JAABA - Janelia Automatic Animal Behavior Annotator

The Janelia Automatic Animal Behavior Annotator (JAABA) is a machine learning-based system that enables researchers to automatically compute interpretable, quantitative statistics describing video of behaving animals. Through our system, users encode their intuition about the structure of behavior by labeling the behavior of the animal, e.g. walking, grooming, or following, in a small set of video frames. JAABA uses machine learning techniques to convert these manual labels into behavior detectors that can then be used to automatically classify the behaviors of animals in large data sets with high throughput. Our system combines an intuitive graphical user interface, a fast and powerful machine learning algorithm, and visualizations of the classifier into an interactive, usable system for creating automatic behavior detectors. JAABA is complementary to video-based tracking methods, and we envision that it will facilitate extraction of detailed, scientifically meaningful measurements of the behavioral effects in large experiments.

JAABA is an open-source, freely available program developed by members of the Branson lab at HHMI Janelia Farm. It is described in detail in the paper "JAABA: Interactive machine learning for automatic annotation of animal behavior", Kabra, Robie, et al., Nature Methods, 2012.

This webpage is currently under development. We will continue to update the documentation.





JAABA was developed by Mayank Kabra, Alice Robie, and Kristin Branson with help from Marta Rivera-Alba, Steven Branson, Ben Arthur, Adam Taylor, Jinyang Liu, Roian Egnor, Andrew Miller. It was funded by the Howard Hughes Medical Institute.