN with memory for matrices and colored textures shows that DVN can interfere with visual working memory, probably at a level of visual detail not easily supported by long-term memory structures or the recoding of the visual pattern elements. The results support a gateway model of visuospatial working memory and raise questions about the most appropriate ways to measure and model the different levels of representation of information that can be held in visual working memory.
Improved Kalman Filter Method for Measurement Noise Reduction in Multi Sensor RFID Systems
Directory of Open Access Journals (Sweden)
Min Chul Kim
2011-10-01
Full Text Available Recently, the range of available Radio Frequency Identification (RFID tags has been widened to include smart RFID tags which can monitor their varying surroundings. One of the most important factors for better performance of smart RFID system is accurate measurement from various sensors. In the multi-sensing environment, some noisy signals are obtained because of the changing surroundings. We propose in this paper an improved Kalman filter method to reduce noise and obtain correct data. Performance of Kalman filter is determined by a measurement and system noise covariance which are usually called the R and Q variables in the Kalman filter algorithm. Choosing a correct R and Q variable is one of the most important design factors for better performance of the Kalman filter. For this reason, we proposed an improved Kalman filter to advance an ability of noise reduction of the Kalman filter. The measurement noise covariance was only considered because the system architecture is simple and can be adjusted by the neural network. With this method, more accurate data can be obtained with smart RFID tags. In a simulation the proposed improved Kalman filter has 40.1%, 60.4% and 87.5% less Mean Squared Error (MSE than the conventional Kalman filter method for a temperature sensor, humidity sensor and oxygen sensor, respectively. The performance of the proposed method was also verified with some experiments.
Improved Kalman filter method for measurement noise reduction in multi sensor RFID systems.
Eom, Ki Hwan; Lee, Seung Joon; Kyung, Yeo Sun; Lee, Chang Won; Kim, Min Chul; Jung, Kyung Kwon
2011-01-01
Recently, the range of available radio frequency identification (RFID) tags has been widened to include smart RFID tags which can monitor their varying surroundings. One of the most important factors for better performance of smart RFID system is accurate measurement from various sensors. In the multi-sensing environment, some noisy signals are obtained because of the changing surroundings. We propose in this paper an improved Kalman filter method to reduce noise and obtain correct data. Performance of Kalman filter is determined by a measurement and system noise covariance which are usually called the R and Q variables in the Kalman filter algorithm. Choosing a correct R and Q variable is one of the most important design factors for better performance of the Kalman filter. For this reason, we proposed an improved Kalman filter to advance an ability of noise reduction of the Kalman filter. The measurement noise covariance was only considered because the system architecture is simple and can be adjusted by the neural network. With this method, more accurate data can be obtained with smart RFID tags. In a simulation the proposed improved Kalman filter has 40.1%, 60.4% and 87.5% less mean squared error (MSE) than the conventional Kalman filter method for a temperature sensor, humidity sensor and oxygen sensor, respectively. The performance of the proposed method was also verified with some experiments.
Hyakutake, Hiroto; Kawasaki, Hidefumi
2004-01-01
We consider the problem of constructing a fixed-size confidence region of the difference of two multinormal means when the covariance matrices have intraclass correlation structure. When the covariance matrices are known, we derive an optimal allocation. A two-stage procedure is given for the problem with unknown covariance matrices.
Xu, Shaoping; Zeng, Xiaoxia; Jiang, Yinnan; Tang, Yiling
2018-01-01
We proposed a noniterative principal component analysis (PCA)-based noise level estimation (NLE) algorithm that addresses the problem of estimating the noise level with a two-step scheme. First, we randomly extracted a number of raw patches from a given noisy image and took the smallest eigenvalue of the covariance matrix of the raw patches as the preliminary estimation of the noise level. Next, the final estimation was directly obtained with a nonlinear mapping (rectification) function that was trained on some representative noisy images corrupted with different known noise levels. Compared with the state-of-art NLE algorithms, the experiment results show that the proposed NLE algorithm can reliably infer the noise level and has robust performance over a wide range of image contents and noise levels, showing a good compromise between speed and accuracy in general.
Pozsgay, Victor; Hirsch, Flavien; Branciard, Cyril; Brunner, Nicolas
2017-12-01
We introduce Bell inequalities based on covariance, one of the most common measures of correlation. Explicit examples are discussed, and violations in quantum theory are demonstrated. A crucial feature of these covariance Bell inequalities is their nonlinearity; this has nontrivial consequences for the derivation of their local bound, which is not reached by deterministic local correlations. For our simplest inequality, we derive analytically tight bounds for both local and quantum correlations. An interesting application of covariance Bell inequalities is that they can act as "shared randomness witnesses": specifically, the value of the Bell expression gives device-independent lower bounds on both the dimension and the entropy of the shared random variable in a local model.
Distance covariance for stochastic processes
DEFF Research Database (Denmark)
Matsui, Muneya; Mikosch, Thomas Valentin; Samorodnitsky, Gennady
2017-01-01
The distance covariance of two random vectors is a measure of their dependence. The empirical distance covariance and correlation can be used as statistical tools for testing whether two random vectors are independent. We propose an analog of the distance covariance for two stochastic processes...
International Nuclear Information System (INIS)
Delakis, Ioannis; Hammad, Omer; Kitney, Richard I
2007-01-01
Wavelet-based de-noising has been shown to improve image signal-to-noise ratio in magnetic resonance imaging (MRI) while maintaining spatial resolution. Wavelet-based de-noising techniques typically implemented in MRI require that noise displays uniform spatial distribution. However, images acquired with parallel MRI have spatially varying noise levels. In this work, a new algorithm for filtering images with parallel MRI is presented. The proposed algorithm extracts the edges from the original image and then generates a noise map from the wavelet coefficients at finer scales. The noise map is zeroed at locations where edges have been detected and directional analysis is also used to calculate noise in regions of low-contrast edges that may not have been detected. The new methodology was applied on phantom and brain images and compared with other applicable de-noising techniques. The performance of the proposed algorithm was shown to be comparable with other techniques in central areas of the images, where noise levels are high. In addition, finer details and edges were maintained in peripheral areas, where noise levels are low. The proposed methodology is fully automated and can be applied on final reconstructed images without requiring sensitivity profiles or noise matrices of the receiver coils, therefore making it suitable for implementation in a clinical MRI setting
Covariance Manipulation for Conjunction Assessment
Hejduk, M. D.
2016-01-01
The manipulation of space object covariances to try to provide additional or improved information to conjunction risk assessment is not an uncommon practice. Types of manipulation include fabricating a covariance when it is missing or unreliable to force the probability of collision (Pc) to a maximum value ('PcMax'), scaling a covariance to try to improve its realism or see the effect of covariance volatility on the calculated Pc, and constructing the equivalent of an epoch covariance at a convenient future point in the event ('covariance forecasting'). In bringing these methods to bear for Conjunction Assessment (CA) operations, however, some do not remain fully consistent with best practices for conducting risk management, some seem to be of relatively low utility, and some require additional information before they can contribute fully to risk analysis. This study describes some basic principles of modern risk management (following the Kaplan construct) and then examines the PcMax and covariance forecasting paradigms for alignment with these principles; it then further examines the expected utility of these methods in the modern CA framework. Both paradigms are found to be not without utility, but only in situations that are somewhat carefully circumscribed.
Characterizing protein conformations by correlation analysis of coarse-grained contact matrices
Lindsay, Richard J.; Siess, Jan; Lohry, David P.; McGee, Trevor S.; Ritchie, Jordan S.; Johnson, Quentin R.; Shen, Tongye
2018-01-01
We have developed a method to capture the essential conformational dynamics of folded biopolymers using statistical analysis of coarse-grained segment-segment contacts. Previously, the residue-residue contact analysis of simulation trajectories was successfully applied to the detection of conformational switching motions in biomolecular complexes. However, the application to large protein systems (larger than 1000 amino acid residues) is challenging using the description of residue contacts. Also, the residue-based method cannot be used to compare proteins with different sequences. To expand the scope of the method, we have tested several coarse-graining schemes that group a collection of consecutive residues into a segment. The definition of these segments may be derived from structural and sequence information, while the interaction strength of the coarse-grained segment-segment contacts is a function of the residue-residue contacts. We then perform covariance calculations on these coarse-grained contact matrices. We monitored how well the principal components of the contact matrices is preserved using various rendering functions. The new method was demonstrated to assist the reduction of the degrees of freedom for describing the conformation space, and it potentially allows for the analysis of a system that is approximately tenfold larger compared with the corresponding residue contact-based method. This method can also render a family of similar proteins into the same conformational space, and thus can be used to compare the structures of proteins with different sequences.
Chemiluminescence in cryogenic matrices
Lotnik, S. V.; Kazakov, Valeri P.
1989-04-01
The literature data on chemiluminescence (CL) in cryogenic matrices have been classified and correlated for the first time. The role of studies on phosphorescence and CL at low temperatures in the development of cryochemistry is shown. The features of low-temperature CL in matrices of nitrogen and inert gases (fine structure of spectra, matrix effects) and the data on the mobility and reactivity of atoms and radicals at very low temperatures are examined. The trends in the development of studies on CL in cryogenic matrices, such as the search for systems involving polyatomic molecules and extending the forms of CL reactions, are followed. The reactions of active nitrogen with hydrocarbons that are accompanied by light emission and CL in the oxidation of carbenes at T >= 77 K are examined. The bibliography includes 112 references.
INFLUENCE OF STOCHASTIC NOISE STATISTICS ON KALMAN FILTER PERFORMANCE BASED ON VIDEO TARGET TRACKING
Institute of Scientific and Technical Information of China (English)
Chen Ken; Napolitano; Zhang Yun; Li Dong
2010-01-01
The system stochastic noises involved in Kalman filtering are preconditioned on being ideally white and Gaussian distributed. In this research,efforts are exerted on exploring the influence of the noise statistics on Kalman filtering from the perspective of video target tracking quality. The correlation of tracking precision to both the process and measurement noise covariance is investigated; the signal-to-noise power density ratio is defined; the contribution of predicted states and measured outputs to Kalman filter behavior is discussed; the tracking precision relative sensitivity is derived and applied in this study case. The findings are expected to pave the way for future study on how the actual noise statistics deviating from the assumed ones impacts on the Kalman filter optimality and degradation in the application of video tracking.
Skew-adjacency matrices of graphs
Cavers, M.; Cioaba, S.M.; Fallat, S.; Gregory, D.A.; Haemers, W.H.; Kirkland, S.J.; McDonald, J.J.; Tsatsomeros, M.
2012-01-01
The spectra of the skew-adjacency matrices of a graph are considered as a possible way to distinguish adjacency cospectral graphs. This leads to the following topics: graphs whose skew-adjacency matrices are all cospectral; relations between the matchings polynomial of a graph and the characteristic
The invariant theory of matrices
Concini, Corrado De
2017-01-01
This book gives a unified, complete, and self-contained exposition of the main algebraic theorems of invariant theory for matrices in a characteristic free approach. More precisely, it contains the description of polynomial functions in several variables on the set of m\\times m matrices with coefficients in an infinite field or even the ring of integers, invariant under simultaneous conjugation. Following Hermann Weyl's classical approach, the ring of invariants is described by formulating and proving the first fundamental theorem that describes a set of generators in the ring of invariants, and the second fundamental theorem that describes relations between these generators. The authors study both the case of matrices over a field of characteristic 0 and the case of matrices over a field of positive characteristic. While the case of characteristic 0 can be treated following a classical approach, the case of positive characteristic (developed by Donkin and Zubkov) is much harder. A presentation of this case...
Novel Diagonal Reloading Based Direction of Arrival Estimation in Unknown Non-Uniform Noise
Directory of Open Access Journals (Sweden)
Hao Zhou
2018-01-01
Full Text Available Nested array can expand the degrees of freedom (DOF from difference coarray perspective, but suffering from the performance degradation of direction of arrival (DOA estimation in unknown non-uniform noise. In this paper, a novel diagonal reloading (DR based DOA estimation algorithm is proposed using a recently developed nested MIMO array. The elements in the main diagonal of the sample covariance matrix are eliminated; next the smallest MN-K eigenvalues of the revised matrix are obtained and averaged to estimate the sum value of the signal power. Further the estimated sum value is filled into the main diagonal of the revised matrix for estimating the signal covariance matrix. In this case, the negative effect of noise is eliminated without losing the useful information of the signal matrix. Besides, the degrees of freedom are expanded obviously, resulting in the performance improvement. Several simulations are conducted to demonstrate the effectiveness of the proposed algorithm.
Exact Inverse Matrices of Fermat and Mersenne Circulant Matrix
Directory of Open Access Journals (Sweden)
Yanpeng Zheng
2015-01-01
Full Text Available The well known circulant matrices are applied to solve networked systems. In this paper, circulant and left circulant matrices with the Fermat and Mersenne numbers are considered. The nonsingularity of these special matrices is discussed. Meanwhile, the exact determinants and inverse matrices of these special matrices are presented.
Enhancing Understanding of Transformation Matrices
Dick, Jonathan; Childrey, Maria
2012-01-01
With the Common Core State Standards' emphasis on transformations, teachers need a variety of approaches to increase student understanding. Teaching matrix transformations by focusing on row vectors gives students tools to create matrices to perform transformations. This empowerment opens many doors: Students are able to create the matrices for…
Group inverses of M-matrices and their applications
Kirkland, Stephen J
2013-01-01
Group inverses for singular M-matrices are useful tools not only in matrix analysis, but also in the analysis of stochastic processes, graph theory, electrical networks, and demographic models. Group Inverses of M-Matrices and Their Applications highlights the importance and utility of the group inverses of M-matrices in several application areas. After introducing sample problems associated with Leslie matrices and stochastic matrices, the authors develop the basic algebraic and spectral properties of the group inverse of a general matrix. They then derive formulas for derivatives of matrix f
International Nuclear Information System (INIS)
Takada, Masahiro; Bridle, Sarah
2007-01-01
Several dark energy experiments are available from a single large-area imaging survey and may be combined to improve cosmological parameter constraints and/or test inherent systematics. Two promising experiments are cosmic shear power spectra and counts of galaxy clusters. However, the two experiments probe the same cosmic mass density field in large-scale structure, therefore the combination may be less powerful than first thought. We investigate the cross-covariance between the cosmic shear power spectra and the cluster counts based on the halo model approach, where the cross-covariance arises from the three-point correlations of the underlying mass density field. Fully taking into account the cross-covariance, as well as non-Gaussian errors on the lensing power spectrum covariance, we find a significant cross-correlation between the lensing power spectrum signals at multipoles l∼10 3 and the cluster counts containing halos with masses M∼>10 14 M o-dot . Including the cross-covariance for the combined measurement degrades and in some cases improves the total signal-to-noise (S/N) ratios up to ∼±20% relative to when the two are independent. For cosmological parameter determination, the cross-covariance has a smaller effect as a result of working in a multi-dimensional parameter space, implying that the two observables can be considered independent to a good approximation. We also discuss the fact that cluster count experiments using lensing-selected mass peaks could be more complementary to cosmic shear tomography than mass-selected cluster counts of the corresponding mass threshold. Using lensing selected clusters with a realistic usable detection threshold ((S/N) cluster ∼6 for a ground-based survey), the uncertainty on each dark energy parameter may be roughly halved by the combined experiments, relative to using the power spectra alone
Poincare covariance and κ-Minkowski spacetime
International Nuclear Information System (INIS)
Dabrowski, Ludwik; Piacitelli, Gherardo
2011-01-01
A fully Poincare covariant model is constructed as an extension of the κ-Minkowski spacetime. Covariance is implemented by a unitary representation of the Poincare group, and thus complies with the original Wigner approach to quantum symmetries. This provides yet another example (besides the DFR model), where Poincare covariance is realised a la Wigner in the presence of two characteristic dimensionful parameters: the light speed and the Planck length. In other words, a Doubly Special Relativity (DSR) framework may well be realised without deforming the meaning of 'Poincare covariance'. -- Highlights: → We construct a 4d model of noncommuting coordinates (quantum spacetime). → The coordinates are fully covariant under the undeformed Poincare group. → Covariance a la Wigner holds in presence of two dimensionful parameters. → Hence we are not forced to deform covariance (e.g. as quantum groups). → The underlying κ-Minkowski model is unphysical; covariantisation does not cure this.
DEFF Research Database (Denmark)
Hounyo, Ulrich
to a gneral class of estimators of integrated covolatility. We then show the first-order asymptotic validity of this method in the multivariate context with a potential presence of jumps, dependent microsturcture noise, irregularly spaced and non-synchronous data. Due to our focus on non...... covariance estimator. As an application of our results, we also consider the bootstrap for regression coefficients. We show that the wild blocks of bootstrap, appropriately centered, is able to mimic both the dependence and heterogeneity of the scores, thus justifying the construction of bootstrap percentile...... intervals as well as variance estimates in this context. This contrasts with the traditional pairs bootstrap which is not able to mimic the score heterogeneity even in the simple case where no microsturcture noise is present. Our Monte Carlo simulations show that the wild blocks of blocks bootstrap improves...
Phenomenological mass matrices with a democratic warp
International Nuclear Information System (INIS)
Kleppe, A.
2018-01-01
Taking into account all available data on the mass sector, we obtain unitary rotation matrices that diagonalize the quark matrices by using a specific parametrization of the Cabibbo-Kobayashi-Maskawa mixing matrix. In this way, we find mass matrices for the up- and down-quark sectors of a specific, symmetric form, with traces of a democratic texture.
Modeling Covariance Breakdowns in Multivariate GARCH
Jin, Xin; Maheu, John M
2014-01-01
This paper proposes a flexible way of modeling dynamic heterogeneous covariance breakdowns in multivariate GARCH (MGARCH) models. During periods of normal market activity, volatility dynamics are governed by an MGARCH specification. A covariance breakdown is any significant temporary deviation of the conditional covariance matrix from its implied MGARCH dynamics. This is captured through a flexible stochastic component that allows for changes in the conditional variances, covariances and impl...
