Movement Sensor Dataset for Dog Behavior Classification

Published: 2 July 2021| Version 1 | DOI: 10.17632/vxhx934tbn.1
Sanni Somppi,
Heini Törnqvist,
Anna Valldeoriola Cardó,
Pekka Kumpulainen,
Heli Väätäjä,
Päivi Majaranta,
Veikko Surakka,
Miiamaaria Kujala,
Outi Vainio


The dataset includes movement sensor data from sensors placed on the collar and the harness of a dog and recorded while the dog is given tasks or activities to perform. The task are: galloping, lying on chest, sitting, sniffing, standing, trotting, and walking. The movement sensors used are: ActiGraph GT9X Link (ActiGraph LLC, Florida, USA) and they include 3D accelerometer and 3D gyroscope. The sampling rate used is 100 Hz. The dataset is described in more detail in the data description article: Vehkaoja, A., Somppi, S., Törnqvist, H., Valldeoriola Cardó, A., Kumpulainen, P., Väätäjä, H., Majaranta, P., Surakka, V., Kujala, M. V., Vainio, O., Description of Movement Sensor Dataset for Dog Behavior Classification, Data in Brief, 2021. The behavior classification results obtained with the dataset are published in: Kumpulainen, P., Valldeoriola Cardó, A., Somppi, S., Törnqvist, H., Väätäjä, H., Majaranta, P., Gizatdinova, Y., Hoog Antink, C., Surakka, V., Kujala, M. V., Vainio, O., and Vehkaoja, A., Dog behaviour classification with movement sensors placed on the harness and the collar, Applied Animal Behavior Science, 2021. The authors of the dataset request researchers to refer to the aforementioned publications when using the data and publishing results produced using it.