Using Sound Location to Monitor Farrowing in Sows

SIMPLE SUMMARY: Automated monitoring can help farmers care during the farrowing of sows and piglets. Five sows were monitored in two field studies. A sound camera with small microphones showing sounds as coloured spots and a security camera was used to record the farrowing of sows and piglets. First, sound spots were compared with audible sounds, analysing video data. This gave many false positives, including visible sound spots but no audible sounds. Of piglet births, 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 slower speed, and sound spots were compared with sounds and behaviour separately. This resulted in better results, but again, many sound spots showed without audible sound. When adding up audible sounds and visible sow behaviour and comparing sound spots with the combination of sound and behaviour, results were much improved, with an accuracy of 91.2%, an error of 8.8%, a sensitivity of 99.6%, and a specificity of 69.7%. We conclude that sound cameras are promising tools, detecting sounds more accurately than humans. The most promising application for the sound camera is detecting the onset of farrowing. ABSTRACT: 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.