Ole E. Barndorff-Nielsen; Neil Shephard
2002-01-01
This paper analyses multivariate high frequency financial data using realised covariation. We provide a new asymptotic distribution theory for standard methods such as regression, correlation analysis and covariance. It will be based on a fixed interval of time (e.g. a day or week), allowing the number of high frequency returns during this period to go to infinity. Our analysis allows us to study how high frequency correlations, regressions and covariances change through time. In particular w...
Diagonalization of the mass matrices
International Nuclear Information System (INIS)
Rhee, S.S.
1984-01-01
It is possible to make 20 types of 3x3 mass matrices which are hermitian. We have obtained unitary matrices which could diagonalize each mass matrix. Since the three elements of mass matrix can be expressed in terms of the three eigenvalues, msub(i), we can also express the unitary matrix in terms of msub(i). (Author)
Wu, Yuanfeng; Gao, Lianru; Zhang, Bing; Zhao, Haina; Li, Jun
2014-01-01
We present a parallel implementation of the optimized maximum noise fraction (G-OMNF) transform algorithm for feature extraction of hyperspectral images on commodity graphics processing units (GPUs). The proposed approach explored the algorithm data-level concurrency and optimized the computing flow. We first defined a three-dimensional grid, in which each thread calculates a sub-block data to easily facilitate the spatial and spectral neighborhood data searches in noise estimation, which is one of the most important steps involved in OMNF. Then, we optimized the processing flow and computed the noise covariance matrix before computing the image covariance matrix to reduce the original hyperspectral image data transmission. These optimization strategies can greatly improve the computing efficiency and can be applied to other feature extraction algorithms. The proposed parallel feature extraction algorithm was implemented on an Nvidia Tesla GPU using the compute unified device architecture and basic linear algebra subroutines library. Through the experiments on several real hyperspectral images, our GPU parallel implementation provides a significant speedup of the algorithm compared with the CPU implementation, especially for highly data parallelizable and arithmetically intensive algorithm parts, such as noise estimation. In order to further evaluate the effectiveness of G-OMNF, we used two different applications: spectral unmixing and classification for evaluation. Considering the sensor scanning rate and the data acquisition time, the proposed parallel implementation met the on-board real-time feature extraction.
ISSUES IN NEUTRON CROSS SECTION COVARIANCES
Energy Technology Data Exchange (ETDEWEB)
Mattoon, C.M.; Oblozinsky,P.
2010-04-30
We review neutron cross section covariances in both the resonance and fast neutron regions with the goal to identify existing issues in evaluation methods and their impact on covariances. We also outline ideas for suitable covariance quality assurance procedures.We show that the topic of covariance data remains controversial, the evaluation methodologies are not fully established and covariances produced by different approaches have unacceptable spread. The main controversy is in very low uncertainties generated by rigorous evaluation methods and much larger uncertainties based on simple estimates from experimental data. Since the evaluators tend to trust the former, while the users tend to trust the latter, this controversy has considerable practical implications. Dedicated effort is needed to arrive at covariance evaluation methods that would resolve this issue and produce results accepted internationally both by evaluators and users.
The construction of factorized S-matrices
International Nuclear Information System (INIS)
Chudnovsky, D.V.
1981-01-01
We study the relationships between factorized S-matrices given as representations of the Zamolodchikov algebra and exactly solvable models constructed using the Baxter method. Several new examples of symmetric and non-symmetric factorized S-matrices are proposed. (orig.)
Variational Bayesian labeled multi-Bernoulli filter with unknown sensor noise statistics
Directory of Open Access Journals (Sweden)
Qiu Hao
2016-10-01
Full Text Available It is difficult to build accurate model for measurement noise covariance in complex backgrounds. For the scenarios of unknown sensor noise variances, an adaptive multi-target tracking algorithm based on labeled random finite set and variational Bayesian (VB approximation is proposed. The variational approximation technique is introduced to the labeled multi-Bernoulli (LMB filter to jointly estimate the states of targets and sensor noise variances. Simulation results show that the proposed method can give unbiased estimation of cardinality and has better performance than the VB probability hypothesis density (VB-PHD filter and the VB cardinality balanced multi-target multi-Bernoulli (VB-CBMeMBer filter in harsh situations. The simulations also confirm the robustness of the proposed method against the time-varying noise variances. The computational complexity of proposed method is higher than the VB-PHD and VB-CBMeMBer in extreme cases, while the mean execution times of the three methods are close when targets are well separated.
Large-region acoustic source mapping using a movable array and sparse covariance fitting.
Zhao, Shengkui; Tuna, Cagdas; Nguyen, Thi Ngoc Tho; Jones, Douglas L
2017-01-01
Large-region acoustic source mapping is important for city-scale noise monitoring. Approaches using a single-position measurement scheme to scan large regions using small arrays cannot provide clean acoustic source maps, while deploying large arrays spanning the entire region of interest is prohibitively expensive. A multiple-position measurement scheme is applied to scan large regions at multiple spatial positions using a movable array of small size. Based on the multiple-position measurement scheme, a sparse-constrained multiple-position vectorized covariance matrix fitting approach is presented. In the proposed approach, the overall sample covariance matrix of the incoherent virtual array is first estimated using the multiple-position array data and then vectorized using the Khatri-Rao (KR) product. A linear model is then constructed for fitting the vectorized covariance matrix and a sparse-constrained reconstruction algorithm is proposed for recovering source powers from the model. The user parameter settings are discussed. The proposed approach is tested on a 30 m × 40 m region and a 60 m × 40 m region using simulated and measured data. Much cleaner acoustic source maps and lower sound pressure level errors are obtained compared to the beamforming approaches and the previous sparse approach [Zhao, Tuna, Nguyen, and Jones, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP) (2016)].
Matrices in Engineering Problems
Tobias, Marvin
2011-01-01
This book is intended as an undergraduate text introducing matrix methods as they relate to engineering problems. It begins with the fundamentals of mathematics of matrices and determinants. Matrix inversion is discussed, with an introduction of the well known reduction methods. Equation sets are viewed as vector transformations, and the conditions of their solvability are explored. Orthogonal matrices are introduced with examples showing application to many problems requiring three dimensional thinking. The angular velocity matrix is shown to emerge from the differentiation of the 3-D orthogo
Covariant diagrams for one-loop matching
Energy Technology Data Exchange (ETDEWEB)
Zhang, Zhengkang [Michigan Center for Theoretical Physics (MCTP), University of Michigan,450 Church Street, Ann Arbor, MI 48109 (United States); Deutsches Elektronen-Synchrotron (DESY),Notkestraße 85, 22607 Hamburg (Germany)
2017-05-30
We present a diagrammatic formulation of recently-revived covariant functional approaches to one-loop matching from an ultraviolet (UV) theory to a low-energy effective field theory. Various terms following from a covariant derivative expansion (CDE) are represented by diagrams which, unlike conventional Feynman diagrams, involve gauge-covariant quantities and are thus dubbed “covariant diagrams.” The use of covariant diagrams helps organize and simplify one-loop matching calculations, which we illustrate with examples. Of particular interest is the derivation of UV model-independent universal results, which reduce matching calculations of specific UV models to applications of master formulas. We show how such derivation can be done in a more concise manner than the previous literature, and discuss how additional structures that are not directly captured by existing universal results, including mixed heavy-light loops, open covariant derivatives, and mixed statistics, can be easily accounted for.
Covariant diagrams for one-loop matching
International Nuclear Information System (INIS)
Zhang, Zhengkang
2017-01-01
We present a diagrammatic formulation of recently-revived covariant functional approaches to one-loop matching from an ultraviolet (UV) theory to a low-energy effective field theory. Various terms following from a covariant derivative expansion (CDE) are represented by diagrams which, unlike conventional Feynman diagrams, involve gauge-covariant quantities and are thus dubbed “covariant diagrams.” The use of covariant diagrams helps organize and simplify one-loop matching calculations, which we illustrate with examples. Of particular interest is the derivation of UV model-independent universal results, which reduce matching calculations of specific UV models to applications of master formulas. We show how such derivation can be done in a more concise manner than the previous literature, and discuss how additional structures that are not directly captured by existing universal results, including mixed heavy-light loops, open covariant derivatives, and mixed statistics, can be easily accounted for.
A Brief Historical Introduction to Matrices and Their Applications
Debnath, L.
2014-01-01
This paper deals with the ancient origin of matrices, and the system of linear equations. Included are algebraic properties of matrices, determinants, linear transformations, and Cramer's Rule for solving the system of algebraic equations. Special attention is given to some special matrices, including matrices in graph theory and electrical…
Robust adaptive multichannel SAR processing based on covariance matrix reconstruction
Tan, Zhen-ya; He, Feng
2018-04-01
With the combination of digital beamforming (DBF) processing, multichannel synthetic aperture radar(SAR) systems in azimuth promise well in high-resolution and wide-swath imaging, whereas conventional processing methods don't take the nonuniformity of scattering coefficient into consideration. This paper brings up a robust adaptive Multichannel SAR processing method which utilizes the Capon spatial spectrum estimator to obtain the spatial spectrum distribution over all ambiguous directions first, and then the interference-plus-noise covariance Matrix is reconstructed based on definition to acquire the Multichannel SAR processing filter. The performance of processing under nonuniform scattering coefficient is promoted by this novel method and it is robust again array errors. The experiments with real measured data demonstrate the effectiveness and robustness of the proposed method.
Fast Computing for Distance Covariance
Huo, Xiaoming; Szekely, Gabor J.
2014-01-01
Distance covariance and distance correlation have been widely adopted in measuring dependence of a pair of random variables or random vectors. If the computation of distance covariance and distance correlation is implemented directly accordingly to its definition then its computational complexity is O($n^2$) which is a disadvantage compared to other faster methods. In this paper we show that the computation of distance covariance and distance correlation of real valued random variables can be...
Mitigating Observation Perturbation Sampling Errors in the Stochastic EnKF
Hoteit, Ibrahim
2015-03-17
The stochastic ensemble Kalman filter (EnKF) updates its ensemble members with observations perturbed with noise sampled from the distribution of the observational errors. This was shown to introduce noise into the system and may become pronounced when the ensemble size is smaller than the rank of the observational error covariance, which is often the case in real oceanic and atmospheric data assimilation applications. This work introduces an efficient serial scheme to mitigate the impact of observations’ perturbations sampling in the analysis step of the EnKF, which should provide more accurate ensemble estimates of the analysis error covariance matrices. The new scheme is simple to implement within the serial EnKF algorithm, requiring only the approximation of the EnKF sample forecast error covariance matrix by a matrix with one rank less. The new EnKF scheme is implemented and tested with the Lorenz-96 model. Results from numerical experiments are conducted to compare its performance with the EnKF and two standard deterministic EnKFs. This study shows that the new scheme enhances the behavior of the EnKF and may lead to better performance than the deterministic EnKFs even when implemented with relatively small ensembles.
Mitigating Observation Perturbation Sampling Errors in the Stochastic EnKF
Hoteit, Ibrahim; Pham, D.-T.; El Gharamti, Mohamad; Luo, X.
2015-01-01
The stochastic ensemble Kalman filter (EnKF) updates its ensemble members with observations perturbed with noise sampled from the distribution of the observational errors. This was shown to introduce noise into the system and may become pronounced when the ensemble size is smaller than the rank of the observational error covariance, which is often the case in real oceanic and atmospheric data assimilation applications. This work introduces an efficient serial scheme to mitigate the impact of observations’ perturbations sampling in the analysis step of the EnKF, which should provide more accurate ensemble estimates of the analysis error covariance matrices. The new scheme is simple to implement within the serial EnKF algorithm, requiring only the approximation of the EnKF sample forecast error covariance matrix by a matrix with one rank less. The new EnKF scheme is implemented and tested with the Lorenz-96 model. Results from numerical experiments are conducted to compare its performance with the EnKF and two standard deterministic EnKFs. This study shows that the new scheme enhances the behavior of the EnKF and may lead to better performance than the deterministic EnKFs even when implemented with relatively small ensembles.
Hypercyclic Abelian Semigroups of Matrices on Cn
International Nuclear Information System (INIS)
Ayadi, Adlene; Marzougui, Habib
2010-07-01
We give a complete characterization of existence of dense orbit for any abelian semigroup of matrices on C n . For finitely generated semigroups, this characterization is explicit and is used to determine the minimal number of matrices in normal form over C which forms a hypercyclic abelian semigroup on C n . In particular, we show that no abelian semigroup generated by n matrices on C n can be hypercyclic. (author)
Generalized Perron--Frobenius Theorem for Nonsquare Matrices
Avin, Chen; Borokhovich, Michael; Haddad, Yoram; Kantor, Erez; Lotker, Zvi; Parter, Merav; Peleg, David
2013-01-01
The celebrated Perron--Frobenius (PF) theorem is stated for irreducible nonnegative square matrices, and provides a simple characterization of their eigenvectors and eigenvalues. The importance of this theorem stems from the fact that eigenvalue problems on such matrices arise in many fields of science and engineering, including dynamical systems theory, economics, statistics and optimization. However, many real-life scenarios give rise to nonsquare matrices. A natural question is whether the...
General Galilei Covariant Gaussian Maps
Gasbarri, Giulio; Toroš, Marko; Bassi, Angelo
2017-09-01
We characterize general non-Markovian Gaussian maps which are covariant under Galilean transformations. In particular, we consider translational and Galilean covariant maps and show that they reduce to the known Holevo result in the Markovian limit. We apply the results to discuss measures of macroscopicity based on classicalization maps, specifically addressing dissipation, Galilean covariance and non-Markovianity. We further suggest a possible generalization of the macroscopicity measure defined by Nimmrichter and Hornberger [Phys. Rev. Lett. 110, 16 (2013)].
Krylov, Piotr
2017-01-01
This monograph is a comprehensive account of formal matrices, examining homological properties of modules over formal matrix rings and summarising the interplay between Morita contexts and K theory. While various special types of formal matrix rings have been studied for a long time from several points of view and appear in various textbooks, for instance to examine equivalences of module categories and to illustrate rings with one-sided non-symmetric properties, this particular class of rings has, so far, not been treated systematically. Exploring formal matrix rings of order 2 and introducing the notion of the determinant of a formal matrix over a commutative ring, this monograph further covers the Grothendieck and Whitehead groups of rings. Graduate students and researchers interested in ring theory, module theory and operator algebras will find this book particularly valuable. Containing numerous examples, Formal Matrices is a largely self-contained and accessible introduction to the topic, assuming a sol...
Competing risks and time-dependent covariates
DEFF Research Database (Denmark)
Cortese, Giuliana; Andersen, Per K
2010-01-01
Time-dependent covariates are frequently encountered in regression analysis for event history data and competing risks. They are often essential predictors, which cannot be substituted by time-fixed covariates. This study briefly recalls the different types of time-dependent covariates......, as classified by Kalbfleisch and Prentice [The Statistical Analysis of Failure Time Data, Wiley, New York, 2002] with the intent of clarifying their role and emphasizing the limitations in standard survival models and in the competing risks setting. If random (internal) time-dependent covariates...
Activities of covariance utilization working group
International Nuclear Information System (INIS)
Tsujimoto, Kazufumi
2013-01-01
During the past decade, there has been a interest in the calculational uncertainties induced by nuclear data uncertainties in the neutronics design of advanced nuclear system. The covariance nuclear data is absolutely essential for the uncertainty analysis. In the latest version of JENDL, JENDL-4.0, the covariance data for many nuclides, especially actinide nuclides, was substantialy enhanced. The growing interest in the uncertainty analysis and the covariance data has led to the organisation of the working group for covariance utilization under the JENDL committee. (author)
THE ALGORITHM AND PROGRAM OF M-MATRICES SEARCH AND STUDY
Directory of Open Access Journals (Sweden)
Y. N. Balonin
2013-05-01
Full Text Available The algorithm and software for search and study of orthogonal bases matrices – minimax matrices (M-matrix are considered. The algorithm scheme is shown, comments on calculation blocks are given, and interface of the MMatrix software system developed with participation of the authors is explained. The results of the universal algorithm work are presented as Hadamard matrices, Belevitch matrices (C-matrices, conference matrices and matrices of even and odd orders complementary and closely related to those ones by their properties, in particular, the matrix of the 22-th order for which there is no C-matrix. Examples of portraits for alternative matrices of the 255-th and the 257-th orders are given corresponding to the sequences of Mersenne and Fermat numbers. A new way to get Hadamard matrices is explained, different from the previously known procedures based on iterative processes and calculations of Lagrange symbols, with theoretical and practical meaning.
Directory of Open Access Journals (Sweden)
Jorswieck E. A.
2004-01-01
Full Text Available The capacity of a cellular multiuser MIMO system depends on various parameters, for example, the system structure, the transmit and receive strategies, the channel state information at the transmitter and the receiver, and the channel properties. Recently, the main focus of research was on single-user MIMO systems, their channel capacity, and their error performance with space-time coding. In general, the capacity of a cellular multiuser MIMO system is limited by additive white Gaussian noise, intracell interference from other users within the cell, and intercell interference from users outside the considered cell. We study one point-to-point link, on which interference acts. The interference models the different system scenarios and various parameters. Therefore, we consider three scenarios in which the noise is subject to different constraints. A general trace constraint is used in the first scenario. The noise covariance matrix eigenvalues are kept fixed in the second scenario, and in the third scenario the entries on the diagonal of the noise covariance matrix are kept fixed. We assume that the receiver as well as the transmitter have perfect channel state information. We solve the corresponding minimax programming problems and characterize the worst-case noise and the optimal transmit strategy. In all scenarios, the achievable capacity of the MIMO system with worst-case noise is equal to the capacity of some MIMO system in which either the channels are orthogonal or the transmit antennas are not allowed to cooperate or in which no channel state information is available at the transmitter. Furthermore, the minimax expressions fulfill a saddle point property. All theoretical results are illustrated by examples and numerical simulations.
