Search results for " random field"

showing 10 items of 41 documents

Two-Stage Bayesian Approach for GWAS With Known Genealogy

2019

Genome-wide association studies (GWAS) aim to assess relationships between single nucleotide polymorphisms (SNPs) and diseases. They are one of the most popular problems in genetics, and have some peculiarities given the large number of SNPs compared to the number of subjects in the study. Individuals might not be independent, especially in animal breeding studies or genetic diseases in isolated populations with highly inbred individuals. We propose a family-based GWAS model in a two-stage approach comprising a dimension reduction and a subsequent model selection. The first stage, in which the genetic relatedness between the subjects is taken into account, selects the promising SNPs. The se…

0301 basic medicineStatistics and ProbabilityBayesian probabilityPopulationSingle-nucleotide polymorphismGenome-wide association studyComputational biologyEstadísticaBiologyKinship coefficientModel selection01 natural sciencesBeta-thalassemia010104 statistics & probability03 medical and health sciencesBeta-thalassemia disorderModelsRobust prior distributionRegularizationDiscrete Mathematics and Combinatorics0101 mathematicsStage (cooking)Genetic associationGenome-wide associationModel selectionVariable-selectionProbability and statisticsBayes factorRegressionBayes factor030104 developmental biologyPhenotypeStatistics Probability and UncertaintyGaussian Markov random field
researchProduct

Stochastic differential calculus for wind-exposed structures with autoregressive continuous (ARC) filters

2008

In this paper, an alternative method to represent Gaussian stationary processes describing wind velocity fluctuations is introduced. The technique may be considered the extension to a time continuous description of the well-known discrete-time autoregressive model to generate Gaussian processes. Digital simulation of Gaussian random processes with assigned auto-correlation function is provided by means of a stochastic differential equation with time delayed terms forced by Gaussian white noise. Solution of the differential equation is a specific sample of the target Gaussian wind process, and in this paper it describes a digitally obtained record of the wind turbolence. The representation o…

Autoregressive continuous (ARC) modelRenewable Energy Sustainability and the EnvironmentStochastic processMechanical EngineeringGaussianOrnstein–Uhlenbeck processGaussian random fieldStochastic differential equationsymbols.namesakeQuasi-static theoryAutoregressive modelFourier transformsymbolsGaussian functionCalculusStochastic differential calculuApplied mathematicsGaussian random processeSettore ICAR/08 - Scienza Delle CostruzioniGaussian processCivil and Structural EngineeringMathematicsJournal of Wind Engineering and Industrial Aerodynamics
researchProduct

One-dimensional heterogeneous solids with uncertain elastic modulus in presence of long-range interactions: Interval versus stochastic analysis

2013

The analysis of one-dimensional non-local elastic solids with uncertain Young's modulus is addressed. Non-local effects are represented as long-range central body forces between non-adjacent volume elements. For comparison purpose, the fluctuating elastic modulus of the material is modeled following both a probabilistic and a non-probabilistic approach. To this aim, a novel definition of the interval field concept, able to limit the overestimation affecting ordinary interval analysis, is introduced. Approximate closed-form expressions are derived for the bounds of the interval displacement field as well as for the mean-value and variance of the stochastic response.

Body forcedecompositionRandom fieldNon-local elasticityStochastic processMechanical EngineeringMathematical analysisKarhunen-Loeve decompositionModulusInterval (mathematics)Karhunen–LoèveComputer Science ApplicationsInterval arithmeticResponse statisticsNon-local elasticity; Interval field; Random field; Karhunen–Loève; decomposition; Upper bound and lower bound; Response statisticsModeling and SimulationDisplacement fieldRandom fieldGeneral Materials ScienceInterval fieldUpper bound and lower boundSettore ICAR/08 - Scienza Delle CostruzioniElastic modulusCivil and Structural EngineeringMathematics
researchProduct

Detecting faulty wireless sensor nodes through Stochastic classification

2011

In many distributed systems, the possibility to adapt the behavior of the involved resources in response to unforeseen failures is an important requirement in order to significantly reduce the costs of management. Autonomous detection of faulty entities, however, is often a challenging task, especially when no direct human intervention is possible, as is the case for many scenarios involving Wireless Sensor Networks (WSNs), which usually operate in inaccessible and hostile environments. This paper presents an unsupervised approach for identifying faulty sensor nodes within a WSN. The proposed algorithm uses a probabilistic approach based on Markov Random Fields, requiring exclusively an ana…

Brooks–Iyengar algorithmComputer scienceDistributed computingReal-time computingProbabilistic logicMarkov processMarkov Random Fieldsymbols.namesakeKey distribution in wireless sensor networksWireless Sensor Networks.Autonomic ComputingSensor nodesymbolsOverhead (computing)Algorithm designWireless sensor network2011 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops)
researchProduct

Arabic Named Entity Recognition: A Feature-Driven Study

2009

The named entity recognition task aims at identifying and classifying named entities within an open-domain text. This task has been garnering significant attention recently as it has been shown to help improve the performance of many natural language processing applications. In this paper, we investigate the impact of using different sets of features in three discriminative machine learning frameworks, namely, support vector machines, maximum entropy and conditional random fields for the task of named entity recognition. Our language of interest is Arabic. We explore lexical, contextual and morphological features and nine data-sets of different genres and annotations. We measure the impact …

Conditional random fieldAcoustics and UltrasonicsComputer sciencebusiness.industryPrinciple of maximum entropycomputer.software_genreMachine learningLinear discriminant analysisCable televisionSupport vector machineDiscriminative modelNamed-entity recognitionEntropy (information theory)Artificial intelligenceElectrical and Electronic EngineeringbusinesscomputerNatural language processingIEEE Transactions on Audio, Speech, and Language Processing
researchProduct

