HABRI Central - Resources: Machine learning based canine posture estimation using inertial data: About

The Human Animal Bond Research Institute (HABRI) is issuing a call for research proposals from institutions and organizations across the globe to investigate the health outcomes of pet ownership and/or animal-assisted interventions (AAI), both for the people and the animals involved. To learn more, visit https://habri.org/grants/funding-opportunities/ close

You are here: Home / Journal Articles / Machine learning based canine posture estimation using inertial data / About

Machine learning based canine posture estimation using inertial data

By M. Marcato, S. Tedesco, C. O'Mahony, B. O'Flynn, P. Galvin

View Resource (HTM)

Licensed under

Category Journal Articles

The aim of this study was to design a new canine posture estimation system specifically for working dogs. The system was composed of Inertial Measurement Units (IMUs) that are commercially available, and a supervised learning algorithm which was developed for different behaviours. Three IMUs, each containing a 3-axis accelerometer, gyroscope, and magnetometer, were attached to the dogs’ chest, back, and neck. To build and test the model, data were collected during a video-recorded behaviour test where the trainee assistance dogs performed static postures (standing, sitting, lying down) and dynamic activities (walking, body shake). Advanced feature extraction techniques were employed for the first time in this field, including statistical, temporal, and spectral methods. The most important features for posture prediction were chosen using Select K Best with ANOVA F-value. The individual contributions of each IMU, sensor, and feature type were analysed using Select K Best scores and Random Forest feature importance. Results showed that the back and chest IMUs were more important than the neck IMU, and the accelerometers were more important than the gyroscopes. The addition of IMUs to the chest and back of dog harnesses is recommended to improve performance. Additionally, statistical and temporal feature domains were more important than spectral feature domains. Three novel cascade arrangements of Random Forest and Isolation Forest were fitted to the dataset. The best classifier achieved an f1-macro of 0.83 and an f1-weighted of 0.90 for the prediction of the five postures, demonstrating a better performance than previous studies. These results were attributed to the data collection methodology (number of subjects and observations, multiple IMUs, use of common working dog breeds) and novel machine learning techniques (advanced feature extraction, feature selection and modelling arrangements) employed. The dataset and code used are publicly available on Mendeley Data and GitHub, respectively.

Date 2023
Publication Title PLoS One
Volume 18
Issue 6
Pages e0286311
ISBN/ISSN 1932-6203
DOI 10.1371/journal.pone.0286311
Author Address Tyndall National Institute, University College Cork, Cork, Ireland.
Additional Language English
Cite this work

Researchers should cite this work as follows:

  1. Algorithms
  2. Animals
  3. Dogs
  4. Machine learning
  5. open access
  6. Posture
  7. Walking
  1. open access