Communications of the ACM
Crowdsourcing Nutrition in a Snap
Credit: Dr. Jay Heller's Blog
Harvard University researchers have developed PlateMate, software that enable users to utilize crowdsourcing to determine the calorie levels of their meals. Users take a picture of each meal and submit it to the crowd, which estimates the calorie level. In testing, PlateMate's calorie estimates have proven to be just as accurate as those of trained nutritionists, and more accurate than the user's own logs.
"Estimating the nutritional value of a meal is a fairly complex task, from a computational standpoint, but with a structured workflow and some cultural awareness, we've expanded what crowdsourcing can achieve," says Microsoft's Jon Noronha, who co-developed PlateMate as an undergraduate student at Harvard. PlateMate, which works in conjunction with Amazon Mechanical Turk, divides nutrition analysis into several tasks, asking groups of Turkers to distinguish between foods in the photo and estimate the calorie values. The researchers designed simple, clearly defined tasks, and algorithms that compare several answers and choose the best one.
"What makes the nutrition application so interesting as a problem in crowdsourcing is that computers are so very far away from doing it on their own — because food is such a human thing," Noronha says.
From Harvard University
View Full Article
Abstracts Copyright © 2011 Information Inc., Bethesda, Maryland, USA
No entries found