Howard Hughes Medical Institute (HHMI) researchers have developed Janelia Automatic Animal Behavior Annotator (JAABA), software that can recognize characteristic animal behaviors like an experienced biologist. The researchers say JAABA can automate and standardize the essential but time-consuming task of classifying animal behavior. "We need automated techniques to keep up with the technology," says HHMI's Kristin Branson.
JAABA can be trained to recognize behaviors in a variety of animals, including adult fruit flies, fruit fly larvae, and mice. "This gives us some very simple information, like speed or how long an animal spends in a certain part of its environment," Branson says. The software also can produce behavior detectors based on training data in as little at 15 seconds. The immediate feedback can help users understand how the software is performing and recognize areas in which it requires additional training, according to Branson.
"Most biologists don't have a background in machine learning, so having an interactive framework where you can see what the classifier can and can't do gives them some comfort interacting with these complicated algorithms," Branson says.
From Howard Hughes Medical Institute
View Full Article
Abstracts Copyright © 2012 Information Inc., Bethesda, Maryland, USA
No entries found