Search for: All records

Global Positioning Systems (GPSs) can collect tracking data to remotely monitor livestock well-being and pasture use. Supervised machine learning requires behavioral observations of monitored animals to identify changes in behavior, which is labor-intensive. Our goal was to identify animal behaviors automatically without using human observations. We designed a novel framework using unsupervised learning techniques. The framework contains two steps. The first step segments cattle tracking data using state-of-the-art time series segmentation algorithms, and the second step groups segments into clusters and then labels the clusters. To evaluate the applicability of our proposed framework, we utilized GPS tracking data collected from five cows in a 1096 ha rangeland pasture. Cow movement pathways were grouped into six behavior clusters based on velocity (m/min) and distance from water. Again, using velocity, these six clusters were classified into walking, grazing, and resting behaviors. The mean velocity for predicted walking and grazing and resting behavior was 44, 13 and 2 min/min, respectively, which is similar to other research. Predicted diurnal behavior patterns showed two primary grazing bouts during early morning and evening, like in other studies. Our study demonstrates that the proposed two-step framework can use unlabeled GPS tracking data to predict cattle behavior without human observations. 

Sensor technologies can identify modified animal activity indicating changes in health status. This study investigated sheep behavior before and after illness caused by mold-contaminated feed using tri-axial accelerometers. Ten ewes were fitted with HerdDogg biometric accelerometers. Five ewes were concurrently fitted with Axivity AX3 accelerometers. The flock was exposed to mold-contaminated feed following an unexpected ration change, and observed symptomatic ewes were treated with a veterinarian-directed protocol. Accelerometer data were evaluated 4 days before exposure (d −4 to −1); the day of ration change (d 0); and 4 days post exposure (d 1 to 4). Herddogg activity index correlated to the variability of minimum and standard deviation of motion intensity monitored by the Axivity accelerometer. Herddogg activity index was lower (p < 0.05) during the mornings (0800 to 1100 h) of days 2 to 4 and the evening of day 1 than days −4 to 0. Symptomatic ewes had lower activity levels in the morning and higher levels at night. After accounting for symptoms, activity levels during days 1 to 4 were lower (p < 0.05) than days −4 to 0 the morning after exposure. Results suggest real-time or near-real time accelerometers have potential to detect illness in ewes.