Acceleration data of African white-backed vultures with behaviour labels

This dataset is part of the publication "Death detector: Using vultures as sentinels to detect carcasses by combining bio-logging and machine learning" and was used to train machine learning algorithms for behaviour classification.
It contains acceleration data collected on multiple African white-backed vultures (Gyps africanus). Each sample is labelled with a ground-truthed behaviour label of the following classes:
Feeding, grooming, standing, lying, soaring and flapping flight.
Feeding, grooming, standing and lying were observed in two captive vultures. Soaring and flapping flights were labelled on 27 free-ranging individuals.
Data was recorded at 20Hz. Each sample is 2 seconds long.