Theses and Dissertations from UMD

Permanent URI for this communityhttp://hdl.handle.net/1903/2

New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a give thesis/dissertation in DRUM

More information is available at Theses and Dissertations at University of Maryland Libraries.

Browse

Filters

2012 - 20132

Settings

Subject: search.filters.subject.Laplacian Eigenmaps

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Data Representation for Learning and Information Fusion in Bioinformatics
    (2013) Rajapakse, Vinodh Nalin; Czaja, Wojciech; Mathematics; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This thesis deals with the rigorous application of nonlinear dimension reduction and data organization techniques to biomedical data analysis. The Laplacian Eigenmaps algorithm is representative of these methods and has been widely applied in manifold learning and related areas. While their asymptotic manifold recovery behavior has been well-characterized, the clustering properties of Laplacian embeddings with finite data are largely motivated by heuristic arguments. We develop a precise bound, characterizing cluster structure preservation under Laplacian embeddings. From this foundation, we introduce flexible and mathematically well-founded approaches for information fusion and feature representation. These methods are applied to three substantial case studies in bioinformatics, illustrating their capacity to extract scientifically valuable information from complex data.
  • Thumbnail Image
    Item
    A Study of the Relationship Between Spectrum and Geometry Through Fourier Frames and Laplacian Eigenmaps
    (2012) Duke, Kevin W.; Benedetto, John J.; Mathematics; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This thesis has two parts. The first part is a study of Fourier frames. We follow the development of the theory, beginning with its classical roots in non-uniform sampling in Paley-Wiener Spaces, to its current state, the study of the spectral properties of finite measures on locally compact abelian groups. The aim of our study is to understand the relationship between the geometry of the supporting set of a measure and the spectral properties it exhibits. In the second part, we study extensions of the Laplacian Eigenmaps algorithm and their uses in hyperspectral image analysis. In particular, we show that there is a natural way of including spatial information in the analysis that improves classification results. We also provide evidence supporting the use of Schrödinger Eigenmaps as a semisupervised tool for feature extraction. Finally, we show that Schrödinger Eigenmaps provides a platform for fusing Laplacian Eigenmaps with other clustering techniques, such as kmeans clustering.