Two-stage framework for visualization of clustered high dimensional data

In this paper, we discuss dimension reduction methods for 2D visualization of high dimensional clustered data. We propose a two-stage framework for visualizing such data based on dimension reduction methods. In the first stage, we obtain the reduced dimensional data by applying a supervised dimensio...

Full description

Saved in:
Bibliographic Details
Published in:2009 IEEE Symposium on Visual Analytics Science and Technology pp. 67 - 74
Main Authors: Jaegul Choo, Bohn, S., Haesun Park
Format: Conference Proceeding
Language:English
Published: IEEE 2009
Subjects:
2D projection
Algorithm design and analysis
clustered data
Data visualization
dimension reduction
Drives
Educational institutions
generalized singular value decomposition
Information analysis
Laboratories
Linear discriminant analysis
orthogonal centroid method
Principal component analysis
regularization
Scattering
Visual analytics
ISBN:9781424452835, 142445283X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we discuss dimension reduction methods for 2D visualization of high dimensional clustered data. We propose a two-stage framework for visualizing such data based on dimension reduction methods. In the first stage, we obtain the reduced dimensional data by applying a supervised dimension reduction method such as linear discriminant analysis which preserves the original cluster structure in terms of its criteria. The resulting optimal reduced dimension depends on the optimization criteria and is often larger than 2. In the second stage, the dimension is further reduced to 2 for visualization purposes by another dimension reduction method such as principal component analysis. The role of the second-stage is to minimize the loss of information due to reducing the dimension all the way to 2. Using this framework, we propose several two-stage methods, and present their theoretical characteristics as well as experimental comparisons on both artificial and real-world text data sets.
ISBN:9781424452835
142445283X
DOI:10.1109/VAST.2009.5332629