Search results for "Covariance function"

showing 10 items of 22 documents

Temperature Covariance in Tree Ring Reconstructions and Model Simulations Over the Past Millennium

2017

Spatial covariance in the simulated temperature evolution over the past millennium has been reported to exceed that of multiproxy-based reconstructions. Here we use tree ring-based temperature reco ...

010504 meteorology & atmospheric sciencesCovariance functionDendroclimatologyRadiative forcingCovariance010502 geochemistry & geophysicsAtmospheric sciences01 natural sciencesGeophysicsClimatologyPaleoclimatologyDendrochronologyGeneral Earth and Planetary SciencesSpatial variabilityGeology0105 earth and related environmental sciencesGeophysical Research Letters
researchProduct

Ray-Space-Based Multichannel Nonnegative Matrix Factorization for Audio Source Separation

2021

Nonnegative matrix factorization (NMF) has been traditionally considered a promising approach for audio source separation. While standard NMF is only suited for single-channel mixtures, extensions to consider multi-channel data have been also proposed. Among the most popular alternatives, multichannel NMF (MNMF) and further derivations based on constrained spatial covariance models have been successfully employed to separate multi-microphone convolutive mixtures. This letter proposes a MNMF extension by considering a mixture model with Ray-Space-transformed signals, where magnitude data successfully encodes source locations as frequency-independent linear patterns. We show that the MNMF alg…

Covariance functionComputer scienceApplied Mathematics020206 networking & telecommunications02 engineering and technologyExtension (predicate logic)Mixture modelMatrix decompositionNon-negative matrix factorizationTime–frequency analysisblind source separationSignal Processing0202 electrical engineering electronic engineering information engineeringSource separationNon -negative matrix factorization (NMF)array signal processingElectrical and Electronic EngineeringAlgorithmIEEE Signal Processing Letters
researchProduct

Measuring Spatiotemporal Dependencies in Bivariate Temporal Random Sets with Applications to Cell Biology

2008

Analyzing spatiotemporal dependencies between different types of events is highly relevant to many biological phenomena (e.g., signaling and trafficking), especially as advances in probes and microscopy have facilitated the imaging of dynamic processes in living cells. For many types of events, the segmented areas can overlap spatially and temporally, forming random clumps. In this paper, we model the binary image sequences of two different event types as a realization of a bivariate temporal random set and propose a nonparametric approach to quantify spatial and spatiotemporal interrelations using the pair correlation, cross-covariance, and the Ripley K functions. Based on these summary st…

Covariance functionModels BiologicalSensitivity and SpecificityPattern Recognition Automated03 medical and health sciences0302 clinical medicineArtificial IntelligenceImage Interpretation Computer-AssistedCells CulturedIndependence (probability theory)030304 developmental biologyMathematics0303 health sciencesModels Statisticalbusiness.industryStochastic processApplied MathematicsNonparametric statisticsReproducibility of ResultsEstimatorImage EnhancementEndocytosisTemporal databaseMicroscopy FluorescenceComputational Theory and Mathematics[SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]Computer Vision and Pattern RecognitionArtificial intelligenceCross-covariancebusinessAlgorithms030217 neurology & neurosurgerySoftwareRealization (probability)IEEE Transactions on Pattern Analysis and Machine Intelligence
researchProduct

When do Improved Covariance Matrix Estimators Enhance Portfolio Optimization? An Empirical Comparative Study of Nine Estimators

2010

The use of improved covariance matrix estimators as an alternative to the sample estimator is considered an important approach for enhancing portfolio optimization. Here we empirically compare the performance of 9 improved covariance estimation procedures by using daily returns of 90 highly capitalized US stocks for the period 1997-2007. We find that the usefulness of covariance matrix estimators strongly depends on the ratio between estimation period T and number of stocks N, on the presence or absence of short selling, and on the performance metric considered. When short selling is allowed, several estimation methods achieve a realized risk that is significantly smaller than the one obtai…

Estimation of covariance matricesMatérn covariance functionCovariance functionCovariance matrixStatisticsEconometricsRational quadratic covariance functionCovariance intersectionCovariancePortfolio optimizationMathematicsSSRN Electronic Journal
researchProduct

Variance estimation and asymptotic confidence bands for the mean estimator of sampled functional data with high entropy unequal probability sampling …

2013

For fixed size sampling designs with high entropy it is well known that the variance of the Horvitz-Thompson estimator can be approximated by the H\'ajek formula. The interest of this asymptotic variance approximation is that it only involves the first order inclusion probabilities of the statistical units. We extend this variance formula when the variable under study is functional and we prove, under general conditions on the regularity of the individual trajectories and the sampling design, that we can get a uniformly convergent estimator of the variance function of the Horvitz-Thompson estimator of the mean function. Rates of convergence to the true variance function are given for the re…

Kullback-Leibler divergence[STAT.TH] Statistics [stat]/Statistics Theory [stat.TH]FOS: Mathematicscovariance functionrejective samplingMathematics - Statistics TheoryStatistics Theory (math.ST)finite populationHorvitz-Thompson estimator[STAT.TH]Statistics [stat]/Statistics Theory [stat.TH]Hájek approximationunequal probability sampling without replacement[ STAT.TH ] Statistics [stat]/Statistics Theory [stat.TH]
researchProduct

How to simulate normal data sets with the desired correlation structure

2010

The Cholesky decomposition is a widely used method to draw samples from multivariate normal distribution with non-singular covariance matrices. In this work we introduce a simple method by using singular value decomposition (SVD) to simulate multivariate normal data even if the covariance matrix is singular, which is often the case in chemometric problems. The covariance matrix can be specified by the user or can be generated by specifying a subset of the eigenvalues. The latter can be an advantage for simulating data sets with a particular latent structure. This can be useful for testing the performance of chemometric methods with data sets matching the theoretical conditions for their app…

