Artificial city

Artificial intelligence to detect the distress of poultry

The technology, which can quantify distress calls made by birds housed in barns, correctly distinguished distress calls from other barn noises with a level of accuracy of 97%, according to a new study.

Until now, farmers have had to rely on animal husbandry to distinguish welfare issues in individual birds and deploying human observers in large flocks is impractical and can further stress the birds.

“Our end goal is not to count distress calls, but to create conditions where chickens can live and have less stress…”

Alan McElligott, associate professor of animal behavior and welfare at city ​​universityHong Kong, told the Guardian newspaper: “Chickens are very vocal, but the distress call tends to be louder than the others and is what we would describe as a purely tonal call.”

His team developed a deep learning tool to automatically identify chicken distress calls based on recordings of individual farm chickens.

“Our end goal is not to count distress calls, but to create conditions where chickens can live and have less stress,” said McElligott, who thinks the technology could be commercially available from 5 years here.

Reduce mortality and reduce labor costs

He also thinks it can be relatively simple to persuade farmers to use the technology, as early disease detection can halt mortality and reduce live weight gains. It could also reduce human labor costs.

The researchers recorded the vocalizations of chickens housed at Lingfeng Poultry, a major poultry producer in Guangxi Province, China. Birds were kept in stacked cages (3 cages per stack and 13-20 individual birds per cage) with approximately 2000-2500 birds in each barn.

The study was published in the Journal of the Royal Society Interface.