Comparison between Numerical and Simulation Methods for Age-dependent Branching Models with Immigration

2000 Mathematics Subject Classification: primary: 60J80, 60J85, secondary: 62M09, 92D40

Computational model of bladder tissue based on its measured optical properties

Urinary bladder diseases are a common problem throughout the world and often difficult to accurately diagnose. Furthermore, they pose a heavy financial burden on health services. Urinary bladder tissue from male pigs was spectrophotometrically measured and the resulting data used to calculate the absorption, transmission, and reflectance parameters, along with the derived coefficients of scattering and absorption. These were employed to create a "generic" computational bladder model based on optical properties, simulating the propagation of photons through the tissue at different wavelengths. Using the Monte-Carlo method and fluorescence spectra of UV and blue excited wavelength, diagnostically important biomarkers were modeled. Additionally, the multifunctional noninvasive diagnostics system "LAKK-M" was used to gather fluorescence data to further provide essential comparisons. The ultimate goal of the study was to successfully simulate the effects of varying excited radiation wavelengths on bladder tissue to determine the effectiveness of photonics diagnostic devices. With increased accuracy, this model could be used to reliably aid in differentiating healthy and pathological tissues within the bladder and potentially other hollow organs.

The development of attenuation compensation models of fluorescence spectroscopy signals

This study examines the effect of blood absorption on the endogenous fluorescence signal intensity of biological tissues. Experimental studies were conducted to identify these effects. To register the fluorescence intensity, the fluorescence spectroscopy method was employed. The intensity of the blood flow was measured by laser Doppler flowmetry. We proposed one possible implementation of the Monte Carlo method for the theoretical analysis of the effect of blood on the fluorescence signals. The simulation is constructed as a four-layer skin optical model based on the known optical parameters of the skin with different levels of blood supply. With the help of the simulation, we demonstrate how the level of blood supply can affect the appearance of the fluorescence spectra. In addition, to describe the properties of biological tissue, which may affect the fluorescence spectra, we turned to the method of diffuse reflectance spectroscopy (DRS). Using the spectral data provided by the DRS, the tissue attenuation effect can be extracted and used to correct the fluorescence spectra.

Bayesian Inference in Large-scale Problems

Many modern applications fall into the category of "large-scale" statistical problems, in which both the number of observations n and the number of features or parameters p may be large. Many existing methods focus on point estimation, despite the continued relevance of uncertainty quantification in the sciences, where the number of parameters to estimate often exceeds the sample size, despite huge increases in the value of n typically seen in many fields. Thus, the tendency in some areas of industry to dispense with traditional statistical analysis on the basis that "n=all" is of little relevance outside of certain narrow applications. The main result of the Big Data revolution in most fields has instead been to make computation much harder without reducing the importance of uncertainty quantification. Bayesian methods excel at uncertainty quantification, but often scale poorly relative to alternatives. This conflict between the statistical advantages of Bayesian procedures and their substantial computational disadvantages is perhaps the greatest challenge facing modern Bayesian statistics, and is the primary motivation for the work presented here.

Two general strategies for scaling Bayesian inference are considered. The first is the development of methods that lend themselves to faster computation, and the second is design and characterization of computational algorithms that scale better in n or p. In the first instance, the focus is on joint inference outside of the standard problem of multivariate continuous data that has been a major focus of previous theoretical work in this area. In the second area, we pursue strategies for improving the speed of Markov chain Monte Carlo algorithms, and characterizing their performance in large-scale settings. Throughout, the focus is on rigorous theoretical evaluation combined with empirical demonstrations of performance and concordance with the theory.

One topic we consider is modeling the joint distribution of multivariate categorical data, often summarized in a contingency table. Contingency table analysis routinely relies on log-linear models, with latent structure analysis providing a common alternative. Latent structure models lead to a reduced rank tensor factorization of the probability mass function for multivariate categorical data, while log-linear models achieve dimensionality reduction through sparsity. Little is known about the relationship between these notions of dimensionality reduction in the two paradigms. In Chapter 2, we derive several results relating the support of a log-linear model to nonnegative ranks of the associated probability tensor. Motivated by these findings, we propose a new collapsed Tucker class of tensor decompositions, which bridge existing PARAFAC and Tucker decompositions, providing a more flexible framework for parsimoniously characterizing multivariate categorical data. Taking a Bayesian approach to inference, we illustrate empirical advantages of the new decompositions.