Mathematical optimizationCovariance functionCovariance matrixProcess Chemistry and TechnologyMathematicsofComputing_NUMERICALANALYSISMultivariate normal distributionCovarianceComputer Science ApplicationsAnalytical ChemistryEstimation of covariance matricesScatter matrixMatrix normal distributionCMA-ESAlgorithmComputer Science::DatabasesSpectroscopySoftwareMathematicsChemometrics and Intelligent Laboratory Systems
researchProduct

Ranking drivers of global carbon and energy fluxes over land

2015

The accurate estimation of carbon and heat fluxes at global scale is paramount for future policy decisions in the context of global climate change. This paper analyzes the relative relevance of potential remote sensing and meteorological drivers of global carbon and energy fluxes over land. The study is done in an indirect way via upscaling both Gross Primary Production (GPP) and latent energy (LE) using Gaussian Process regression (GPR). In summary, GPR is successfully compared to multivariate linear regression (RMSE gain of +4.17% in GPP and +7.63% in LE) and kernel ridge regression (+2.91% in GPP and +3.07% in LE). The best GP models are then studied in terms of explanatory power based o…

MeteorologyCovariance functionKrigingBayesian multivariate linear regressionLatent heatGlobal warmingEnvironmental sciencePrimary productionContext (language use)VegetationAtmospheric sciences2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
researchProduct

Estimate the mean electricity consumption curve by survey and take auxiliary information into account

2012

In this thesis, we are interested in estimating the mean electricity consumption curve. Since the study variable is functional and storage capacities are limited or transmission cost are high survey sampling techniques are interesting alternatives to signal compression techniques. We extend, in this functional framework, estimation methods that take into account available auxiliary information and that can improve the accuracy of the Horvitz-Thompson estimator of the mean trajectory. The first approach uses the auxiliary information at the estimation stage, the mean curve is estimated using model-assisted estimators with functional linear regression models. The second method involves the au…

Model-assisted estimator[ MATH.MATH-GM ] Mathematics [math]/General Mathematics [math.GM]Unequal probability sampling without replacement[MATH.MATH-GM] Mathematics [math]/General Mathematics [math.GM]Functional linear modelCovariance functionFunctional central limit theoremConfidence bandFunctional dataBootstrapSurvey sampling[MATH.MATH-GM]Mathematics [math]/General Mathematics [math.GM]Théorème central limite fonctionnelDonnées fonctionnellesHajek variance approximationFonction de covariancePlan à probabilités inégales sans remiseEstimateur de Horvitz-ThompsonModèle linéaire fonctionnelApproximation de HájekHorvitz-Thompson estimatorSondageBande de confianceEstimateur model-assisted
researchProduct

Rateless Codes Performance Analysis in Correlated Channel Model for GEO Free Space Optics Downlinks

2012

Settore ING-INF/03 - TelecomunicazioniFree Space Optics (FSO) technologies for satellite communications offer several advantages: wide bandwidth high rate capability immunity to electromagnetic interference and small equipment size. Thus they are suitable for inter-satellite links deep space communications and also for high data rate ground-to-satellite/satellite-to-ground communications. Nevertheless FSO links suffer impairments that cause power signal degradation at the receiver. Scattering and absorption cause power signal attenuations predictable by suitable deterministic models. Optical turbulence causes random irradiance fluctuations which can generate signal fading events and can thereby only be predicted by statistical models. Attenuation and fading events can corrupt FSO links and so it would be recommended to add mitigation error codes on the communication link. FSO channel can be described as an erasure channel: fading events can cause erasure errors. We have identified in rateless codes (RCs) a suitable solution to be employed in FSO links. RCs do not need feedback and they add a redundant coding on the source data that allows the receiver to recover the whole payload despite erasure errors. We implemented two different of rateless codes: Luby Transform (LT) and Raptor. We analyzed their performances on a simulated turbulent GEO FSO downlink (1 Gbps - OOK modulation) at a 106 μm wavelength and for different values of zenith angles. Assuming a plane-wave propagation and employing Hufnagel-Valley we modeled the downlink using: 1) a temporal correlated channel model based on Gamma-Gamma probability distribution and 2) an irradiance covariance function that we converted on a time function using Taylor frozen eddies hypothesis. Our new channel model is able to simulate irradiance fluctuations at different turbulence conditions as it will be shown in the full paper. We will also report performance results of LT and Raptor codes at overhead range varying between 0 and 50% and for different values of source packets.Settore ING-INF/01 - Elettronica
researchProduct

Sign and rank covariance matrices

2000

The robust estimation of multivariate location and shape is one of the most challenging problems in statistics and crucial in many application areas. The objective is to find highly efficient, robust, computable and affine equivariant location and covariance matrix estimates. In this paper, three different concepts of multivariate sign and rank are considered and their ability to carry information about the geometry of the underlying distribution (or data cloud) are discussed. New techniques for robust covariance matrix estimation based on different sign and rank concepts are proposed and algorithms for computing them outlined. In addition, new tools for evaluating the qualitative and quant…

Statistics and ProbabilityCovariance functionCovariance matrixApplied MathematicsMathematicsofComputing_NUMERICALANALYSISCovariance intersectionCovarianceEstimation of covariance matricesMatérn covariance functionScatter matrixStatisticsRational quadratic covariance functionStatistics Probability and UncertaintyAlgorithmMathematicsJournal of Statistical Planning and Inference
researchProduct