International Journal of Scientific Research and Engineering Development

The Smart Wildlife Movement Prediction and Tracking System uses data-driven methods to predict how animals will move, which helps with wildlife conservation and monitoring. The system uses historical location data of animals and preprocessing techniques to find movement features like displacement and trajectory. A hybrid approach is used to guess where animals will be in the future. It uses both rule-based prediction and machine learning, specifically the K-Nearest Neighbors (KNN) regression model. The system uses statistical measures like average displacement and standard deviation to figure out the likely movement zone, which is shown as a prediction radius. Using HTML, a web-based interface is created and connected to a Python backend. Leaflet is then used to show animal paths and predicted zones on a map. Metrics like Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and spatial distance error are used to evaluate performance. These metrics show that prediction accuracy is better than rule-based methods. The system offers a useful and scalable way to track animals, set up camera traps, and keep an eye on the environment. Real-time data integration and mobile app deployment may be some of the improvements that come next.

Shifa Bilal Tamboli, Simeen Phiroj Mulani, Arman Tajuddin Shiakh,"Smart Wildlife Movement Prediction and Tracking System" International Journal of Scientific Research and Engineering Development, V9(2): Page(2403-2406) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.