iPCA: An Interactive System for PCA‐based Visual Analytics

Principle Component Analysis (PCA) is a widely used mathematical technique in many fields for factor and trend analysis, dimension reduction, etc. However, it is often considered to be a “black box” operation whose results are difficult to interpret and sometimes counter‐intuitive to the user. In order to assist the user in better understanding and utilizing PCA, we have developed a system that visualizes the results of principal component analysis using multiple coordinated views and a rich set of user interactions. Our design philosophy is to support analysis of multivariate datasets through extensive interaction with the PCA output. To demonstrate the usefulness of our system, we performed a comparative user study with a known commercial system, SAS/INSIGHT's Interactive Data Exploration. Participants in our study solved a number of high‐level analysis tasks with each interface and rated the systems on ease of learning and usefulness. Based on the participants' accuracy, speed, and qualitative feedback, we observe that our system helps users to better understand relationships between the data and the calculated eigenspace, which allows the participants to more accurately analyze the data. User feedback suggests that the interactivity and transparency of our system are the key strengths of our approach.

[1]  Heidrun Schumann,et al.  Enhancing the visualization process with principal component analysis to support the exploration of trends , 2006, APVIS.

[2]  Kai Li,et al.  Visualization methods for statistical analysis of microarray clusters , 2005, BMC Bioinformatics.

[3]  John T. Stasko,et al.  Dust & Magnet: Multivariate Information Visualization Using a Magnet Metaphor , 2005, Inf. Vis..

[4]  Deborah Silver,et al.  Illustrative Deformation for Data Exploration , 2007, IEEE Transactions on Visualization and Computer Graphics.

[5]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[6]  I. Jolliffe Principal Component Analysis , 2002 .

[7]  Ben Shneiderman,et al.  Knowledge discovery in high-dimensional data: case studies and a user survey for the rank-by-feature framework , 2006, IEEE Transactions on Visualization and Computer Graphics.

[8]  Shiping Huang,et al.  Exploration of dimensionality reduction for text visualization , 2005, Coordinated and Multiple Views in Exploratory Visualization (CMV'05).

[9]  Yehuda Koren,et al.  Visualization of labeled data using linear transformations , 2003, IEEE Symposium on Information Visualization 2003 (IEEE Cat. No.03TH8714).

[10]  Christopher Ahlberg,et al.  Spotfire: an information exploration environment , 1996, SGMD.

[11]  Marc Alexa,et al.  Visual component analysis , 2004, VISSYM'04.

[12]  Ravin Balakrishnan,et al.  Using deformations for browsing volumetric data , 2003, IEEE Visualization, 2003. VIS 2003..

[13]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Luis Mateus Rocha,et al.  Singular value decomposition and principal component analysis , 2003 .

[15]  Jürgen Koenemann,et al.  A comparative usability evaluation of user interfaces for online product catalog , 2000, EC '00.

[16]  Jessica K. Hodgins,et al.  Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces , 2004, SIGGRAPH 2004.

[17]  Chris North,et al.  An Insight-Based Longitudinal Study of Visual Analytics , 2006, IEEE Transactions on Visualization and Computer Graphics.

[18]  Christopher Williamson,et al.  Dynamic queries for information exploration: an implementation and evaluation , 1992, CHI.

[19]  M. Brand,et al.  Fast low-rank modifications of the thin singular value decomposition , 2006 .

[20]  Benjamin B. Bederson,et al.  Does zooming improve image browsing? , 1999, DL '99.