Latent class models for the joint distribution of multivariate categorical, such as the PARAFAC decomposition, data play an important role in the analysis of population structure. In this context, the number of latent classes is interpreted as the number of genetically distinct subpopulations of an organism, an important factor in the analysis of evolutionary processes and conservation status. Existing methods focus on point estimates of the number of subpopulations, and lack robust uncertainty quantification. Moreover, whether the number of latent classes in these models is even an identified parameter is an open question. In Chapter 3, we show that when the model is properly specified, the correct number of subpopulations can be recovered almost surely. We then propose an alternative method for estimating the number of latent subpopulations that provides good quantification of uncertainty, and provide a simple procedure for verifying that the proposed method is consistent for the number of subpopulations. The performance of the model in estimating the number of subpopulations and other common population structure inference problems is assessed in simulations and a real data application.

In contingency table analysis, sparse data is frequently encountered for even modest numbers of variables, resulting in non-existence of maximum likelihood estimates. A common solution is to obtain regularized estimates of the parameters of a log-linear model. Bayesian methods provide a coherent approach to regularization, but are often computationally intensive. Conjugate priors ease computational demands, but the conjugate Diaconis--Ylvisaker priors for the parameters of log-linear models do not give rise to closed form credible regions, complicating posterior inference. In Chapter 4 we derive the optimal Gaussian approximation to the posterior for log-linear models with Diaconis--Ylvisaker priors, and provide convergence rate and finite-sample bounds for the Kullback-Leibler divergence between the exact posterior and the optimal Gaussian approximation. We demonstrate empirically in simulations and a real data application that the approximation is highly accurate, even in relatively small samples. The proposed approximation provides a computationally scalable and principled approach to regularized estimation and approximate Bayesian inference for log-linear models.

Another challenging and somewhat non-standard joint modeling problem is inference on tail dependence in stochastic processes. In applications where extreme dependence is of interest, data are almost always time-indexed. Existing methods for inference and modeling in this setting often cluster extreme events or choose window sizes with the goal of preserving temporal information. In Chapter 5, we propose an alternative paradigm for inference on tail dependence in stochastic processes with arbitrary temporal dependence structure in the extremes, based on the idea that the information on strength of tail dependence and the temporal structure in this dependence are both encoded in waiting times between exceedances of high thresholds. We construct a class of time-indexed stochastic processes with tail dependence obtained by endowing the support points in de Haan's spectral representation of max-stable processes with velocities and lifetimes. We extend Smith's model to these max-stable velocity processes and obtain the distribution of waiting times between extreme events at multiple locations. Motivated by this result, a new definition of tail dependence is proposed that is a function of the distribution of waiting times between threshold exceedances, and an inferential framework is constructed for estimating the strength of extremal dependence and quantifying uncertainty in this paradigm. The method is applied to climatological, financial, and electrophysiology data.

The remainder of this thesis focuses on posterior computation by Markov chain Monte Carlo. The Markov Chain Monte Carlo method is the dominant paradigm for posterior computation in Bayesian analysis. It has long been common to control computation time by making approximations to the Markov transition kernel. Comparatively little attention has been paid to convergence and estimation error in these approximating Markov Chains. In Chapter 6, we propose a framework for assessing when to use approximations in MCMC algorithms, and how much error in the transition kernel should be tolerated to obtain optimal estimation performance with respect to a specified loss function and computational budget. The results require only ergodicity of the exact kernel and control of the kernel approximation accuracy. The theoretical framework is applied to approximations based on random subsets of data, low-rank approximations of Gaussian processes, and a novel approximating Markov chain for discrete mixture models.

Data augmentation Gibbs samplers are arguably the most popular class of algorithm for approximately sampling from the posterior distribution for the parameters of generalized linear models. The truncated Normal and Polya-Gamma data augmentation samplers are standard examples for probit and logit links, respectively. Motivated by an important problem in quantitative advertising, in Chapter 7 we consider the application of these algorithms to modeling rare events. We show that when the sample size is large but the observed number of successes is small, these data augmentation samplers mix very slowly, with a spectral gap that converges to zero at a rate at least proportional to the reciprocal of the square root of the sample size up to a log factor. In simulation studies, moderate sample sizes result in high autocorrelations and small effective sample sizes. Similar empirical results are observed for related data augmentation samplers for multinomial logit and probit models. When applied to a real quantitative advertising dataset, the data augmentation samplers mix very poorly. Conversely, Hamiltonian Monte Carlo and a type of independence chain Metropolis algorithm show good mixing on the same dataset.