Improvement of covariance data for fast reactors
International Nuclear Information System (INIS)
Shibata, Keiichi; Hasegawa, Akira
2000-02-01
We estimated covariances of the JENDL-3.2 data on the nuclides and reactions needed to analyze fast-reactor cores for the past three years, and produced covariance files. The present work was undertaken to re-examine the covariance files and to make some improvements. The covariances improved are the ones for the inelastic scattering cross section of 16 O, the total cross section of 23 Na, the fission cross section of 235 U, the capture cross section of 238 U, and the resolved resonance parameters for 238 U. Moreover, the covariances of 233 U data were newly estimated by the present work. The covariances obtained were compiled in the ENDF-6 format. (author)
The modified Gauss diagonalization of polynomial matrices
International Nuclear Information System (INIS)
Saeed, K.
1982-10-01
The Gauss algorithm for diagonalization of constant matrices is modified for application to polynomial matrices. Due to this modification the diagonal elements become pure polynomials rather than rational functions. (author)
Quantum Hilbert matrices and orthogonal polynomials
DEFF Research Database (Denmark)
Andersen, Jørgen Ellegaard; Berg, Christian
2009-01-01
Using the notion of quantum integers associated with a complex number q≠0 , we define the quantum Hilbert matrix and various extensions. They are Hankel matrices corresponding to certain little q -Jacobi polynomials when |q|<1 , and for the special value they are closely related to Hankel matrice...
Discrete canonical transforms that are Hadamard matrices
International Nuclear Information System (INIS)
Healy, John J; Wolf, Kurt Bernardo
2011-01-01
The group Sp(2,R) of symplectic linear canonical transformations has an integral kernel which has quadratic and linear phases, and which is realized by the geometric paraxial optical model. The discrete counterpart of this model is a finite Hamiltonian system that acts on N-point signals through N x N matrices whose elements also have a constant absolute value, although they do not form a representation of that group. Those matrices that are also unitary are Hadamard matrices. We investigate the manifolds of these N x N matrices under the Sp(2,R) equivalence imposed by the model, and find them to be on two-sided cosets. By means of an algorithm we determine representatives that lead to collections of mutually unbiased bases.
Harvey, Nate
2016-08-01
Extending results from previous work by Bandikova et al. (2012) and Inacio et al. (2015), this paper analyzes Gravity Recovery and Climate Experiment (GRACE) star camera attitude measurement noise by processing inter-camera quaternions from 2003 to 2015. We describe a correction to star camera data, which will eliminate a several-arcsec twice-per-rev error with daily modulation, currently visible in the auto-covariance function of the inter-camera quaternion, from future GRACE Level-1B product releases. We also present evidence supporting the argument that thermal conditions/settings affect long-term inter-camera attitude biases by at least tens-of-arcsecs, and that several-to-tens-of-arcsecs per-rev star camera errors depend largely on field-of-view.
Abel-grassmann's groupoids of modulo matrices
International Nuclear Information System (INIS)
Javaid, Q.; Awan, M.D.; Naqvi, S.H.A.
2016-01-01
The binary operation of usual addition is associative in all matrices over R. However, a binary operation of addition in matrices over Z/sub n/ of a nonassociative structures of AG-groupoids and AG-groups are defined and investigated here. It is shown that both these structures exist for every integer n >≥ 3. Various properties of these structures are explored like: (i) Every AG-groupoid of matrices over Z/sub n/ is transitively commutative AG-groupoid and is a cancellative AG-groupoid if n is prime. (ii) Every AG-groupoid of matrices over Z/sub n/ of Type-II is a T/sup 3/-AG-groupoid. (iii) An AG-groupoid of matrices over Z/sub n/ ; G /sub nAG/(t,u), is an AG-band, if t+u=1(mod n). (author)
Cross-section covariance propagation for LWR fuel cells in one and two dimensions - 308
International Nuclear Information System (INIS)
Ball, M.; Novog, D.R.; Parisi, C.; D'Auria, F.
2010-01-01
Within the framework of the Uncertainty Analysis in Modeling (UAM) for Design, Operation and Safety Analysis of LWRs Benchmark sponsored by the OECD/NEA, a tool has been developed for the propagation of covariance uncertainty through resonance self-shielding and other neutron kinetics calculations using a direct, cross-section generation and substitution approach. The motivation behind the work described in this paper was to develop a portable uncertainty propagation tool that could be easily implemented with several neutron kinetics codes, without relying on detailed knowledge of the internal workings of those codes or access to adjoint solutions. Implemented initially with the SCALE code package, 'self-shielded' covariance matrices for common LWR fuel cells have been calculated, as well as contributions to K eff uncertainty by selected neutron cross-sections and processes in both one and two dimensions. The one dimensional results generated by the tool are compared against those obtained using the TSUNAMI-1D module of SCALE in order to verify the efficacy of the methodology. One-dimensional results show good agreement with TSUNAMI-1D, but there is also an indication that the loss of dimensionality corresponding to one-dimensional equivalent geometries of two-dimensional fuel cells may lead to significant changes in the calculated uncertainty on K eff arising from particular neutron-nuclide reactions. (authors)
Noise and non-linearities in high-throughput data
International Nuclear Information System (INIS)
Nguyen, Viet-Anh; Lió, Pietro; Koukolíková-Nicola, Zdena; Bagnoli, Franco
2009-01-01
High-throughput data analyses are becoming common in biology, communications, economics and sociology. The vast amounts of data are usually represented in the form of matrices and can be considered as knowledge networks. Spectra-based approaches have proved useful in extracting hidden information within such networks and for estimating missing data, but these methods are based essentially on linear assumptions. The physical models of matching, when applicable, often suggest non-linear mechanisms, that may sometimes be identified as noise. The use of non-linear models in data analysis, however, may require the introduction of many parameters, which lowers the statistical weight of the model. According to the quality of data, a simpler linear analysis may be more convenient than more complex approaches. In this paper, we show how a simple non-parametric Bayesian model may be used to explore the role of non-linearities and noise in synthetic and experimental data sets
Free probability and random matrices
Mingo, James A
2017-01-01
This volume opens the world of free probability to a wide variety of readers. From its roots in the theory of operator algebras, free probability has intertwined with non-crossing partitions, random matrices, applications in wireless communications, representation theory of large groups, quantum groups, the invariant subspace problem, large deviations, subfactors, and beyond. This book puts a special emphasis on the relation of free probability to random matrices, but also touches upon the operator algebraic, combinatorial, and analytic aspects of the theory. The book serves as a combination textbook/research monograph, with self-contained chapters, exercises scattered throughout the text, and coverage of important ongoing progress of the theory. It will appeal to graduate students and all mathematicians interested in random matrices and free probability from the point of view of operator algebras, combinatorics, analytic functions, or applications in engineering and statistical physics.
Quantum matrices in two dimensions
International Nuclear Information System (INIS)
Ewen, H.; Ogievetsky, O.; Wess, J.
1991-01-01
Quantum matrices in two-dimensions, admitting left and right quantum spaces, are classified: they fall into two families, the 2-parametric family GL p,q (2) and a 1-parametric family GL α J (2). Phenomena previously found for GL p,q (2) hold in this general situation: (a) powers of quantum matrices are again quantum and (b) entries of the logarithm of a two-dimensional quantum matrix form a Lie algebra. (orig.)
Covariance descriptor fusion for target detection
Cukur, Huseyin; Binol, Hamidullah; Bal, Abdullah; Yavuz, Fatih
2016-05-01
Target detection is one of the most important topics for military or civilian applications. In order to address such detection tasks, hyperspectral imaging sensors provide useful images data containing both spatial and spectral information. Target detection has various challenging scenarios for hyperspectral images. To overcome these challenges, covariance descriptor presents many advantages. Detection capability of the conventional covariance descriptor technique can be improved by fusion methods. In this paper, hyperspectral bands are clustered according to inter-bands correlation. Target detection is then realized by fusion of covariance descriptor results based on the band clusters. The proposed combination technique is denoted Covariance Descriptor Fusion (CDF). The efficiency of the CDF is evaluated by applying to hyperspectral imagery to detect man-made objects. The obtained results show that the CDF presents better performance than the conventional covariance descriptor.
DEFF Research Database (Denmark)
Barndorff-Nielsen, Ole Eiler; Shephard, N.
2004-01-01
This paper analyses multivariate high frequency financial data using realized covariation. We provide a new asymptotic distribution theory for standard methods such as regression, correlation analysis, and covariance. It will be based on a fixed interval of time (e.g., a day or week), allowing...... the number of high frequency returns during this period to go to infinity. Our analysis allows us to study how high frequency correlations, regressions, and covariances change through time. In particular we provide confidence intervals for each of these quantities....
Covariant canonical quantization of fields and Bohmian mechanics
International Nuclear Information System (INIS)
Nikolic, H.
2005-01-01
We propose a manifestly covariant canonical method of field quantization based on the classical De Donder-Weyl covariant canonical formulation of field theory. Owing to covariance, the space and time arguments of fields are treated on an equal footing. To achieve both covariance and consistency with standard non-covariant canonical quantization of fields in Minkowski spacetime, it is necessary to adopt a covariant Bohmian formulation of quantum field theory. A preferred foliation of spacetime emerges dynamically owing to a purely quantum effect. The application to a simple time-reparametrization invariant system and quantum gravity is discussed and compared with the conventional non-covariant Wheeler-DeWitt approach. (orig.)
Synchronous correlation matrices and Connes’ embedding conjecture
Energy Technology Data Exchange (ETDEWEB)
Dykema, Kenneth J., E-mail: kdykema@math.tamu.edu [Department of Mathematics, Texas A& M University, College Station, Texas 77843-3368 (United States); Paulsen, Vern, E-mail: vern@math.uh.edu [Department of Mathematics, University of Houston, Houston, Texas 77204 (United States)
2016-01-15
In the work of Paulsen et al. [J. Funct. Anal. (in press); preprint arXiv:1407.6918], the concept of synchronous quantum correlation matrices was introduced and these were shown to correspond to traces on certain C*-algebras. In particular, synchronous correlation matrices arose in their study of various versions of quantum chromatic numbers of graphs and other quantum versions of graph theoretic parameters. In this paper, we develop these ideas further, focusing on the relations between synchronous correlation matrices and microstates. We prove that Connes’ embedding conjecture is equivalent to the equality of two families of synchronous quantum correlation matrices. We prove that if Connes’ embedding conjecture has a positive answer, then the tracial rank and projective rank are equal for every graph. We then apply these results to more general non-local games.
Proofs of Contracted Length Non-covariance
International Nuclear Information System (INIS)
Strel'tsov, V.N.
1994-01-01
Different proofs of contracted length non covariance are discussed. The way based on the establishment of interval inconstancy (dependence on velocity) seems to be the most convincing one. It is stressed that the known non covariance of the electromagnetic field energy and momentum of a moving charge ('the problem 4/3') is a direct consequence of contracted length non covariance. 8 refs
Indian Academy of Sciences (India)
IAS Admin
harmonic analysis and complex analysis, in ... gebra describes not only the study of linear transforma- tions and .... special case of the Jordan canonical form of matrices. ..... Richard Bronson, Schaum's Outline Series Theory And Problems Of.
Virial expansion for almost diagonal random matrices
Yevtushenko, Oleg; Kravtsov, Vladimir E.
2003-08-01
Energy level statistics of Hermitian random matrices hat H with Gaussian independent random entries Higeqj is studied for a generic ensemble of almost diagonal random matrices with langle|Hii|2rangle ~ 1 and langle|Hi\
Realistic Noise Assessment and Strain Analysis of Iranian Permanent GPS Stations
Razeghi, S. M.; Amiri Simkooei, A. A.; Sharifi, M. A.
2012-04-01
To assess noise characteristics of Iranian Permanent GPS Stations (IPGS), northwestern part of this network namely Azerbaijan Continuous GPS Station (ACGS), was selected. For a realistic noise assessment it is required to model all deterministic signals of the GPS time series by means of least squares harmonic estimation (LS-HE) and derive all periodic behavior of the series. After taking all deterministic signals into account, the least squares variance component estimation (LS-VCE) is used to obtain a realistic noise model (white noise plus flicker noise) of the ACGS. For this purpose, one needs simultaneous GPS time series for which a multivariate noise assessment is applied. Having determined realistic noise model, a realistic strain analysis of the network is obtained for which one relies on the finite element methods. Finite element is now considered to be a new functional model and the new stochastic model is given based on the multivariate noise assessment using LS-VCE. The deformation rates of the components along with their full covariance matries are input to the strain analysis. Further, the results are also provided using a pure white noise model. The normalized strains for these two models show that the strain parameters derived from a realistic noise model are less significant than those derived from the white model. This could be either due to the short time span of the time series used or due to the intrinsic behavior of the strain parameters in the ACGS. Longer time series are required to further elaborate this issue.
Covariate analysis of bivariate survival data
Energy Technology Data Exchange (ETDEWEB)
Bennett, L.E.
1992-01-01
The methods developed are used to analyze the effects of covariates on bivariate survival data when censoring and ties are present. The proposed method provides models for bivariate survival data that include differential covariate effects and censored observations. The proposed models are based on an extension of the univariate Buckley-James estimators which replace censored data points by their expected values, conditional on the censoring time and the covariates. For the bivariate situation, it is necessary to determine the expectation of the failure times for one component conditional on the failure or censoring time of the other component. Two different methods have been developed to estimate these expectations. In the semiparametric approach these expectations are determined from a modification of Burke's estimate of the bivariate empirical survival function. In the parametric approach censored data points are also replaced by their conditional expected values where the expected values are determined from a specified parametric distribution. The model estimation will be based on the revised data set, comprised of uncensored components and expected values for the censored components. The variance-covariance matrix for the estimated covariate parameters has also been derived for both the semiparametric and parametric methods. Data from the Demographic and Health Survey was analyzed by these methods. The two outcome variables are post-partum amenorrhea and breastfeeding; education and parity were used as the covariates. Both the covariate parameter estimates and the variance-covariance estimates for the semiparametric and parametric models will be compared. In addition, a multivariate test statistic was used in the semiparametric model to examine contrasts. The significance of the statistic was determined from a bootstrap distribution of the test statistic.
Community Detection for Correlation Matrices
Directory of Open Access Journals (Sweden)
Mel MacMahon
2015-04-01
Full Text Available A challenging problem in the study of complex systems is that of resolving, without prior information, the emergent, mesoscopic organization determined by groups of units whose dynamical activity is more strongly correlated internally than with the rest of the system. The existing techniques to filter correlations are not explicitly oriented towards identifying such modules and can suffer from an unavoidable information loss. A promising alternative is that of employing community detection techniques developed in network theory. Unfortunately, this approach has focused predominantly on replacing network data with correlation matrices, a procedure that we show to be intrinsically biased because of its inconsistency with the null hypotheses underlying the existing algorithms. Here, we introduce, via a consistent redefinition of null models based on random matrix theory, the appropriate correlation-based counterparts of the most popular community detection techniques. Our methods can filter out both unit-specific noise and system-wide dependencies, and the resulting communities are internally correlated and mutually anticorrelated. We also implement multiresolution and multifrequency approaches revealing hierarchically nested subcommunities with “hard” cores and “soft” peripheries. We apply our techniques to several financial time series and identify mesoscopic groups of stocks which are irreducible to a standard, sectorial taxonomy; detect “soft stocks” that alternate between communities; and discuss implications for portfolio optimization and risk management.
Community Detection for Correlation Matrices
MacMahon, Mel; Garlaschelli, Diego
2015-04-01
A challenging problem in the study of complex systems is that of resolving, without prior information, the emergent, mesoscopic organization determined by groups of units whose dynamical activity is more strongly correlated internally than with the rest of the system. The existing techniques to filter correlations are not explicitly oriented towards identifying such modules and can suffer from an unavoidable information loss. A promising alternative is that of employing community detection techniques developed in network theory. Unfortunately, this approach has focused predominantly on replacing network data with correlation matrices, a procedure that we show to be intrinsically biased because of its inconsistency with the null hypotheses underlying the existing algorithms. Here, we introduce, via a consistent redefinition of null models based on random matrix theory, the appropriate correlation-based counterparts of the most popular community detection techniques. Our methods can filter out both unit-specific noise and system-wide dependencies, and the resulting communities are internally correlated and mutually anticorrelated. We also implement multiresolution and multifrequency approaches revealing hierarchically nested subcommunities with "hard" cores and "soft" peripheries. We apply our techniques to several financial time series and identify mesoscopic groups of stocks which are irreducible to a standard, sectorial taxonomy; detect "soft stocks" that alternate between communities; and discuss implications for portfolio optimization and risk management.
Covariant diagrams for one-loop matching
International Nuclear Information System (INIS)
Zhang, Zhengkang
2016-10-01
We present a diagrammatic formulation of recently-revived covariant functional approaches to one-loop matching from an ultraviolet (UV) theory to a low-energy effective field theory. Various terms following from a covariant derivative expansion (CDE) are represented by diagrams which, unlike conventional Feynman diagrams, involve gaugecovariant quantities and are thus dubbed ''covariant diagrams.'' The use of covariant diagrams helps organize and simplify one-loop matching calculations, which we illustrate with examples. Of particular interest is the derivation of UV model-independent universal results, which reduce matching calculations of specific UV models to applications of master formulas. We show how such derivation can be done in a more concise manner than the previous literature, and discuss how additional structures that are not directly captured by existing universal results, including mixed heavy-light loops, open covariant derivatives, and mixed statistics, can be easily accounted for.
