Automated detection of lameness in sheep using machine learning approaches: novel insights into behavioural differences among lame and non-lame sheep

Abstract

Lameness in sheep is the biggest cause of concern regarding poor health and welfare among sheep-producing countries. Best practice for lameness relies on rapid treatment, yet there are no objective measures of lameness detection. Accelerometers and gyroscopes have been widely used in human activity studies and their use is becoming increasingly common in livestock. In this study, we used 23 datasets (10 non-lame and 13 lame sheep) from an accelerometer-and gyroscope-based ear sensor with a sampling frequency of 16 Hz to develop and compare algorithms that can differentiate lameness within three different activities (walking, standing and lying). We show for the first time that features extracted from accelerometer and gyroscope signals can differentiate between lame and non-lame sheep while standing, walking and lying. The random forest algorithm performed best for classifying lameness with an accuracy of 84.91% within lying, 81.15% within standing and 76.83% within walking and overall correctly classified over 80% sheep within activities. Both accelerometer-and gyroscope-based features ranked among the top 10 features for classification. Our results suggest that novel behavioural differences between lame and non-lame sheep across all three activities could be used to develop an automated system for lameness detection.

Exploring the Potential of Precision Livestock Farming Technologies to Help Address Farm Animal Welfare

“…Lameness can be detected in pigs using images and sensors (Pluym et al, 2013;Stavrakakis et al, 2015), while gait scores can be evaluated in poultry using optical flow and sensors (De Alencar Nääs et al, 2010;Dawkins et al, 2017;Van Hertem et al, 2018). Sensors can be used to detect lameness in sheep (Shrestha et al, 2018;Kaler et al, 2020) and soundbased systems to monitor lameness and foot lesions in cattle (Volkmann et al, 2019).…”

Do we automatically detect health- or general welfare-related issues? A framework

“…Changes in milk yield, rumination and neck activity were shown to serve as early signs of lameness [30], whereas, rumination and activity served also for the identification of metritis [31], metabolic digestive disorders [32] and mastitis [25]. Moreover, changes in activity also indicated the occurrence of lameness in broilers [18] and in sheep [33]. Lowe et al [34] found that milk consumption, body temperatures of the side and shoulder and number and duration of lying bouts have the potential to be suitable measures of neonatal calf diarrhoea.…”

Lameness Detection in Cows Using Hierarchical Deep Learning and Synchrosqueezed Wavelet Transform

“…represents the synchrosqueezed transform at the centres ω l of successive frequency bins. To derive the SSWT transform, first, the reassigned frequencies are calculated for all the scales at each fixed time point b using equation (3). Then, for each desired IF of ω l , T s (ω l , b) is calculated by summing all W s (a, b) taking into account the distance between the reassigned frequency ω(a, b) and ω l .…”

“…Accelerometers have been used for human and animal gait analysis [1] [2]. It has been documented that the use of cowworn sensors such as accelerometers is becoming an emerging technology in diary industry meanwhile the accelerometrybased gait measurements are still rather underdeveloped [3]. Accelerometers and gyroscopes have been used for sheep behaviour and lameness classification [4] [5].…”