Gesture Modeling by Hanklet-Based Hidden Markov Model

2015

In this paper we propose a novel approach for gesture modeling. We aim at decomposing a gesture into sub-trajectories that are the output of a sequence of atomic linear time invariant (LTI) systems, and we use a Hidden Markov Model to model the transitions from the LTI system to another. For this purpose, we represent the human body motion in a temporal window as a set of body joint trajectories that we assume are the output of an LTI system. We describe the set of trajectories in a temporal window by the corresponding Hankel matrix (Hanklet), which embeds the observability matrix of the LTI system that produced it. We train a set of HMMs (one for each gesture class) with a discriminative a…

Conditional random fieldKinectbusiness.industryComputer scienceMaximum-entropy Markov modelAction ClassificationHankel matrixMarkov modelHidden Markov ModelLTI system theoryGestureAction RecognitionGesture recognitionObservabilityArtificial intelligencebusinessHidden Markov modelAlgorithmHankel matrixSkeleton
researchProduct

Hidden Markov random field model and Broyden–Fletcher–Goldfarb–Shanno algorithm for brain image segmentation

2018

International audience; Many routine medical examinations produce images of patients suffering from various pathologies. With the huge number of medical images, the manual analysis and interpretation became a tedious task. Thus, automatic image segmentation became essential for diagnosis assistance. Segmentation consists in dividing the image into homogeneous and significant regions. We focus on hidden Markov random fields referred to as HMRF to model the problem of segmentation. This modelisation leads to a classical function minimisation problem. Broyden-Fletcher-Goldfarb-Shanno algorithm referred to as BFGS is one of the most powerful methods to solve unconstrained optimisation problem. …

Dice coefficient criterionComputer scienceBrain image segmentation02 engineering and technologyMR-images[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]Theoretical Computer Science03 medical and health sciences0302 clinical medicineArtificial Intelligence0202 electrical engineering electronic engineering information engineering[INFO]Computer Science [cs]SegmentationBrain magnetic resonance imagingHidden Markov modelRandom fieldbusiness.industryBroyden-Fletcher-Goldfarb-Shanno algorithmPattern recognitionImage segmentationhidden Markov random fieldMinimization3. Good healthHomogeneousBroyden–Fletcher–Goldfarb–Shanno algorithm020201 artificial intelligence & image processingAutomatic segmentationArtificial intelligenceHidden Markov random fieldbusiness030217 neurology & neurosurgerySoftwareJournal of Experimental & Theoretical Artificial Intelligence
researchProduct

Generalized Wiener Process and Kolmogorov's Equation for Diffusion induced by Non-Gaussian Noise Source

2005

We show that the increments of generalized Wiener process, useful to describe non-Gaussian white noise sources, have the properties of infinitely divisible random processes. Using functional approach and the new correlation formula for non-Gaussian white noise we derive directly from Langevin equation, with such a random source, the Kolmogorov's equation for Markovian non-Gaussian process. From this equation we obtain the Fokker-Planck equation for nonlinear system driven by white Gaussian noise, the Kolmogorov-Feller equation for discontinuous Markovian processes, and the fractional Fokker-Planck equation for anomalous diffusion. The stationary probability distributions for some simple cas…

Diffusion equationStatistical Mechanics (cond-mat.stat-mech)General MathematicsMathematical analysisGeneral Physics and AstronomyFOS: Physical sciencesOrnstein–Uhlenbeck processCondensed Matter - Soft Condensed MatterGaussian random fieldLangevin equationsymbols.namesakeStochastic differential equationAdditive white Gaussian noiseGaussian noisesymbolsProcess and Kolmogorov'sSoft Condensed Matter (cond-mat.soft)Fokker–Planck equationCondensed Matter - Statistical MechanicsMathematics
researchProduct

Monte Carlo simulation for the response analysis of long-span suspended cables under wind loads

2004

This paper presents a time-domain approach for analyzing nonlinear random vibrations of long-span suspended cables under transversal wind. A consistent continuous model of the cable, fully accounting for geometrical nonlinearities inherent in cable behavior, is adopted. The effects of spatial correlation are properly included by modeling wind velocity fluctuation as a random function of time and of a single spatial variable ranging over cable span, namely as a one-variate bi-dimensional (1V-2D) random field. Within the context of a Galerkin`s discretization of the equations governing cable motion, a very efficient Monte Carlo-based technique for second-order analysis of the response is prop…

EngineeringRandom fieldDiscretizationSuspended cablebusiness.industrysuspended cable; wind velocity random field; Proper Orthogonal DecompositionMonte Carlo methodRandom functionBuilding and ConstructionMechanicsStructural engineeringAerodynamicsProper orthogonal decompositionWind speedVibrationNonlinear systemModeling and SimulationWind velocityRandom fieldNonlinear vibrationDigital simulationbusinessCivil and Structural EngineeringWind and Structures
researchProduct

Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis

2016

This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images. The generative MRF acts on higher-levels of a dCNN feature pyramid, controling the image layout at an abstract level. We apply the method to both photographic and non-photo-realistic (artwork) synthesis tasks. The MRF regularizer prevents over-excitation artifacts and reduces implausible feature mixtures common to previous dCNN inversion approaches, permitting synthezing photographic content with increased visual plausibility. Unlike standard MRF-based texture synthesis, the combined system can both match and adap…

FOS: Computer and information sciencesRandom fieldMarkov random fieldArtificial neural networkMarkov chainComputer sciencebusiness.industryComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION020207 software engineeringPattern recognition02 engineering and technologyIterative reconstructionConvolutional neural networkComputingMethodologies_PATTERNRECOGNITION0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionArtificial intelligencebusinessGenerative grammarTexture synthesis2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
researchProduct