Sökning: id:"swepub:oai:gup.ub.gu.se/272430" >
Latent Gaussian ran...
Latent Gaussian random field mixture models
-
- Bolin, David, 1983 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för matematiska vetenskaper,Department of Mathematical Sciences,Chalmers tekniska högskola,Chalmers University of Technology
-
- Wallin, Jonas, 1981 (författare)
- Lund University,Lunds universitet,Statistiska institutionen,Ekonomihögskolan,Department of Statistics,Lund University School of Economics and Management, LUSEM
-
- Lindgren, F. (författare)
- University of Edinburgh
-
(creator_code:org_t)
- Elsevier BV, 2019
- 2019
- Engelska.
-
Ingår i: Computational Statistics & Data Analysis. - : Elsevier BV. - 0167-9473. ; 130, s. 80-93
- Relaterad länk:
-
http://dx.doi.org/10...
-
visa fler...
-
https://gup.ub.gu.se...
-
https://doi.org/10.1...
-
https://research.cha...
-
https://research.cha...
-
https://research.cha...
-
https://lup.lub.lu.s...
-
visa färre...
Abstract
Ämnesord
Stäng
- For many problems in geostatistics, land cover classification, and brain imaging the classical Gaussian process models are unsuitable due to sudden, discontinuous, changes in the data. To handle data of this type, we introduce a new model class that combines discrete Markov random fields (MRFs) with Gaussian Markov random fields. The model is defined as a mixture of several, possibly multivariate, Gaussian Markov random fields. For each spatial location, the discrete MRF determines which of the Gaussian fields in the mixture that is observed. This allows for the desired discontinuous changes of the latent processes, and also gives a probabilistic representation of where the changes occur spatially. By combining stochastic gradient minimization with sparse matrix techniques we obtain computationally efficient methods for both likelihood-based parameter estimation and spatial interpolation. The model is compared to Gaussian models and standard MRF models using simulated data and in application to upscaling of soil permeability data. (C) 2018 Elsevier B.V. All rights reserved.
Ämnesord
- NATURVETENSKAP -- Matematik -- Sannolikhetsteori och statistik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Probability Theory and Statistics (hsv//eng)
- NATURVETENSKAP -- Geovetenskap och miljövetenskap -- Naturgeografi (hsv//swe)
- NATURAL SCIENCES -- Earth and Related Environmental Sciences -- Physical Geography (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
Nyckelord
- Random field
- Spatial statistics
- Gaussian mixture
- Stochastic gradient
- Geostatistics
- Gaussian
- markov random-fields
- brain mr-images
- stochastic-approximation
- maximum-likelihood
- gradient algorithm
- em algorithm
- segmentation
- matrix
- Spatial statistics
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas