Elke Rundensteiner, the William Smith Dean’s Professor in Computer Science and Founding Head of WPI’s Data Science Program, recently received the InfoVis 20-Year Test-of-Time Award from the Institute of Electrical and Electronics Engineers (IEEE) for her pioneering work on data visualization and visual analytics in 2003.
This award honors articles published at previous IEEE conferences, in this case in 2003, that have withstood the test of time by remaining useful 20 years later and that have had significant impact and influence on future advances within and beyond the visualization community, according to the award’s organizers. Award selection is based on measures such as the numbers of citations, the quality and influence of its ideas, and other criteria.
Rundensteiner and her team, which included the late computer science professor Matthew Ward and former PhD students Jing Yang and Wei Peng, are being honored for their work on interactive hierarchical dimension ordering, spacing, and filtering for the exploration of high-dimensional datasets.
“I fondly remember my close research collaboration with my colleague Matt Ward over a 17-year time span from 1998 to 2014 that resulted in a series of 7 National Science Foundation (NSF) research grants and one National Security Agency (NSA) grant for our work at the intersection of visualization and data analytics,” Rundensteiner said. “This allowed us to collaborate with countless joint PhD students, contributing cutting-edge advances to the then-newly emerging area of visual analytics, which led to this inspiring award. Matt was not only a creative thinker at the forefront of his time, he was a supportive colleague and generous friend and remains a true inspiration for me.”
According to the award selection committee, the work that Rundensteiner and her team undertook presents a thoughtful, elegant, and powerful approach to managing the complexities of high-dimensional data and reducing clutter in visualizations such as parallel coordinates. The team’s research provided insight by clustering the dimensions of high-dimensional data sets into a hierarchical structure (instead of just clustering the data itself), which then can be exploited to make sense of this complex data more efficiently. The paper, “Interactive heirarchical dimension ordering, spacing and filtering for exploration of high dimensional datasets,” laid the groundwork for subsequent research and influenced the design of other tools and techniques, the award committee noted.
“Citations to the original paper have increased over time, showing evidence of lasting value, and the ideas introduced in the work are still relevant today,” the award committee wrote. “The paper shows us how we can solve a problem through interactive visualization design and presents convincing options for future analysts and designers. These ideas underpin subsequent research on synthesizing new summary dimensions, contribute to contemporary thinking on explainability, and have influenced the design of many other high dimensional visualization tools and techniques.”