Precision Feeding and Management of Farm Animals, 2nd Edition

In this study, the implementation of traditional machine learning models in the intelligent management of swine is explored, focusing on the impact of LDA preprocessing on pig facial recognition using an SVM. Through experimental analysis, the kernel functions for two testing protocols, one utilizing an SVM exclusively and the other employing a combination of LDA and an SVM, were identified as polynomial and RBF, both with coefficients of 0.03. Individual identification tests conducted on 10 pigs demonstrated that the enhanced protocol improved identification accuracy from 83.66% to 86.30%. Additionally, the training and testing durations were reduced to 0.7% and 0.3% of the original times, respectively. These findings suggest that LDA preprocessing significantly enhances the efficiency of individual pig identification using an SVM, providing empirical evidence for the deployment of SVM classifiers in mobile and embedded systems. Full article

Traditional measurement methods often rely on manual operations, which are not only inefficient but also cause stress to cattle, affecting animal welfare. Currently, non-contact cattle dimension measurement usually involves the use of multi-view images combined with point cloud or 3D reconstruction technologies, which are costly and less flexible in actual farming environments. To address this, this study proposes an automated cattle dimension measurement method based on an improved keypoint detection model combined with unilateral depth imaging. Firstly, YOLOv8-Pose is selected as the keypoint detection model and SimSPPF replaces the original SPPF to optimize spatial pyramid pooling, reducing computational complexity. The CARAFE architecture, which enhances upsampling content-aware capabilities, is introduced at the neck. The improved YOLOv8-pose achieves a mAP of 94.4%, a 2% increase over the baseline model. Then, cattle keypoints are captured on RGB images and mapped to depth images, where keypoints are optimized using conditional filtering on the depth image. Finally, cattle dimension parameters are calculated using the cattle keypoints combined with Euclidean distance, the Moving Least Squares (MLS) method, Radial Basis Functions (RBFs), and Cubic B-Spline Interpolation (CB-SI). The average relative errors for the body height, lumbar height, body length, and chest girth of the 23 measured beef cattle were 1.28%, 3.02%, 6.47%, and 4.43%, respectively. The results show that the method proposed in this study has high accuracy and can provide a new approach to non-contact beef cattle dimension measurement. Full article

Heat stress (HS) is one of the key factors affecting an animal’s immune system and productivity, as a result of a physiological reaction combined with environmental factors. This study examined the short-term effects of heat stress on cow behavior, as recorded by innovative technologies, and its impact on blood gas parameters, using 56 of the 1070 cows clinically evaluated during the second and subsequent lactations within the first 30 days postpartum. Throughout the experiment (from 4 June 2024 until 1 July 2024), cow behavior parameters (rumination time min/d. (RT), body temperature (°C), reticulorumen pH, water consumption (L/day), cow activity (h/day)) were monitored using specialized SmaXtec boluses and employing a blood gas analyzer (Siemens Healthineers, 1200 Courtneypark Dr E Mississauga, L5T 1P2, Canada). During the study period, the temperature–humidity index (THI), based on ambient temperature and humidity, was recorded and used to calculate THI and to categorize the data into four THI classes as follows: 1—THI 60–63 (4 June 2024–12 June 2024); 2—THI 65–69 (13 June 2024–18 June 2024); 3—THI 73–75 (19 June 2024–25 June 2024); and 4—THI 73–78 (26 June 2024–1 July 2024). The results showed that heat stress significantly reduced rumination time by up to 70% in cows within the highest THI class (73 to 78) and increased body temperature by 2%. It also caused a 12.6% decrease in partial carbon dioxide pressure (pCO2) and a 32% increase in partial oxygen pressure (pO2), also decreasing plasma sodium by 1.36% and potassium by 6%, while increasing chloride by 3%. The findings underscore the critical need for continuous monitoring, early detection, and proactive management to mitigate the adverse impacts of heat stress on dairy cow health and productivity. Recommendations include the use of advanced monitoring technologies and specific blood gas parameter tracking to detect the early signs of heat stress and implement more timely interventions. Full article

