Predicting Lameness in Sheep Activity Using Tri-Axial Acceleration Signals

Abstract

Lameness is a clinical symptom associated with a number of sheep diseases around the world, having adverse effects on weight gain, fertility, and lamb birth weight, and increasing the risk of secondary diseases. Current methods to identify lame animals rely on labour intensive visual inspection. The aim of this current study was to determine the ability of a collar, leg, and ear attached tri-axial accelerometer to discriminate between sound and lame gait movement in sheep. Data were separated into 10 s mutually exclusive behaviour epochs and subjected to Quadratic Discriminant Analysis (QDA). Initial analysis showed the high misclassification of lame grazing events with sound grazing and standing from all deployment modes. The final classification model, which included lame walking and all sound activity classes, yielded a prediction accuracy for lame locomotion of 82%, 35%, and 87% for the ear, collar, and leg deployments, respectively. Misclassification of sound walking with lame walking within the leg accelerometer dataset highlights the superiority of an ear mode of attachment for the classification of lame gait characteristics based on time series accelerometer data.

Keywords: acceleromter; activity; behavior; lameness; on-animal sensor; sheep.

Figure 1

Experimental animal displaying the ear and neck (collar) locations evaluated. Insert shows the axis orientation of the sensor. Refer to Figure 3 for leg attachment display.

Figure 2

Workflow of the steps employed to classify sheep behaviour from a tri-axial accelerometer.

Figure 3

Experimental animal showing the method used to simulate lameness behaviour (main photo and inset). The method of restraint prevented any weight bearing on the restrained limb.

Figure 4

Raw ear acceleration signals for sound and lame walking. Note the increased amplitude of lame walking signals. Insert highlights the difference in amplitude between lame and sound walking signals.