Systematic characterization of thermodynamic and dynamical phase behavior in systems with short-ranged attraction

In this paper we demonstrate the feasibility and utility of an augmented version of the Gibbs ensemble Monte Carlo method for computing the phase behavior of systems with strong, extremely short-ranged attractions. For generic potential shapes, this approach allows for the investigation of narrower attractive widths than those previously reported. Direct comparison to previous self-consistent Ornstein-Zernike approximation calculations is made. A preliminary investigation of out-of-equilibrium behavior is also performed. Our results suggest that the recent observations of stable cluster phases in systems without long-ranged repulsions are intimately related to gas-crystal and metastable gas-liquid phase separation.

An Environment for Rapid Derivatives Design and Experimentation

In the highly competitive world of modern finance, new derivatives are continually required to take advantage of changes in financial markets, and to hedge businesses against new risks. The research described in this paper aims to accelerate the development and pricing of new derivatives in two different ways. Firstly, new derivatives can be specified mathematically within a general framework, enabling new mathematical formulae to be specified rather than just new parameter settings. This Generic Pricing Engine (GPE) is expressively powerful enough to specify a wide range of stand¬ard pricing engines. Secondly, the associated price simulation using the Monte Carlo method is accelerated using GPU or multicore hardware. The parallel implementation (in OpenCL) is automatically derived from the mathematical description of the derivative. As a test, for a Basket Option Pricing Engine (BOPE) generated using the GPE, on the largest problem size, an NVidia GPU runs the generated pricing engine at 45 times the speed of a sequential, specific hand-coded implementation of the same BOPE. Thus a user can more rapidly devise, simulate and experiment with new derivatives without actual programming.

Artificial Neural Network and Neutron Aplication in a Volume Fraction Calculation in Annular and Stratified Multiphase System

Multiphase flows, type oil–water-gas are very common among different industrial activities, such as chemical industries and petroleum extraction, and its measurements show some difficulties to be taken. Precisely determining the volume fraction of each one of the elements that composes a multiphase flow is very important in chemical plants and petroleum industries. This work presents a methodology able to determine volume fraction on Annular and Stratified multiphase flow system with the use of neutrons and artificial intelligence, using the principles of transmission/scattering of fast neutrons from a 241Am-Be source and measurements of point flow that are influenced by variations of volume fractions. The proposed geometries used on the mathematical model was used to obtain a data set where the thicknesses referred of each material had been changed in order to obtain volume fraction of each phase providing 119 compositions that were used in the simulation with MCNP-X –computer code based on Monte Carlo Method that simulates the radiation transport. An artificial neural network (ANN) was trained with data obtained using the MCNP-X, and used to correlate such measurements with the respective real fractions. The ANN was able to correlate the data obtained on the simulation with MCNP-X with the volume fractions of the multiphase flows (oil-water-gas), both in the pattern of annular flow as stratified, resulting in a average relative error (%) for each production set of: annular (air= 3.85; water = 4.31; oil=1.08); stratified (air=3.10, water 2.01, oil = 1.45). The method demonstrated good efficiency in the determination of each material that composes the phases, thus demonstrating the feasibility of the technique.

Diseño y optimización de un aplanador de flujo neutrónico para dopaje de silicio en el Reactor RA-10.

El reactor multipropósito RA-10 que se construirá en Ezeiza tiene como objetivo principal aumentar la producción de radioisótopos destinados al diagnóstico de enfermedades; adicionalmente el proyecto RA-10 permitirá ofrecer al sistema científico-tecnológico oportunidades de investigación, desarrollo y producción. Entre ellas se contará con una facilidad de dopaje de silicio a través de transmutación neutrónica para producir material semiconductor. La principal ventaja de esta técnica de fabricación es que se obtiene el semiconductor más homogéneamente dopado del mercado. Esto se logra irradiando a la pieza con un flujo neutrónico axialmente uniforme. La uniformidad axial se obtiene diseñando un aplanador de flujo que consiste en un conjunto de anillos de acero de diferentes espesores para lograr aplanar el perfil de flujo neutrónico que irradia al silicio. El objetivo de este trabajo es diseñar e implementar un algoritmo que permita calcular los espesores óptimos de acero de forma tal de modificar el perfil de flujo neutrónico que se genera en el núcleo para uniformizarlo lo más posible. Se proponen y evalúan mejoras para incrementar el valor del flujo neutrónico al cual se uniformiza. Posteriormente se evalúan los tiempos necesarios para obtener diferentes resistividades objetivo y se realizan cálculos de activación neutrónica para determinar los tiempos de decaimiento necesarios para cumplir los límites de actividad requeridos. Se realizan además cálculos de calentamiento para determinar la potencia que se debe disipar para refrigerar la facilidad.