4 February 2013 Improving projection-based data analysis by feature space transformations
Author Affiliations +
Generating effective visual embedding of high-dimensional data is difficult - the analyst expects to see the structure of the data in the visualization, as well as patterns and relations. Given the high dimensionality, noise and imperfect embedding techniques, it is hard to come up with a satisfactory embedding that preserves the data structure well, whilst highlighting patterns and avoiding visual clutters at the same time. In this paper, we introduce a generic framework for improving the quality of an existing embedding in terms of both structural preservation and class separation by feature space transformations. A compound quality measure based on structural preservation and visual clutter avoidance is proposed to access the quality of embeddings. We evaluate the effectiveness of our approach by applying it to several widely used embedding techniques using a set of benchmark data sets and the result looks promising.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Matthias Schaefer, Matthias Schaefer, Leishi Zhang, Leishi Zhang, Tobias Schreck, Tobias Schreck, Andrada Tatu, Andrada Tatu, John A. Lee, John A. Lee, Michel Verleysen, Michel Verleysen, Daniel A. Keim, Daniel A. Keim, } "Improving projection-based data analysis by feature space transformations", Proc. SPIE 8654, Visualization and Data Analysis 2013, 86540H (4 February 2013); doi: 10.1117/12.2000701; https://doi.org/10.1117/12.2000701


A survey and task based quality assessment of static 2D...
Proceedings of SPIE (February 08 2015)
Geodesic self-organizing map
Proceedings of SPIE (March 11 2005)
Visualization of cluster hierarchies
Proceedings of SPIE (May 14 1998)

Back to Top