Detection of rumination in cattle using an accelerometer ear-tag: A comparison of analytical methods and individual animal and generic models

• DOI: 10.1016/j.compag.2021.106595
• Publication Date: 2021-12-02T11:51:56Z
• Authors: Anita Z. Chang; Eloise S. Fogarty; Luis E. Moraes; Alvaro García-Guerra; David L. Swain; Mark G. Trotter
• Keywords: Tree (set theory)

On-animal sensors are revolutionising livestock farming by automating individual animal monitoring. Rumination is closely linked to cow health and physiology a perfect candidate for monitoring using on-animal sensors. The purpose of the current study was determine if tri-axial accelerometer ear-tag could be used detect rumination behaviour in eight multiparous Angus crossbreed cows housed semi-enclosed barn. Different machine learning algorithms (classification regression tree, random forest, linear discriminant analysis, quadratic analysis) epoch lengths (1 s, 5 10 30 60 90 mixed) were tested ability predict rumination. Two approaches taken develop prediction models: 1) generic model developed from data all (generic model) 2) an (individual model). most accurate utilised classification tree with mixed (accuracy = 86.2%, sensitivity 75.3%, specificity 92.5%). Accuracy, sensitivity, improved when proposed ‘individual model’ average accuracy 98.4%. details how can modelled technology, provides insight as described may integrated commercial contexts.