Porcine lie detectors: Automatic quantification of posture state and transitions in sows using inertial sensors

Robin Thompson,Stephanie M Matheson,Thomas Plötz,Sandra A Edwards,Ilias Kyriazakis

doi:10.1016/j.compag.2016.07.017

Robin Thompson, Stephanie M Matheson + Show 3 more

Open Access

https://doi.org/10.1016/j.compag.2016.07.017

Copy DOI

Abstract

This paper presents a novel approach to automated classification and quantification of sow postures and posture transitions that may enable large scale and accurate continuous behaviour assessment on farm. Automatic classification and quantification of postures and posture transitions in domestic animals has substantial potential to enhance their welfare and productivity. Analysis of such behaviours in farrowing sows can highlight the need for human intervention or lead to the prediction of movement patterns that are potentially dangerous for their piglets, such as crushing when the sow lies down. Data were recorded by a tri-axial accelerometer secured to the hind-end of each sow, in a deployment that involved six sows over the period around parturition. The posture state (standing, sitting, lateral and sternal lying) was automatically classified for the full dataset with a mean F1 score (a measure of predictive performance between 0 and 1) of 0.78. Sitting was shown to present a greater challenge to classification with a F1 score of 0.54, compared to the lateral lying postures, which were classified with an average F1 score of 0.91. Posture transitions were detected with aF1 score of 0.79. We automatically extracted and visualized a range of features that characterise the manner in which the sows changed posture in order to provide comparative descriptors of sow activity and lying style that can be used to assess the influence of genetics or housing design. The methodology presented in this paper can be applied in large scale deployments with potential for enhancing animal welfare and productivity on farm.

Highlights

Automatic classification and quantification of postures and posture transitions in domestic animals has substantial potential to enhance their welfare and productivity
The confusion matrix (Fig. 4) shows that the misclassifications of the sitting class were mostly classified as Standing and Sternal Lie
The Empirical Cumulative Distribution Function (ECDF) were generated from the underlying distribution of the feature values that were the primary output of the algorithms

Summary

Introduction

Automatic classification and quantification of postures and posture transitions in domestic animals has substantial potential to enhance their welfare and productivity. Freedom of movement was one of the original ‘‘Five Freedoms” in the Brambell Report on farm animal welfare (Brambell, 1965), and the ability of housing systems to deliver this in a species-relevant way is a key component in modern welfare assessment schemes (Blokhuis et al, 2010). Changes in posture and activity may be indicative of impending health problems (Szyszka and Kyriazakis, 2013; Weary et al, 2009). In the case of the domestic sow, automated posture assessments may facilitate the identification of additional specific behaviour traits that may confer advantages or disadvantages to the production system. Since the sow poses a significant crushing risk to the piglets (Marchant et al, 2001; Pitts et al, 2002; Špinka et al, 2000; Wechsler and Hegglin, 1997), the way in which she lies whilst in farrowing accommodation relates to her maternal ability and the adequacy of the housing provision, and has consequences towards the survival of her piglets

Objectives

Results

Discussion

Conclusion