Covariant diagrams for one-loop matching
Energy Technology Data Exchange (ETDEWEB)
Zhang, Zhengkang [Michigan Univ., Ann Arbor, MI (United States). Michigan Center for Theoretical Physics; Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany)
2016-10-15
We present a diagrammatic formulation of recently-revived covariant functional approaches to one-loop matching from an ultraviolet (UV) theory to a low-energy effective field theory. Various terms following from a covariant derivative expansion (CDE) are represented by diagrams which, unlike conventional Feynman diagrams, involve gaugecovariant quantities and are thus dubbed ''covariant diagrams.'' The use of covariant diagrams helps organize and simplify one-loop matching calculations, which we illustrate with examples. Of particular interest is the derivation of UV model-independent universal results, which reduce matching calculations of specific UV models to applications of master formulas. We show how such derivation can be done in a more concise manner than the previous literature, and discuss how additional structures that are not directly captured by existing universal results, including mixed heavy-light loops, open covariant derivatives, and mixed statistics, can be easily accounted for.
СREATION OF CORRELATION FUNCTIONS OF LINEAR CONTINUOUS SYSTEMS BASED ON THEIR FUNDAMENTAL MATRICES
Directory of Open Access Journals (Sweden)
N. A. Vunder
2015-11-01
Full Text Available The paper presents a method of creating correlation matrices and functions of the state vectors and outputs of the linear continuous systems functioning under the conditions of stochastic stationary, in a broad sense, effects. Fundamental matrices form the basis of the method. We have shown that for the linear continuous systems with single dimensional input and single dimensional output the correlation output function of such system can be found as the free movement of this system generated by its initial state. This state is constructed from the variance matrix of the state vector and the transposed output matrix. We have elucidated that when a continuous system belongs to a class of multi-dimensional input – multi-dimensional output systems, the following options are available for solving the problem of creation of the correlation function of a linear system. The first option is to partition the system into separate channels. Then the approach developed for systems with onedimensional input and one-dimensional output is applied to each of the separate channels. The second option is used to preserve the vector nature of the stochastic external influence. It consists in partition of output vector to scalar components by separating output matrix into separate rows with subsequent formation of the correlation function according to the scheme for single dimensional input and single dimensional output type systems. The third option is based on the scalarization of matrix correlation output function by applying the singular value decomposition to it. That gives the possibility to form scalar majorant and minorant of correlation output functions. We have established that a key component of a computational procedure of creating the correlation function of continuous linear system is a variance matrix of the system state vector. In the case of functioning under an exogenous stochastic effect like "white noise" the variance matrix is calculated by
Chequered surfaces and complex matrices
International Nuclear Information System (INIS)
Morris, T.R.; Southampton Univ.
1991-01-01
We investigate a large-N matrix model involving general complex matrices. It can be reinterpreted as a model of two hermitian matrices with specific couplings, and as a model of positive definite hermitian matrices. Large-N perturbation theory generates dynamical triangulations in which the triangles can be chequered (i.e. coloured so that neighbours are opposite colours). On a sphere there is a simple relation between such triangulations and those generated by the single hermitian matrix model. For the torus (and a quartic potential) we solve the counting problem for the number of triangulations that cannot be quechered. The critical physics of chequered triangulations is the same as that of the hermitian matrix model. We show this explicitly by solving non-perturbatively pure two-dimensional ''chequered'' gravity. The interpretative framework given here applies to a number of other generalisations of the hermitian matrix model. (orig.)
Covariance and sensitivity data generation at ORNL
International Nuclear Information System (INIS)
Leal, L. C.; Derrien, H.; Larson, N. M.; Alpan, A.
2005-01-01
Covariance data are required to assess uncertainties in design parameters in several nuclear applications. The error estimation of calculated quantities relies on the nuclear data uncertainty information available in the basic nuclear data libraries, such as the US Evaluated Nuclear Data Library, ENDF/B. The uncertainty files in the ENDF/B library are obtained from the analysis of experimental data and are stored as variance and covariance data. In this paper we address the generation of covariance data in the resonance region done with the computer code SAMMY. SAMMY is used in the evaluation of the experimental data in the resolved and unresolved resonance energy regions. The data fitting of cross sections is based on the generalised least-squares formalism (Bayesian theory) together with the resonance formalism described by R-matrix theory. Two approaches are used in SAMMY for the generation of resonance parameter covariance data. In the evaluation process SAMMY generates a set of resonance parameters that fit the data, and, it provides the resonance parameter covariances. For resonance parameter evaluations where there are no resonance parameter covariance data available, the alternative is to use an approach called the 'retroactive' resonance parameter covariance generation. In this paper, we describe the application of the retroactive covariance generation approach for the gadolinium isotopes. (authors)
Covariance Evaluation Methodology for Neutron Cross Sections
Energy Technology Data Exchange (ETDEWEB)
Herman,M.; Arcilla, R.; Mattoon, C.M.; Mughabghab, S.F.; Oblozinsky, P.; Pigni, M.; Pritychenko, b.; Songzoni, A.A.
2008-09-01
We present the NNDC-BNL methodology for estimating neutron cross section covariances in thermal, resolved resonance, unresolved resonance and fast neutron regions. The three key elements of the methodology are Atlas of Neutron Resonances, nuclear reaction code EMPIRE, and the Bayesian code implementing Kalman filter concept. The covariance data processing, visualization and distribution capabilities are integral components of the NNDC methodology. We illustrate its application on examples including relatively detailed evaluation of covariances for two individual nuclei and massive production of simple covariance estimates for 307 materials. Certain peculiarities regarding evaluation of covariances for resolved resonances and the consistency between resonance parameter uncertainties and thermal cross section uncertainties are also discussed.
Intrinsic Density Matrices of the Nuclear Shell Model
International Nuclear Information System (INIS)
Deveikis, A.; Kamuntavichius, G.
1996-01-01
A new method for calculation of shell model intrinsic density matrices, defined as two-particle density matrices integrated over the centre-of-mass position vector of two last particles and complemented with isospin variables, has been developed. The intrinsic density matrices obtained are completely antisymmetric, translation-invariant, and do not employ a group-theoretical classification of antisymmetric states. They are used for exact realistic density matrix expansion within the framework of the reduced Hamiltonian method. The procedures based on precise arithmetic for calculation of the intrinsic density matrices that involve no numerical diagonalization or orthogonalization have been developed and implemented in the computer code. (author). 11 refs., 2 tabs
Covariant perturbations of Schwarzschild black holes
International Nuclear Information System (INIS)
Clarkson, Chris A; Barrett, Richard K
2003-01-01
We present a new covariant and gauge-invariant perturbation formalism for dealing with spacetimes having spherical symmetry (or some preferred spatial direction) in the background, and apply it to the case of gravitational wave propagation in a Schwarzschild black-hole spacetime. The 1 + 3 covariant approach is extended to a '1 + 1 + 2 covariant sheet' formalism by introducing a radial unit vector in addition to the timelike congruence, and decomposing all covariant quantities with respect to this. The background Schwarzschild solution is discussed and a covariant characterization is given. We give the full first-order system of linearized 1 + 1 + 2 covariant equations, and we show how, by introducing (time and spherical) harmonic functions, these may be reduced to a system of first-order ordinary differential equations and algebraic constraints for the 1 + 1 + 2 variables which may be solved straightforwardly. We show how both odd- and even-parity perturbations may be unified by the discovery of a covariant, frame- and gauge-invariant, transverse-traceless tensor describing gravitational waves, which satisfies a covariant wave equation equivalent to the Regge-Wheeler equation for both even- and odd-parity perturbations. We show how the Zerilli equation may be derived from this tensor, and derive a similar transverse-traceless tensor equation equivalent to this equation. The so-called special quasinormal modes with purely imaginary frequency emerge naturally. The significance of the degrees of freedom in the choice of the two frame vectors is discussed, and we demonstrate that, for a certain frame choice, the underlying dynamics is governed purely by the Regge-Wheeler tensor. The two transverse-traceless Weyl tensors which carry the curvature of gravitational waves are discussed, and we give the closed system of four first-order ordinary differential equations describing their propagation. Finally, we consider the extension of this work to the study of
Vogel, Curtis R; Tyler, Glenn A; Wittich, Donald J
2014-07-01
We introduce a framework for modeling, analysis, and simulation of aero-optics wavefront aberrations that is based on spatial-temporal covariance matrices extracted from wavefront sensor measurements. Within this framework, we present a quasi-homogeneous structure function to analyze nonhomogeneous, mildly anisotropic spatial random processes, and we use this structure function to show that phase aberrations arising in aero-optics are, for an important range of operating parameters, locally Kolmogorov. This strongly suggests that the d5/3 power law for adaptive optics (AO) deformable mirror fitting error, where d denotes actuator separation, holds for certain important aero-optics scenarios. This framework also allows us to compute bounds on AO servo lag error and predictive control error. In addition, it provides us with the means to accurately simulate AO systems for the mitigation of aero-effects, and it may provide insight into underlying physical processes associated with turbulent flow. The techniques introduced here are demonstrated using data obtained from the Airborne Aero-Optics Laboratory.
Scott, M
2012-08-01
The time-covariance function captures the dynamics of biochemical fluctuations and contains important information about the underlying kinetic rate parameters. Intrinsic fluctuations in biochemical reaction networks are typically modelled using a master equation formalism. In general, the equation cannot be solved exactly and approximation methods are required. For small fluctuations close to equilibrium, a linearisation of the dynamics provides a very good description of the relaxation of the time-covariance function. As the number of molecules in the system decrease, deviations from the linear theory appear. Carrying out a systematic perturbation expansion of the master equation to capture these effects results in formidable algebra; however, symbolic mathematics packages considerably expedite the computation. The authors demonstrate that non-linear effects can reveal features of the underlying dynamics, such as reaction stoichiometry, not available in linearised theory. Furthermore, in models that exhibit noise-induced oscillations, non-linear corrections result in a shift in the base frequency along with the appearance of a secondary harmonic.
Random matrices and random difference equations
International Nuclear Information System (INIS)
Uppuluri, V.R.R.
1975-01-01
Mathematical models leading to products of random matrices and random difference equations are discussed. A one-compartment model with random behavior is introduced, and it is shown how the average concentration in the discrete time model converges to the exponential function. This is of relevance to understanding how radioactivity gets trapped in bone structure in blood--bone systems. The ideas are then generalized to two-compartment models and mammillary systems, where products of random matrices appear in a natural way. The appearance of products of random matrices in applications in demography and control theory is considered. Then random sequences motivated from the following problems are studied: constant pulsing and random decay models, random pulsing and constant decay models, and random pulsing and random decay models
Quantum Entanglement and Reduced Density Matrices
Purwanto, Agus; Sukamto, Heru; Yuwana, Lila
2018-05-01
We investigate entanglement and separability criteria of multipartite (n-partite) state by examining ranks of its reduced density matrices. Firstly, we construct the general formula to determine the criterion. A rank of origin density matrix always equals one, meanwhile ranks of reduced matrices have various ranks. Next, separability and entanglement criterion of multipartite is determined by calculating ranks of reduced density matrices. In this article we diversify multipartite state criteria into completely entangled state, completely separable state, and compound state, i.e. sub-entangled state and sub-entangledseparable state. Furthermore, we also shorten the calculation proposed by the previous research to determine separability of multipartite state and expand the methods to be able to differ multipartite state based on criteria above.
Covariation in Natural Causal Induction.
Cheng, Patricia W.; Novick, Laura R.
1991-01-01
Biases and models usually offered by cognitive and social psychology and by philosophy to explain causal induction are evaluated with respect to focal sets (contextually determined sets of events over which covariation is computed). A probabilistic contrast model is proposed as underlying covariation computation in natural causal induction. (SLD)
Xie, Hong-Wei; Qiu, Wei; Heyer, Nicholas J; Zhang, Mei-Bian; Zhang, Peng; Zhao, Yi-Ming; Hamernik, Roger P
2016-01-01
matric. Multiple linear regression analysis among complex exposed workers demonstrated that the correlation between HTL3,4,6 and CNE controlling for age was improved when using the kurtosis-adjusted CNE compared with the unadjusted CNE (R = 0.386 versus 0.350) and that noise accounted for a greater proportion of hearing loss. In addition, although dose-response curves for AHFNIHL were distinctly different when using unadjusted CNE, they overlapped when using the kurtosis-adjusted CNE. For the same exposure level, the prevalence of NIHL is greater in workers exposed to complex noise environments than in workers exposed to a continuous noise. Kurtosis adjustment of CNE improved the correlation with NIHL and provided a single metric for dose-response effects across different types of noise. The kurtosis-adjusted CNE may be a reasonable candidate for use in NIHL risk assessment across a wide variety of noise environments.
TH-A-18C-07: Noise Suppression in Material Decomposition for Dual-Energy CT
International Nuclear Information System (INIS)
Dong, X; Petrongolo, M; Wang, T; Zhu, L
2014-01-01
Purpose: A general problem of dual-energy CT (DECT) is that the decomposition is sensitive to noise in the two sets of dual-energy projection data, resulting in severely degraded qualities of decomposed images. We have previously proposed an iterative denoising method for DECT. Using a linear decomposition function, the method does not gain the full benefits of DECT on beam-hardening correction. In this work, we expand the framework of our iterative method to include non-linear decomposition models for noise suppression in DECT. Methods: We first obtain decomposed projections, which are free of beam-hardening artifacts, using a lookup table pre-measured on a calibration phantom. First-pass material images with high noise are reconstructed from the decomposed projections using standard filter-backprojection reconstruction. Noise on the decomposed images is then suppressed by an iterative method, which is formulated in the form of least-square estimation with smoothness regularization. Based on the design principles of a best linear unbiased estimator, we include the inverse of the estimated variance-covariance matrix of the decomposed images as the penalty weight in the least-square term. Analytical formulae are derived to compute the variance-covariance matrix from the measured decomposition lookup table. Results: We have evaluated the proposed method via phantom studies. Using non-linear decomposition, our method effectively suppresses the streaking artifacts of beam-hardening and obtains more uniform images than our previous approach based on a linear model. The proposed method reduces the average noise standard deviation of two basis materials by one order of magnitude without sacrificing the spatial resolution. Conclusion: We propose a general framework of iterative denoising for material decomposition of DECT. Preliminary phantom studies have shown the proposed method improves the image uniformity and reduces noise level without resolution loss. In the future
Malware analysis using visualized image matrices.
Han, KyoungSoo; Kang, BooJoong; Im, Eul Gyu
2014-01-01
This paper proposes a novel malware visual analysis method that contains not only a visualization method to convert binary files into images, but also a similarity calculation method between these images. The proposed method generates RGB-colored pixels on image matrices using the opcode sequences extracted from malware samples and calculates the similarities for the image matrices. Particularly, our proposed methods are available for packed malware samples by applying them to the execution traces extracted through dynamic analysis. When the images are generated, we can reduce the overheads by extracting the opcode sequences only from the blocks that include the instructions related to staple behaviors such as functions and application programming interface (API) calls. In addition, we propose a technique that generates a representative image for each malware family in order to reduce the number of comparisons for the classification of unknown samples and the colored pixel information in the image matrices is used to calculate the similarities between the images. Our experimental results show that the image matrices of malware can effectively be used to classify malware families both statically and dynamically with accuracy of 0.9896 and 0.9732, respectively.
Malware Analysis Using Visualized Image Matrices
Directory of Open Access Journals (Sweden)
KyoungSoo Han
2014-01-01
Full Text Available This paper proposes a novel malware visual analysis method that contains not only a visualization method to convert binary files into images, but also a similarity calculation method between these images. The proposed method generates RGB-colored pixels on image matrices using the opcode sequences extracted from malware samples and calculates the similarities for the image matrices. Particularly, our proposed methods are available for packed malware samples by applying them to the execution traces extracted through dynamic analysis. When the images are generated, we can reduce the overheads by extracting the opcode sequences only from the blocks that include the instructions related to staple behaviors such as functions and application programming interface (API calls. In addition, we propose a technique that generates a representative image for each malware family in order to reduce the number of comparisons for the classification of unknown samples and the colored pixel information in the image matrices is used to calculate the similarities between the images. Our experimental results show that the image matrices of malware can effectively be used to classify malware families both statically and dynamically with accuracy of 0.9896 and 0.9732, respectively.
Energy Technology Data Exchange (ETDEWEB)
Zepon, Karine Modolon [CIMJECT, Departamento de Engenharia Mecânica, Universidade Federal de Santa Catarina, 88040-900 Florianópolis, SC (Brazil); TECFARMA, Universidade do Sul de Santa Catarina, 88704-900 Tubarão, SC (Brazil); Petronilho, Fabricia [FICEXP, Universidade do Sul de Santa Catarina, 88704-900 Tubarão, SC (Brazil); Soldi, Valdir [POLIMAT, Universidade Federal de Santa Catarina, 88040-900 Florianópolis, SC (Brazil); Salmoria, Gean Vitor [CIMJECT, Departamento de Engenharia Mecânica, Universidade Federal de Santa Catarina, 88040-900 Florianópolis, SC (Brazil); Kanis, Luiz Alberto, E-mail: luiz.kanis@unisul.br [TECFARMA, Universidade do Sul de Santa Catarina, 88704-900 Tubarão, SC (Brazil)
2014-11-01
The production and evaluation of cornstarch/cellulose acetate/silver sulfadiazine extrudate matrices are reported herein. The matrices were melt extruded under nine different conditions, altering the temperature and the screw speed values. The surface morphology of the matrices was examined by scanning electron microscopy. The micrographs revealed the presence of non-melted silver sulfadiazine microparticles in the matrices extruded at lower temperature and screw speed values. The thermal properties were evaluated and the results for both the biopolymer and the drug indicated no thermal degradation during the melt extrusion process. The differential scanning analysis of the extrudate matrices showed a shift to lower temperatures for the silver sulfadiazine melting point compared with the non-extruded drug. The starch/cellulose acetate matrices containing silver sulfadiazine demonstrated significant inhibition of the growth of Pseudomonas aeruginosa and Staphylococcus aureus. In vivo inflammatory response tests showed that the extrudate matrices, with or without silver sulfadiazine, did not trigger chronic inflammatory processes. - Highlights: • Melt extruded bio-based matrices containing silver sulfadiazine was produced. • The silver sulfadiazine is stable during melt-extrusion. • The extrudate matrices shown bacterial growth inhibition. • The matrices obtained have potential to development wound healing membranes.
