B-SOiD: An Open Source Unsupervised Algorithm for Discovery of Spontaneous Behaviors

Abstract

Studying naturalistic behavior remains a prohibitively difficult objective. Recent machine learning advances have enabled limb localization. Extracting behaviors, however, requires ascertaining the spatiotemporal patterns of these positions. To provide the missing bridge from poses to actions and their kinematics, we developed B-SOiD - an open-source, unsupervised algorithm that identifies behavior without user bias. By training a machine classifier on pose pattern statistics clustered using new methods, our approach achieves greatly improved processing speed and the ability to generalize across subjects or labs. Using a frameshift alignment paradigm, B-SOiD overcomes previous temporal resolution barriers that prevent the use of other algorithms with electrophysiological recordings. Using only a single, off-the-shelf camera, B-SOiD provides categories of sub-action for trained behaviors and kinematic measures of individual limb trajectories in an animal model. These behavioral and kinematic measures are difficult but critical to obtain, particularly in the study of pain, OCD, and movement disorders.