Dog behaviour classification with movement sensors placed on the harness and the collar
| Autor: | Sanni Somppi, Miiamaaria V. Kujala, Heli Väätäjä, Heini Törnqvist, Antti Vehkaoja, Christoph Hoog Antink, Yulia Gizatdinova, Anna Valldeoriola Cardó, Veikko Surakka, Outi Vainio, Päivi Majaranta, Pekka Kumpulainen |
|---|---|
| Přispěvatelé: | Departments of Faculty of Veterinary Medicine, Equine and Small Animal Medicine, Helsinki One Health (HOH), Outi Vainio / Principal Investigator, Research Centre for Animal Welfare, Tampere University, BioMediTech, Computing Sciences |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
dogs
aktiivisuus Computer science Wearable computer Accelerometer 413 Veterinary science 01 natural sciences Collar law.invention Canine 0403 veterinary science Food Animals Sniffing law Accelerometry Dog älyvaatteet Computer vision 412 Animal science dairy science 318 Medical biotechnology Movement (music) Wearable technology Gyroscope 04 agricultural and veterinary sciences liikkeentunnistus koneoppiminen behaviour classification Activity monitoring eläimet eläinten koulutus activity monitoring Behaviour classification 040301 veterinary sciences aktigrafia canine Sitting koira eläinten käyttäytyminen wearable technology ACCELEROMETER Classifier (linguistics) MEASURED PHYSICAL-ACTIVITY accelerometry puettava teknologia VALIDITY käyttäytyminen business.industry 010401 analytical chemistry ANIMALS 113 Computer and information sciences Actigraphy 0104 chemical sciences ACCELERATION DATA koulutus mittarit (mittaus) Animal Science and Zoology Artificial intelligence business actigraphy |
| Popis: | Dog owners’ understanding of the daily behaviour of their dogs may be enhanced by movement measurements that can detect repeatable dog behaviour, such as levels of daily activity and rest as well as their changes. The aim of this study was to evaluate the performance of supervised machine learning methods utilising accelerometer and gyroscope data provided by wearable movement sensors in classification of seven typical dog activities in a semi-controlled test situation. Forty-five middle to large sized dogs participated in the study. Two sensor devices were attached to each dog, one on the back of the dog in a harness and one on the neck collar. Altogether 54 features were extracted from the acceleration and gyroscope signals divided in two-second segments. The performance of four classifiers were compared using features derived from both sensor modalities. and from the acceleration data only. The results were promising; the movement sensor at the back yielded up to 91 % accuracy in classifying the dog activities and the sensor placed at the collar yielded 75 % accuracy at best. Including the gyroscope features improved the classification accuracy by 0.7–2.6 %, depending on the classifier and the sensor location. The most distinct activity was sniffing, whereas the static postures (lying on chest, sitting and standing) were the most challenging behaviours to classify, especially from the data of the neck collar sensor. The data used in this article as well as the signal processing scripts are openly available in Mendeley Data, https://doi.org/10.17632/vxhx934tbn.1. publishedVersion |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|