Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 4 of 4
Full-Text Articles in Physical Sciences and Mathematics
On Improving Performance Of The Binary Logistic Regression Classifier, Michael Chang
On Improving Performance Of The Binary Logistic Regression Classifier, Michael Chang
UNLV Theses, Dissertations, Professional Papers, and Capstones
Logistic Regression, being both a predictive and an explanatory method, is one of the most commonly used statistical and machine learning method in almost all disciplines. There are many situations, however, when the accuracies of the fitted model are low for predicting either the success event or the failure event. Several statistical and machine learning approaches exist in the literature to handle these situations. This thesis presents several new approaches to improve the performance of the fitted model, and the proposed methods have been applied to real datasets.
Transformations of predictors is a common approach in fitting multiple linear and …
An Application Of Conformal Mapping To The Boundary Element Method For Unconfined Steady Seepage With A Phreatic Surface, Jorge Eduardo Reyes
An Application Of Conformal Mapping To The Boundary Element Method For Unconfined Steady Seepage With A Phreatic Surface, Jorge Eduardo Reyes
UNLV Theses, Dissertations, Professional Papers, and Capstones
In this thesis, numerical results using the Boundary Element Method (BEM) for groundwater flow in a domain with a boundary that contains numerous singularities with a phreatic surface are developed. The flow in the domain is modeled using Darcy’s law for a homogeneous isotropic porous medium. The boundary conditions are a combination of Dirichlet and Neumann with the phreatic surface having both boundary conditions. Exact solutions by Conformal Mapping for simplified domains with the same singularity as the original domain allow for modifications to the BEM resulting in an improvement to the numerical solution.
An iterative process is used to …
Numerical Study In The Conservative Arbitrary Lagrangian-Eulerian (Ale) Method For An Unsteady Stokes/Parabolic Interface Problem With Jump Coefficients And A Moving Interface, Michael Joseph Ramirez
Numerical Study In The Conservative Arbitrary Lagrangian-Eulerian (Ale) Method For An Unsteady Stokes/Parabolic Interface Problem With Jump Coefficients And A Moving Interface, Michael Joseph Ramirez
UNLV Theses, Dissertations, Professional Papers, and Capstones
Towards numerical analyses for fluid-structure interaction (FSI) problems in the future, in this thesis the arbitrary Lagrangian-Eulerian (ALE) finite element method within a conservative form is developed and analyzed for a linearized FSI problem - an unsteady Stokes/parabolic interface problem with jump coefficients and moving interface, and the corresponding mixed finite element approximation is developed and analyzed for both semi- and fully discrete schemes based upon the so-called conservative formulation. In terms of a novel H1-projection technique, their stability and optimal convergence properties are obtained for approximating the real solution equipped with lower regularity.
Numerical Analysis And Fluid Flow Modeling Of Incompressible Navier-Stokes Equations, Tahj Hill
Numerical Analysis And Fluid Flow Modeling Of Incompressible Navier-Stokes Equations, Tahj Hill
UNLV Theses, Dissertations, Professional Papers, and Capstones
The Navier-Stokes equations (NSE) are an essential set of partial differential equations for governing the motion of fluids. In this paper, we will study the NSE for an incompressible flow, one which density ρ = ρ0 is constant.
First, we will present the derivation of the NSE and discuss solutions and boundary conditions for the equations. We will then discuss the Reynolds number, a dimensionless number that is important in the observations of fluid flow patterns. We will study the NSE at various Reynolds numbers, and use the Reynolds number to write the NSE in a nondimensional form.
We will …