Internet of Animals: Wireless Spatio-Temporal Observation of Dairy Goats Using Unsupervised Deep Learning (GEITPLF)

In goat farming, how can we develop/improve a wireless automated monitoring system with sensors on the animal to provide the farmer with real-time insight into the daily (inter)action of the dairy goats? The precision farming technology in this case aims at the optimization of the production process and especially at the healthy living conditions for the animal.

By equipping each goat with a wireless accelerometer and UWB tag, we can collect both activity data and data regarding their position. We apply new deep learning techniques to this data to compute useful statistics, as well as detect important events, such as deliveries, and general health problems. The project explicitly aims for the lowest possible effort in terms of required wireless and positioning infrastructure and energy consumption of the sensors and of the calculation module.

The dairy goat industry has been growing quickly. In Flanders it already houses over 26 000 animals, which produce over 30 million liters of milk annually. As the industry becomes more commercialized, society is also becoming more concerned with the overall welfare of livestock.