Communications of the ACM
New Data Science Method Makes Charts Easier to Read at a Glance
Researchers at Columbia Engineering and Tufts University have developed a technique for measuring visual complexity by supplying a score that automatically identifies difficult charts.
Credit: Gabriel Ryan/Wu Lab/Columbia Engineering
Columbia Engineering and Tufts University researchers have developed a technique to measure visual complexity by supplying a score that automatically identifies difficult charts.
The researchers say the "Pixel Approximate Entropy" method could help first responders in emergency situations read data at a glance and make better decisions faster.
Says Columbia's Gabriel Ryan, "Our method gives visualization systems a way to measure how difficult line charts are to read, so now we can design these systems to automatically simplify or summarize charts that would be hard to read on their own."
Ryan and Columbia's Eugene Wu tweaked a low-dimensional entropy measure to operate on line charts, then performed user studies to demonstrate the quantification could predict how well users perceived the content of charts.
The researchers believe the method will help developers advance artificial intelligence-driven data science systems.
From Columbia Engineering
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found