Show simple item record

dc.contributor.advisorMallick, Bani K.
dc.contributor.advisorSang, Huiyan
dc.creatorKonomi, Bledar
dc.date.accessioned2012-02-14T22:19:24Z
dc.date.accessioned2012-02-16T16:16:26Z
dc.date.available2014-01-15T07:05:28Z
dc.date.created2011-12
dc.date.issued2012-02-14
dc.date.submittedDecember 2011
dc.identifier.urihttps://hdl.handle.net/1969.1/ETD-TAMU-2011-12-10267
dc.description.abstractThe main objective of this dissertation is to apply Bayesian modeling to different complex and high-dimensional spatial data sets. I develop Bayesian hierarchical spatial models for both the observed location and the observation variable. Throughout this dissertation I execute the inference of the posterior distributions using Markov chain Monte Carlo by developing computational strategies that can reduce the computational cost. I start with a "high level" image analysis by modeling the pixels with a Gaussian process and the objects with a marked-point process. The proposed method is an automatic image segmentation and classification procedure which simultaneously detects the boundaries and classifies the objects in the image into one of the predetermined shape families. Next, I move my attention to the piecewise non-stationary Gaussian process models and their computational challenges for very large data sets. I simultaneously model the non-stationarity and reduce the computational cost by using the innovative technique of full-scale approximation. I successfully demonstrate the proposed reduction technique to the Total Ozone Matrix Spectrometer (TOMS) data. Furthermore, I extend the reduction method for the non-stationary Gaussian process models to a dynamic partition of the space by using a modified Treed Gaussian Model. This modification is based on the use of a non-stationary function and the full-scale approximation. The proposed model can deal with piecewise non-stationary geostatistical data with unknown partitions. Finally, I apply the method to the TOMS data to explore the non-stationary nature of the data.en
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.subjectObject classificationen
dc.subjectImage segmentationen
dc.subjectNanoparticlesen
dc.subjectMarkov-chain Monte-carloen
dc.subjectBayesian shape analysisen
dc.subjectPredictive processen
dc.subjectFull-scale approximationen
dc.subjectBayesian treed Gaussian processen
dc.titleBayesian Spatial Modeling of Complex and High Dimensional Dataen
dc.typeThesisen
thesis.degree.departmentStatisticsen
thesis.degree.disciplineStatisticsen
thesis.degree.grantorTexas A&M Universityen
thesis.degree.nameDoctor of Philosophyen
thesis.degree.levelDoctoralen
dc.contributor.committeeMemberHuang, Jianhua
dc.contributor.committeeMemberEfendiev, Yalchin
dc.type.genrethesisen
dc.type.materialtexten
local.embargo.terms2014-01-15


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record