Sökning: "Gaussian mixture models"

Visar resultat 1 - 5 av 36 avhandlingar innehållade orden Gaussian mixture models.

1. 1. Spatial Mixture Models with Applications in Medical Imaging and Spatial Point Processes

   Författare :Anders Hildeman; Göteborgs universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Non-Gaussian; Bayesian level set inversion; Point processes; Substitute CT; Finite mixture models; Spatial statistics; Gaussian fields; Non-Gaussian;

   Sammanfattning : Finite mixture models have proven to be a great tool for both modeling non-standard probability distributions and for classification problems (using the latent variable interpretation). In this thesis we are building spatial models by incorporating spatially dependent categorical latent random fields in a hierarchical manner similar to that of finite mixture models. LÄS MER

3. 2. On flexible random field models for spatial statistics: Spatial mixture models and deformed SPDE models

   Författare :Anders Hildeman; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Spatial statistics; Significant wave height; Spatial mixture model; Stochastic partial differential equation; Log-Gaussian Cox process; Point process; Gaussian random field; Substitute-CT;

   Sammanfattning : Spatial random fields are one of the key concepts in statistical analysis of spatial data. The random field explains the spatial dependency and serves the purpose of regularizing interpolation of measured values or to act as an explanatory model. LÄS MER

4. 3. Bayesian Cluster Analysis : Some Extensions to Non-standard Situations

   Författare :Jessica Franzén; Daniel Thorburn; Jukka Corander; Stockholms universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Cluster analysis; Clustering; Classification; Mixture model; Gaussian; Bayesian inference; MCMC; Gibbs sampler; Deviant group; Longitudinal; Missing data; Multiple imputation; Statistics; Statistik; Statistics; statistik;

   Sammanfattning : The Bayesian approach to cluster analysis is presented. We assume that all data stem from a finite mixture model, where each component corresponds to one cluster and is given by a multivariate normal distribution with unknown mean and variance. LÄS MER

5. 4. Towards Asymptotic Vector Quantization

   Författare :Jonas Samuelsson; Chalmers tekniska högskola; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; EM algorithm; parametric models; expectation maximization; spectrum coding; Gaussian mixture models; fast search; bounded support; multidimensional companding; vector quantization; high rate quantization;

   Sammanfattning : We study topics in source coding, and vector quantization (VQ) in particular. We approach VQ from two directions: a theoretical starting point based on high rate quantization theory, and a practical based on a database desription of the signal source. LÄS MER

7. 5. Spatio-Temporal Estimation for Mixture Models and Gaussian Markov Random Fields - Applications to Video Analysis and Environmental Modelling

   Författare :Johan Lindström; Matematisk statistik; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; vegetation; time series analysis; video segmentation; spatio-temporal modelling; precipitation; Markov chain Monte Carlo; Gaussian Markov random fields; expectation maximisation; change point detection; Bayesian recursive estimation; African Sahel; adaptive Gaussian mixtures;

   Sammanfattning : In this thesis computationally intensive methods are used to estimate models and to make inference for large, spatio-temporal data sets. The thesis is divided into two parts: the first two papers are concerned with video analysis, while the last three papers model and investigate environmental data from the Sahel area in northern Africa. LÄS MER