Abstract
Zoos offer educational and scientific advantages but face high maintenance costs and challenges in animal care due to diverse species' habits. Challenges include tracking animals, detecting illnesses, and creating suitable habitats. Despite the potential benefits, data-driven approaches like those in digital agriculture are rarely used in zoos due to cost and technical limitations. We developed a deep learning framework called SmartZoo to address these issues and enable efficient animal monitoring, condition alerts, and data aggregation. Animal movement data was treated as a time sequence; the time sequence was predicted using a transformer-based model; and the range of the cage was predicted by plotting the predicted animal movement based on the generated time sequence. We used K-means clustering to evaluate whether the data generated by the SmartZoo model would be more different than a real dataset when each were compared to random data from a Gaussian distribution. We discovered that the data generated by our model is closer to real data than random data, and we were able to demonstrate that the model excels at generating data that resembles real-world data. In the future, we hope our framework may assist zoological experts in caring for animals, enabling them to support the important educational missions of zoos.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call