Can Tail and Ear Postures Be Suitable to Capture the Affective State of Growing Pigs?

Behavioral responses to artificial insemination and the effect of positive reinforcement training

Dairy cattle experience a variety of stressors associated with routine farm practices, including injections, pen movements, regrouping, and artificial insemination. The primary objective of this study was to assess ear position (categorized according to 5 positions) and body movement responses of heifers during their first experience of artificial insemination, in comparison with responses during baseline observations before and after this procedure. A secondary objective was to test whether heifers exposed to positive reinforcement training (PRT) responded differently to this procedure. We tested 12 heifers (13 ± 0.7 mo. old); 7 were trained using PRT (as part of another study) and 5 had no experience with PRT. Ear axial and ear forward positions were more frequent during observations before and after artificial insemination relative to during artificial insemination (4.57 ± 0.82 vs. 0.31 ± 0.82 times/period, and 3.45 ± 0.51 vs. 0.50 ± 0.51 times/period, respectively). Backward pinned ear position was observed less frequently before and after versus during artificial insemination (0.12 ± 0.76 vs. 3.76 ± 0.76 times/period). We found no effect of period relative to artificial insemination on any of the 4 body movements assessed (leaning forward, backward, and steps taken with front legs and back legs).We found an effect of PRT on forward ear position (1.00 ± 0.51 times/PRT group vs. 2.95 ± 0.60 times/control group), and found that control heifers leaned forward and took more steps with their front legs than did PRT heifers (0.93 ± 0.57 times/PRT group vs. 3.55 ± 0.67 times/control group and 1.29 ± 0.68 times/PRT group vs. 3.85 ± 0.81 times/control group). We conclude that heifers experiencing artificial insemination for the first time express distinct ear positions that are consistent with responses to a negative emotional state. Further work is required to validate these responses and to determine the extent that they can be used to assess affective responses to this and other procedures.

Tail posture and motion in relation to natural behaviour in juvenile and adult pigs

The tail of pigs has been suggested as a welfare indicator as it can provide insight into a pig's behavioural and emotional states. Tail posture and motion have so far mainly been studied in the context of tail biting behaviour. The aim of this study was to investigate the relationship between pigs' natural behaviour and their tail posture and tail motion. This was studied in a free-range farm in which tail biting is absent. In total 214 pigs of different age categories were observed individually (sows, gilts, boars, and 6-month old pigs) or by group (6-month and 1-year old pigs) for their tail posture, tail motion and behaviour, using live observations and videos obtained by drone. Results showed that a fully curled tail occurred most during locomotion (P < 0.001); and an actively hanging tail occurred more during foraging (P < 0.001), excavation (P = 0.006), feeding (P = 0.017), receipt of agonistic behaviour (P = 0.036), and non-agonistic social interactions (P = 0.046). A fully curled tail (P < 0.001) and a half curled tail (P < 0.005) occurred least in the group of sows. Tail motion was infrequent (6.7% of observations), and involved mainly loosely wagging, which occurred more during locomotion (P = 0.006) and non-agonistic social interactions (P = 0.006). A higher temperature-humidity index increased the probability of half curled tails (P < 0.001) and loose wagging (P < 0.001), while reducing the probability of active (P < 0.001) and passive hanging tails (P = 0.013). These results provide insight into tail posture and tail motion in pigs under semi-natural conditions, showing especially that hanging tails are not primarily associated with tail biting, and that the use of tail postures for welfare assessment should be in consideration with the context in which the animals are kept.

Happy Cow or Thinking Pig? WUR Wolf—Facial Coding Platform for Measuring Emotions in Farm Animals

Emotions play an indicative and informative role in the investigation of farm animal behaviors. Systems that respond and can measure emotions provide a natural user interface in enabling the digitalization of animal welfare platforms. The faces of farm animals can be one of the richest channels for expressing emotions. WUR Wolf (Wageningen University & Research: Wolf Mascot), a real-time facial recognition platform that can automatically code the emotions of farm animals, is presented in this study. The developed Python-based algorithms detect and track the facial features of cows and pigs, analyze the appearance, ear postures, and eye white regions, and correlate these with the mental/emotional states of the farm animals. The system is trained on a dataset of facial features of images of farm animals collected in over six farms and has been optimized to operate with an average accuracy of 85%. From these, the emotional states of animals in real time are determined. The software detects 13 facial actions and an inferred nine emotional states, including whether the animal is aggressive, calm, or neutral. A real-time emotion recognition system based on YoloV3, a Faster YoloV4-based facial detection platform and an ensemble Convolutional Neural Networks (RCNN) is presented. Detecting facial features of farm animals simultaneously in real time enables many new interfaces for automated decision-making tools for livestock farmers. Emotion sensing offers a vast potential for improving animal welfare and animal–human interactions.