Monitoring of behavioural activities and milk yield of dairy cows as an indicator of health status

Behavioural activities and milk production of dairy cows are affected by their health status. This study shows the potential of using real-time monitoring of behavioural activities and milk yield production as indicator of health status of individual dairy cows. The study was carried out on a Danish commercial dairy farm, with approximately 400-450 lactating cows and equipped with milking robots. The CowView Real-Time-Location-System (GEA®) provides several behavioural activities in the form of the time spent performing each of them along with total distance travelled by each cow. Given the stated hypothesis, the hourly average of the total distance walked by a cow, the time spent in the cubicle and at the feeding area were selected as behavioural activities to combine with the daily milk yield of each cow. These data were then analysed for a complete lactation period. By applying Dynamic Auto-Regression (DAR) techniques the time evolution of the behavioural activities and the milk yield from each individual cow was determined. It was found that by using the data from the past 5-7 days it was possible to forecast the behavioural activity for the following 2-3 days. Therefore, deviations between the measured and predicted values (e.g. of 15% or higher), can be used as an indication of a change in the health status of an individual cow in the herd. The continuous monitoring of these variables during a lactation period can provide the farmer with a tool to assess the health status of each cow in the herd.status: publishe