Evaluation of the RumiWatchSystem for measuring grazing behaviour of cows

Abstract

Feeding behaviour is an important parameter of animal performance, health and welfare, as well as reflecting levels and quality of feed available. Previously, sensors were only used for measuring animal feeding behaviour in indoor housing systems. However, sensors such as the RumiWatchSystem can also monitor such behaviour continuously in pasture-based environments. Therefore, the aim of this study was to validate the RumiWatchSystem to record cow activity and feeding behaviour in a pasture-based system. The RumiWatchSystem was evaluated against visual observation across two different experiments. The time duration per hour at grazing, rumination, walking, standing and lying recorded by the RumiWatchSystem was compared to the visual observation data in Experiment 1. Concordance Correlation Coefficient (CCC) values of CCC=0.96 for grazing, CCC=0.99 for rumination, CCC=1.00 for standing and lying and CCC=0.92 for walking were obtained. The number of grazing and rumination bouts within one hour were also analysed resulting in Cohen's Kappa (κ)=0.62 and κ=0.86 for grazing and rumination bouts, respectively. Experiment 2 focused on the validation of grazing bites and rumination chews. The accordance between visual observation and automated measurement by the RumiWatchSystem was high with CCC=0.78 and CCC=0.94 for grazing bites and rumination chews, respectively. These results indicate that the RumiWatchSystem is a reliable sensor technology for observing cow activity and feeding behaviour in a pasture based milk production system, and may be used for research purposes in a grazing environment.

Dairy cattle behavior classifications based on decision tree learning using 3‐axis neck‐mounted accelerometers

“…In the previous studies involving three‐axis accelerometers mounted to the head or neck of cows, sampling frequency settings varied: every 1 s (Oudshoorn et al., ; Watanabe et al., ), 0.5 s (Mattachini, Riva, Perazzolo, Naldi, & Provolo, ), 0.1 s (Dutta et al., ; Martiskainen et al., ; Shen et al., ; Werner et al., ), 0.02 s (Diosdado et al., ), and 0.01 s (Scheibe & Gromann, ). For this study, sampling frequency was set at 20 Hz (per 0.05 s) which enabled proper behavioral classification.…”

“…() and Werner et al. () set the time window as 1 min, and Shen et al. () set the time window as 1 s. Different time windows have also used: 2 hr (Borchers et al., ), 10 s (Martiskainen et al., ), 5 s (Dutta et al., ), and 1–10 min (Diosdado et al., ).…”

“…during lying, virtually no changes were observed in acceleration waveforms.When behavior patterns are investigated using acceleration data, various parameters are sometimes calculated for setting time windows. In order to calculate total, mean, and deviations of accelerations,Watanabe et al (2008) andWerner et al (2018) set the time window as 1 min, and Shen et al (2014) set the time window as 1 s. Different time windows have also used: 2 hr (Borchers et al, 2017), 10 s (Martiskainen et al, 2009), 5 s (Dutta et al, 2014), and 1-10 min (Diosdado et al, 2015). When changes in behavior patterns F I G U R E 3 Accelerometer waves observed during rumination (51.2 s) in longitudinal (top figure), vertical (middle figure), and horizontal directions (bottom figure).…”

Review: Grass-based dairy systems, data and precision technologies

“…Most commercial sensors that are used on farms for measuring grazing behaviour use an accelerometer around the neck (e.g. Heattime ® by SCR Engineers, Netanya, Israel (Molfino et al, 2017) or MooMonitor + ; Dairymaster, Tralee, Ireland (Werner et al, 2017)).…”

“…One system for research uses a pressure band sensor in a halter to detect jaw movements (Zehner et al, 2017). It is called the RumiWatch (Itin + Hoch GmbH, Liestal, Switzerland) and the recorded jaw movements are used to measure feeding behaviour (Werner et al, 2017). The RumiWatch is capable of measuring detailed grazing behaviour such as rumination chews and grazing bites as well as rumination and grazing times (Werner et al, 2017).…”