Semantic Communications for Remote Animal Health and Welfare Monitoring in Extensive Livestock Systems
Supervisors
Prof Anil Fernando, Department of Computer and Information Sciences, University of Strathclyde
Prof Muhammad Ali Imran, James Watt School of Engineering, University of Glasgow
Prof Muhammad Munir, Biomedical and Life Sciences, University of Lancaster
Summary
Farmers who raise sheep and cattle on hills and other remote areas face a real challenge: their animals roam over huge areas, often far from mobile phone signal, making it hard to spot health problems like illness or lameness early. Wearable sensors could help by tracking behaviour and vital signs, but sending large amounts of video, sound, or movement data wirelessly uses a lot of battery power which is a serious limitation for devices that need to work unattended in remote fields for months at a time.
This project will develop a smarter way to monitor animal health remotely. Instead of transmitting everything the sensor records, the system will be trained to recognise only the meaningful signals such as "this animal may be showing signs of respiratory illness" or
"feeding behaviour has changed" and send just that summary. This dramatically cuts the amount of data transmitted, saving battery power and allowing devices to run for much longer in the field.
Bringing together expertise in animal health, AI, and wireless communications, the project aims to make remote livestock monitoring more practical and affordable, helping farmers, catch health and welfare issues earlier, improve animal wellbeing, and reduce the time and cost of manually checking animals across difficult terrain.