Automated detection of oestrus and mastitis in dairy cows

The development and test of detection models for oestrus and mastitis in da iry cows is described in a PhD thesis that was defended in Wageningen on Ju ne 5, 2000. These models were based on sensors for milk yield, milk tempera ture, electrical conductivity of milk, and cow activity and concentrate int ake, and on combined processing of the sensor data. The models alert farmer s to cows that need attention, because of possible oestrus or mastitis. A f irst detection model for cows, milked twice a day, was based on time series models for the sensor variables. A time series model describes the depende nce between successive observation. The parameters of the time series model s were fitted on-line for each cow after each milking by means of a Kalman filter, a mathematical method to estimate the state of a system on-line. Th e Kalman filter gives the best estimate of the current state of a system ba sed on all preceding observations. This model was tested for 2 years on two experimental farms, and under field conditions on four farms over several years. A second detection model, for cows milked in an automatic milking sy stem (AMS), was based on a generalization of the first model. Two data sets (one small, one large) were used for testing. The results for oestrus dete ction were good for both models. The results for mastitis detection were va rying (in some cases good, in order cases moderate). Fuzzy logic was used t o classify mastitis and oestrus alerts with both detection models, to reduc e the number of false positive alerts. Fuzzy logic makes approximate reason ing possible, where statements can be partly true or false. Input for the f uzzy logic model were alerts from the detection models and additional infor mation. The number for false positive alerts decreased considerably, while the number of detected cases remained at the same level. There models make automated detection possible in practice.