Predicting Animal Movements within the Context of Small Data – Insights from France Rose’s SmallData Presentation

The CRC 1597 Small Data invited Emmy Noether fellow France Rose from the University of Cologne to give a presentation on her research on animal behaviour time series.

Time series data, that is, repeated measurements over time of a value, is of particular interest given the potential it has to predict future data. The current development of sensor technology and its application in the field of animal behaviour has allowed for continuous readings over long periods of time, however when it comes to predicting future data, we are still faced by a small data challenge due to the low number of subjects than can be measured for a specific purpose. In her research, Dr. Rose trains neural networks to predict the movements of different animal species, an approach that has led to some meaningful results.

We thank Dr. Rose for her insightful presentation and look forward to the many more applications that small data research methodologies will bring in the future.

Administrative Manager

Marc Schumacher

Institute of Medical Biometry and Statistics,
Faculty of Medicine and Medical Center –
University of Freiburg