Polynomial sequences generated by infinite Hessenberg matrices
Directory of Open Access Journals (Sweden)
Verde-Star Luis
2017-01-01
Full Text Available We show that an infinite lower Hessenberg matrix generates polynomial sequences that correspond to the rows of infinite lower triangular invertible matrices. Orthogonal polynomial sequences are obtained when the Hessenberg matrix is tridiagonal. We study properties of the polynomial sequences and their corresponding matrices which are related to recurrence relations, companion matrices, matrix similarity, construction algorithms, and generating functions. When the Hessenberg matrix is also Toeplitz the polynomial sequences turn out to be of interpolatory type and we obtain additional results. For example, we show that every nonderogative finite square matrix is similar to a unique Toeplitz-Hessenberg matrix.
Di, Xin; Gohel, Suril; Thielcke, Andre; Wehrl, Hans F; Biswal, Bharat B
2017-11-01
Relationships between spatially remote brain regions in human have typically been estimated by moment-to-moment correlations of blood-oxygen-level dependent signals in resting-state using functional MRI (fMRI). Recently, studies using subject-to-subject covariance of anatomical volumes, cortical thickness, and metabolic activity are becoming increasingly popular. However, question remains on whether these measures reflect the same inter-region connectivity and brain network organizations. In the current study, we systematically analyzed inter-subject volumetric covariance from anatomical MRI images, metabolic covariance from fluorodeoxyglucose positron emission tomography images from 193 healthy subjects, and resting-state moment-to-moment correlations from fMRI images of a subset of 44 subjects. The correlation matrices calculated from the three methods were found to be minimally correlated, with higher correlation in the range of 0.31, as well as limited proportion of overlapping connections. The volumetric network showed the highest global efficiency and lowest mean clustering coefficient, leaning toward random-like network, while the metabolic and resting-state networks conveyed properties more resembling small-world networks. Community structures of the volumetric and metabolic networks did not reflect known functional organizations, which could be observed in resting-state network. The current results suggested that inter-subject volumetric and metabolic covariance do not necessarily reflect the inter-regional relationships and network organizations as resting-state correlations, thus calling for cautions on interpreting results of inter-subject covariance networks.
International Nuclear Information System (INIS)
Bombardelli, Diego
2016-01-01
In these notes we review the S-matrix theory in (1+1)-dimensional integrable models, focusing mainly on the relativistic case. Once the main definitions and physical properties are introduced, we discuss the factorization of scattering processes due to integrability. We then focus on the analytic properties of the two-particle scattering amplitude and illustrate the derivation of the S-matrices for all the possible bound states using the so-called bootstrap principle. General algebraic structures underlying the S-matrix theory and its relation with the form factors axioms are briefly mentioned. Finally, we discuss the S-matrices of sine-Gordon and SU (2), SU (3) chiral Gross–Neveu models. (topical review)
Comparison of JADE and canonical correlation analysis for ECG de-noising.
Kuzilek, Jakub; Kremen, Vaclav; Lhotska, Lenka
2014-01-01
This paper explores differences between two methods for blind source separation within frame of ECG de-noising. First method is joint approximate diagonalization of eigenmatrices, which is based on estimation of fourth order cross-cummulant tensor and its diagonalization. Second one is the statistical method known as canonical correlation analysis, which is based on estimation of correlation matrices between two multidimensional variables. Both methods were used within method, which combines the blind source separation algorithm with decision tree. The evaluation was made on large database of 382 long-term ECG signals and the results were examined. Biggest difference was found in results of 50 Hz power line interference where the CCA algorithm completely failed. Thus main power of CCA lies in estimation of unstructured noise within ECG. JADE algorithm has larger computational complexity thus the CCA perfomed faster when estimating the components.
Matrices Aléatoires Tri-diagonales et Par Blocs.
MEKKI, Slimane
2014-01-01
Dans ce mémoire l'étude porte sur la densité de matrice aléatoire, les densités des valeurs propres d'une matrice pour les trois ensembles G.O.E, G.U.E, G.S.E. Après nous avons explicité les formules des densités de valeurs propres des matrices tri-diagonales dans les cas HERMITE et LAGUERRE Des simulations sur les constantes de normalisations pour les densités des matrices aléatoires ou des valeurs propres sont présentées.
Hidden symmetries and equilibrium properties of multiplicative white-noise stochastic processes
International Nuclear Information System (INIS)
Arenas, Zochil González; Barci, Daniel G
2012-01-01
Multiplicative white-noise stochastic processes continue to attract attention in a wide area of scientific research. The variety of prescriptions available for defining them makes the development of general tools for their characterization difficult. In this work, we study equilibrium properties of Markovian multiplicative white-noise processes. For this, we define the time reversal transformation for such processes, taking into account that the asymptotic stationary probability distribution depends on the prescription. Representing the stochastic process in a functional Grassmann formalism, we avoid the necessity of fixing a particular prescription. In this framework, we analyze equilibrium properties and study hidden symmetries of the process. We show that, using a careful definition of the equilibrium distribution and taking into account the appropriate time reversal transformation, usual equilibrium properties are satisfied for any prescription. Finally, we present a detailed deduction of a covariant supersymmetric formulation of a multiplicative Markovian white-noise process and study some of the constraints that it imposes on correlation functions using Ward–Takahashi identities. (paper)
Hidden symmetries and equilibrium properties of multiplicative white-noise stochastic processes
González Arenas, Zochil; Barci, Daniel G.
2012-12-01
Multiplicative white-noise stochastic processes continue to attract attention in a wide area of scientific research. The variety of prescriptions available for defining them makes the development of general tools for their characterization difficult. In this work, we study equilibrium properties of Markovian multiplicative white-noise processes. For this, we define the time reversal transformation for such processes, taking into account that the asymptotic stationary probability distribution depends on the prescription. Representing the stochastic process in a functional Grassmann formalism, we avoid the necessity of fixing a particular prescription. In this framework, we analyze equilibrium properties and study hidden symmetries of the process. We show that, using a careful definition of the equilibrium distribution and taking into account the appropriate time reversal transformation, usual equilibrium properties are satisfied for any prescription. Finally, we present a detailed deduction of a covariant supersymmetric formulation of a multiplicative Markovian white-noise process and study some of the constraints that it imposes on correlation functions using Ward-Takahashi identities.
Hierarchical quark mass matrices
International Nuclear Information System (INIS)
Rasin, A.
1998-02-01
I define a set of conditions that the most general hierarchical Yukawa mass matrices have to satisfy so that the leading rotations in the diagonalization matrix are a pair of (2,3) and (1,2) rotations. In addition to Fritzsch structures, examples of such hierarchical structures include also matrices with (1,3) elements of the same order or even much larger than the (1,2) elements. Such matrices can be obtained in the framework of a flavor theory. To leading order, the values of the angle in the (2,3) plane (s 23 ) and the angle in the (1,2) plane (s 12 ) do not depend on the order in which they are taken when diagonalizing. We find that any of the Cabbibo-Kobayashi-Maskawa matrix parametrizations that consist of at least one (1,2) and one (2,3) rotation may be suitable. In the particular case when the s 13 diagonalization angles are sufficiently small compared to the product s 12 s 23 , two special CKM parametrizations emerge: the R 12 R 23 R 12 parametrization follows with s 23 taken before the s 12 rotation, and vice versa for the R 23 R 12 R 23 parametrization. (author)
Laminin active peptide/agarose matrices as multifunctional biomaterials for tissue engineering.
Yamada, Yuji; Hozumi, Kentaro; Aso, Akihiro; Hotta, Atsushi; Toma, Kazunori; Katagiri, Fumihiko; Kikkawa, Yamato; Nomizu, Motoyoshi
2012-06-01
Cell adhesive peptides derived from extracellular matrix components are potential candidates to afford bio-adhesiveness to cell culture scaffolds for tissue engineering. Previously, we covalently conjugated bioactive laminin peptides to polysaccharides, such as chitosan and alginate, and demonstrated their advantages as biomaterials. Here, we prepared functional polysaccharide matrices by mixing laminin active peptides and agarose gel. Several laminin peptide/agarose matrices showed cell attachment activity. In particular, peptide AG73 (RKRLQVQLSIRT)/agarose matrices promoted strong cell attachment and the cell behavior depended on the stiffness of agarose matrices. Fibroblasts formed spheroid structures on the soft AG73/agarose matrices while the cells formed a monolayer with elongated morphologies on the stiff matrices. On the stiff AG73/agarose matrices, neuronal cells extended neuritic processes and endothelial cells formed capillary-like networks. In addition, salivary gland cells formed acini-like structures on the soft matrices. These results suggest that the peptide/agarose matrices are useful for both two- and three-dimensional cell culture systems as a multifunctional biomaterial for tissue engineering. Copyright Â© 2012 Elsevier Ltd. All rights reserved.
Modifications of Sp(2) covariant superfield quantization
Energy Technology Data Exchange (ETDEWEB)
Gitman, D.M.; Moshin, P.Yu
2003-12-04
We propose a modification of the Sp(2) covariant superfield quantization to realize a superalgebra of generating operators isomorphic to the massless limit of the corresponding superalgebra of the osp(1,2) covariant formalism. The modified scheme ensures the compatibility of the superalgebra of generating operators with extended BRST symmetry without imposing restrictions eliminating superfield components from the quantum action. The formalism coincides with the Sp(2) covariant superfield scheme and with the massless limit of the osp(1,2) covariant quantization in particular cases of gauge-fixing and solutions of the quantum master equations.
Lisano, Michael E.
2007-01-01
Recent literature in applied estimation theory reflects growing interest in the sigma-point (also called unscented ) formulation for optimal sequential state estimation, often describing performance comparisons with extended Kalman filters as applied to specific dynamical problems [c.f. 1, 2, 3]. Favorable attributes of sigma-point filters are described as including a lower expected error for nonlinear even non-differentiable dynamical systems, and a straightforward formulation not requiring derivation or implementation of any partial derivative Jacobian matrices. These attributes are particularly attractive, e.g. in terms of enabling simplified code architecture and streamlined testing, in the formulation of estimators for nonlinear spaceflight mechanics systems, such as filter software onboard deep-space robotic spacecraft. As presented in [4], the Sigma-Point Consider Filter (SPCF) algorithm extends the sigma-point filter algorithm to the problem of consider covariance analysis. Considering parameters in a dynamical system, while estimating its state, provides an upper bound on the estimated state covariance, which is viewed as a conservative approach to designing estimators for problems of general guidance, navigation and control. This is because, whether a parameter in the system model is observable or not, error in the knowledge of the value of a non-estimated parameter will increase the actual uncertainty of the estimated state of the system beyond the level formally indicated by the covariance of an estimator that neglects errors or uncertainty in that parameter. The equations for SPCF covariance evolution are obtained in a fashion similar to the derivation approach taken with standard (i.e. linearized or extended) consider parameterized Kalman filters (c.f. [5]). While in [4] the SPCF and linear-theory consider filter (LTCF) were applied to an illustrative linear dynamics/linear measurement problem, in the present work examines the SPCF as applied to
Covariant quantizations in plane and curved spaces
International Nuclear Information System (INIS)
Assirati, J.L.M.; Gitman, D.M.
2017-01-01
We present covariant quantization rules for nonsingular finite-dimensional classical theories with flat and curved configuration spaces. In the beginning, we construct a family of covariant quantizations in flat spaces and Cartesian coordinates. This family is parametrized by a function ω(θ), θ element of (1,0), which describes an ambiguity of the quantization. We generalize this construction presenting covariant quantizations of theories with flat configuration spaces but already with arbitrary curvilinear coordinates. Then we construct a so-called minimal family of covariant quantizations for theories with curved configuration spaces. This family of quantizations is parametrized by the same function ω(θ). Finally, we describe a more wide family of covariant quantizations in curved spaces. This family is already parametrized by two functions, the previous one ω(θ) and by an additional function Θ(x,ξ). The above mentioned minimal family is a part at Θ = 1 of the wide family of quantizations. We study constructed quantizations in detail, proving their consistency and covariance. As a physical application, we consider a quantization of a non-relativistic particle moving in a curved space, discussing the problem of a quantum potential. Applying the covariant quantizations in flat spaces to an old problem of constructing quantum Hamiltonian in polar coordinates, we directly obtain a correct result. (orig.)
Covariant quantizations in plane and curved spaces
Energy Technology Data Exchange (ETDEWEB)
Assirati, J.L.M. [University of Sao Paulo, Institute of Physics, Sao Paulo (Brazil); Gitman, D.M. [Tomsk State University, Department of Physics, Tomsk (Russian Federation); P.N. Lebedev Physical Institute, Moscow (Russian Federation); University of Sao Paulo, Institute of Physics, Sao Paulo (Brazil)
2017-07-15
We present covariant quantization rules for nonsingular finite-dimensional classical theories with flat and curved configuration spaces. In the beginning, we construct a family of covariant quantizations in flat spaces and Cartesian coordinates. This family is parametrized by a function ω(θ), θ element of (1,0), which describes an ambiguity of the quantization. We generalize this construction presenting covariant quantizations of theories with flat configuration spaces but already with arbitrary curvilinear coordinates. Then we construct a so-called minimal family of covariant quantizations for theories with curved configuration spaces. This family of quantizations is parametrized by the same function ω(θ). Finally, we describe a more wide family of covariant quantizations in curved spaces. This family is already parametrized by two functions, the previous one ω(θ) and by an additional function Θ(x,ξ). The above mentioned minimal family is a part at Θ = 1 of the wide family of quantizations. We study constructed quantizations in detail, proving their consistency and covariance. As a physical application, we consider a quantization of a non-relativistic particle moving in a curved space, discussing the problem of a quantum potential. Applying the covariant quantizations in flat spaces to an old problem of constructing quantum Hamiltonian in polar coordinates, we directly obtain a correct result. (orig.)
Construction of covariance matrix for experimental data
International Nuclear Information System (INIS)
Liu Tingjin; Zhang Jianhua
1992-01-01
For evaluators and experimenters, the information is complete only in the case when the covariance matrix is given. The covariance matrix of the indirectly measured data has been constructed and discussed. As an example, the covariance matrix of 23 Na(n, 2n) cross section is constructed. A reasonable result is obtained
Smooth individual level covariates adjustment in disease mapping.
Huque, Md Hamidul; Anderson, Craig; Walton, Richard; Woolford, Samuel; Ryan, Louise
2018-05-01
Spatial models for disease mapping should ideally account for covariates measured both at individual and area levels. The newly available "indiCAR" model fits the popular conditional autoregresssive (CAR) model by accommodating both individual and group level covariates while adjusting for spatial correlation in the disease rates. This algorithm has been shown to be effective but assumes log-linear associations between individual level covariates and outcome. In many studies, the relationship between individual level covariates and the outcome may be non-log-linear, and methods to track such nonlinearity between individual level covariate and outcome in spatial regression modeling are not well developed. In this paper, we propose a new algorithm, smooth-indiCAR, to fit an extension to the popular conditional autoregresssive model that can accommodate both linear and nonlinear individual level covariate effects while adjusting for group level covariates and spatial correlation in the disease rates. In this formulation, the effect of a continuous individual level covariate is accommodated via penalized splines. We describe a two-step estimation procedure to obtain reliable estimates of individual and group level covariate effects where both individual and group level covariate effects are estimated separately. This distributed computing framework enhances its application in the Big Data domain with a large number of individual/group level covariates. We evaluate the performance of smooth-indiCAR through simulation. Our results indicate that the smooth-indiCAR method provides reliable estimates of all regression and random effect parameters. We illustrate our proposed methodology with an analysis of data on neutropenia admissions in New South Wales (NSW), Australia. © 2018 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.
Development of covariance date for fast reactor cores. 3
International Nuclear Information System (INIS)
Shibata, Keiichi; Hasegawa, Akira
1999-03-01
Covariances have been estimated for nuclear data contained in JENDL-3.2. As for Cr and Ni, the physical quantities for which covariances are deduced are cross sections and the first order Legendre-polynomial coefficient for the angular distribution of elastically scattered neutrons. The covariances were estimated by using the same methodology that had been used in the JENDL-3.2 evaluation in order to keep a consistency between mean values and their covariances. In a case where evaluated data were based on experimental data, the covariances were estimated from the same experimental data. For cross section that had been evaluated by nuclear model calculations, the same model was applied to generate the covariances. The covariances obtained were compiled into ENDF-6 format files. The covariances, which had been prepared by the previous fiscal year, were re-examined, and some improvements were performed. Parts of Fe and 235 U covariances were updated. Covariances of nu-p and nu-d for 241 Pu and of fission neutron spectra for 233,235,238 U and 239,240 Pu were newly added to data files. (author)
The Antitriangular Factorization of Saddle Point Matrices
Pestana, J.
