No description available.

No description available.

No description available.

No description available.

No description available.

This degree project addresses poaching challenges by employing predictive analysis of animal movements and their correlation with the dynamic environment using a machine learning approach. The goal is to provide accurate predictions of animal movements, enabling rangers to intercept potential threats and safeguard wildlife from snares. A wide analysis considers previous studies on animal movements and both animal and environment data availability. To efficiently represent the dynamic environment and correlate it with animal movement data, accurate matching of environment variables to each animal measurement is crucial. We selected multiple environment datasets to capture a sufficient amount ofenvironmental properties. Due to practical constraints, daily representation of the environment is not achievable, and weekly mean or monthly mode values are used instead. Data insights are obtained through the training of a regression neural network using the filtered environmental and animal movement data. The results highlight the significant role ofenvironmental features in predicting animal movements, emphasizing their importance for accurate predictions. Despite some offset and few erroneous predictions, a strong similarity between animal predicted trajectory and animal true trajectory was achieved, indicating that the model is capable to capture general patterns and to correctly tune in predictions of detailed movements as well. The overall offset of the trajectories is still a weak point of this model, but it may just indicate the presence of some underlying systematic error that can be corrected through further work. The integration of such a developed prediction model into existing frameworks could assist law enforcingauthorities in preventing poaching activities.

As human settlement expands into the natural habitats of wild animals, the conflict between humans and wildlife increases. The human-elephant conflict is one that causes a tremendous amount of damage, often to poor villages close to the savannah. In this master's thesis, a system is developed, that is intended to detect, localise and track elephants from seismic vibrations generated from footsteps. The system consists of multiple devices, with three geophones, and a microprocessor each. To detect the footsteps, two different methods are evaluated. One that analyses features consistion of the normalised standard deviation, frequency peak, spectral centroid and low compared to high frequency content of a signal. These features of the signal are then compared to those of an elephant footstep. The other one compares the frequency content of the seismic wave from a footstep to an computed average of known elephant footsteps. The signal feature method performed the best with an accuracy of 89 %, and detecting 54 % of the footsteps. The detected footstep is sent to a backend where further calculations are done. With one device, estimations of the direction of arrival (DOA) angle can be made. This is done using a delay and sum algorithm. By using a Kalman filter on the DOA estimates, the bearing to the elephant can be tracked over time. From the detected elephant footsteps it has been shown that it is possible to estimate the direction of an elephant with quite high performance and by applying a Kalman filter to track the elephant, it has been shown that the filter gives better and more reasonable estimates. With two devices, a location can be estimated with triangulation and also an elephant's position can be tracked. With triangulation, where the easting position estimated to some extent, but the northing position did not give good results. By using these localisations estimates in a Kalman filter the elephant could be tracked in most of the cases with high enough performance and especially when there weren't too many high northing estimates. By using separate DOA estimations in an extended Kalman filter the easting position could be tracked fairly well, while the northing updates had some strange behaviours, most probably because of implementation error. / Project Ngulia

No description available.

No description available.

No description available.