Studying animal social interactions holds immense importance in understanding their behavior, with significant implications for neuroscience and ecology.
The Brain Cognition and Brain Disease Institute (BCBDI) at the Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, has introduced a groundbreaking method known as the Social Behavior Atlas (SBeA). This innovative approach utilizes artificial intelligence (AI) to track and analyze the behavior of multiple animals in three dimensions (3D).
Featured in Nature Machine Intelligence, this study unveils a pioneering technique for analyzing multi-animal behavior. Unlike conventional methods that rely on predefined categories of social behavior, the SBeA framework employs a few-shot learning AI algorithm. Simultaneously, this algorithm demonstrates exceptional accuracy, surpassing 90 percent, in identifying similar-looking animals. Consequently, it enables the exploration of previously undefined distinctions in animal social behavior.
Furthermore, a key strength of the SBeA framework lies in its capacity to synthesize vast amounts of data and train models with enhanced precision. According to Wei Pengfei, the lead author of the study, this results in more accurate estimations of 3D social gestures.
The SBeA technology proves particularly adept at determining 3D social posture, distinguishing individual animals, and scrutinizing subtle social interactions across various species, including mice, birds, and domestic dogs. Moreover, its potential for cross-species applications heralds a new era in the study of social behavior, transcending traditional boundaries between different animal types.
Visit CxO Global FORUM or CxO News Live for all the latest updates.
