Open-Source Wearable Sensors for Behavioral Analysis of Sheep Undergoing Heat Stress

Heat stress (HS) negatively affects animal productivity and welfare. The usage of wearable sensors to detect behavioral changes in ruminants undergoing HS has not been well studied. This study aimed investigate sheep’s behavior using a sensor explore how ambient temperature influenced the algorithm’s capacity classify behaviors. Six sheep (Suffolk, Dorset, or Suffolk × Dorset) were assigned 1 2 groups cross-over experimental design. Groups one two rooms where they housed for 20d prior switching rooms. thermal environment within was altered five times per period. In first room, began at thermoneutral level gradually increased before decreasing. Simultaneously, second hot temperatures decreased increasing again. Physiological responses (respiratory rate, heart rectal temperature) analyzed linear mixed-effects model. A random forest algorithm developed lying, standing, eating, ruminating (while lying standing). Thermal shifted daily budgets, total time spent standing conditions (p = 0.036). Although models had similar behaviors range, their accuracy when applied outside that range. may help shifts indicative stress, algorithms must be robustly derived across environments.