Indonesia promotes digital technology for economic recovery – OpenGov Asia

A research team led by the City University of Hong Kong (CityU) has developed a deep learning model that can identify and quantify chicken distress calls from natural barn sounds with 97% accuracy. This breakthrough will help improve the conditions and welfare of chickens raised on crowded commercial farms.

The research is led by Dr. Alan McElligott, Associate Professor, and Dr. Liu Kai, Assistant Professor, in the Department of Infectious Diseases and Public Health at the Jockey Club College of Veterinary Medicine and Life Sciences at CityU, in collaboration with the Imperial College London, Queen Mary University London, University of Surrey and Guangxi Veterinary Research Institute. Other members include Ms. Mao Axiu, PhD student, and Ms. Claire Giraudet, research assistant, in the Department of Infectious Diseases and Public Health at CityU.

The annual worldwide production of chickens exceeds 25 billion birds, which are often housed in very large flocks, numbering in the thousands. Distress calls triggered by various sources have been suggested as an ‘iceberg indicator’ of chicken welfare, which can indicate mortality and growth rates. However, to date, the distress call assessment process has relied largely on manual annotation; it is labor intensive, time consuming and subject to the subjective judgments of individuals.

The research team collected and analyzed records of “spotted” and “three-yellow” breeds at a poultry farm in Guangxi, with approximately 2,000 to 2,500 birds per house, and developed a new automated, objective and cost-effective assessment and quantification of distress calls, based on deep learning combined with bio-acoustic techniques.

The algorithm covers frequency ranges from 0 Hz to the Nyquist frequency of 11,025 Hz, which can distinguish distress calls from natural sounds in the poultry house with 97% accuracy and accurately detects when chickens are stressed due to their internal physical condition or external factors. , such as overcrowding, lack of food and water, or attacks from other chickens.

Dr McElligott noted that it is sometimes difficult to convince farmers who have to deal with producing these animals at a fixed price for supermarkets and everyone else to adopt the technology to improve their welfare. The team’s end goal is not just to count distress calls, but to create conditions where chickens can live with less distress.

In the future, this technology should potentially allow staff to monitor the welfare of chickens in real time and remotely, supporting earlier breeding interventions if necessary. It can also reduce analyst workloads and make it easier to analyze large datasets, improving animal husbandry and management, Dr. Liu said.

The algorithm has fully taken into account the constraints of computational resources and is suitable for practical deployment on farms, according to Mao.

The document was published in the Royal Society Interface Journaland the team expects the technology to be commercially deployed within five years.

Under the leadership of Chairman Way Kuo of CityU, the concept of developing veterinary education in Hong Kong was first envisioned in 2008. Operating under the innovative concept of “One Health”, the Jockey Club College of Veterinary Medicine and Life Sciences of CityU was created. , the first and only veterinary college in Hong Kong.

Guided by the core principles of One Health, CityU will continue to pioneer excellence in veterinary education and research in Hong Kong, Asia and globally, with a focus on public health, food safety and animal welfare for the well-being of society.

Comments are closed.