Classification of broiler behaviours using triaxial accelerometer and machine learning

X Yang; Y Zhao; G M Street; Y Huang; S D Filip To; J L Purswell

doi:10.1016/j.animal.2021.100269

Classification of broiler behaviours using triaxial accelerometer and machine learning

Animal. 2021 Jul;15(7):100269. doi: 10.1016/j.animal.2021.100269. Epub 2021 Jun 5.

Authors

X Yang¹, Y Zhao², G M Street³, Y Huang⁴, S D Filip To⁵, J L Purswell⁶

Affiliations

¹ Department of Animal Science, The University of Tennessee, Knoxville, TN 37996, USA.
² Department of Animal Science, The University of Tennessee, Knoxville, TN 37996, USA. Electronic address: yzhao@utk.edu.
³ Department of Wildlife, Fisheries and Aquaculture, Mississippi State University, Mississippi State, MS 39762, USA.
⁴ United States Department of Agriculture, Agricultural Research Service, Crop Production Systems Research Unit, Stoneville, MS 38776, USA.
⁵ Department of Agricultural and Biological Engineering, Mississippi State University, Mississippi State, MS 39762, USA.
⁶ USDA Agricultural Research Service, Poultry Research Unit, Mississippi State, MS 39762, USA.

PMID: 34102430
DOI: 10.1016/j.animal.2021.100269

Abstract

Understanding broiler behaviours provides important implications for animal well-being and farm management. The objectives of this study were to classify specific broiler behaviours by analysing data from wearable accelerometers using two machine learning models, K-Nearest Neighbour (KNN) and Support Vector Machine (SVM). Lightweight triaxial accelerometers were used to record accelerations of nine 7-week-old broilers at a sampling frequency of 40 Hz. A total of 261.6-min data were labelled for four behaviours - walking, resting, feeding and drinking. Instantaneous motion features including magnitude area, vector magnitude, movement variation, energy, and entropy were extracted and stored in a dataset which was then segmented by one of the six window lengths (1, 3, 5, 7, 10 and 20 s) with 50% overlap between consecutive windows. The mean, variation, SD, minimum and maximum of each instantaneous motion feature and two-way correlations of acceleration data were calculated within each window, yielding a total of 43 statistic features for training and testing of machine learning models. Performance of the models was evaluated using pure behaviour datasets (single behaviour type per dataset) and continuous behaviour datasets (continuous recording that involved multiple behaviour types per dataset). For pure behaviour datasets, both KNN and SVM models showed high sensitivities in classifying broiler resting (87% and 85%, respectively) and walking (99% and 99%, respectively). The accuracies of SVM were higher than KNN in differentiating feeding (88% and 75%, respectively) and drinking (83% and 62%, respectively) behaviours. Sliding window with 1-s length yielded the best performance for classifying continuous behaviour datasets. The performance of classification model generally improved as more birds were included for training. In conclusion, classification of specific broiler behaviours can be achieved by recording bird triaxial accelerations and analysing acceleration data through machine learning. Performances of different machine learning models differ in classifying specific broiler behaviours.

Keywords: Behaviour recognition; Poultry; Sliding window; Supervised learning; Wearable sensor.

MeSH terms

Accelerometry / veterinary
Animals
Behavior, Animal*
Chickens*
Machine Learning
Support Vector Machine