A Visual Analytics Approach for Correlation, Classification, and Regression Analysis
Chad A. Steed, J. Edward Swan II, Patrick J. Fitzpatrick, and T.J. Jankun-Kelly. A Visual Analytics Approach for Correlation, Classification, and Regression Analysis. Technical Report ORNL/TM-2012/68, Oak Ridge National Laboratory, Oak Ridge, TN, USA, 2012.
Download
Abstract
New approaches that combine the strengths of humans and machines are necessary to equip analysts with the proper tools for exploring today's increasing complex, multivariate data sets. In this paper, a visual data mining framework, called the Multidimensional Data eXplorer (MDX), is described that addresses the challenges of today's data by combining automated statistical analytics with a highly interactive parallel coordinates based canvas. In addition to several intuitive interaction capabilities, this framework offers a rich set of graphical statistical indicators, interactive regression analysis, visual correlation mining, automated axis arrangements and filtering, and data classification techniques. The current work provides a detailed description of the system as well as a discussion of key design aspects and critical feedback from domain experts.
BibTeX
@TechReport{TR12-vaa,
author = {Chad A. Steed and J. Edward {Swan~II} and Patrick J. Fitzpatrick
and T.J. Jankun-Kelly},
title = {A Visual Analytics Approach for Correlation, Classification, and
Regression Analysis},
institution = {Oak Ridge National Laboratory, Oak Ridge, TN, USA},
type = {Technical Report},
number = {ORNL/TM-2012/68},
date = {February 21},
month = {February},
year = 2012,
abstract = {
New approaches that combine the strengths of humans and machines are
necessary to equip analysts with the proper tools for exploring
today's increasing complex, multivariate data sets. In this paper, a
visual data mining framework, called the Multidimensional Data
eXplorer (MDX), is described that addresses the challenges of today's
data by combining automated statistical analytics with a highly
interactive parallel coordinates based canvas. In addition to several
intuitive interaction capabilities, this framework offers a rich set of
graphical statistical indicators, interactive regression analysis,
visual correlation mining, automated axis arrangements and filtering,
and data classification techniques. The current work provides a
detailed description of the system as well as a discussion of key
design aspects and critical feedback from domain experts.
},
}