The accurate estimation of basal endogenous losses (BEL) of amino acids at the ileum is indispensable to improve nutrient utilization efficiency. This study used a quantitative proteomic approach to identify variations in BEL in the ileal digesta of growing pigs fed a nitrogen-free diet (NFD) or a casein diet (CAS). Eight barrow pigs (39.8 ± 6.3 kg initial body weight (BW)) were randomly assigned to a 2 × 2 crossover design. A total of 348 proteins were identified and quantified in both treatments, of which 101 showed a significant differential abundance between the treatments (p < 0.05). Functional and pathway enrichment analyses revealed that the endogenous proteins were associated with intestinal metabolic function. Furthermore, differentially abundant proteins (DAPs) in the digesta of pigs fed the NFD enriched terms and pathways that suggest intestinal inflammation, the activation of innate antimicrobial host defense, an increase in cellular autophagy and epithelial turnover, and reduced synthesis of pancreatic and intestinal secretions. These findings suggest that casein diets may provide a more accurate estimation of BEL because they promote normal gastrointestinal secretions. Overall, proteomic and bioinformatic analyses provided valuable insights into the composition of endogenous proteins in the ileal digesta and their relationship with the functions, processes, and pathways modified by diet composition. Full article

Accurate and efficient access to Mongolian horse body size information is an important component in the modernization of the equine industry. Aiming at the shortcomings of manual measurement methods, such as low efficiency and high risk, this study converts the traditional horse body measure measurement problem into a measurement keypoint localization problem and proposes a top-down automatic Mongolian horse body measure measurement method by integrating the target detection algorithm and keypoint detection algorithm. Firstly, the SimAM parameter-free attention mechanism is added to the YOLOv8n backbone network to constitute the SimAM–YOLOv8n algorithm, which provides the base image for the subsequent accurate keypoint detection; secondly, the coordinate regression-based RTMPose keypoint detection algorithm is used for model training to realize the keypoint localization of the Mongolian horse. Lastly, the cosine annealing method was employed to dynamically adjust the learning rate throughout the entire training process, and subsequently conduct body measurements based on the information of each keypoint. The experimental results show that the average accuracy of the SimAM–YOLOv8n algorithm proposed in this study was 90.1%, and the average accuracy of the RTMPose algorithm was 91.4%. Compared with the manual measurements, the shoulder height, chest depth, body height, body length, croup height, angle of shoulder and angle of croup had mean relative errors (MRE) of 3.86%, 4.72%, 3.98%, 2.74%, 2.89%, 4.59% and 5.28%, respectively. The method proposed in this study can provide technical support to realize accurate and efficient Mongolian horse measurements. Full article

The hypothesis of this study was that there were changes in biomarkers registered by innovative technologies in cows with subclinical acidosis. The aim of this study was to identify changes in the in-line milk fat-to-protein ratio and cow feeding behaviors such as reticulorumen pH, reticulorumen temperature, cow activity, and water intake with subclinical acidosis. From a total of 98 cows, 59 cows were selected to meet the following criteria (2 or more lactations, with 31 days in milk (DIM)). The selected animals were separated into two groups based on general clinical examination and reticulorumen pH: the subclinical acidosis group (SCA, n = 23) and the healthy group (HC, n = 36). During the diagnosis of subclinical acidosis and following the clinical examination of the healthy group using the BROLIS HerdLine system, the daily averages of milk yield (kg/day), milk fat (%), milk protein (%), and the milk fat-to-protein ratio were recorded. Simultaneously, by using Smaxtec technology, reticulorumen parameters and cow activity, including pH, temperature (°C), rumination time (minutes/day), and water intake (hours/day), were registered. Changes in parameters measured using innovative technologies were able to identify cows with subclinical acidosis. Cows with subclinical acidosis had a lower reticulorumen pH by 18.8% (p < 0.0001), a decreased milk yield by 10.49% (p < 0.001), a lower milk fat-to-protein ratio by 11.88% (p < 0.01), and a decreased rumination time by 6.59% (p < 0.01). However, the activity of these cows was higher by 57.19% (p < 0.001) compared to healthy cows. From a practical point of view, we suggest that veterinarians and farmers track parameters such as reticulorumen pH, milk yield, milk fat-to-protein ratio, rumination time, and activity for the identification of subclinical acidosis. Full article

