A Graphic User Interface is developed to determine the existence of a particular sequence of piano notes within a monophonic sound waveform. Such waveforms are recorded within the Graphic User Interface and then passed to the monophonic analysis engine. The first phase of analysis segments the PCM sound data to localize the potential note locations. The second phase of analysis takes the segmented note locations, moves them to the frequency-domain, and utilizes a probabilistic identification process to determine the identity of each note. Two sound files can be processed together to decide if any notes are common between them. A frequency-based comparison model allows flexibility in finding overlap between the files. Theoretical concepts are visualized using the Graphic User Interface making it a tool for developing additional insight into the analysis of music. / Graduation date: 1997

In many applications of graphical models arising in computer vision, the hidden variables of interest are most naturally specified by continuous, non-Gaussian distributions. There exist inference algorithms for discrete approximations to these continuous distributions, but for the high-dimensional variables typically of interest, discrete inference becomes infeasible. Stochastic methods such as particle filters provide an appealing alternative. However, existing techniques fail to exploit the rich structure of the graphical models describing many vision problems. Drawing on ideas from regularized particle filters and belief propagation (BP), this paper develops a nonparametric belief propagation (NBP) algorithm applicable to general graphs. Each NBP iteration uses an efficient sampling procedure to update kernel-based approximations to the true, continuous likelihoods. The algorithm can accomodate an extremely broad class of potential functions, including nonparametric representations. Thus, NBP extends particle filtering methods to the more general vision problems that graphical models can describe. We apply the NBP algorithm to infer component interrelationships in a parts-based face model, allowing location and reconstruction of occluded features.

This thesis presents Pathway Informed Analysis (PIA), a classification method for predicting disease states (diagnosis) from metabolic profile measurements that incorporates biological knowledge in the form of metabolic pathways. A metabolic pathway describes a set of chemical reactions that perform a specific biological function. A significant amount of biological knowledge produced by efforts to identify and understand these pathways is formalized in readily accessible databases such as the Kyoto Encyclopedia of Genes and Genomes. PIA uses metabolic pathways to identify relationships among the metabolite concentrations that are measured by a metabolic profile. Specifically, PIA assumes that the class-conditional metabolite concentrations (diseased vs. healthy, respectively) follow multivariate normal distributions. It further assumes that conditional independence statements about these distributions derived from the pathways relate the concentrations of the metabolites to each other. The two assumptions allow for a natural representation of the class-conditional distributions using a type of probabilistic graphical model called a Gaussian Markov Random Field. PIA efficiently estimates the parameters defining these distributions from example patients to produce a classifier. It classifies an undiagnosed patient by evaluating both models to determine the most probable class given their metabolic profile. We apply PIA to a data set of cancer patients to diagnose those with a muscle wasting disease called cachexia. Standard machine learning algorithms such as Naive Bayes, Tree-augmented Naive Bayes, Support Vector Machines and C4.5 are used to evaluate the performance of PIA. The overall classification accuracy of PIA is better than these algorithms on this data set but the difference is not statistically significant. We also apply PIA to several other classification tasks. Some involve predicting various manipulations of the metabolic processes performed in experiments with worms. Other tasks are to classify pigs according to properties of their dietary intake. The accuracy of PIA at these tasks is not significantly better than the standard algorithms.

Thesis (M.S.)--University of Montana, 2007. / Title from title screen. Description based on contents viewed Mar. 14, 2007. Includes bibliographical references (p. 84).

We propose Bayesian methods for estimating the precision matrix in Gaussian graphical models. The methods lead to sparse and adaptively shrunk estimators of the precision matrix, and thus conduct model selection and estimation simultaneously. Our methods are based on selection and shrinkage priors leading to parsimonious parameterization of the precision (inverse covariance) matrix, which is essential in several applications in learning relationships among the variables. In Chapter I, we employ the Laplace prior on the off-diagonal element of the precision matrix, which is similar to the lasso model in a regression context. This type of prior encourages sparsity while providing shrinkage estimates. Secondly we introduce a novel type of selection prior that develops a sparse structure of the precision matrix by making most of the elements exactly zero, ensuring positive-definiteness. In Chapter II we extend the above methods to perform classification. Reverse-phase protein array (RPPA) analysis is a powerful, relatively new platform that allows for high-throughput, quantitative analysis of protein networks. One of the challenges that currently limits the potential of this technology is the lack of methods that allows for accurate data modeling and identification of related networks and samples. Such models may improve the accuracy of biological sample classification based on patterns of protein network activation, and provide insight into the distinct biological relationships underlying different cancers. We propose a Bayesian sparse graphical modeling approach motivated by RPPA data using selection priors on the conditional relationships in the presence of class information. We apply our methodology to an RPPA data set generated from panels of human breast cancer and ovarian cancer cell lines. We demonstrate that the model is able to distinguish the different cancer cell types more accurately than several existing models and to identify differential regulation of components of a critical signaling network (the PI3K-AKT pathway) between these cancers. This approach represents a powerful new tool that can be used to improve our understanding of protein networks in cancer. In Chapter III we extend these methods to mixtures of Gaussian graphical models for clustered data, with each mixture component being assumed Gaussian with an adaptive covariance structure. We model the data using Dirichlet processes and finite mixture models and discuss appropriate posterior simulation schemes to implement posterior inference in the proposed models, including the evaluation of normalizing constants that are functions of parameters of interest which are a result of the restrictions on the correlation matrix. We evaluate the operating characteristics of our method via simulations, as well as discuss examples based on several real data sets.

