A Comparison of Some Dimension Reduction Techniques with Varied Parameters
Issue Date
2017-13-31Author
Oderio, Nicholas
Publisher
University of Kansas
Format
46 pages
Type
Thesis
Degree Level
M.A.
Discipline
Mathematics
Rights
Copyright held by the author.
Metadata
Show full item recordAbstract
This paper presents and explains several methods of dimensionality reduction of data sets, beginning with the well known PCA and moving onto techniques that deal with data on a nonlinear manifold. Methods for handling data whose underlying structure is a nonlinear manifold are separated by whether or not sparse matrices are involved in the computation. Additionally, the methods discussed are demonstrated and compared by running them on data sets whose underlying structure is known. Results from same methods with different values for input parameters are also examined. Finally, some results on a small set of Persyst EEG data collected as a part of the Epilepsy Bioinformatics Study for Antiepileptogenic Therapy from the Laboratory of Neuro Imaging at USC Stevens Institute of Neuroimaging and Informatics in the Keck School of Medicine of USC is analyzed using some of these methods.
Collections
- Mathematics Dissertations and Theses [179]
- Theses [3901]
Items in KU ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
We want to hear from you! Please share your stories about how Open Access to this item benefits YOU.