Two randomized complete block design experiments evaluated the influence that varying degrees of ingredient inclusion accuracy in a finishing diet have on growth performance and carcass traits. Treatments included (1) normal inclusion tolerance with a 0.454 kg tolerance for all ingredients (CON) or (2) variable inclusion tolerance where each ingredient was randomly increased or decreased but the targeted as-fed quantity for the daily delivery was met (VAR). In Experiment. 1, black Angus heifers (n = 60; initial shrunk BW = 460 ± 26.2 kg) were used in a 112 d experiment. Ten pens in total (5 pens/treatment, 6 heifers/pen) were used. The targeted diet (DM basis) consisted of high-moisture ear corn (75%), dried distiller’s grains (20%), and a liquid supplement (5%). As-fed inclusion rates for DDGS and LS varied from formulated targets by −20, −15, −10, −5, 0, +5, +10, +15 or +20%. The HMEC inclusion was adjusted so that the targeted as-fed amount of the diet was delivered daily. Treatment did not alter ADG, DMI, G:F, HCW, dressing percentage, rib-eye area, rib fat, USDA marbling score, KPH, yield grade, retail yield, empty body fat, or body weight at 28% estimated EBF, nor liver abscess prevalence or severity (p ≥ 0.15). In Exp. 2, Charolais–Angus cross steers (n = 128; initial shrunk BW = 505 ± 32.1 kg) were used in a 94 d experiment. Steers were assigned to pens (8 pens/treatment; 8 steers/pen) and one of the two management strategies used in Exp. 1 was employed. Ractopamine HCl was fed (300 mg per head daily) during the final 28 d. Diets consisted of (DM basis) dry-rolled corn (63%), dried distiller’s grains plus solubles (15%), liquid supplement (5%), grass hay (7%), and corn silage (10%). Ingredient inclusions were randomized in the same manner as Exp. 1, except LS inclusion was held constant. Corn silage inclusion was adjusted so that the targeted as-fed amount of the diet was delivered each day. Steers from VAR had increased (p = 0.01) DMI, but similar (p = 0.75) ADG resulting in reduced (p ≤ 0.02) G:F and growth-performance-predicted Net Energy for maintenance and gain. Treatment did not influence (p ≥ 0.38) HCW, dressing percentage, rib-eye area, rib fat, KPH, yield grade, retail yield, empty body fat, or body weight at 28% estimated EBF. A tendency for an increased USDA marbling score (p = 0.08) was noted in VAR. Under the conditions of this experiment, randomly altering ingredient proportions can impact growth performance and efficiency measures depending upon the type of finishing diet fed. Full article

Acquiring phenotypic data from livestock constitutes a crucial yet cumbersome phase in the breeding process. Traditionally, obtaining livestock phenotypic data primarily involves manual, on-body measurement methods. This approach not only requires extensive labor but also induces stress on animals, which leads to potential economic losses. Presently, the integration of next-generation Artificial Intelligence (AI), visual processing, intelligent sensing, multimodal fusion processing, and robotic technology is increasingly prevalent in livestock farming. The advantages of these technologies lie in their rapidity and efficiency, coupled with their capability to acquire livestock data in a non-contact manner. Based on this, we provide a comprehensive summary and analysis of the primary advanced technologies employed in the non-contact acquisition of livestock phenotypic data. This review focuses on visual and AI-related techniques, including 3D reconstruction technology, body dimension acquisition techniques, and live animal weight estimation. We introduce the development of livestock 3D reconstruction technology and compare the methods of obtaining 3D point cloud data of livestock through RGB cameras, laser scanning, and 3D cameras. Subsequently, we explore body size calculation methods and compare the advantages and disadvantages of RGB image calculation methods and 3D point cloud body size calculation methods. Furthermore, we also compare and analyze weight estimation methods of linear regression and neural networks. Finally, we discuss the challenges and future trends of non-contact livestock phenotypic data acquisition. Through emerging technologies like next-generation AI and computer vision, the acquisition, analysis, and management of livestock phenotypic data are poised for rapid advancement. Full article

Automatic Milking System (AMS) installations are increasing in the USA despite the higher investment cost than conventional systems. Surveys on AMSs conducted outside the USA focused on small–medium herds, specific regions, or aspects of AMS milking. This study described farmers’ perceptions about the decision-making process of adopting an AMS in the USA’s large dairies (≥7 AMS boxes) regarding changes in technology, housing, management practices, labor, herd performance, and health. After being contacted, 27 of 55 farmers from large AMS herds completed the survey. The main reasons for adopting an AMS were labor costs, cows’ welfare, and herd performance. Most farms constructed new barns, used a free-flow traffic system, and changed their feed management. Increases in water and energy use were perceived by 42% and 62% of farmers, respectively. Farmers estimated decreases in labor costs of over 21%, and AMS employees worked 40–60 h/week. Milk production increases were reported by 58%, with 32% observing higher milk fat and protein content. Easier sick cow detection, better mastitis management, and improvements in pregnancy rates were reported. Thus, farmers transitioning to AMSs perceived altered resource utilization, labor cost savings, and improvements in employee quality of life, animal welfare, and farm management. While 54% of respondents would recommend an AMS to other farms, 38% suggested considering additional aspects prior to adoption. Full article