Krylov subspace methods for approximating functions of symmetric positive definite matrices with applications to applied statistics and anomalous diffusion

Matrix function approximation is a current focus of worldwide interest and finds application in a variety of areas of applied mathematics and statistics. In this thesis we focus on the approximation of A^(-α/2)b, where A ∈ ℝ^(n×n) is a large, sparse symmetric positive definite matrix and b ∈ ℝ^n is a vector. In particular, we will focus on matrix function techniques for sampling from Gaussian Markov random fields in applied statistics and the solution of fractional-in-space partial differential equations. Gaussian Markov random fields (GMRFs) are multivariate normal random variables characterised by a sparse precision (inverse covariance) matrix. GMRFs are popular models in computational spatial statistics as the sparse structure can be exploited, typically through the use of the sparse Cholesky decomposition, to construct fast sampling methods. It is well known, however, that for sufficiently large problems, iterative methods for solving linear systems outperform direct methods. Fractional-in-space partial differential equations arise in models of processes undergoing anomalous diffusion. Unfortunately, as the fractional Laplacian is a non-local operator, numerical methods based on the direct discretisation of these equations typically requires the solution of dense linear systems, which is impractical for fine discretisations. In this thesis, novel applications of Krylov subspace approximations to matrix functions for both of these problems are investigated. Matrix functions arise when sampling from a GMRF by noting that the Cholesky decomposition A = LL^T is, essentially, a `square root' of the precision matrix A. Therefore, we can replace the usual sampling method, which forms x = L^(-T)z, with x = A^(-1/2)z, where z is a vector of independent and identically distributed standard normal random variables. Similarly, the matrix transfer technique can be used to build solutions to the fractional Poisson equation of the form ϕn = A^(-α/2)b, where A is the finite difference approximation to the Laplacian. Hence both applications require the approximation of f(A)b, where f(t) = t^(-α/2) and A is sparse. In this thesis we will compare the Lanczos approximation, the shift-and-invert Lanczos approximation, the extended Krylov subspace method, rational approximations and the restarted Lanczos approximation for approximating matrix functions of this form. A number of new and novel results are presented in this thesis. Firstly, we prove the convergence of the matrix transfer technique for the solution of the fractional Poisson equation and we give conditions by which the finite difference discretisation can be replaced by other methods for discretising the Laplacian. We then investigate a number of methods for approximating matrix functions of the form A^(-α/2)b and investigate stopping criteria for these methods. In particular, we derive a new method for restarting the Lanczos approximation to f(A)b. We then apply these techniques to the problem of sampling from a GMRF and construct a full suite of methods for sampling conditioned on linear constraints and approximating the likelihood. Finally, we consider the problem of sampling from a generalised Matern random field, which combines our techniques for solving fractional-in-space partial differential equations with our method for sampling from GMRFs.

Numerical methods for the variable-order fractional advection-diffusion equation with a nonlinear source term

In this paper, we consider a variable-order fractional advection-diffusion equation with a nonlinear source term on a finite domain. Explicit and implicit Euler approximations for the equation are proposed. Stability and convergence of the methods are discussed. Moreover, we also present a fractional method of lines, a matrix transfer technique, and an extrapolation method for the equation. Some numerical examples are given, and the results demonstrate the effectiveness of theoretical analysis.

Numerical schemes and multivariate extrapolation of a two-dimensional anomalous sub-diffusion equation

Anomalous dynamics in complex systems have gained much interest in recent years. In this paper, a two-dimensional anomalous subdiffusion equation (2D-ASDE) is considered. Two numerical methods for solving the 2D-ASDE are presented. Their stability, convergence and solvability are discussed. A new multivariate extrapolation is introduced to improve the accuracy. Finally, numerical examples are given to demonstrate the effectiveness of the schemes and confirm the theoretical analysis.

Stability and convergence of a new explicit finite-difference approximation for the variable-order nonlinear fractional diffusion equation

In this paper, we consider the variable-order nonlinear fractional diffusion equation View the MathML source where xRα(x,t) is a generalized Riesz fractional derivative of variable order View the MathML source and the nonlinear reaction term f(u,x,t) satisfies the Lipschitz condition |f(u1,x,t)-f(u2,x,t)|less-than-or-equals, slantL|u1-u2|. A new explicit finite-difference approximation is introduced. The convergence and stability of this approximation are proved. Finally, some numerical examples are provided to show that this method is computationally efficient. The proposed method and techniques are applicable to other variable-order nonlinear fractional differential equations.

