This research communication addresses the goal of validating an algorithm to monitor natural occurrence of feeding behaviours in dairy Mediterranean buffalo based on the output of a noseband pressure sensor (RumiWatch®, halter). Several characteristics of the feeding behaviour were detected with a very high (ruminating boluses), high (chews per bolus) and moderate degree of correlation (chews per minute) with video analyses (gold standard). All of them were associated with a low mean difference with the gold standard, and the mean relative measurement error ranged between low (ruminating boluses) and moderate (chews per bolus and chews per minute). The proportion of correctly detected events for the variables rumination and eating time was 98 and 99%, respectively. The collection of data and subsequent evaluation of the parameters investigated may provide objective information on Mediterranean Buffalo behaviours allowing for reliable studies of the animal welfare in this ruminant in the future.

This research communication validates an algorithm to monitor natural occurrence of locomotor behaviours in dairy Mediterranean buffalo based on the output of a 3-dimensional accelerometer (RumiWatch®, pedometer). Several characteristics of the locomotor behaviour were detected with a very high (up-right, lying and standing time) or high degree of correlation (walking time and number of strides) and a low mean difference with the video recording. The proportion of correctly detected events exceeded 99 % for the following variables: stand up and lie down events, as well as number of lying, standing or walking bouts. The mean relative measurement error was less than 10 % for the variables: lying, standing, up-right times and number of strides as compared with gold standard. This new algorithm may represent the base for a future early and real-time disease warning system aiming to gain higher health standard in these ruminants.