Classification of cattle behaviours using neck-mounted accelerometer-equipped collars and convolutional neural networks

Dejan Pavlovic, Christopher Davison, Andrew Hamilton, Oskar Marko, Robert Atkinson, Craig Michie, Vladimir Crnojević, Ivan Andonovic, Xavier Bellekens, Christos Tachtatzis

Research output: Contribution to journalArticlepeer-review

3 Downloads (Pure)

Abstract

Monitoring cattle behaviour is core to the early detection of health and welfare issues and to optimise the fertility of large herds. Accelerometer-based sensor systems that provide activity profiles are now used extensively on commercial farms and have evolved to identify behaviours such as the time spent ruminating and eating at an individual animal level. Acquiring this information at scale is central to informing on-farm management decisions. The paper presents the development of a Convolutional Neural Network (CNN) that classifies cattle behavioural states ('rumination', 'eating' and 'other') using data generated from neck-mounted accelerometer collars. During three farm trials in the United Kingdom (Easter Howgate Farm, Edinburgh, UK), 18 steers were monitored to provide raw acceleration measurements, with ground truth data provided by muzzle-mounted pressure sensor halters. A range of neural network architectures are explored and rigorous hyper-parameter searches are performed to optimise the network. The computational complexity and memory footprint of CNN models are not readily compatible with deployment on low-power processors which are both memory and energy constrained. Thus, progressive reductions of the CNN were executed with minimal loss of performance in order to address the practical implementation challenges, defining the trade-off between model performance versus computation complexity and memory footprint to permit deployment on micro-controller architectures. The proposed methodology achieves a compression of 14.30 compared to the unpruned architecture but is nevertheless able to accurately classify cattle behaviours with an overall F1 score of 0.82 for both FP32 and FP16 precision while achieving a reasonable battery lifetime in excess of 5.7 years.

Original languageEnglish
Article number4050
Number of pages18
JournalSensors
Volume21
Issue number12
DOIs
Publication statusPublished - 12 Jun 2021

Keywords

  • precision agriculture
  • convolutional neural networks
  • cattle behavour monitoring

Fingerprint

Dive into the research topics of 'Classification of cattle behaviours using neck-mounted accelerometer-equipped collars and convolutional neural networks'. Together they form a unique fingerprint.

Cite this