CTCombine : rotating and combining CT data with an accurate detector model, to simulate radiotherapy portal imaging at non-zero beam angles

Established Monte Carlo user codes BEAMnrc and DOSXYZnrc permit the accurate and straightforward simulation of radiotherapy experiments and treatments delivered from multiple beam angles. However, when an electronic portal imaging detector (EPID) is included in these simulations, treatment delivery from non-zero beam angles becomes problematic. This study introduces CTCombine, a purpose-built code for rotating selected CT data volumes, converting CT numbers to mass densities, combining the results with model EPIDs and writing output in a form which can easily be read and used by the dose calculation code DOSXYZnrc. The geometric and dosimetric accuracy of CTCombine’s output has been assessed by simulating simple and complex treatments applied to a rotated planar phantom and a rotated humanoid phantom and comparing the resulting virtual EPID images with the images acquired using experimental measurements and independent simulations of equivalent phantoms. It is expected that CTCombine will be useful for Monte Carlo studies of EPID dosimetry as well as other EPID imaging applications.

CT imaging of an Egyptian mummy

Over the last few years various research groups around the world have employed X-ray Computed Tomography (CT) imaging in the study of mummies – Toronto-Boston (1,2), Manchester(3). Prior to the development of CT scanners, plane X-rays were used in the investigation of mummies. Xeroradiography has also been employed(4). In a xeroradiograph, objects of similar X-ray density (very difficult to see on a conventional X-ray) appear edge-enhanced and so are seen much more clearly. CT scanners became available in the early 1970s. A CT scanner produces cross-sectional X-rays of objects. On a conventional X-radiograph individual structures are often very difficult to see because all the structures lying in the path of the X-ray beam are superimposed, a problem that does not occur with CT. Another advantage of CT is that the information in a series of consecutive images may be combined to produce a three-dimensional reconstruction of an object. Slices of different thickness and magnification may be chosen. Why CT a mummy? Prior to the availability of CT scanners, the only way of finding out about the inside of a mummy in any detail was to unwrap and dissect it. This has been done by various research groups – most notably the Manchester, UK and Pennsylvania University, USA mummy projects(5,6). Unwrapping a mummy and carrying out an autopsy is obviously very destructive. CT studies hold the possibility of producing a lot more information than is possible from plain X-rays and are able to show the undisturbed arrangement of the wrapped body. CT is also able to provide information about the internal structure of bones, organ packs, etc that wouldn’t be possible without sawing through the bones etc. The mummy we have scanned is encased in a coffin which would have to have been broken open in order to remove the body.

Corneal topography with Scheimpflug imaging and videokeratography : comparative study of normal eyes

PURPOSE: To compare the repeatability within anterior corneal topography measurements and agreement between measurements with the Pentacam HR rotating Scheimpflug camera and with a previously validated Placido disk–based videokeratoscope (Medmont E300). ------ SETTING: Contact Lens and Visual Optics Laboratory, School of Optometry, Queensland University of Technology, Brisbane, Queensland, Australia. ----- METHODS: Normal eyes in 101 young adult subjects had corneal topography measured using the Scheimpflug camera (6 repeated measurements) and videokeratoscope (4 repeated measurements). The best-fitting axial power corneal spherocylinder was calculated and converted into power vectors. Corneal higher-order aberrations (HOAs) (up to the 8th Zernike order) were calculated using the corneal elevation data from each instrument. ----- RESULTS: Both instruments showed excellent repeatability for axial power spherocylinder measurements (repeatability coefficients <0.25 diopter; intraclass correlation coefficients >0.9) and good agreement for all power vectors. Agreement between the 2 instruments was closest when the mean of multiple measurements was used in analysis. For corneal HOAs, both instruments showed reasonable repeatability for most aberration terms and good correlation and agreement for many aberrations (eg, spherical aberration, coma, higher-order root mean square). For other aberrations (eg, trefoil and tetrafoil), the 2 instruments showed relatively poor agreement. ----- CONCLUSIONS: For normal corneas, the Scheimpflug system showed excellent repeatability and reasonable agreement with a previously validated videokeratoscope for the anterior corneal axial curvature best-fitting spherocylinder and several corneal HOAs. However, for certain aberrations with higher azimuthal frequencies, the Scheimpflug system had poor agreement with the videokeratoscope; thus, caution should be used when interpreting these corneal aberrations with the Scheimpflug system.