2014-01-01
Mastronardi and Van Dooren [SIAM J. Matrix Anal. Appl., 34 (2013), pp. 173-196] recently introduced the block antitriangular ("Batman") decomposition for symmetric indefinite matrices. Here we show the simplification of this factorization for saddle point matrices and demonstrate how it represents the common nullspace method. We show that rank-1 updates to the saddle point matrix can be easily incorporated into the factorization and give bounds on the eigenvalues of matrices important in saddle point theory. We show the relation of this factorization to constraint preconditioning and how it transforms but preserves the structure of block diagonal and block triangular preconditioners. © 2014 Society for Industrial and Applied Mathematics.
Bapat, Ravindra B
2014-01-01
This new edition illustrates the power of linear algebra in the study of graphs. The emphasis on matrix techniques is greater than in other texts on algebraic graph theory. Important matrices associated with graphs (for example, incidence, adjacency and Laplacian matrices) are treated in detail. Presenting a useful overview of selected topics in algebraic graph theory, early chapters of the text focus on regular graphs, algebraic connectivity, the distance matrix of a tree, and its generalized version for arbitrary graphs, known as the resistance matrix. Coverage of later topics include Laplacian eigenvalues of threshold graphs, the positive definite completion problem and matrix games based on a graph. Such an extensive coverage of the subject area provides a welcome prompt for further exploration. The inclusion of exercises enables practical learning throughout the book. In the new edition, a new chapter is added on the line graph of a tree, while some results in Chapter 6 on Perron-Frobenius theory are reo...
Bayesian Nonparametric Clustering for Positive Definite Matrices.
Cherian, Anoop; Morellas, Vassilios; Papanikolopoulos, Nikolaos
2016-05-01
Symmetric Positive Definite (SPD) matrices emerge as data descriptors in several applications of computer vision such as object tracking, texture recognition, and diffusion tensor imaging. Clustering these data matrices forms an integral part of these applications, for which soft-clustering algorithms (K-Means, expectation maximization, etc.) are generally used. As is well-known, these algorithms need the number of clusters to be specified, which is difficult when the dataset scales. To address this issue, we resort to the classical nonparametric Bayesian framework by modeling the data as a mixture model using the Dirichlet process (DP) prior. Since these matrices do not conform to the Euclidean geometry, rather belongs to a curved Riemannian manifold,existing DP models cannot be directly applied. Thus, in this paper, we propose a novel DP mixture model framework for SPD matrices. Using the log-determinant divergence as the underlying dissimilarity measure to compare these matrices, and further using the connection between this measure and the Wishart distribution, we derive a novel DPM model based on the Wishart-Inverse-Wishart conjugate pair. We apply this model to several applications in computer vision. Our experiments demonstrate that our model is scalable to the dataset size and at the same time achieves superior accuracy compared to several state-of-the-art parametric and nonparametric clustering algorithms.
Energy Technology Data Exchange (ETDEWEB)
Bourget, Antoine; Troost, Jan [Laboratoire de Physique Théorique, École Normale Supérieure, 24 rue Lhomond, 75005 Paris (France)
2016-03-23
We construct a covariant generating function for the spectrum of chiral primaries of symmetric orbifold conformal field theories with N=(4,4) supersymmetry in two dimensions. For seed target spaces K3 and T{sup 4}, the generating functions capture the SO(21) and SO(5) representation theoretic content of the chiral ring respectively. Via string dualities, we relate the transformation properties of the chiral ring under these isometries of the moduli space to the Lorentz covariance of perturbative string partition functions in flat space.
International Nuclear Information System (INIS)
Aizawa, N; Chakrabarti, R; Mohammed, S S Naina; Segar, J
2007-01-01
Representations of the quantum superalgebra U q [osp(1/2)] and their relations to the basic hypergeometric functions are investigated. We first establish Clebsch-Gordan decomposition for the superalgebra U q [osp(1/2)] in which the representations having no classical counterparts are incorporated. Formulae for these Clebsch-Gordan coefficients are derived, and is observed that they may be expressed in terms of the Q-Hahn polynomials. We next investigate representations of the quantum supergroup OSp q (1/2) which are not well defined in the classical limit. Employing the universal T-matrix, the representation matrices are obtained explicitly, and found to be related to the little Q-Jacobi polynomials. Characteristically, the relation Q = -q is satisfied in all cases. Using the Clebsch-Gordan coefficients derived here, we construct new noncommutative spaces that are covariant under the coaction of the even-dimensional representations of the quantum supergroup OSp q (1/2)
GLq(N)-covariant quantum algebras and covariant differential calculus
International Nuclear Information System (INIS)
Isaev, A.P.; Pyatov, P.N.
1992-01-01
GL q (N)-covariant quantum algebras with generators satisfying quadratic polynomial relations are considered. It is that, up to some innessential arbitrariness, there are only two kinds of such quantum algebras, namely, the algebras with q-deformed commutation and q-deformed anticommutation relations. 25 refs
Introduction to covariant formulation of superstring (field) theory
International Nuclear Information System (INIS)
Anon.
1987-01-01
The author discusses covariant formulation of superstring theories based on BRS invariance. New formulation of superstring was constructed by Green and Schwarz in the light-cone gauge first and then a covariant action was discovered. The covariant action has some interesting geometrical interpretation, however, covariant quantizations are difficult to perform because of existence of local supersymmetries. Introducing extra variables into the action, a modified action has been proposed. However, it would be difficult to prescribe constraints to define a physical subspace, or to reproduce the correct physical spectrum. Hence the old formulation, i.e., the Neveu-Schwarz-Ramond (NSR) model for covariant quantization is used. The author begins by quantizing the NSR model in a covariant way using BRS charges. Then the author discusses the field theory of (free) superstring
Graphical representation of covariant-contravariant modal formulae
Directory of Open Access Journals (Sweden)
Miguel Palomino
2011-08-01
Full Text Available Covariant-contravariant simulation is a combination of standard (covariant simulation, its contravariant counterpart and bisimulation. We have previously studied its logical characterization by means of the covariant-contravariant modal logic. Moreover, we have investigated the relationships between this model and that of modal transition systems, where two kinds of transitions (the so-called may and must transitions were combined in order to obtain a simple framework to express a notion of refinement over state-transition models. In a classic paper, Boudol and Larsen established a precise connection between the graphical approach, by means of modal transition systems, and the logical approach, based on Hennessy-Milner logic without negation, to system specification. They obtained a (graphical representation theorem proving that a formula can be represented by a term if, and only if, it is consistent and prime. We show in this paper that the formulae from the covariant-contravariant modal logic that admit a "graphical" representation by means of processes, modulo the covariant-contravariant simulation preorder, are also the consistent and prime ones. In order to obtain the desired graphical representation result, we first restrict ourselves to the case of covariant-contravariant systems without bivariant actions. Bivariant actions can be incorporated later by means of an encoding that splits each bivariant action into its covariant and its contravariant parts.
Bayesian Noise Estimation for Non-ideal Cosmic Microwave Background Experiments
Wehus, I. K.; Næss, S. K.; Eriksen, H. K.
2012-03-01
We describe a Bayesian framework for estimating the time-domain noise covariance of cosmic microwave background (CMB) observations, typically parameterized in terms of a 1/f frequency profile. This framework is based on the Gibbs sampling algorithm, which allows for exact marginalization over nuisance parameters through conditional probability distributions. In this paper, we implement support for gaps in the data streams and marginalization over fixed time-domain templates, and also outline how to marginalize over confusion from CMB fluctuations, which may be important for high signal-to-noise experiments. As a by-product of the method, we obtain proper constrained realizations, which themselves can be useful for map making. To validate the algorithm, we demonstrate that the reconstructed noise parameters and corresponding uncertainties are unbiased using simulated data. The CPU time required to process a single data stream of 100,000 samples with 1000 samples removed by gaps is 3 s if only the maximum posterior parameters are required, and 21 s if one also wants to obtain the corresponding uncertainties by Gibbs sampling.
BAYESIAN NOISE ESTIMATION FOR NON-IDEAL COSMIC MICROWAVE BACKGROUND EXPERIMENTS
International Nuclear Information System (INIS)
Wehus, I. K.; Næss, S. K.; Eriksen, H. K.
2012-01-01
We describe a Bayesian framework for estimating the time-domain noise covariance of cosmic microwave background (CMB) observations, typically parameterized in terms of a 1/f frequency profile. This framework is based on the Gibbs sampling algorithm, which allows for exact marginalization over nuisance parameters through conditional probability distributions. In this paper, we implement support for gaps in the data streams and marginalization over fixed time-domain templates, and also outline how to marginalize over confusion from CMB fluctuations, which may be important for high signal-to-noise experiments. As a by-product of the method, we obtain proper constrained realizations, which themselves can be useful for map making. To validate the algorithm, we demonstrate that the reconstructed noise parameters and corresponding uncertainties are unbiased using simulated data. The CPU time required to process a single data stream of 100,000 samples with 1000 samples removed by gaps is 3 s if only the maximum posterior parameters are required, and 21 s if one also wants to obtain the corresponding uncertainties by Gibbs sampling.
BAYESIAN NOISE ESTIMATION FOR NON-IDEAL COSMIC MICROWAVE BACKGROUND EXPERIMENTS
Energy Technology Data Exchange (ETDEWEB)
Wehus, I. K. [Theoretical Physics, Imperial College London, London SW7 2AZ (United Kingdom); Naess, S. K.; Eriksen, H. K., E-mail: i.k.wehus@fys.uio.no, E-mail: sigurdkn@astro.uio.no, E-mail: h.k.k.eriksen@astro.uio.no [Institute of Theoretical Astrophysics, University of Oslo, P.O. Box 1029, Blindern, N-0315 Oslo (Norway)
2012-03-01
We describe a Bayesian framework for estimating the time-domain noise covariance of cosmic microwave background (CMB) observations, typically parameterized in terms of a 1/f frequency profile. This framework is based on the Gibbs sampling algorithm, which allows for exact marginalization over nuisance parameters through conditional probability distributions. In this paper, we implement support for gaps in the data streams and marginalization over fixed time-domain templates, and also outline how to marginalize over confusion from CMB fluctuations, which may be important for high signal-to-noise experiments. As a by-product of the method, we obtain proper constrained realizations, which themselves can be useful for map making. To validate the algorithm, we demonstrate that the reconstructed noise parameters and corresponding uncertainties are unbiased using simulated data. The CPU time required to process a single data stream of 100,000 samples with 1000 samples removed by gaps is 3 s if only the maximum posterior parameters are required, and 21 s if one also wants to obtain the corresponding uncertainties by Gibbs sampling.
Estimated correlation matrices and portfolio optimization
Pafka, Szilárd; Kondor, Imre
2004-11-01
Correlations of returns on various assets play a central role in financial theory and also in many practical applications. From a theoretical point of view, the main interest lies in the proper description of the structure and dynamics of correlations, whereas for the practitioner the emphasis is on the ability of the models to provide adequate inputs for the numerous portfolio and risk management procedures used in the financial industry. The theory of portfolios, initiated by Markowitz, has suffered from the “curse of dimensions” from the very outset. Over the past decades a large number of different techniques have been developed to tackle this problem and reduce the effective dimension of large bank portfolios, but the efficiency and reliability of these procedures are extremely hard to assess or compare. In this paper, we propose a model (simulation)-based approach which can be used for the systematical testing of all these dimensional reduction techniques. To illustrate the usefulness of our framework, we develop several toy models that display some of the main characteristic features of empirical correlations and generate artificial time series from them. Then, we regard these time series as empirical data and reconstruct the corresponding correlation matrices which will inevitably contain a certain amount of noise, due to the finiteness of the time series. Next, we apply several correlation matrix estimators and dimension reduction techniques introduced in the literature and/or applied in practice. As in our artificial world the only source of error is the finite length of the time series and, in addition, the “true” model, hence also the “true” correlation matrix, are precisely known, therefore in sharp contrast with empirical studies, we can precisely compare the performance of the various noise reduction techniques. One of our recurrent observations is that the recently introduced filtering technique based on random matrix theory performs
Blind Identification of FIR Channels in the Presence of Unknown Noise
Directory of Open Access Journals (Sweden)
Kon Max Wong
2007-01-01
Full Text Available Blind channel identification techniques based on second-order statistics (SOS of the received data have been a topic of active research in recent years. Among the most popular is the subspace method (SS proposed by Moulines et al. (1995. It has good performance when the channel output is corrupted by white noise. However, when the channel noise is correlated and unknown as is often encountered in practice, the performance of the SS method degrades severely. In this paper, we address the problem of estimating FIR channels in the presence of arbitrarily correlated noise whose covariance matrix is unknown. We propose several algorithms according to the different available system resources: (1 when only one receiving antenna is available, by upsampling the output, we develop the maximum a posteriori (MAP algorithm for which a simple criterion is obtained and an efficient implementation algorithm is developed; (2 when two receiving antennae are available, by upsampling both the outputs and utilizing canonical correlation decomposition (CCD to obtain the subspaces, we present two algorithms (CCD-SS and CCD-ML to blindly estimate the channels. Our algorithms perform well in unknown noise environment and outperform existing methods proposed for similar scenarios.
Mahalanobis Distance Based Iterative Closest Point
DEFF Research Database (Denmark)
Hansen, Mads Fogtmann; Blas, Morten Rufus; Larsen, Rasmus
2007-01-01
the notion of a mahalanobis distance map upon a point set with associated covariance matrices which in addition to providing correlation weighted distance implicitly provides a method for assigning correspondence during alignment. This distance map provides an easy formulation of the ICP problem that permits...... a fast optimization. Initially, the covariance matrices are set to the identity matrix, and all shapes are aligned to a randomly selected shape (equivalent to standard ICP). From this point the algorithm iterates between the steps: (a) obtain mean shape and new estimates of the covariance matrices from...... the aligned shapes, (b) align shapes to the mean shape. Three different methods for estimating the mean shape with associated covariance matrices are explored in the paper. The proposed methods are validated experimentally on two separate datasets (IMM face dataset and femur-bones). The superiority of ICP...
On Skew Circulant Type Matrices Involving Any Continuous Fibonacci Numbers
Directory of Open Access Journals (Sweden)
Zhaolin Jiang
2014-01-01
inverse matrices of them by constructing the transformation matrices. Furthermore, the maximum column sum matrix norm, the spectral norm, the Euclidean (or Frobenius norm, and the maximum row sum matrix norm and bounds for the spread of these matrices are given, respectively.
Immanant Conversion on Symmetric Matrices
Directory of Open Access Journals (Sweden)
Purificação Coelho M.
2014-01-01
Full Text Available Letr Σn(C denote the space of all n χ n symmetric matrices over the complex field C. The main objective of this paper is to prove that the maps Φ : Σn(C -> Σn (C satisfying for any fixed irre- ducible characters X, X' -SC the condition dx(A +aB = dχ·(Φ(Α + αΦ(Β for all matrices A,В ε Σ„(С and all scalars a ε C are automatically linear and bijective. As a corollary of the above result we characterize all such maps Φ acting on ΣИ(С.
Directory of Open Access Journals (Sweden)
Jianxin Feng
2014-01-01
Full Text Available The recursive estimation problem is studied for a class of uncertain dynamical systems with different delay rates sensor network and autocorrelated process noises. The process noises are assumed to be autocorrelated across time and the autocorrelation property is described by the covariances between different time instants. The system model under consideration is subject to multiplicative noises or stochastic uncertainties. The sensor delay phenomenon occurs in a random way and each sensor in the sensor network has an individual delay rate which is characterized by a binary switching sequence obeying a conditional probability distribution. By using the orthogonal projection theorem and an innovation analysis approach, the desired recursive robust estimators including recursive robust filter, predictor, and smoother are obtained. Simulation results are provided to demonstrate the effectiveness of the proposed approaches.
Covariant single-hole optical potential
International Nuclear Information System (INIS)
Kam, J. de
1982-01-01
In this investigation a covariant optical potential model is constructed for scattering processes of mesons from nuclei in which the meson interacts repeatedly with one of the target nucleons. The nuclear binding interactions in the intermediate scattering state are consistently taken into account. In particular for pions and K - projectiles this is important in view of the strong energy dependence of the elementary projectile-nucleon amplitude. Furthermore, this optical potential satisfies unitarity and relativistic covariance. The starting point in our discussion is the three-body model for the optical potential. To obtain a practical covariant theory I formulate the three-body model as a relativistic quasi two-body problem. Expressions for the transition interactions and propagators in the quasi two-body equations are found by imposing the correct s-channel unitarity relations and by using dispersion integrals. This is done in such a way that the correct non-relativistic limit is obtained, avoiding clustering problems. Corrections to the quasi two-body treatment from the Pauli principle and the required ground-state exclusion are taken into account. The covariant equations that we arrive at are amenable to practical calculations. (orig.)
The 'golden' matrices and a new kind of cryptography
International Nuclear Information System (INIS)
Stakhov, A.P.
2007-01-01
We consider a new class of square matrices called the 'golden' matrices. They are a generalization of the classical Fibonacci Q-matrix for continuous domain. The 'golden' matrices can be used for creation of a new kind of cryptography called the 'golden' cryptography. The method is very fast and simple for technical realization and can be used for cryptographic protection of digital signals (telecommunication and measurement systems)
Advanced incomplete factorization algorithms for Stiltijes matrices
Energy Technology Data Exchange (ETDEWEB)
Il`in, V.P. [Siberian Division RAS, Novosibirsk (Russian Federation)
1996-12-31
The modern numerical methods for solving the linear algebraic systems Au = f with high order sparse matrices A, which arise in grid approximations of multidimensional boundary value problems, are based mainly on accelerated iterative processes with easily invertible preconditioning matrices presented in the form of approximate (incomplete) factorization of the original matrix A. We consider some recent algorithmic approaches, theoretical foundations, experimental data and open questions for incomplete factorization of Stiltijes matrices which are {open_quotes}the best{close_quotes} ones in the sense that they have the most advanced results. Special attention is given to solving the elliptic differential equations with strongly variable coefficients, singular perturbated diffusion-convection and parabolic equations.