This thesis describe two graphical modeling languages that can be used for specifying the access control setup in most systems that store information in a tree based structure. The Tree-based Access control Modeling Language (TACOMA) is the simplest language that is defined. It is easy to learn and use as it has only 8 symbols and two relations. With this language it is possible to define the exact access control rules for users using a graphical notation. The simplicity of the language do however come at a cost: it is best suited for small or medium sized tasks where the number of users and objects being controlled are limited. To solve the scalability problem a second language is also presented. The Policy Tree-based Access control Modeling Language (PTACOMA) is a policy based version of TACOMA that doubles the number of symbols and relations. While it is harder to learn it scales better to larger tasks. It also allows for distributed specification of access rules where administrators of different domains can be responsible for specifying their own access control rules. Domains can be organized in a hierarchical manner so that administrators on a higher level can create policies that have higher priority and therefor limits what administrators at lower levels can do. The thesis describes the two languages in detail and provides a comparison between them to show the strong and weak points of each language. There is also a detailed case study that shows how the two languages can be used for specifying access control in SNMPv3.

A common way of organizing Windows, Icons, Menus, and Pointers (WIMP) interfaces is to group tools into tool containers, providing one visual representation. Common tool containers include toolbars and menus, as well as more complex tool containers, like Microsoft Offices Ribbon, Toolglasses, and marking menus. The location of tool containers has been studied extensively in the past using Fittss Law, which governs selection time; however, selection time is only one aspect of user performance. In this thesis, I show that tool container location affects other aspects of user performance, specifically attention and awareness. The problem investigated in this thesis is that designers lack an understanding of the effects of tool container location on two important user performance factors: attention and group awareness. My solution is to provide an initial understanding of the effects of tool container location on these factors. In solving this problem, I developed a taxonomy of tool container location, and carried out two research studies. The two research studies investigated tool container location in two contexts: single-user performance with desktop interfaces, and group performance in tabletop interfaces. Through the two studies, I was able to show that tool container location does affect attention and group awareness, and to provide new recommendations for interface designers.

No description available.

This thesis describes a probabilistic approach to imagesegmentation and interpretation. The focus of the investigation is the development of a systematic way of combining color, brightness, texture and geometric features extracted from an image to arrive at a consistent interpretation for each pixel in the image. The contribution of this thesis is thus the presentation of a novel framework for the fusion of extracted image features producing a segmentation of an image into relevant regions. Further, a solution to the sub-pixel mixing problem is presented based on solving a probabilistic linear program. This work is specifically aimed at interpreting and digitizing multi-spectral aerial imagery of the Earth's surface. The features of interest for extraction are those of relevance to environmental management, monitoring and protection. The presented algorithms are suitable for use within a larger interpretive system. Some results are presented and contrasted with other techniques. The integration of these algorithms into a larger system is based firmly on a probabilistic methodology and the use of statistical decision theory to accomplish uncertain inference within the visual formalism of a graphical probability model.

A common way of organizing Windows, Icons, Menus, and Pointers (WIMP) interfaces is to group tools into tool containers, providing one visual representation. Common tool containers include toolbars and menus, as well as more complex tool containers, like Microsoft Offices Ribbon, Toolglasses, and marking menus. The location of tool containers has been studied extensively in the past using Fittss Law, which governs selection time; however, selection time is only one aspect of user performance. In this thesis, I show that tool container location affects other aspects of user performance, specifically attention and awareness. The problem investigated in this thesis is that designers lack an understanding of the effects of tool container location on two important user performance factors: attention and group awareness. My solution is to provide an initial understanding of the effects of tool container location on these factors. In solving this problem, I developed a taxonomy of tool container location, and carried out two research studies. The two research studies investigated tool container location in two contexts: single-user performance with desktop interfaces, and group performance in tabletop interfaces. Through the two studies, I was able to show that tool container location does affect attention and group awareness, and to provide new recommendations for interface designers.