The automated recognition of individual cows is foundational for implementing intelligent farming. Traditional methods of individual cow recognition from an overhead perspective primarily rely on singular back features and perform poorly for cows with diverse orientation distributions and partial body visibility in the frame. This study proposes an open-set method for individual cow recognition based on spatial feature transformation and metric learning to address these issues. Initially, a spatial transformation deep feature extraction module, ResSTN, which incorporates preprocessing techniques, was designed to effectively address the low recognition rate caused by the diverse orientation distribution of individual cows. Subsequently, by constructing an open-set recognition framework that integrates three attention mechanisms, four loss functions, and four distance metric methods and exploring the impact of each component on recognition performance, this study achieves refined and optimized model configurations. Lastly, introducing moderate cropping and random occlusion strategies during the data-loading phase enhances the model’s ability to recognize partially visible individuals. The method proposed in this study achieves a recognition accuracy of 94.58% in open-set scenarios for individual cows in overhead images, with an average accuracy improvement of 2.98 percentage points for cows with diverse orientation distributions, and also demonstrates an improved recognition performance for partially visible and randomly occluded individual cows. This validates the effectiveness of the proposed method in open-set recognition, showing significant potential for application in precision cattle farming management.

The aim of this study was to investigate the loss of docosahexaenoic acid (DHA) from three supplements (two powders and one oil) after digestion (rumen and gastrointestinal) and their effects on the number and composition of rumen bacteria, using an in vitro approach. The concentration of supplements has a significant impact on the DHA loss rate and algal oil exhibited the highest rate of loss, but bioaccessibility was not significantly different from the other supplements. 16S rRNA sequencing showed that three DHA supplements altered the bacterial composition of in vitro batch cultures inoculated with rumen microorganisms from cows, and caused changes in the relative abundance of important bacterial phyla, families, and genera. DHA supplements altered the abundance of bacterial species, including Prevotella, Ruminobacter, Succiniclassicum, Succinivibrio, Lachnospiraceae, and Muribaculaceae. Importantly, these changes may be associated with the ruminal response in biohydrogenation. Algal oil has the most significant impact on rumen microbiota by reducing the richness and diversity of rumen microbiota, and significantly altering the composition of multiple important microbiota.

In agricultural production, peanut shells, as a by‐product of peanut processing, are often discarded. However, they are rich in fiber, crude protein, carbohydrates, minerals (such as calcium and phosphorus), as well as bioactive substances like polyphenols and flavonoids, thus having potential feeding value. Currently, the application potential of peanut shells in the field of animal nutrition has not been fully explored. The lack of comprehensive and systematic studies on their nutritional composition, digestive and metabolic characteristics, and optimal addition levels in different animal production systems limits the accurate evaluation and scientific application of their feeding value. In addition, different processing methods have significantly different effects on improving the nutritional components of peanut shells, and they contain anti‐nutritional factors such as phytic acid and oxalic acid, whose contents vary greatly with peanut varieties and producing areas, further increasing the complexity of evaluating their feeding value. Although relevant studies have achieved certain results, there are still many issues in the development and utilization of peanut shells that need further in‐depth exploration and optimization. This review will comprehensively evaluate the nutritional value of peanut shells, analyze in detail their conventional nutritional components, bioactive substances, and anti‐nutritional factors, so as to clarify their true value in animal nutrition. Meanwhile, it will conduct in‐depth research on the application effects of peanut shells in different livestock feeding systems. Through these studies, it aims to provide a scientific basis for the reasonable and efficient application of peanut shells in livestock feeding and offer new ideas and methods for solving the current problems of feed resource shortage and environmental issues.

In this study, we investigated the effects of lentinan (LNT) on hematological parameters, immune indices, and metabolite levels in dairy cows. We randomly assigned forty Holstein cows to four treatment groups. The treatments consisted of 0, 5, 10, and 15 g/d of LNT. Compared with the control group, the addition of 10 g/d of LNT decreased the content of ALT and IL-8 but simultaneously increased the content of IL-4 in the cows’ serum. Supplementation with 10 g/d of LNT decreased the levels of lymphocyte, RDW, ALT, AST, TC, IL-2, and IL-8, but, concurrently, in-creased the levels of granulocytes and IL-4 in their serum. In addition, supplementation with 15 g/d of LNT decreased the levels of RDW, TC, IL-2, and IL-8, but, at the same time, increased the levels of IL-4 and IgM in their serum. For the metabolomic analysis, cows fed with 0 and 10 g/d of LNT were selected. The results showed that 10 metabolites, including reduced nicotinamide riboside and trehalose, were upregulated in the 10 g/d group. These differential metabolites were enriched in tyrosine metabolism and trehalose degradation and altered two metabolic pathways of ubiquinone and other terpene quinone biosynthesis, as well as starch and sucrose metabolism. These findings provide evidence that LNT could be used to reduce the risk of inflammation in dairy cows.

Current research on dairy cows primarily focuses on peak lactation, with limited exploration of late lactation. This study investigated the effects of α-amylase supplementation on production performance, blood metabolites, nutrient digestibility, and rumen fermentation in late-lactation Holstein cows. Thirty cows (average milk yield: 37.48 ± 1.63 kg; parity: 2.44 ± 0.70; lactation days: 210.17 ± 2.20) were randomly divided into two groups: the control group (CON) received a basal diet, while the experimental group (AM) was supplemented with 15 g/day α-amylase for 7 weeks (1-week adaptation + 6-week trial). Results showed that α-amylase significantly increased milk yield, energy-corrected milk (ECM), and milk protein yield (p < 0.01) and improved fat-corrected milk (p < 0.05). Milk protein content, total solids, and milk fat yield also tended to rise (p = 0.061, p = 0.067, p = 0.091, respectively). No significant differences were observed in dry matter intake (DMI), feed efficiency, or somatic cell count. Serum amylase concentration increased markedly in the AM group (p < 0.01), while other blood parameters remained unchanged. Starch digestibility improved significantly (p < 0.05), and neutral detergent fiber (NDF) digestibility showed a positive trend (p = 0.063). Rumen propionate concentration rose significantly (p < 0.05), with no major changes in pH, ammonia nitrogen, or acetate-to-propionate ratio. In conclusion, α-amylase supplementation in late lactation enhances nutrient digestibility, modulates rumen fermentation, and improves production performance, offering metabolic regulation potential for extending high productivity in late-stage lactation.

The aim of this study was to evaluate the effects of lentinan (LNT) on the quality of colostrum produced by perinatal dairy cows and the health status of their newborn calves. A total of 40 expectant Holstein cows, matched for parity and expected date of delivery, were selected and randomly divided into four groups: a control group fed a total mixed diet (TMR); a low LNT group (10 g/d, LLNT); a medium LNT group (20 g/d, MLNT); and a high LNT group (40 g/d, HLNT). The study commenced 21 days prior to parturition and continued for three weeks. Colostrum was collected from the cows immediately after delivery and subsequently fed to the newborn calves. The results indicated that colostrum milk protein production and IgG production in the MLNT group were significantly increased (p < 0.05). Following colostrum gavage, serum SOD and IgG in both the MLNT and HLNT groups showed significant increases (p < 0.05), while MDA and IL-1β levels were significantly decreased (p < 0.05). Moreover, calves in the MLNT and HLNT groups experienced lower incidences of diarrhea, pneumonia, and overall morbidity compared to those in the control group. In conclusion, LNT enhanced the quality of colostrum in perinatal cows and contributed to the health of newborn calves through colostrum. This study offers new research avenues for improving the health of newborn calves and provides a theoretical foundation for the development of LNT as a novel feed additive.