Supporting Large-scale Geographical Visualization in a Multi-granularity Way

Abstract

Urban data (e.g., real estate data, crime data) often have multiple attributes which are highly geography-related. With the scale of data increases, directly visualizing millions of individual data points on top of a map would overwhelm users’ perceptual and cognitive capacity and lead to high latency when users interact with the data. In this demo, we present ConvexCubes, a system that supports interactive visualization of large-scale multidimensional urban data in a multi-granularity way. Comparing to state-of-theart visualization-driven data structures, it exploits real-world geographic semantics (e.g., country, state, city) rather than using gridbased aggregation. Instead of calculating everything on demand, ConvexCubes utilizes existing visualization results to efficiently support different kinds of user interactions, such as zooming & panning, filtering and granularity control

Publication
In the 11th ACM International Conference on Web Search and Data Mining (WSDM)