Enabling decision trend analysis with interactive scatter plot matrices visualization

详细信息    查看全文

• 作者：Wen Bo Wang^a ; Mao Lin Huang^a ; ^b ; ^{mao.huang@uts.edu.au" class="auth_mail" title="E-mail the corresponding author} ; Quang Vinh Nguyen^d ; Weidong Huang^e ; Kang Zhang^b ; ^c ; Tze-Haw Huang^a
• 关键词：Rough set theory ; Dimensionality reduction ; Scatter plot matrices ; Parrallel coordinate geomery ; Visual data analytics ; Visual decision making
• 刊名：Journal of Visual Languages & Computing
• 出版年：2016
• 出版时间：April 2016
• 年：2016
• 卷：33
• 期：Complete
• 页码：13-23
• 全文大小：5900 K

文摘

This paper presents a new interactive scatter plot visualization for multi-dimensional data analysis. We apply Rough Set Theory (RST) to reduce the visual complexity through dimensionality reduction. We use an innovative point-to-region mouse click concept to enable direct interactions with scatter points that are theoretically impossible. To show the decision trend we use a virtual Z dimension to display a set of linear flows showing approximation of the decision trend. We conducted case studies to demonstrate the effectiveness and usefulness of our new technique for analyzing the property of three popular data sets including wine quality, wages and cars. The paper also includes a pilot usability study to evaluate parallel coordinate visualization with scatter plot matrices visualization with RST results.