Marroig, G; Cheverud, J M
2001-12-01
Similarity of genetic and phenotypic variation patterns among populations is important for making quantitative inferences about past evolutionary forces acting to differentiate populations and for evaluating the evolution of relationships among traits in response to new functional and developmental relationships. Here, phenotypic co variance and correlation structure is compared among Platyrrhine Neotropical primates. Comparisons range from among species within a genus to the superfamily level. Matrix correlation followed by Mantel's test and vector correlation among responses to random natural selection vectors (random skewers) were used to compare correlation and variance/covariance matrices of 39 skull traits. Sampling errors involved in matrix estimates were taken into account in comparisons using matrix repeatability to set upper limits for each pairwise comparison. Results indicate that covariance structure is not strictly constant but that the amount of variance pattern divergence observed among taxa is generally low and not associated with taxonomic distance. Specific instances of divergence are identified. There is no correlation between the amount of divergence in covariance patterns among the 16 genera and their phylogenetic distance derived from a conjoint analysis of four already published nuclear gene datasets. In contrast, there is a significant correlation between phylogenetic distance and morphological distance (Mahalanobis distance among genus centroids). This result indicates that while the phenotypic means were evolving during the last 30 millions years of New World monkey evolution, phenotypic covariance structures of Neotropical primate skulls have remained relatively consistent. Neotropical primates can be divided into four major groups based on their feeding habits (fruit-leaves, seed-fruits, insect-fruits, and gum-insect-fruits). Differences in phenotypic covariance structure are correlated with differences in feeding habits, indicating
On the Eigenvalues and Eigenvectors of Block Triangular Preconditioned Block Matrices
Pestana, Jennifer
2014-01-01
Block lower triangular matrices and block upper triangular matrices are popular preconditioners for 2×2 block matrices. In this note we show that a block lower triangular preconditioner gives the same spectrum as a block upper triangular preconditioner and that the eigenvectors of the two preconditioned matrices are related. © 2014 Society for Industrial and Applied Mathematics.
On Investigating GMRES Convergence using Unitary Matrices
Czech Academy of Sciences Publication Activity Database
Duintjer Tebbens, Jurjen; Meurant, G.; Sadok, H.; Strakoš, Z.
2014-01-01
Roč. 450, 1 June (2014), s. 83-107 ISSN 0024-3795 Grant - others:GA AV ČR(CZ) M100301201; GA MŠk(CZ) LL1202 Institutional support: RVO:67985807 Keywords : GMRES convergence * unitary matrices * unitary spectra * normal matrices * Krylov residual subspace * Schur parameters Subject RIV: BA - General Mathematics Impact factor: 0.939, year: 2014
Nuclear data covariances in the Indian context
International Nuclear Information System (INIS)
Ganesan, S.
2014-01-01
The topic of covariances is recognized as an important part of several ongoing nuclear data science activities, since 2007, in the Nuclear Data Physics Centre of India (NDPCI). A Phase-1 project in collaboration with the Statistics department in Manipal University, Karnataka (Prof. K.M. Prasad and Prof. S. Nair) on nuclear data covariances was executed successfully during 2007-2011 period. In Phase-I, the NDPCI has conducted three national Theme meetings sponsored by the DAE-BRNS in 2008, 2010 and 2013 on nuclear data covariances. In Phase-1, the emphasis was on a thorough basic understanding of the concept of covariances including assigning uncertainties to experimental data in terms of partial errors and micro correlations, through a study and a detailed discussion of open literature. Towards the end of Phase-1, measurements and a first time covariance analysis of cross-sections for 58 Ni (n, p) 58 Co reaction measured in Mumbai Pelletron accelerator using 7 Li (p,n) reactions as neutron source in the MeV energy region were performed under a PhD programme on nuclear data covariances in which enrolled are two students, Shri B.S. Shivashankar and Ms. Shanti Sheela. India is also successfully evolving a team of young researchers to code nuclear data of uncertainties, with the perspectives on covariances, in the IAEA-EXFOR format. A Phase-II DAE-BRNS-NDPCI proposal of project at Manipal has been submitted and the proposal is undergoing a peer-review at this time. In Phase-2, modern nuclear data evaluation techniques that including covariances will be further studied as a research and development effort, as a first time effort. These efforts include the use of techniques such as that of the Kalman filter. Presently, a 48 hours lecture series on treatment of errors and their propagation is being formulated under auspices of the Homi Bhabha National Institute. The talk describes the progress achieved thus far in the learning curve of the above-mentioned and exciting
Lee, Ken Voon
2013-04-01
The purpose of this action research was to increase the mastery level of Form Five Social Science students in Tawau II National Secondary School in the operations of addition, subtraction and multiplication of matrices in Mathematics. A total of 30 students were involved. Preliminary findings through the analysis of pre-test results and questionnaire had identified the main problem faced in which the students felt confused with the application of principles of the operations of matrices when performing these operations. Therefore, an action research was conducted using an intervention programme called "G.P.S Matrices" to overcome the problem. This programme was divided into three phases. 'Gift of Matrices' phase aimed at forming matrix teaching aids. The second and third phases were 'Positioning the Elements of Matrices' and 'Strenghtening the Concept of Matrices'. These two phases were aimed at increasing the level of understanding and memory of the students towards the principles of matrix operations. Besides, this third phase was also aimed at creating an interesting learning environment. A comparison between the results of pre-test and post-test had shown a remarkable improvement in students' performances after implementing the programme. In addition, the analysis of interview findings also indicated a positive feedback on the changes in students' attitude, particularly in the aspect of students' understanding level. Moreover, the level of students' memory also increased following the use of the concrete matrix teaching aids created in phase one. Besides, teachers felt encouraging when conducive learning environment was created through students' presentation activity held in third phase. Furthermore, students were voluntarily involved in these student-centred activities. In conclusion, this research findings showed an increase in the mastery level of students in these three matrix operations and thus the objective of the research had been achieved.
Photonic quantum simulator for unbiased phase covariant cloning
Knoll, Laura T.; López Grande, Ignacio H.; Larotonda, Miguel A.
2018-01-01
We present the results of a linear optics photonic implementation of a quantum circuit that simulates a phase covariant cloner, using two different degrees of freedom of a single photon. We experimentally simulate the action of two mirrored 1→ 2 cloners, each of them biasing the cloned states into opposite regions of the Bloch sphere. We show that by applying a random sequence of these two cloners, an eavesdropper can mitigate the amount of noise added to the original input state and therefore, prepare clones with no bias, but with the same individual fidelity, masking its presence in a quantum key distribution protocol. Input polarization qubit states are cloned into path qubit states of the same photon, which is identified as a potential eavesdropper in a quantum key distribution protocol. The device has the flexibility to produce mirrored versions that optimally clone states on either the northern or southern hemispheres of the Bloch sphere, as well as to simulate optimal and non-optimal cloning machines by tuning the asymmetry on each of the cloning machines.
AFCI-2.0 Neutron Cross Section Covariance Library
Energy Technology Data Exchange (ETDEWEB)
Herman, M.; Herman, M; Oblozinsky, P.; Mattoon, C.M.; Pigni, M.; Hoblit, S.; Mughabghab, S.F.; Sonzogni, A.; Talou, P.; Chadwick, M.B.; Hale, G.M.; Kahler, A.C.; Kawano, T.; Little, R.C.; Yount, P.G.
2011-03-01
The cross section covariance library has been under development by BNL-LANL collaborative effort over the last three years. The project builds on two covariance libraries developed earlier, with considerable input from BNL and LANL. In 2006, international effort under WPEC Subgroup 26 produced BOLNA covariance library by putting together data, often preliminary, from various sources for most important materials for nuclear reactor technology. This was followed in 2007 by collaborative effort of four US national laboratories to produce covariances, often of modest quality - hence the name low-fidelity, for virtually complete set of materials included in ENDF/B-VII.0. The present project is focusing on covariances of 4-5 major reaction channels for 110 materials of importance for power reactors. The work started under Global Nuclear Energy Partnership (GNEP) in 2008, which changed to Advanced Fuel Cycle Initiative (AFCI) in 2009. With the 2011 release the name has changed to the Covariance Multigroup Matrix for Advanced Reactor Applications (COMMARA) version 2.0. The primary purpose of the library is to provide covariances for AFCI data adjustment project, which is focusing on the needs of fast advanced burner reactors. Responsibility of BNL was defined as developing covariances for structural materials and fission products, management of the library and coordination of the work; LANL responsibility was defined as covariances for light nuclei and actinides. The COMMARA-2.0 covariance library has been developed by BNL-LANL collaboration for Advanced Fuel Cycle Initiative applications over the period of three years, 2008-2010. It contains covariances for 110 materials relevant to fast reactor R&D. The library is to be used together with the ENDF/B-VII.0 central values of the latest official release of US files of evaluated neutron cross sections. COMMARA-2.0 library contains neutron cross section covariances for 12 light nuclei (coolants and moderators), 78 structural
AFCI-2.0 Neutron Cross Section Covariance Library
International Nuclear Information System (INIS)
Herman, M.; Oblozinsky, P.; Mattoon, C.M.; Pigni, M.; Hoblit, S.; Mughabghab, S.F.; Sonzogni, A.; Talou, P.; Chadwick, M.B.; Hale, G.M.; Kahler, A.C.; Kawano, T.; Little, R.C.; Yount, P.G.
2011-01-01
The cross section covariance library has been under development by BNL-LANL collaborative effort over the last three years. The project builds on two covariance libraries developed earlier, with considerable input from BNL and LANL. In 2006, international effort under WPEC Subgroup 26 produced BOLNA covariance library by putting together data, often preliminary, from various sources for most important materials for nuclear reactor technology. This was followed in 2007 by collaborative effort of four US national laboratories to produce covariances, often of modest quality - hence the name low-fidelity, for virtually complete set of materials included in ENDF/B-VII.0. The present project is focusing on covariances of 4-5 major reaction channels for 110 materials of importance for power reactors. The work started under Global Nuclear Energy Partnership (GNEP) in 2008, which changed to Advanced Fuel Cycle Initiative (AFCI) in 2009. With the 2011 release the name has changed to the Covariance Multigroup Matrix for Advanced Reactor Applications (COMMARA) version 2.0. The primary purpose of the library is to provide covariances for AFCI data adjustment project, which is focusing on the needs of fast advanced burner reactors. Responsibility of BNL was defined as developing covariances for structural materials and fission products, management of the library and coordination of the work; LANL responsibility was defined as covariances for light nuclei and actinides. The COMMARA-2.0 covariance library has been developed by BNL-LANL collaboration for Advanced Fuel Cycle Initiative applications over the period of three years, 2008-2010. It contains covariances for 110 materials relevant to fast reactor R and D. The library is to be used together with the ENDF/B-VII.0 central values of the latest official release of US files of evaluated neutron cross sections. COMMARA-2.0 library contains neutron cross section covariances for 12 light nuclei (coolants and moderators), 78
Improved efficiency of maximum likelihood analysis of time series with temporally correlated errors
Langbein, John
2017-08-01
Most time series of geophysical phenomena have temporally correlated errors. From these measurements, various parameters are estimated. For instance, from geodetic measurements of positions, the rates and changes in rates are often estimated and are used to model tectonic processes. Along with the estimates of the size of the parameters, the error in these parameters needs to be assessed. If temporal correlations are not taken into account, or each observation is assumed to be independent, it is likely that any estimate of the error of these parameters will be too low and the estimated value of the parameter will be biased. Inclusion of better estimates of uncertainties is limited by several factors, including selection of the correct model for the background noise and the computational requirements to estimate the parameters of the selected noise model for cases where there are numerous observations. Here, I address the second problem of computational efficiency using maximum likelihood estimates (MLE). Most geophysical time series have background noise processes that can be represented as a combination of white and power-law noise, 1/f^{α } with frequency, f. With missing data, standard spectral techniques involving FFTs are not appropriate. Instead, time domain techniques involving construction and inversion of large data covariance matrices are employed. Bos et al. (J Geod, 2013. doi: 10.1007/s00190-012-0605-0) demonstrate one technique that substantially increases the efficiency of the MLE methods, yet is only an approximate solution for power-law indices >1.0 since they require the data covariance matrix to be Toeplitz. That restriction can be removed by simply forming a data filter that adds noise processes rather than combining them in quadrature. Consequently, the inversion of the data covariance matrix is simplified yet provides robust results for a wider range of power-law indices.
Predicting Covariance Matrices with Financial Conditions Indexes
A. Opschoor (Anne); D.J.C. van Dijk (Dick); M. van der Wel (Michel)
2013-01-01
textabstractWe model the impact of financial conditions on asset market volatility and correlation. We propose extensions of (factor-)GARCH models for volatility and DCC models for correlation that allow for including indexes that measure financial conditions. In our empirical application we
Dias, Adriano; Cordeiro, Ricardo
2007-07-01
Noise is the most frequent type of occupational exposure and can lead to both auditory and extra-auditory dysfunction as well as increasing the risk of work accidents. The purpose of this study was to estimate the attributable fraction of work accidents related to occupational noise exposure in a medium-sized city in Southeast Brazil. In this hospital-based case-control study, including 600 cases and 822 controls, the odds ratio of work accidents (controlled for several covariables) was obtained classifying occupational noise exposure into four levels and determining the prevalence at each level. Based on these data, the calculated attributable fraction was 0.3041 (95%CI: 0.2341-0.3676), i.e., 30% of work accidents in the study area were statistically associated with occupational noise exposure. The authors discuss the causes of this association and the implications for the prevention of work accidents.
Central subspace dimensionality reduction using covariance operators.
Kim, Minyoung; Pavlovic, Vladimir
2011-04-01
We consider the task of dimensionality reduction informed by real-valued multivariate labels. The problem is often treated as Dimensionality Reduction for Regression (DRR), whose goal is to find a low-dimensional representation, the central subspace, of the input data that preserves the statistical correlation with the targets. A class of DRR methods exploits the notion of inverse regression (IR) to discover central subspaces. Whereas most existing IR techniques rely on explicit output space slicing, we propose a novel method called the Covariance Operator Inverse Regression (COIR) that generalizes IR to nonlinear input/output spaces without explicit target slicing. COIR's unique properties make DRR applicable to problem domains with high-dimensional output data corrupted by potentially significant amounts of noise. Unlike recent kernel dimensionality reduction methods that employ iterative nonconvex optimization, COIR yields a closed-form solution. We also establish the link between COIR, other DRR techniques, and popular supervised dimensionality reduction methods, including canonical correlation analysis and linear discriminant analysis. We then extend COIR to semi-supervised settings where many of the input points lack their labels. We demonstrate the benefits of COIR on several important regression problems in both fully supervised and semi-supervised settings.
International Nuclear Information System (INIS)
Fu, C.Y.; Hetrick, D.M.
1982-01-01
Recent ratio data, with carefully evaluated covariances, were combined with eleven of the ENDF/B-V dosimetry cross sections using the generalized least-squares method. The purpose was to improve these evaluated cross sections and covariances, as well as to generate values for the cross-reaction covariances. The results represent improved cross sections as well as realistic and usable covariances. The latter are necessary for meaningful intergral-differential comparisons and for spectrum unfolding
Covariance problem in two-dimensional quantum chromodynamics
International Nuclear Information System (INIS)
Hagen, C.R.
1979-01-01
The problem of covariance in the field theory of a two-dimensional non-Abelian gauge field is considered. Since earlier work has shown that covariance fails (in charged sectors) for the Schwinger model, particular attention is given to an evaluation of the role played by the non-Abelian nature of the fields. In contrast to all earlier attempts at this problem, it is found that the potential covariance-breaking terms are identical to those found in the Abelian theory provided that one expresses them in terms of the total (i.e., conserved) current operator. The question of covariance is thus seen to reduce in all cases to a determination as to whether there exists a conserved global charge in the theory. Since the charge operator in the Schwinger model is conserved only in neutral sectors, one is thereby led to infer a probable failure of covariance in the non-Abelian theory, but one which is identical to that found for the U(1) case
Schroedinger covariance states in anisotropic waveguides
International Nuclear Information System (INIS)
Angelow, A.; Trifonov, D.
1995-03-01
In this paper Squeezed and Covariance States based on Schroedinger inequality and their connection with other nonclassical states are considered for particular case of anisotropic waveguide in LiNiO 3 . Here, the problem of photon creation and generation of squeezed and Schroedinger covariance states in optical waveguides is solved in two steps: 1. Quantization of electromagnetic field is provided in the presence of dielectric waveguide using normal-mode expansion. The photon creation and annihilation operators are introduced, expanding the solution A-vector(r-vector,t) in a series in terms of the Sturm - Liouville mode-functions. 2. In terms of these operators the Hamiltonian of the field in a nonlinear waveguide is derived. For such Hamiltonian we construct the covariance states as stable (with nonzero covariance), which minimize the Schroedinger uncertainty relation. The evolutions of the three second momenta of q-circumflex j and p-circumflex j are calculated. For this Hamiltonian all three momenta are expressed in terms of one real parameters s only. It is found out how covariance, via this parameter s, depends on the waveguide profile n(x,y), on the mode-distributions u-vector j (x,y), and on the waveguide phase mismatching Δβ. (author). 37 refs
Form of the manifestly covariant Lagrangian
Johns, Oliver Davis
1985-10-01
The preferred form for the manifestly covariant Lagrangian function of a single, charged particle in a given electromagnetic field is the subject of some disagreement in the textbooks. Some authors use a ``homogeneous'' Lagrangian and others use a ``modified'' form in which the covariant Hamiltonian function is made to be nonzero. We argue in favor of the ``homogeneous'' form. We show that the covariant Lagrangian theories can be understood only if one is careful to distinguish quantities evaluated on the varied (in the sense of the calculus of variations) world lines from quantities evaluated on the unvaried world lines. By making this distinction, we are able to derive the Hamilton-Jacobi and Klein-Gordon equations from the ``homogeneous'' Lagrangian, even though the covariant Hamiltonian function is identically zero on all world lines. The derivation of the Klein-Gordon equation in particular gives Lagrangian theoretical support to the derivations found in standard quantum texts, and is also shown to be consistent with the Feynman path-integral method. We conclude that the ``homogeneous'' Lagrangian is a completely adequate basis for covariant Lagrangian theory both in classical and quantum mechanics. The article also explores the analogy with the Fermat theorem of optics, and illustrates a simple invariant notation for the Lagrangian and other four-vector equations.
