Combining Spatial and Telemetric Features for Learning Animal Movement Models

Berk Kapicioglu, Robert Schapire, Martin Wikelski, Tamara Broderick
Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, PMLR R8:268-275, 2010.

Abstract

We introduce a new graphical model for tracking radio-tagged animals and learning their movement patterns. The model provides a principled way to combine radio telemetry data with an arbitrary set of userdefined, spatial features. We describe an efficient stochastic gradient algorithm for fitting model parameters to data and demonstrate its effectiveness via asymptotic analysis and synthetic experiments. We also apply our model to real datasets, and show that it outperforms the most popular radio telemetry software package used in ecology. We conclude that integration of different data sources under a single statistical framework, coupled with appropriate parameter and state estimation procedures, produces both accurate location estimates and an interpretable statistical model of animal movement.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR8-kapicioglu10a, title = {Combining Spatial and Telemetric Features for Learning Animal Movement Models}, author = {Kapicioglu, Berk and Schapire, Robert and Wikelski, Martin and Broderick, Tamara}, booktitle = {Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence}, pages = {268--275}, year = {2010}, editor = {Grünwald, Peter and Spirtes, Peter}, volume = {R8}, series = {Proceedings of Machine Learning Research}, month = {08--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r8/main/assets/kapicioglu10a/kapicioglu10a.pdf}, url = {https://proceedings.mlr.press/r8/kapicioglu10a.html}, abstract = {We introduce a new graphical model for tracking radio-tagged animals and learning their movement patterns. The model provides a principled way to combine radio telemetry data with an arbitrary set of userdefined, spatial features. We describe an efficient stochastic gradient algorithm for fitting model parameters to data and demonstrate its effectiveness via asymptotic analysis and synthetic experiments. We also apply our model to real datasets, and show that it outperforms the most popular radio telemetry software package used in ecology. We conclude that integration of different data sources under a single statistical framework, coupled with appropriate parameter and state estimation procedures, produces both accurate location estimates and an interpretable statistical model of animal movement.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Combining Spatial and Telemetric Features for Learning Animal Movement Models %A Berk Kapicioglu %A Robert Schapire %A Martin Wikelski %A Tamara Broderick %B Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2010 %E Peter Grünwald %E Peter Spirtes %F pmlr-vR8-kapicioglu10a %I PMLR %P 268--275 %U https://proceedings.mlr.press/r8/kapicioglu10a.html %V R8 %X We introduce a new graphical model for tracking radio-tagged animals and learning their movement patterns. The model provides a principled way to combine radio telemetry data with an arbitrary set of userdefined, spatial features. We describe an efficient stochastic gradient algorithm for fitting model parameters to data and demonstrate its effectiveness via asymptotic analysis and synthetic experiments. We also apply our model to real datasets, and show that it outperforms the most popular radio telemetry software package used in ecology. We conclude that integration of different data sources under a single statistical framework, coupled with appropriate parameter and state estimation procedures, produces both accurate location estimates and an interpretable statistical model of animal movement. %Z Reissued by PMLR on 04 October 2026.
APA
Kapicioglu, B., Schapire, R., Wikelski, M. & Broderick, T.. (2010). Combining Spatial and Telemetric Features for Learning Animal Movement Models. Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R8:268-275 Available from https://proceedings.mlr.press/r8/kapicioglu10a.html. Reissued by PMLR on 04 October 2026.

Related Material