Evaluation and validation of an automatic jaw movement recorder (RumiWatch) for ingestive and rumination behaviours of dairy cows during grazing and supplementation.

Close observation of dairy cows with regard to how they eat and ruminate may assist in detecting diseases, controlling reproductive status and estimating intake. However, direct observation of cows on pasture is time consuming and difficult to do. Consequently, different systems have been developed to automatically record behavioural characteristics; among them is the RumiWatch System (RWS; Itin and Hoch GmbH, Liestal, Switzerland). The RumiWatch System (RWS), built in a cow halter, uses data gathered by a pressure sensor in combination with data collected by a triaxial accelerometer to detect different behavioural characteristics in dairy cows. The literature shows that RWS should be able to record individual animal behaviour over several days with high precision. However, as yet, the RWS has not been thoroughly validated under grazing conditions. Therefore, the aim of a study by Dr M. Rombach and colleagues was to validate the RWS, against direct observation, in measuring intake and rumination behaviour during grazing and supplementation in the barn. A further objective was to examine whether it is possible to refine the algorithm used by the evaluation software RumiWatch Converter 0.7.3.2 to improve the accuracy of the RWS. The results of the study were published in the Journal of Dairy Science, Volume 101 of 2018, pages 2463–2475, the title being: Evaluation and validation of an automatic jaw movement recorder (RumiWatch) for ingestive and rumination behaviours of dairy cows during grazing and supplementation. 

The data were collected from an experiment carried out with 18 lactating Holstein cows in a crossover block design using 3 treatments and 3 measuring periods. All cows grazed night and day for 19 hours per day, and were either not supplemented or supplemented with chopped whole plant maize silage, or chopped whole-plant maize silage mixed with a protein concentrate. During the measuring periods, the cows were equipped with the RumiWatch Halter, and their intake and rumination behaviours were recorded concurrently by the RumiWatch Halter and by direct observation.

Comparison of the concurrently measured data showed that the RWS detected jaw movements reliably, but classification errors occurred. The prediction error was relatively low for the number of rumination boluses, rumination chews and total eating chews, but the prediction error was relatively high for the number of prehension bites and time spent in prehension and eating. Both converter versions performed equally well in differentiating eating and rumination behaviour when the cows were supplemented in the barn or when grazing and supplementation activities were combined. For grazing cows, with no supplementation, more reliable results were obtained when the RumiWatch Converter 0.7.3.11 was used. These included the measurements of total number of eating chews, rumination chews, prehension bites and time spent in these activities.

In conclusion: Although promising, it is clear that further research is required to improve the accuracy of the RWS and new or altered algorithms will have to be developed to allow differentiation between mastication chews and prehension bites while eating. Thus, farmers should understand that results with the system remain an approximation and do not quantify, at least for now.