Detecting Oestrus by Monitoring Sows’ Visits to a Boar

This paper suggests a method for automatic detection of sows returning to 1 oestrus in the gestation department. The detection is based on monitoring of 2 sows’ visits to a boar, where the duration and frequency of visits are modelled 3 separately and subsequently combined. The hypothesis is that it is possible 4 to reduce the response time and the number of false alarms compared to 5 previously published attempts. The duration of visits to a boar is defined 6 as seconds per hour the sow is near the boar – logarithmically transformed. 7 The duration is modelled with a multiprocess dynamic linear model with 8 first order Markov probabilities. The indicator of oestrus is the probability 9 of the model describing oestrus, P (MOE), and it is monitored with a thresh10 old value. The frequency of visits to a boar is defined as number of visits 11 per 6 hours. A dynamic generalised linear model with two built-in diurnal 12 periods is applied. The indicator of oestrus is the relative deviation from the 13 ∗Corresponding author: email: [email protected] Email addresses: [email protected] (T. Ostersen), [email protected] (C. Cornou), [email protected] (A. R. Kristensen) 1Present address: Danish Agriculture and Food Council, Pig Research Centre, Axeltorv 3, DK-1609 Copenhagen V, Denmark Preprint submitted to Computers and Electronics in Agriculture May 27, 2010 Manuscript (Latex) Click here to view linked References