Analysis of Cattle Social Transitional Behaviour: Attraction and Repulsion.

摘要: Understanding social interactions in livestock groups could improve management practices, but this can be difficult and time-consuming using traditional methods of live observations video recordings. Sensor technologies machine learning techniques provide insight not previously possible. In study, based on the animals' location information acquired by a new cooperative wireless localisation system, unsupervised approaches were performed to identify structure small group cattle yearlings (n=10) behaviour an individual. The paper first defined affinity between animal pair ranks their distance. Unsupervised clustering algorithms then performed, including K-means agglomerative hierarchical clustering. particular, was applied logical physical By comparing result distance distance, leader animals influence individual herd identified, which provides valuable for studying herds. Improvements device robustness replication work would confirm practical application technology analysis methodologies.