AUTHOR=Kyriazakis Ilias , Alameer Ali , Bučková Katarína , Muns Ramon TITLE=Toward the automated detection of behavioral changes associated with the post-weaning transition in pigs JOURNAL=Frontiers in Veterinary Science VOLUME=Volume 9 - 2022 YEAR=2023 URL=https://www.frontiersin.org/journals/veterinary-science/articles/10.3389/fvets.2022.1087570 DOI=10.3389/fvets.2022.1087570 ISSN=2297-1769 ABSTRACT=We modified and applied an automated method capable of capturing behavioural changes associated with the post-weaning transition in pigs. The method depends solely on video captured, image data without relying on sensors or additional pig markings, and is data-driven, as it correctly learns the variations within each behaviour of relevance, using data manually annotated by a behavioural scientist. For the purposes of this experiment, the method quantified total group feeding and drinking behaviour, as well as posture (i.e., standing and non-standing) during the first week post-weaning, when the risk of post-weaning diarrhoea is high. The method was applied in the presence (and absence) of in-feed antimicrobial, which are expected to affect piglet performance and health in the short-term, by minimising the risk from post-weaning enteric disorders. The automatically quantified changes in behaviour were consistent with the effects of the absence of antimicrobial on pig performance and health, manifested as reduced feed efficiency and looser faeces. In these piglets both drinking and standing behaviours were increased during the first week post-weaning. The correlation between faecal consistency and drinking behaviour a week post weaning was relatively high, suggesting that these behaviours may have a diagnostic value. There was no effect of antimicrobial treatment on feeding behaviour, which increased with time. The method developed here is capable of automatically monitoring several different behaviours of a group of pigs at the same time, and potentially this may be where its value as a diagnostic tool may lie