Advanced search
2 files | 2.32 MB Add to list

On the use of on-cow accelerometers for the classification of behaviours in dairy barns

Said Benaissa (UGent) , Frank Tuyttens (UGent) , David Plets (UGent) , Toon De Pessemier (UGent) , Jens Trogh, Emmeric Tanghe (UGent) , Luc Martens (UGent) , Leen Vandaele, Annelies Van Nuffel (UGent) , Wout Joseph (UGent) , et al.
Author
Organization
Abstract
Analysing behaviours can provide insight into the health and overall well-being of dairy cows. Automatic monitoring systems using e.g., accelerometers are becoming increasingly important to accurately quantify cows' behaviours as the herd size increases. The aim of this study is to automatically classify cows' behaviours by comparing leg- and neck-mounted accelerometers, and to study the effect of the sampling rate and the number of accelerometer axes logged on the classification performances. Lying, standing, and feeding behaviours of 16 different lactating dairy cows were logged for 6 h with 3D-accelerometers. The behaviours were simultaneously recorded using visual observation and video recordings as a reference. Different features were extracted from the raw data and machine learning algorithms were used for the classification. The classification models using combined data of the neck- and the leg-mounted accelerometers have classified the three behaviours with high precision (80-99%) and sensitivity (87-99%). For the leg-mounted accelerometer, lying behaviour was classified with high precision (99%) and sensitivity (98%). Feeding was classified more accurately by the neck-mounted versus the leg-mounted accelerometer (precision 92% versus 80%; sensitivity 97% versus 88%). Standing was the most difficult behaviour to classify when only one accelerometer was used. In addition, the classification performances were not highly influenced when only X, X and Z, or Z and Y axes were used for the classification instead of three axes, especially for the neck-mounted accelerometer. Moreover, the accuracy of the models decreased with about 20% when the sampling rate was decreased from 1 Hz to 0.05 Hz.
Keywords
ACCELERATION, GHZ, Accelerometer, Dairy cows, Machine learning, Behaviours classification, Feature extraction

Downloads

  • WICA 862a.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.53 MB
  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 791.06 KB

Citation

Please use this url to cite or link to this publication:

MLA
Benaissa, Said, et al. “On the Use of On-Cow Accelerometers for the Classification of Behaviours in Dairy Barns.” RESEARCH IN VETERINARY SCIENCE, vol. 125, 2019, pp. 425–33, doi:10.1016/j.rvsc.2017.10.005.
APA
Benaissa, S., Tuyttens, F., Plets, D., De Pessemier, T., Trogh, J., Tanghe, E., … Sonck, B. (2019). On the use of on-cow accelerometers for the classification of behaviours in dairy barns. RESEARCH IN VETERINARY SCIENCE, 125, 425–433. https://doi.org/10.1016/j.rvsc.2017.10.005
Chicago author-date
Benaissa, Said, Frank Tuyttens, David Plets, Toon De Pessemier, Jens Trogh, Emmeric Tanghe, Luc Martens, et al. 2019. “On the Use of On-Cow Accelerometers for the Classification of Behaviours in Dairy Barns.” RESEARCH IN VETERINARY SCIENCE 125: 425–33. https://doi.org/10.1016/j.rvsc.2017.10.005.
Chicago author-date (all authors)
Benaissa, Said, Frank Tuyttens, David Plets, Toon De Pessemier, Jens Trogh, Emmeric Tanghe, Luc Martens, Leen Vandaele, Annelies Van Nuffel, Wout Joseph, and Bart Sonck. 2019. “On the Use of On-Cow Accelerometers for the Classification of Behaviours in Dairy Barns.” RESEARCH IN VETERINARY SCIENCE 125: 425–433. doi:10.1016/j.rvsc.2017.10.005.
Vancouver
1.
Benaissa S, Tuyttens F, Plets D, De Pessemier T, Trogh J, Tanghe E, et al. On the use of on-cow accelerometers for the classification of behaviours in dairy barns. RESEARCH IN VETERINARY SCIENCE. 2019;125:425–33.
IEEE
[1]
S. Benaissa et al., “On the use of on-cow accelerometers for the classification of behaviours in dairy barns,” RESEARCH IN VETERINARY SCIENCE, vol. 125, pp. 425–433, 2019.
@article{8629658,
  abstract     = {{Analysing behaviours can provide insight into the health and overall well-being of dairy cows. Automatic monitoring systems using e.g., accelerometers are becoming increasingly important to accurately quantify cows' behaviours as the herd size increases. The aim of this study is to automatically classify cows' behaviours by comparing leg- and neck-mounted accelerometers, and to study the effect of the sampling rate and the number of accelerometer axes logged on the classification performances. Lying, standing, and feeding behaviours of 16 different lactating dairy cows were logged for 6 h with 3D-accelerometers. The behaviours were simultaneously recorded using visual observation and video recordings as a reference. Different features were extracted from the raw data and machine learning algorithms were used for the classification. The classification models using combined data of the neck- and the leg-mounted accelerometers have classified the three behaviours with high precision (80-99%) and sensitivity (87-99%). For the leg-mounted accelerometer, lying behaviour was classified with high precision (99%) and sensitivity (98%). Feeding was classified more accurately by the neck-mounted versus the leg-mounted accelerometer (precision 92% versus 80%; sensitivity 97% versus 88%). Standing was the most difficult behaviour to classify when only one accelerometer was used. In addition, the classification performances were not highly influenced when only X, X and Z, or Z and Y axes were used for the classification instead of three axes, especially for the neck-mounted accelerometer. Moreover, the accuracy of the models decreased with about 20% when the sampling rate was decreased from 1 Hz to 0.05 Hz.}},
  author       = {{Benaissa, Said and Tuyttens, Frank and Plets, David and De Pessemier, Toon and Trogh, Jens and Tanghe, Emmeric and Martens, Luc and Vandaele, Leen and Van Nuffel, Annelies and Joseph, Wout and Sonck, Bart}},
  issn         = {{0034-5288}},
  journal      = {{RESEARCH IN VETERINARY SCIENCE}},
  keywords     = {{ACCELERATION,GHZ,Accelerometer,Dairy cows,Machine learning,Behaviours classification,Feature extraction}},
  language     = {{eng}},
  pages        = {{425--433}},
  title        = {{On the use of on-cow accelerometers for the classification of behaviours in dairy barns}},
  url          = {{http://dx.doi.org/10.1016/j.rvsc.2017.10.005}},
  volume       = {{125}},
  year         = {{2019}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: