The Community for Technology Leaders
Green Image
Issue No. 02 - Feb. (2013 vol. 19)
ISSN: 1077-2626
pp: 291-305
J. E. Nam , Microsoft Corp., Redmond, WA, USA
K. Mueller , Microsoft Corp., Redmond, WA, USA
Gaining a true appreciation of high-dimensional space remains difficult since all of the existing high-dimensional space exploration techniques serialize the space travel in some way. This is not so foreign to us since we, when traveling, also experience the world in a serial fashion. But we typically have access to a map to help with positioning, orientation, navigation, and trip planning. Here, we propose a multivariate data exploration tool that compares high-dimensional space navigation with a sightseeing trip. It decomposes this activity into five major tasks: 1) Identify the sights: use a map to identify the sights of interest and their location; 2) Plan the trip: connect the sights of interest along a specifyable path; 3) Go on the trip: travel along the route; 4) Hop off the bus: experience the location, look around, zoom into detail; and 5) Orient and localize: regain bearings in the map. We describe intuitive and interactive tools for all of these tasks, both global navigation within the map and local exploration of the data distributions. For the latter, we describe a polygonal touchpad interface which enables users to smoothly tilt the projection plane in high-dimensional space to produce multivariate scatterplots that best convey the data relationships under investigation. Motion parallax and illustrative motion trails aid in the perception of these transient patterns. We describe the use of our system within two applications: 1) the exploratory discovery of data configurations that best fit a personal preference in the presence of tradeoffs and 2) interactive cluster analysis via cluster sculpting in N-D.
travel industry, computational geometry, data analysis, data structures, data visualisation, interactive systems, pattern clustering, high-D data visualization systems, TripAdvisorN-D, tourism-inspired high-dimensional space exploration framework, space travel, positioning, orientation, global navigation, trip planning, multivariate data exploration tool, sight identification, go-on-the-trip, hop-off-the-bus, orient-and-localize, interactive tools, data distributions, polygonal touchpad interface, motion parallax, illustrative motion, exploratory data discovery, interactive cluster analysis, cluster sculpting, data representation, Vectors, Principal component analysis, Navigation, Three dimensional displays, Data visualization, Space exploration, Measurement, visual analytics, High-dimensional data, coordinated and multiple views, zooming and navigation techniques, data transformation and representation, data clustering
J. E. Nam, K. Mueller, "TripAdvisor^{N-D}: A Tourism-Inspired High-Dimensional Space Exploration Framework with Overview and Detail", IEEE Transactions on Visualization & Computer Graphics, vol. 19, no. , pp. 291-305, Feb. 2013, doi:10.1109/TVCG.2012.65
190 ms
(Ver 3.3 (11022016))