Researchers hatch tech that identifies 'clucks for help'
Local | Leopold Chen 12 Jul 2022
City University researchers have developed a technology to identify "clucks for help" from chickens and distinguish those sounds from sounds of distress over physical discomfort, insufficient food and water or being attacked.
The research enables the automatic identification and counting of the distress cluck, which is considered an iceberg indicator of chicken welfare and therefore bears importance for the mortality and growth rates.
Prior to the research, such identification and statistics relied on labor-intensive, time-consuming and inaccurate manual annotation, the researchers said.
The research - led by two professors from the university's department of infectious disease and public health, Alan McElligott and Liu Kai - was conducted in collaboration with three British universities as well as the Guangxi Veterinary Research Institute.
Researchers collected and analyzed recordings of the Speckled Sussex breeds and "three-yellow" or sanhuangji at a Guangxi poultry farm that housed 2,000 to 2,500 birds per henhouse, and developed an automated system to assess and quantify distress calls based on deep learning combined with bio-acoustic techniques.
The system contains an algorithm that covers frequency ranges from 0Hz to 11,025Hz, allowing distress calls to be distinguished from natural sounds.
The system, with a 97-percent accuracy level, can help farmers monitor chickens from a distance. Reasons for the distress calls might be attributed to the birds' physical wellbeing or external factors like overcrowding, not getting enough food and water or attacks from other chickens.
Improving the living conditions and welfare of the chickens is the aim, given that chickens are usually raised in clusters of thousands.
"Sometimes it's difficult to convince farmers who have to deal with producing these animals at a set price for supermarkets and everyone else to adopt technology to improve their welfare," McElligott said.
"Our end goal is not just to count distress calls, but to create conditions in which the chickens can live with less distress."
Liu said: "In the future, this technology will potentially allow staff to monitor chicken welfare in real time and remotely, promoting earlier husbandry interventions when necessary.
"This can also reduce the workload of analysts and facilitate the analysis of large datasets, thus improving the husbandry and management of the animals."
The research was published in the Journal of the Royal Society Interface and the researchers expect the technology to be deployed commercially within five years.
Team member Mao Axiu said: "Our algorithm fully considered the constraints in computation resources and is suitable for practical deployment on farms."
