On the Development of a Wearable Animal Monitor

SIMPLE SUMMARY: The choice of sensors for detecting animal behavior through wearable devices has the greatest impact on the quality of the behavior learning process and the cost of production. The present study evaluated, through a machine learning process, the most important features in the detection and classification of sheep behavior, as well as the individual contribution of each of the sensors included in the monitoring collar. The study showed that the gyroscope had a very low contribution towards improving accuracy, despite its high production cost, and also shares very similar characteristics with the accelerometer used in the collar. Conversely, the thermometer, which was intended for other monitoring scenarios, proved to be essential in detecting some states, especially the ones related to postures in which the animal tends to wrap the collar and thus increases the temperature of the device. The final feature set provided by the thermometer and accelerometer was considered a good basis for building an animal behavior monitoring system. ABSTRACT: Animal monitoring is a task traditionally performed by pastoralists, as a way of ensuring the safety and well-being of animals; a tremendously arduous and lonely task, it requires long walks and extended periods of contact with the animals. The Internet of Things and the possibility of applying sensors to different kinds of devices, in particular the use of wearable sensors, has proven not only to be less invasive to the animals, but also to have a low cost and to be quite efficient. The present work analyses the most impactful monitored features in the behavior learning process and their learning results. It especially addresses the impact of a gyroscope, which heavily influences the cost of the collar. Based on the chosen set of sensors, a learning model is subsequently established, and the learning outcomes are analyzed. Finally, the animal behavior prediction capability of the learning model (which was based on the sensed data of adult animals) is additionally subjected and evaluated in a scenario featuring younger animals. Results suggest that not only is it possible to accurately classify these behaviors (with a balanced accuracy around 91%), but that removing the gyroscope can be advantageous. Results additionally show a positive contribution of the thermometer in behavior identification but evidences the need for further confirmation in future work, considering different seasons of different years and scenarios including more diverse animals’ behavior.