Visual Cluster Analysis of Multidimensional Data

PhD Thesis Proposal Defence


Title: "Visual Cluster Analysis of Multidimensional Data"

by

Mr. Nan CAO


ABSTRACT:

Multidimensional data are commonly used to represent both structured and 
unstructured information. Unfortunately, multidimensional data analysis is 
very challenging as the data are usually complex in nature, huge in 
amount, and contain both statistical and geometrical features. Clustering 
as a fundamental data analysis technique has been widely used in many 
applications. However, it is often difficult for users to understand and 
evaluate multidimensional clustering results, especially the quality of 
clusters and their semantics. Information visualization can be of great 
value for multidimensional data analysis as it can represent 
multidimensional data in intuitive ways and also support explorative 
visual analysis which keeps humans in the loop.

In this thesis proposal, we introduce two categories of visualization 
designs for multivariate data cluster analysis and multifaceted topic 
investigation respectively. Four different visualizations have been 
introduced within these two categories. In the first category, we design 
DICON an icon-based cluster visualization that embeds statistical 
information into a multi-attribute display to facilitate cluster 
interpretation, evaluation, and comparison. For the second category, we 
introduce ContexTour, FacetAtlas, and SolarMap, all of which are based on 
our proposed multifaceted entity relational data model. All of these 
visualizations are designed to uncover the multidimensional cluster 
patterns from different perspectives.


Date:                   Monday, 28 May 2012

Time:                   10:00am - 12:00noon

Venue:                  Room 3494
                         lifts 25/26

Committee Members:      Dr. Huamin Qu (Supervisor)
                         Dr. Pedro Sander (Chairperson)
 			Prof. Long Quan
 			Dr. Chiew-Lan Tai


**** ALL are Welcome ****