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

Steed, Chad A¹  SwanII, J. Edward²  Fitzpatrick, Patrick J.²  Jankun-Kelly, T.J.² 

[1] ORNL;Mississippi State University (MSU)

关键词: CLASSIFICATION;    DESIGN;    FEEDBACK;    REGRESSION ANALYSIS;    DATA ACQUISITION SYSTEMS visual analytics;    parallel coordinates;    information visualization;    correlation mining;    regression;    data classification;    multivariate analysis;   

DOI  :  10.2172/1035521
RP-ID  :  ORNL/TM-2012/68
PID  :  OSTI ID: 1035521
Others  :  TRN: US201205%%410

学科分类：社会科学、人文和艺术（综合）

美国|英语

来源: SciTech Connect

【 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.