No description available.

One often wishes to understand the probability distribution of stochastic data from experiment or computer simulations. However, where no model is given, practitioners must resort to parametric or non-parametric methods in order to gain information about the underlying distribution. Others have used initially a nonparametric estimator in order to understand the underlying shape of a set of data, and then later returned with a parametric method to locate the peaks. However they are interested in estimating spectra, which may have multiple peaks, where in this work we are interested in approximating the peak position of a single-peak probability distribution. One method of analyzing a distribution of data is by fitting a curve to, or smoothing them. Polynomial regression and least-squares fit are examples of smoothing methods. Initial understanding of the underlying distribution can be obscured depending on the degree of smoothing. Problems such as under and oversmoothing must be addressed in order to determine the shape of the underlying distribution. Furthermore, smoothing of skewed data can give a biased estimation of the peak position. We propose two new approaches for statistical mode estimation based on the assumption that the underlying distribution has only one peak. The first method imposes the global constraint of unimodality locally, by requiring negative curvature over some domain. The second method performs a search that assumes a position of the distribution's peak and requires positive slope to the left, and negative slope to the right. Each approach entails a constrained least-squares fit to the raw cumulative probability distribution. We compare the relative efficiencies [12] of finding the peak location of these two estimators for artificially generated data from known families of distributions Weibull, beta, and gamma. Within each family a parameter controls the skewness or kurtosis, quantifying the shapes of the distributions for comparison. We also compare our methods with other estimators such as the kernel-density estimator, adaptive histogram, and polynomial regression. By comparing the effectiveness of the estimators, we can determine which estimator best locates the peak position. We find that our estimators do not perform better than other known estimators. We also find that our estimators are biased. Overall, an adaptation of kernel estimation proved to be the most efficient. The results for the work done in this thesis will be submitted, in a different form, for publication by D.A. Rabson and J.K. Looper.

Title from PDF of title page. / Document formatted into pages; contains 93 pages. / Thesis (M.S.)--University of South Florida, 2003. / Includes bibliographical references. / Text (Electronic thesis) in PDF format. / ABSTRACT: One often wishes to understand the probability distribution of stochastic data from experiment or computer simulations. However, where no model is given, practitioners must resort to parametric or non-parametric methods in order to gain information about the underlying distribution. Others have used initially a nonparametric estimator in order to understand the underlying shape of a set of data, and then later returned with a parametric method to locate the peaks. However they are interested in estimating spectra, which may have multiple peaks, where in this work we are interested in approximating the peak position of a single-peak probability distribution. One method of analyzing a distribution of data is by fitting a curve to, or smoothing them. Polynomial regression and least-squares fit are examples of smoothing methods. Initial understanding of the underlying distribution can be obscured depending on the degree of smoothing. / ABSTRACT: Problems such as under and oversmoothing must be addressed in order to determine the shape of the underlying distribution.Furthermore, smoothing of skewed data can give a biased estimation of the peak position. We propose two new approaches for statistical mode estimation based on the assumption that the underlying distribution has only one peak. The first method imposes the global constraint of unimodality locally, by requiring negative curvature over some domain. The second method performs a search that assumes a position of the distribution's peak and requires positive slope to the left, and negative slope to the right. / ABSTRACT: Each approach entails a constrained least-squares fit to the raw cumulative probability distribution.We compare the relative efficiencies [12] of finding the peak location of these two estimators for artificially generated data from known families of distributions Weibull, beta, and gamma. Within each family a parameter controls the skewness or kurtosis, quantifying the shapes of the distributions for comparison. We also compare our methods with other estimators such as the kernel-density estimator, adaptive histogram, and polynomial regression. By comparing the effectiveness of the estimators, we can determine which estimator best locates the peak position. We find that our estimators do not perform better than other known estimators. We also find that our estimators are biased. / ABSTRACT: Overall, an adaptation of kernel estimation proved to be the most efficient.The results for the work done in this thesis will be submitted, in a different form, for publication by D.A. Rabson and J.K. Looper. / System requirements: World Wide Web browser and PDF reader. / Mode of access: World Wide Web.

This paper is concerned with the numerical analysis of the autoconvolution equation $x*x=y$ restricted to the interval [0,1]. We present a discrete constrained least squares approach and prove its convergence in $L^p(0,1),1<p<\infinite$ , where the regularization is based on a prescribed bound for the total variation of admissible solutions. This approach includes the case of non-smooth solutions possessing jumps. Moreover, an adaption to the Sobolev space $H^1(0,1)$ and some remarks on monotone functions are added. The paper is completed by a numerical case study concerning the determination of non-monotone smooth and non-smooth functions x from the autoconvolution equation with noisy data y.

