Scientists have created an artificial intelligence (AI) that can automatically identify and count chicken distress signals. They claim that the new technology will be available in five years, allowing farmers to save the lives of these birds.
The AI, which detects and quantifies distress calls made by chickens housed in massive indoor sheds, can correctly distinguish distress calls from other barn noises with 97% accuracy, according to the researchers.
Chicks make distress calls, which are high-pitched, repetitive chirps, to attract the mother hen’s attention when they are hungry or in distress. However, in a commercial chicken farm, it can be difficult to tell when the chickens are unhappy, socially isolated, or hungry. Responding to these calls could mean the difference between life and death.
Researchers from the City University of Hong Kong recorded the vocalizations of chickens housed at Lingfeng Poultry Ltd., a major poultry producer in China’s Guangxi province, to improve these efforts.
The chickens were housed in stacked cages (three cages per stack, with 13 to 20 individuals per cage), with approximately 2000 to 2500 chickens in each barn.
The researchers recorded the environment for a year, recording everything from natural farm sounds like workers hosing down barn floors to chick distress calls.
They then converted all of these noises into sound pictures known as spectrograms and used the images to train a deep learning AI program.
“Chickens are very vocal, but the distress call tends to be louder than the others, and is what we would describe as a pure tonal call,” The Guardian quoted Alan McElligott, an associate professor of animal behavior and welfare at the City University of Hong Kong.
“Even to the untrained ear, it’s not too difficult to pick them out.”
