A Visual Analytics Approach for Correlation, Classification, and Regression Analysis

Steed, Chad A ; SwanII, J. Edward ; Fitzpatrick, Patrick J. ; Jankun-Kelly, T.J.

Oak Ridge National Laboratory

关键词: Visual Analytics;    Multivariate Analysis;    Correlation Mining;    Feedback;    Parallel Coordinates;   

DOI  :  10.2172/1035521
RP-ID  :  ORNL/TM-2012/68
RP-ID  :  DE-AC05-00OR22725
RP-ID  :  1035521

美国|英语

来源: UNT Digital Library

【 摘 要 】

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 novel 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.