University of Houston
Department of Computer Science
In partial fulfillment of the Requirements for the Degree of
Master of Science


Wei Kang
will defend his thesis

An Empirical Evaluation of Clustering Algorithms Applied to Martian Topography

Abstract

With Mars becoming the center of our spatial exploration, there is an increased need to obtain Martian topography images from orbiters to elucidate topographic features such as craters, plateaus and channels. To perform this task, appropriate clustering algorithms need to be chosen from a large family of clustering methodologies. In this thesis we show an empirical evaluation of various clustering algorithms applied to Martian topography data. These clustering algorithms include agglomerative clustering, k-Means, fuzzy c-Means, EM (Expectation Maximization), SOM (Self Organizing Maps). We also tried SVM (Support Vector Machines), a relatively new supervised learning method.

Date: Monday, April 25th, 2005
Time: 4:00 PM
Place: 550-PGH



Faculty, students, and the general public are invited.
Thesis Advisor: Dr. Ricardo Vilalta