Steven Matthews (Newcastle University): Abstract

Early detection of health and welfare compromises in commercial pig farms is essential for timely intervention to enhance treatment success, reduce impact on welfare, and promote sustainable pig production.

Behavioural changes may appear before or accompany physiological signs and have diagnostic value. Changes in behaviour are not easy to quantify and require lengthy observation input by farm staff, which is impractical on a commercial scale. An automated early-warning system may provide an alternative by objectively measuring behaviour with video cameras to automatically monitor and detect behavioural changes.

This talk will cover developments in this area and the application of data mining to this problem.

Organised by BCS SGAI The Specialist Group on Artificial Intelligence http://www.bcs-sgai.org