Visualizing High-dimensional Data by Introducing Map Metaphors

2016 Fiscal Year Final Research Report

• Project/Area Number: 26730061
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: High performance computing
• Research Institution: Keio University (2015-2016); The University of Tokyo (2014)
• Principal Investigator: WU Hsiang-Yun 慶應義塾大学, 理工学部(矢上), 特任助教 (00706749)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: 高次元データ / 視覚メタファー / 地図

Outline of Final Research Achievements

In this research, (1) a construction of algorithms for transforming numerical data to geographical data, (2) an improvement in readability of map expressions by introducing intuitive map compositions and annotation placement, (3) a framework of map customization according to user preference. The three challenges of the project were conducted step-by-step within the three years. We formulate the problem as a series of visualization processes from the transformation of high dimensional numerical data to geographical data, and generation of intuitive map representation. Furthermore, we define aesthetic criteria for representing optimality at each stage of data conversion and visualization. The presentation results are also changed according to the users' preferences through several intervention processes. The effectiveness of the approach was evaluated and verified through several experiments using an eye-tracking system.

Free Research Field

情報可視化