Visual Identification and Extraction of Intrinsic Axes in High-Dimensional Data

Abstract

Interactive axis extraction for high-dimensional data visualization has been demonstrated to be powerful in high-dimensional data exploring and understanding. The extracted axes help to yield new 2-D arrangements of data points, providing new insights into the data. However, the existing interfaces for extraction only support linear axes or non-linear axes without specific semantics. When the data points lie in a manifold, it is hard to capture intrinsic features of the manifold by either linear axes or non-linear axes without specific semantics. Furthermore, a dataset with complicated topology would contain holes and branches. While a branch often indicates a local trend, it may not make sense to project data points to an axis in a different branch. In this paper, we propose an interactive visual interface to identify and extract intrinsic axes in high-dimensional data. The system contains four major views. The topology view presents the skeleton-based topology of the dataset. The detail view provides a force-directed layout of a high-dimensional data and allows interactive extracting intrinsic axes. The characteristics of extracted axes are visualized in the intrinsic axes view. The projection view layouts data points aligning with extracted intrinsic axes. Case studies and comparative experiments demonstrate the usefulness of our visual analytics system.