In this paper an overview is given on the application of directional basis functions, known under the name Curvelets/Contourlets, to various aspects of seismic processing and imaging. Key concepts in the approach are the use of (i) that localize in both domains (e.g. space and angle); (ii) non-linear estimation, which corresponds to localized muting on the coefficients, possibly supplemented by constrained optimization (iii) invariance of the basis functions under the imaging operators. We will discuss applications that include multiple and ground roll removal; sparseness-constrained least-squares migration and the computation of 4-D difference cubes.

This paper is concerned with the numerical analysis of the autoconvolution equation $x*x=y$ restricted to the interval [0,1]. We present a discrete constrained least squares approach and prove its convergence in $L^p(0,1),1<p<\infinite$ , where the regularization is based on a prescribed bound for the total variation of admissible solutions. This approach includes the case of non-smooth solutions possessing jumps. Moreover, an adaption to the Sobolev space $H^1(0,1)$ and some remarks on monotone functions are added. The paper is completed by a numerical case study concerning the determination of non-monotone smooth and non-smooth functions x from the autoconvolution equation with noisy data y.

Nonnegative matrix factorization (NMF) is a useful dimension reduction method that has been investigated and applied in various areas. NMF is considered for high-dimensional data in which each element has a nonnegative value, and it provides a low-rank approximation formed by factors whose elements are also nonnegative. The nonnegativity constraints imposed on the low-rank factors not only enable natural interpretation but also reveal the hidden structure of data. Extending the benefits of NMF to multidimensional arrays, nonnegative tensor factorization (NTF) has been shown to be successful in analyzing complicated data sets. Despite the success, NMF and NTF have been actively developed only in the recent decade, and algorithmic strategies for computing NMF and NTF have not been fully studied. In this thesis, computational challenges regarding NMF, NTF, and related least squares problems are addressed. First, efficient algorithms of NMF and NTF are investigated based on a connection from the NMF and the NTF problems to the nonnegativity-constrained least squares (NLS) problems. A key strategy is to observe typical structure of the NLS problems arising in the NMF and the NTF computation and design a fast algorithm utilizing the structure. We propose an accelerated block principal pivoting method to solve the NLS problems, thereby significantly speeding up the NMF and NTF computation. Implementation results with synthetic and real-world data sets validate the efficiency of the proposed method. In addition, a theoretical result on the classical active-set method for rank-deficient NLS problems is presented. Although the block principal pivoting method appears generally more efficient than the active-set method for the NLS problems, it is not applicable for rank-deficient cases. We show that the active-set method with a proper starting vector can actually solve the rank-deficient NLS problems without ever running into rank-deficient least squares problems during iterations. Going beyond the NLS problems, it is presented that a block principal pivoting strategy can also be applied to the l1-regularized linear regression. The l1-regularized linear regression, also known as the Lasso, has been very popular due to its ability to promote sparse solutions. Solving this problem is difficult because the l1-regularization term is not differentiable. A block principal pivoting method and its variant, which overcome a limitation of previous active-set methods, are proposed for this problem with successful experimental results. Finally, a group-sparsity regularization method for NMF is presented. A recent challenge in data analysis for science and engineering is that data are often represented in a structured way. In particular, many data mining tasks have to deal with group-structured prior information, where features or data items are organized into groups. Motivated by an observation that features or data items that belong to a group are expected to share the same sparsity pattern in their latent factor representations, We propose mixed-norm regularization to promote group-level sparsity. Efficient convex optimization methods for dealing with the regularization terms are presented along with computational comparisons between them. Application examples of the proposed method in factor recovery, semi-supervised clustering, and multilingual text analysis are presented.

Pro optimalizaci letových trajektorií ve velmi malé nadmorské výšce, terenní vlastnosti musí být zahrnuty velice přesne. Proto rychlá a efektivní evaluace terenních dat je velice důležitá vzhledem nato, že čas potrebný pro optimalizaci musí být co nejkratší. Navyše, na optimalizaci letové trajektorie se využívájí metody založené na výpočtu gradientu. Proto musí být aproximační funkce terenních dat spojitá do určitého stupne derivace. Velice nádejná metoda na aproximaci terenních dat je aplikace víceroměrných simplex polynomů. Cílem této práce je implementovat funkci, která vyhodnotí dané terenní data na určitých bodech spolu s gradientem pomocí vícerozměrných splajnů. Program by měl vyčíslit více bodů najednou a měl by pracovat v $n$-dimensionálním prostoru.