A Chinese research team has developed artificial intelligence (AI) technology that addresses crucial challenges in accurately detecting animal social behavior, according to the Shenzhen Institute of Advanced Technology (SIAT) under the Chinese Academy of Sciences.

The most difficult part of multi-animal social behavior analysis is to distinguish between animals that look very similar at the same time.

The new technology, Social Behavior Atlas (SBeA), developed by researchers from the SIAT, can identify similar-looking animals with more than 90 percent accuracy, eliminating the need to define social behavior categories in advance, which may help discover new, undefined differences in animal social behavior.

The new algorithm can also effectively synthesize a large volume of new data and train models with higher accuracy, thus obtaining more accurate 3D social gesture estimation results, said Wei Pengfei, correspondence author of the study.

SBeA is suitable for accurately calculating 3D social posture, identity and fine social modules in mice, birds and domestic dogs, with potential for cross-species applications, Wei said.

The study was recently published in the journal Nature Machine Intelligence.