October 4, 2007, CS COLLOQUIUM
The Thrill of Discovery: Information Visualization for High-Dimensional Spaces
Ben Shneiderman, University of Maryland
In this colloquium, Professor Shneiderman introduced the concept of information visualization and presented the research achievement in his Human-Computer Interaction Lab.
Information visualization is a good approach to assisting the user in observing the data distribution in chosen feature space. It is the presentation of abstract data in a graphical form so that the user may use his visual perception to evaluate and analyze the data. Professor Shneiderman presented his information visualization research with different data type: 1-D Linear, 2-D Map, 3-D world, multi-var, Temporal, tree and Network. Professor Shneiderman also introduced the Interactive Exploration Tool of Multidimensional Data, Hierarchical Clustering Explorer (HCE), which applies the hierarchical clustering algorithm without a predetermined number of clusters, and then enables users to determine the natural grouping with interactive visual feedback (dendrogram and color mosaic) and dynamic query controls.
Through the Information visualization, we can present data to users, by means of images instead of abstract data. And then help users to improve understanding of the data being presented.