Numerical simulation of the Riesz fractional diffusion equation with a nonlinear source term

In this paper, A Riesz fractional diffusion equation with a nonlinear source term (RFDE-NST) is considered. This equation is commonly used to model the growth and spreading of biological species. According to the equivalent of the Riemann-Liouville(R-L) and Gr¨unwald-Letnikov(GL) fractional derivative definitions, an implicit difference approximation (IFDA) for the RFDE-NST is derived. We prove the IFDA is unconditionally stable and convergent. In order to evaluate the efficiency of the IFDA, a comparison with a fractional method of lines (FMOL) is used. Finally, two numerical examples are presented to show that the numerical results are in good agreement with our theoretical analysis.

Fundamental solution and discrete random walk model for time-space fractional diffusion equation

In this paper, we consider a time-space fractional diffusion equation of distributed order (TSFDEDO). The TSFDEDO is obtained from the standard advection-dispersion equation by replacing the first-order time derivative by the Caputo fractional derivative of order α∈(0,1], the first-order and second-order space derivatives by the Riesz fractional derivatives of orders β 1∈(0,1) and β 2∈(1,2], respectively. We derive the fundamental solution for the TSFDEDO with an initial condition (TSFDEDO-IC). The fundamental solution can be interpreted as a spatial probability density function evolving in time. We also investigate a discrete random walk model based on an explicit finite difference approximation for the TSFDEDO-IC.

A novel profluorescent dinitroxide for imaging polypropylene degradation

Free-radical processes underpin the thermo-oxidative degradation of polyolefins. Thus, to extend the lifetime of these polymers, stabilizers are generally added during processing to scavenge the free radicals formed as the polymer degrades. Nitroxide radical precursors, such as hindered amine stabilizers (HAS),1,2 are common polypropylene additives as the nitroxide moiety is a potent scavenger of polymer alkyl radicals (R¥). Oxidation of HAS by radicals formed during polypropylene degradation yields nitroxide radicals (RRNO¥), which rapidly trap the polymer degradation species to produce alkoxyamines, thus retarding oxidative polymer degradation. This increase in polymer stability is demonstrated by a lengthening of the “induction period” of the polymer (the time prior to a sharp rise in the oxidation of the polymer). Instrumental techniques such as chemiluminescence or infrared spectroscopy are somewhat limited in detecting changes in the polymer during the initial stages of degradation. Therefore, other methods for observing polymer degradation have been sought as the useful life of a polymer does not extend far beyond its “induction period”

PDMS spreading morphological patterns on substrates of different hydrophilicity in air vacuum and water

In paper has been to investigate the morphological patterns and kinetics of PDMS spreading on silicon wafer using combination of techniques like ellipsometry, atomic force microscope (AFM), scanning electron microscope (SEM) and optical microscopy. A macroscopic silicone oil drops as well as PDMS water based emulsions were studied after deposition on a flat surface of silicon wafer in air, water and vacuum. our own measurements using an imaging ellipsometer, which also clearly shows the presence of a precursor film. The diffusion constant of this film, measured with a 60 000 cS PDMS sample spreading on a hydrophilic silicon wafer, is Df = 1.4  10-11 m2/s. Regardless of their size, density and method of deposition, droplets on both types of wafer (hydrophilic and hydrophobic) flatten out over a period of many hours, up to 3 days. During this process neighbouring droplets may coalesce, but there is strong evidence that some of the PDMS from the droplets migrates into a thin, continuous film that covers the surface in between droplets. The thin film appears to be ubiquitous if there has been any deposition of PDMS. However, this statement needs further verification. One question is whether the film forms immediately after forced drying, or whether in some or all cases it only forms by spreading from isolated droplets as they slowly flatten out.