Using Sound Location to Monitor Farrowing in Sows.

Precision Livestock Farming systems can help pig farmers prevent health and welfare issues around farrowing. Five sows were monitored in two field studies. A Sorama L642V sound camera, visualising sound sources as coloured spots using a 64-microphone array, and a Bascom XD10-4 security camera with a built-in microphone were used in a farrowing unit. Firstly, sound spots were compared with audible sounds, using the Observer XT (Noldus Information Technology), analysing video data at normal speed. This gave many false positives, including visible sound spots without audible sounds. In total, 23 of 50 piglet births were visible, but none were audible. The sow's behaviour changed when farrowing started. One piglet was silently crushed. Secondly, data were analysed at a 10-fold slower speed when comparing sound spots with audible sounds and sow behaviour. This improved results, but accuracy and specificity were still low. When combining audible sound with visible sow behaviour and comparing sound spots with combined sound and behaviour, the accuracy was 91.2%, the error was 8.8%, the sensitivity was 99.6%, and the specificity was 69.7%. We conclude that sound cameras are promising tools, detecting sound more accurately than the human ear. There is potential to use sound cameras to detect the onset of farrowing, but more research is needed to detect piglet births or crushing.

Lying Postures of Dairy Cows in Cubicles and on Pasture.

Cows housed indoors with cubicles are probably more restricted in their choice of lying posture and orientation compared with cows housed on pasture. We therefore compared lying postures on pasture in Uruguay and the Netherlands with lying postures in cubicles in the Netherlands, also recording orientation on pasture in Uruguay and divider and bedding type in Dutch cubicles. We visited one farm with four herds in Uruguay, doing live observations, and 25 Dutch farms, taking pictures of cows. Observations of 205 cows on pasture in Uruguay showed more long postures, lying on their belly with their neck stretched. Two herds preferred lying towards north and south, while one herd preferred west and east. Pictures of 217 cows on pasture in the Netherlands showed more wide postures (lying on the side with three or four legs stretched out). Pictures of 527 cows in cubicles in the Netherlands showed more narrow postures (lying on the side with hind legs folded). More long postures (lying on the belly with a stretched neck) and less short postures (lying with the head folded back) were seen in cubicles with soft floors and English dividers; more narrow postures were seen in cubicles with concrete floors. Wide postures were seen more in cubicles with mattresses and free-hanging dividers. We conclude that since cows in cubicles show more narrow postures than on pasture and cannot choose their orientation, their choice in showing preferred behavior is restricted. More research is needed to study the consequences of restricted choice in lying behavior on the health and welfare of dairy cows.