Damaging behaviors, like feather pecking (FP), have large economic and welfare consequences in the commercial laying hen industry. Selective breeding can be used to obtain animals that are less likely to perform damaging behavior on their pen-mates. However, with the growing tendency to keep birds in large groups, identifying specific birds that are performing or receiving FP is difficult. With current developments in sensor technologies, it may now be possible to identify laying hens in large groups that show less FP behavior and select them for breeding. We propose using a combination of sensor technology and genomic methods to identify feather peckers and victims in groups. In this review, we will describe the use of “-omics” approaches to understand FP and give an overview of sensor technologies that can be used for animal monitoring, such as ultra-wideband, radio frequency identification, and computer vision. We will then discuss the identification of indicator traits from both sensor technologies and genomics approaches that can be used to select animals for breeding against damaging behavior.

To maintain dairy cattle health and welfare at commensurable levels, analysis of the behaviors occurring between cows should be performed. This type of behavioral analysis is highly dependent on reliable and robust tracking of individuals, for it to be viable and applicable on-site. In this article, we introduce a novel method for continuous tracking and data-marker based identification of individual cows based on convolutional neural networks (CNNs). The methodology for data acquisition and overall implementation of tracking/identification is described. The Region of Interest (ROI) for the recordings was limited to a waiting area with free entrances to four automatic milking stations and a total size of 6 × 18 meters. There were 252 Swedish Holstein cows during the time of study that had access to the waiting area at a conventional dairy barn with varying conditions and illumination. Three Axis M3006-V cameras placed in the ceiling at 3.6 meters height and providing top-down view were used for recordings. The total amount of video data collected was 4 months, containing 500 million frames. To evaluate the system two 1-h recordings were chosen. The exit time and gate-id found by the tracker for each cow were compared with the exit times produced by the gates. In total there were 26 tracks considered, and 23 were correctly tracked. Given those 26 starting points, the tracker was able to maintain the correct position in a total of 101.29 min or 225 s in average per starting point/individual cow. Experiments indicate that a cow could be tracked close to 4 min before failure cases emerge and that cows could be successfully tracked for over 20 min in mildly-crowded (< 10 cows) scenes. The proposed system is a crucial stepping stone toward a fully automated tool for continuous monitoring of cows and their interactions with other individuals and the farm-building environment.

While fully automated livestock production may be considered the ultimate goal for optimising productivity at the farm level, the benefits and costs of such a development at the scale at which it needs to be implemented must also be considered from social and ethical perspectives. Automation resulting from Precision Livestock Farming (PLF) could alter fundamental views of human-animal interactions on farm and, even further, potentially compromise human and animal welfare and health if PLF development does not include a flexible, holistic strategy for integration. To investigate topic segregation, inclusion of socio-ethical aspects, and consideration of human-animal interactions within the PLF research field, the abstracts from 644 peer-reviewed publications were analysed using the recent advances in the Natural Language Processing (NLP). Two Latent Dirichlet Allocation (LDA) probabilistic models with varying number of topics (13 and 3 for Model 1 and Model 2, respectively) were implemented to create a generalised research topic overview. The visual representation of topics produced by LDA Model 1 and Model 2 revealed prominent similarities in the terms contributing to each topic, with only weight for each term being different. The majority of terms for both models were process-oriented, obscuring the inclusion of social and ethical angles in PLF publications. A subset of articles (5%,n= 32) was randomly selected for manual examination of the full text to evaluate whether abstract text and focus reflected that of the article as a whole. Few of these articles (12.5%,n= 4) focused specifically on broader ethical or societal considerations of PLF or (9.4%,n= 3) discussed PLF with respect to human-animal interactions. While there was consideration of the impact of PLF on animal welfare and farmers in nearly half of the full texts examined (46.9%,n= 15), this was often limited to a few statements in passing. Further, these statements were typically general rather than specific and presented PLF as beneficial to human users and animal recipients. To develop PLF that is in keeping with the ethical values and societal concerns of the public and consumers, projects, and publications that deliberately combine social context with technological processes and results are needed.

The aim of this study was to investigate how the activity of cattle under natural grazing conditions is related to their individual parasite contribution (IPC). Potentially, the individuals contributing the most to the contamination of the pasture with gastrointestinal nematodes (GIN) could then be identified and selectively treated based on sensor data thresholds. A total of 58 steers of the dairy breeds Swedish Red (SR, n = 19) and Swedish Holstein (SH, n = 39) were used for sensor-based data collection that lasted for a total of 10 weeks from 4 May to 13 July 2022. All steers were inoculated with a priming dose of nematode larvae and weighed in conjunction with the pasture release. The animals were then divided into four experimental groups and treated with ivermectin (IVM PO, Boehringer Ingelheim, 0.5 mg/kg BW) at different intervals to obtain an exposure contrast (Group A was left untreated, Group B/IVM PO-4w was treated after 4 weeks, Group C/IVM PO-8w was treated after 8 weeks, and Group D/IVM PO-4&8w was treated after 4 weeks and then after 8 weeks). The steers were weighed on four further occasions, during which faecal samples were also taken for parasite testing. Activity data were collected using leg-mounted IceQube sensors and body weight data and faecal samples were collected bi-weekly. The new threshold metric (IPC) was proposed for individuals with different faecal egg count (FEC) levels [NO (no contribution) <20 EPG, LO (low contribution) = 20–150 EPG, ME (medium contribution) = 150–250 EPG, and HI (high contribution) ≥250 EPG] The effects of IPC on activity patterns were analysed stepwise using a Generalised Estimating Equations model implemented in Python programming language. Results showed significant effects of different IPC values on motion index and number of steps taken (adjusted p-value of 0.008, 0.018, 0.041, and 0.001 for individuals with NO, LO, ME, and HI IPC values, respectively). There were some breed effects on the average number of steps and minutes spent lying. The results also provide alternative threshold methods aimed at finding more sustainable ways of using anthelmintics and integrating individual data into future parasite control strategies.

Precision livestock farming (PLF) technologies have been heavily promoted in the past, but the implementation of these technologies is not easy. Numerous technical challenges need to be solved befo...

Data on body weight, as well as objective measures of body condition and size, are essential for appropriate decision-making on farm level, for example in calculations of nutrient requirements, health monitoring, and breeding-related assessment. Weighing dairy cattle and assessing their body condition are labour-intensive and are therefore often not performed as frequently as desired under practical farm conditions. Although recent research has shown strong potential for computer vision and image analysis in automated estimation of body weight, body condition score, and conformation, many existing workflows still depend on fixed multi-camera or 3D setups that increase hardware and deployment costs. We therefore developed a two-step, smartphone-centred workflow for practical live-weight estimation in dairy cattle. First, a Mask R-CNN segmentation model was trained on 567 manually annotated cow images collected under varied barn conditions and achieved an F1 score of 0.98. Second, body weight was discretized into nine data-driven categories using a Gaussian Mixture Model (BIC-selected), after which the source weight variable was removed to prevent leakage and a leak-safe pipeline (imputation, robust scaling, fold-internal SMOTE, Extra Trees) was trained within the training partition. Primary evaluation used cow-level grouped splitting so that all features based on repeated observations from the same cow remained in a single partition; a PyCaret implementation was used as an independent cross-check. On the 216-image grouped holdout, the tuned Extra Trees model achieved a macro-F1 of 0.936 (95% CI 0.860–0.983) with a 4.2% error rate. These results were obtained on 1080 images collected using the developed camera app and not used for segmentation-model training. The idea is to further streamline the algorithm to allow its downscaling and transition in the form of a smartphone application to be used on-farm as an open-source support tool.