Determination of covariant Schwinger terms in anomalous gauge theories
International Nuclear Information System (INIS)
Kelnhofer, G.
1991-01-01
A functional integral method is used to determine equal time commutators between the covariant currents and the covariant Gauss-law operators in theories which are affected by an anomaly. By using a differential geometrical setup we show how the derivation of consistent- and covariant Schwinger terms can be understood on an equal footing. We find a modified consistency condition for the covariant anomaly. As a by-product the Bardeen-Zumino functional, which relates consistent and covariant anomalies, can be interpreted as connection on a certain line bundle over all gauge potentials. Finally the covariant commutator anomalies are calculated for the two- and four dimensional case. (orig.)
Cross-population myelination covariance of human cerebral cortex.
Ma, Zhiwei; Zhang, Nanyin
2017-09-01
Cross-population covariance of brain morphometric quantities provides a measure of interareal connectivity, as it is believed to be determined by the coordinated neurodevelopment of connected brain regions. Although useful, structural covariance analysis predominantly employed bulky morphological measures with mixed compartments, whereas studies of the structural covariance of any specific subdivisions such as myelin are rare. Characterizing myelination covariance is of interest, as it will reveal connectivity patterns determined by coordinated development of myeloarchitecture between brain regions. Using myelin content MRI maps from the Human Connectome Project, here we showed that the cortical myelination covariance was highly reproducible, and exhibited a brain organization similar to that previously revealed by other connectivity measures. Additionally, the myelination covariance network shared common topological features of human brain networks such as small-worldness. Furthermore, we found that the correlation between myelination covariance and resting-state functional connectivity (RSFC) was uniform within each resting-state network (RSN), but could considerably vary across RSNs. Interestingly, this myelination covariance-RSFC correlation was appreciably stronger in sensory and motor networks than cognitive and polymodal association networks, possibly due to their different circuitry structures. This study has established a new brain connectivity measure specifically related to axons, and this measure can be valuable to investigating coordinated myeloarchitecture development. Hum Brain Mapp 38:4730-4743, 2017. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.
CONVERGENCE OF POWERS OF CONTROLLABLE INTUITIONISTIC FUZZY MATRICES
Riyaz Ahmad Padder; P. Murugadas
2016-01-01
Convergences of powers of controllable intuitionistic fuzzy matrices have been stud¬ied. It is shown that they oscillate with period equal to 2, in general. Some equalities and sequences of inequalities about powers of controllable intuitionistic fuzzy matrices have been obtained.
Covariant extensions and the nonsymmetric unified field
International Nuclear Information System (INIS)
Borchsenius, K.
1976-01-01
The problem of generally covariant extension of Lorentz invariant field equations, by means of covariant derivatives extracted from the nonsymmetric unified field, is considered. It is shown that the contracted curvature tensor can be expressed in terms of a covariant gauge derivative which contains the gauge derivative corresponding to minimal coupling, if the universal constant p, characterizing the nonsymmetric theory, is fixed in terms of Planck's constant and the elementary quantum of charge. By this choice the spinor representation of the linear connection becomes closely related to the spinor affinity used by Infeld and Van Der Waerden (Sitzungsber. Preuss. Akad. Wiss. Phys. Math. Kl.; 9:380 (1933)) in their generally covariant formulation of Dirac's equation. (author)
Computing more proper covariances of energy dependent nuclear data
International Nuclear Information System (INIS)
Vanhanen, R.
2016-01-01
Highlights: • We present conditions for covariances of energy dependent nuclear data to be proper. • We provide methods to detect non-positive and inconsistent covariances in ENDF-6 format. • We propose methods to find nearby more proper covariances. • The methods can be used as a part of a quality assurance program. - Abstract: We present conditions for covariances of energy dependent nuclear data to be proper in the sense that the covariances are positive, i.e., its eigenvalues are non-negative, and consistent with respect to the sum rules of nuclear data. For the ENDF-6 format covariances we present methods to detect non-positive and inconsistent covariances. These methods would be useful as a part of a quality assurance program. We also propose methods that can be used to find nearby more proper energy dependent covariances. These methods can be used to remove unphysical components, while preserving most of the physical components. We consider several different senses in which the nearness can be measured. These methods could be useful if a re-evaluation of improper covariances is not feasible. Two practical examples are processed and analyzed. These demonstrate some of the properties of the methods. We also demonstrate that the ENDF-6 format covariances of linearly dependent nuclear data should usually be encoded with the derivation rules.
Loop diagrams without γ matrices
International Nuclear Information System (INIS)
McKeon, D.G.C.; Rebhan, A.
1993-01-01
By using a quantum-mechanical path integral to compute matrix elements of the form left-angle x|exp(-iHt)|y right-angle, radiative corrections in quantum-field theory can be evaluated without encountering loop-momentum integrals. In this paper we demonstrate how Dirac γ matrices that occur in the proper-time ''Hamiltonian'' H lead to the introduction of a quantum-mechanical path integral corresponding to a superparticle analogous to one proposed recently by Fradkin and Gitman. Direct evaluation of this path integral circumvents many of the usual algebraic manipulations of γ matrices in the computation of quantum-field-theoretical Green's functions involving fermions
Covariance Spectroscopy for Fissile Material Detection
International Nuclear Information System (INIS)
Trainham, Rusty; Tinsley, Jim; Hurley, Paul; Keegan, Ray
2009-01-01
Nuclear fission produces multiple prompt neutrons and gammas at each fission event. The resulting daughter nuclei continue to emit delayed radiation as neutrons boil off, beta decay occurs, etc. All of the radiations are causally connected, and therefore correlated. The correlations are generally positive, but when different decay channels compete, so that some radiations tend to exclude others, negative correlations could also be observed. A similar problem of reduced complexity is that of cascades radiation, whereby a simple radioactive decay produces two or more correlated gamma rays at each decay. Covariance is the usual means for measuring correlation, and techniques of covariance mapping may be useful to produce distinct signatures of special nuclear materials (SNM). A covariance measurement can also be used to filter data streams because uncorrelated signals are largely rejected. The technique is generally more effective than a coincidence measurement. In this poster, we concentrate on cascades and the covariance filtering problem
Optimal covariate designs theory and applications
Das, Premadhis; Mandal, Nripes Kumar; Sinha, Bikas Kumar
2015-01-01
This book primarily addresses the optimality aspects of covariate designs. A covariate model is a combination of ANOVA and regression models. Optimal estimation of the parameters of the model using a suitable choice of designs is of great importance; as such choices allow experimenters to extract maximum information for the unknown model parameters. The main emphasis of this monograph is to start with an assumed covariate model in combination with some standard ANOVA set-ups such as CRD, RBD, BIBD, GDD, BTIBD, BPEBD, cross-over, multi-factor, split-plot and strip-plot designs, treatment control designs, etc. and discuss the nature and availability of optimal covariate designs. In some situations, optimal estimations of both ANOVA and the regression parameters are provided. Global optimality and D-optimality criteria are mainly used in selecting the design. The standard optimality results of both discrete and continuous set-ups have been adapted, and several novel combinatorial techniques have been applied for...
Covariate Imbalance and Precision in Measuring Treatment Effects
Liu, Xiaofeng Steven
2011-01-01
Covariate adjustment can increase the precision of estimates by removing unexplained variance from the error in randomized experiments, although chance covariate imbalance tends to counteract the improvement in precision. The author develops an easy measure to examine chance covariate imbalance in randomization by standardizing the average…
Covariant description of Hamiltonian form for field dynamics
International Nuclear Information System (INIS)
Ozaki, Hiroshi
2005-01-01
Hamiltonian form of field dynamics is developed on a space-like hypersurface in space-time. A covariant Poisson bracket on the space-like hypersurface is defined and it plays a key role to describe every algebraic relation into a covariant form. It is shown that the Poisson bracket has the same symplectic structure that was brought in the covariant symplectic approach. An identity invariant under the canonical transformations is obtained. The identity follows a canonical equation in which the interaction Hamiltonian density generates a deformation of the space-like hypersurface. The equation just corresponds to the Yang-Feldman equation in the Heisenberg pictures in quantum field theory. By converting the covariant Poisson bracket on the space-like hypersurface to four-dimensional commutator, we can pass over to quantum field theory in the Heisenberg picture without spoiling the explicit relativistic covariance. As an example the canonical QCD is displayed in a covariant way on a space-like hypersurface
Classification en référence à une matrice stochastique
Verdun , Stéphane; Cariou , Véronique; Qannari , El Mostafa
2009-01-01
International audience; Etant donné un tableau de données X portant sur un ensemble de n objets, et une matrice stochastique S qui peut être assimilée à une matrice de transition d'une chaîne de Markov, nous proposons une méthode de partitionnement consistant à appliquer la matrice S sur X de manière itérative jusqu'à convergence. Les classes formant la partition sont déterminées à partir des états stationnaires de la matrice stochastique. Cette matrice stochastique peut être issue d'une matr...
2014-04-01
materials, the affinity ligand would need identification , as well as chemistries that graft the affinity ligand onto the surface of magnetic...ACTIVE CAPTURE MATRICES FOR THE DETECTION/ IDENTIFICATION OF PHARMACEUTICALS...6 As shown in Figure 2.3-1a, the spectra exhibit similar baselines and the spectral peaks lineup . Under these circumstances, the spectral
Pieciak, Tomasz; Aja-Fernandez, Santiago; Vegas-Sanchez-Ferrero, Gonzalo
2017-10-01
Parallel magnetic resonance imaging (pMRI) techniques have gained a great importance both in research and clinical communities recently since they considerably accelerate the image acquisition process. However, the image reconstruction algorithms needed to correct the subsampling artifacts affect the nature of noise, i.e., it becomes non-stationary. Some methods have been proposed in the literature dealing with the non-stationary noise in pMRI. However, their performance depends on information not usually available such as multiple acquisitions, receiver noise matrices, sensitivity coil profiles, reconstruction coefficients, or even biophysical models of the data. Besides, some methods show an undesirable granular pattern on the estimates as a side effect of local estimation. Finally, some methods make strong assumptions that just hold in the case of high signal-to-noise ratio (SNR), which limits their usability in real scenarios. We propose a new automatic noise estimation technique for non-stationary Rician noise that overcomes the aforementioned drawbacks. Its effectiveness is due to the derivation of a variance-stabilizing transformation designed to deal with any SNR. The method was compared to the main state-of-the-art methods in synthetic and real scenarios. Numerical results confirm the robustness of the method and its better performance for the whole range of SNRs.
Binary Positive Semidefinite Matrices and Associated Integer Polytopes
DEFF Research Database (Denmark)
Letchford, Adam N.; Sørensen, Michael Malmros
2012-01-01
We consider the positive semidefinite (psd) matrices with binary entries, along with the corresponding integer polytopes. We begin by establishing some basic properties of these matrices and polytopes. Then, we show that several families of integer polytopes in the literature-the cut, boolean qua...
Chain of matrices, loop equations and topological recursion
Orantin, Nicolas
2009-01-01
Random matrices are used in fields as different as the study of multi-orthogonal polynomials or the enumeration of discrete surfaces. Both of them are based on the study of a matrix integral. However, this term can be confusing since the definition of a matrix integral in these two applications is not the same. These two definitions, perturbative and non-perturbative, are discussed in this chapter as well as their relation. The so-called loop equations satisfied by integrals over random matrices coupled in chain is discussed as well as their recursive solution in the perturbative case when the matrices are Hermitean.
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
Zhao, Liang; Liao, Siyu; Wang, Yanzhi; Li, Zhe; Tang, Jian; Pan, Victor; Yuan, Bo
2017-01-01
Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neural networks with weight matrices of LDR matrices, referred as LDR neural networks, can achieve significant reduction in space and computational complexity while retaining high accuracy. We formally study LDR matrices in deep learning. First, we prove the universal approximation property of LDR neural networks with a ...
Parametric Covariance Model for Horizon-Based Optical Navigation
Hikes, Jacob; Liounis, Andrew J.; Christian, John A.
2016-01-01
This Note presents an entirely parametric version of the covariance for horizon-based optical navigation measurements. The covariance can be written as a function of only the spacecraft position, two sensor design parameters, the illumination direction, the size of the observed planet, the size of the lit arc to be used, and the total number of observed horizon points. As a result, one may now more clearly understand the sensitivity of horizon-based optical navigation performance as a function of these key design parameters, which is insight that was obscured in previous (and nonparametric) versions of the covariance. Finally, the new parametric covariance is shown to agree with both the nonparametric analytic covariance and results from a Monte Carlo analysis.
Activities on covariance estimation in Japanese Nuclear Data Committee
Energy Technology Data Exchange (ETDEWEB)
Shibata, Keiichi [Japan Atomic Energy Research Inst., Tokai, Ibaraki (Japan). Tokai Research Establishment
1997-03-01
Described are activities on covariance estimation in the Japanese Nuclear Data Committee. Covariances are obtained from measurements by using the least-squares methods. A simultaneous evaluation was performed to deduce covariances of fission cross sections of U and Pu isotopes. A code system, KALMAN, is used to estimate covariances of nuclear model calculations from uncertainties in model parameters. (author)
The Modern Origin of Matrices and Their Applications
Debnath, L.
2014-01-01
This paper deals with the modern development of matrices, linear transformations, quadratic forms and their applications to geometry and mechanics, eigenvalues, eigenvectors and characteristic equations with applications. Included are the representations of real and complex numbers, and quaternions by matrices, and isomorphism in order to show…
Flux Jacobian Matrices For Equilibrium Real Gases
Vinokur, Marcel
1990-01-01
Improved formulation includes generalized Roe average and extension to three dimensions. Flux Jacobian matrices derived for use in numerical solutions of conservation-law differential equations of inviscid flows of ideal gases extended to real gases. Real-gas formulation of these matrices retains simplifying assumptions of thermodynamic and chemical equilibrium, but adds effects of vibrational excitation, dissociation, and ionization of gas molecules via general equation of state.
Cross-covariance functions for multivariate geostatistics
Genton, Marc G.
2015-05-01
Continuously indexed datasets with multiple variables have become ubiquitous in the geophysical, ecological, environmental and climate sciences, and pose substantial analysis challenges to scientists and statisticians. For many years, scientists developed models that aimed at capturing the spatial behavior for an individual process; only within the last few decades has it become commonplace to model multiple processes jointly. The key difficulty is in specifying the cross-covariance function, that is, the function responsible for the relationship between distinct variables. Indeed, these cross-covariance functions must be chosen to be consistent with marginal covariance functions in such a way that the second-order structure always yields a nonnegative definite covariance matrix. We review the main approaches to building cross-covariance models, including the linear model of coregionalization, convolution methods, the multivariate Matérn and nonstationary and space-time extensions of these among others. We additionally cover specialized constructions, including those designed for asymmetry, compact support and spherical domains, with a review of physics-constrained models. We illustrate select models on a bivariate regional climate model output example for temperature and pressure, along with a bivariate minimum and maximum temperature observational dataset; we compare models by likelihood value as well as via cross-validation co-kriging studies. The article closes with a discussion of unsolved problems. © Institute of Mathematical Statistics, 2015.
Cross-covariance functions for multivariate geostatistics
Genton, Marc G.; Kleiber, William
2015-01-01
Continuously indexed datasets with multiple variables have become ubiquitous in the geophysical, ecological, environmental and climate sciences, and pose substantial analysis challenges to scientists and statisticians. For many years, scientists developed models that aimed at capturing the spatial behavior for an individual process; only within the last few decades has it become commonplace to model multiple processes jointly. The key difficulty is in specifying the cross-covariance function, that is, the function responsible for the relationship between distinct variables. Indeed, these cross-covariance functions must be chosen to be consistent with marginal covariance functions in such a way that the second-order structure always yields a nonnegative definite covariance matrix. We review the main approaches to building cross-covariance models, including the linear model of coregionalization, convolution methods, the multivariate Matérn and nonstationary and space-time extensions of these among others. We additionally cover specialized constructions, including those designed for asymmetry, compact support and spherical domains, with a review of physics-constrained models. We illustrate select models on a bivariate regional climate model output example for temperature and pressure, along with a bivariate minimum and maximum temperature observational dataset; we compare models by likelihood value as well as via cross-validation co-kriging studies. The article closes with a discussion of unsolved problems. © Institute of Mathematical Statistics, 2015.
Almost commuting self-adjoint matrices: The real and self-dual cases
Loring, Terry A.; Sørensen, Adam P. W.
2016-08-01
We show that a pair of almost commuting self-adjoint, symmetric matrices is close to a pair of commuting self-adjoint, symmetric matrices (in a uniform way). Moreover, we prove that the same holds with self-dual in place of symmetric and also for paths of self-adjoint matrices. Since a symmetric, self-adjoint matrix is real, we get a real version of Huaxin Lin’s famous theorem on almost commuting matrices. Similarly, the self-dual case gives a version for matrices over the quaternions. To prove these results, we develop a theory of semiprojectivity for real C*-algebras and also examine various definitions of low-rank for real C*-algebras.