Date of Award

2024

Degree Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Computer Science and Statistics

First Advisor

Noah Daniels

Abstract

Visualizing high dimensional data can be a challenging task due to the difficulty people face in comprehending information beyond three dimensions. Further research and development of tools in this area could prove valuable for creating efficient, intuitive, and accurate visualizations. It could also provide insight into the manifold hypothesis, which suggests that high dimensional data can exist in low dimensional space.

This thesis proposes the utilization of clustered manifold mapping as a novel visualization technique that summarizes a dataset into a hierarchal tree of clusters by partitioning the data based on a user-specified distance metric. A subset of clusters can be carefully selected from the tree to create a 3D graph using the Unity game engine, which enables the user to interact with the and explore various features of the data.

The graphs produced with this approach will be quantitatively and qualitatively compared with existing methods such as UMAP, which demonstrates its contributions to the field of visualizing high dimensional data. Furthermore, visualizing the tree of clusters in addition to the graph provides a greater understanding into the field of clustered manifold mapping.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.