Recognising primate behaviours using AI

AI model recognising chimpanzee behaviours, such as nut-cracking and eating.   | Photo Credit: Kyoto University, Primate Research Institute

An international team of researchers have developed an artificial intelligence (AI) model that can help recognise behaviours of chimpanzees in the wild. The AI-powered approach can potentially capture novel behavioural indicators that can more accurately measure the viability of threatened populations, according to an Oxford University release.

(Sign up to our Technology newsletter, Today's Cache, for insights on emerging themes at the intersection of technology, business and policy. Click here to subscribe for free.)

“This (AI model) can help us examine the social and ecological drivers of behaviour, as well as monitor how these communities are responding to environmental pressures caused by climate change and habitat degradation from human activities,” Daniel Schofield, researcher and DPhil student at Oxford University’s Primate Models Lab, said.

Also read | This predictive fire model uses CAT scans, advanced computing to forecast wildfires

Chimpanzees are facing a high risk of extinction and have already disappeared completely from four countries, as per the World Wide Fund for Nature (WWF).

The AI tool can automatically recognise behaviour in wild primates using both the audio as well as the visual stream of information from a video, crucial in the wild where an animal behaviour might be heard but not seen, such as cracking nuts behind a tree or inaudible actions, the university explained.

The approach will allow researchers and wildlife conservationists to significantly cut back on time and resources spent analysing animal behaviour in video footage.

The computer model was trained using videos from two populations of wild chimpanzees in West Africa from Bossou in Guinea, and Cantanhez National Park in Guinea-Bissau, to capture several behaviours like nut-cracking, eating, and buttress drumming.

Also Read |Machine Learning could solve biggest challenges in the world, AWS executive says

“For species such as chimpanzees which have remarkable behavioural complexity, cross-site comparisons of video datasets using AI presents an exciting opportunity to capture subtle variation between groups and the evolution of behaviour over time at a scale and depth not previously possible,” Schofield noted.

The team’s method is not restricted to chimpanzees, and can be trained to recognise any behaviour, the university said.

The international collaboration included scientists from the University of Exeter, Chubu Gakuin University, Japan Monkey Centre, University of Rochester and California Institute of Technology.

Our code of editorial values

This article is closed for comments.
Please Email the Editor

Printable version | Dec 7, 2021 6:02:54 PM |

Next Story