Monitoring feeding behaviour of dairy cows using accelerometers

Monitoring cow behaviour has become increasingly important in understanding the nutrition production, management of the well being, and overall health of dairy cows. Methods of assessing behavioural activity have changed in recent years favouring automatic recording techniques. Traditional methods to measure behaviour such as direct observation or time-lapse video, are labour-intensive and time-consuming. Automated recording devices have become increasingly common to measure behaviour accurately. Thus, the development of automated monitoring systems that can continuously and accurately quantify feeding behaviour are required for efficient monitoring and control of modern and automated dairy farms. The aim of this study was to evaluate the possible use of a 3D accelerometer to record feeding behaviour of dairy cows. Feeding behaviour (feeding time and number of visits to the manger) of 12 lactating dairy cows was recorded for approximately 3 h with 3D-accelerometer data loggers (HOBO Pendant G logger). The sensors were positioned in the high part of the neck to monitor head movements. Behaviour was simultaneously recorded using visual observation as a reference. Linear regression analysis between the measurement methods showed that the recorded feeding time (R-2=0.90. n=12, P<0.001) was closely related to visual observations. In contrast, the number of visits was inadequately recorded by the 3D-accelerometer, showing a poor relationship with visual observations (R-2=0.31, n=12, P<0.06). Results suggest that the use of accelerometer sensors can be a reliable and suitable technology for monitoring feeding behaviour of individual dairy cows in free stall housing. However, further research is necessary to develop an appropriate device able to detect and recognise the movements connected with the head movement during feeding. Such a device could be part of an automatic livestock management tool for the efficient monitoring and control of comfort and welfare of dairy cows under the intensive conditions of modern automated dairy farms.