Effective livestock management has become essential owing to an aging workforce and the growth of large-scale farming operations in the agricultural industry. Conventional monitoring methods, primarily reliant on manual observation, are increasingly reaching their limits, necessitating the development of innovative automated solutions. This study developed a system, termed mixed-ELAN, for real-time sow and piglet behavior detection using an extended ELAN architecture with diverse kernel sizes. The standard convolution operations within the ELAN framework were replaced with MixConv using diverse kernel sizes to enhance feature learning capabilities. To ensure high reliability, a performance evaluation of all techniques was conducted using a k-fold cross-validation (k = 3). The proposed architecture was applied to YOLOv7 and YOLOv9, yielding improvements of 1.5% and 2%, with mean average precision scores of 0.805 and 0.796, respectively, compared with the original models. Both models demonstrated significant performance improvements in detecting behaviors critical for piglet growth and survival, such as crushing and lying down, highlighting the effectiveness of the proposed architecture. These advances highlight the potential of AI and computer vision in agriculture, as well as the system’s benefits for improving animal welfare and farm management efficiency. The proposed architecture enhances the real-time monitoring and understanding of livestock behavior, establishing improved benchmarks for smart farming technologies and enabling further innovation in livestock management.

We aimed to investigate the impact of heat stress (HS) on the expression of tight junction (TJ) proteins and the interaction between genes affecting intestinal barrier function using transcriptomics in the porcine jejunum. Twenty-four barrows (crossbred Yorkshire × Landrace × Duroc; average initial body weight, 56.71 ± 1.74 kg) were placed in different temperatures (normal temperature [NT]; HS) and reared for 56 days. At the end of the experiment, jejunal samples were collected from three pigs per treatment for transcriptome and reverse-transcription quantitative polymerase chain reaction (RT-qPCR) analyses. We identified 43 differentially expressed genes, involving five Kyoto Encyclopedia of Genes and Genomes pathways, eight molecular functions, seven cellular components (CCs), and nine biological processes, using gene ontology enrichment analysis. Genes associated with the actin cytoskeleton, filament-binding pathways, and TJ proteins were selected and analyzed by RT-qPCR. Significant differences in relative mRNA expression showed that downregulated genes in the HS group included ZO1, CLDN1, OCLN, PCK1, and PCK2, whereas ACTG2, DES, MYL9, MYLK, TPM1, TPM2, CNN1, PDLIM3, and PCP4 were upregulated by HS (p < 0.05). These findings indicate that HS in growing-finishing pigs induces depression in gut integrity, which may be related to genes involved in the actin cytoskeleton and filaments of CC.

A total of sixty crossbred ([Landrace × Yorkshire] × Duroc) pigs with an initial body weight of 46.34 ± 0.13 kg were randomly assigned to four treatments under thermoneutral (TN, 22 °C) or heat-stress (HS, 31 °C) conditions for 54 d trial (Phase 1: 0–26 d; Phase 2: 27–54 d): a control diet (16% CP in phase 1, 14% CP in phase 2) under TN (PC), a control diet under HS (NC), a low crude protein (LCP) diet (14% CP in phase 1, 12% CP in phase 2) under HS (LCP) and an LCP diet with increased crystalline AA (an increase in 5% in Lys, Met, Thr and Trp based on calculated SID AA) (LCP5) under HS. Experimental treatments consisted of five replicate pens, with three pigs per pen. The results showed that HS reduced (p < 0.05) growth performance and nutrient digestibility compared to TN. However, LCP5 improved (p < 0.05) growth performance and nutrient digestibility compared to other HS groups. Heat stress adversely affected (p < 0.05) intestinal morphology, gut integrity and serum oxidative markers, but these effects were alleviated (p < 0.05) by LCP5 supplementation. Notably, LCP5 improved (p < 0.05) the production of butyric acids among short-chain fatty acid production and decreased (p < 0.05) proteobacteria and Spirochaetota in phylum in feces. These findings highlight the potential of LCP diets supplemented with crystalline AA as an effective nutritional strategy to mitigate the negative effects of HS on pigs, enhancing their performance, gut health and overall welfare in high-temperature environments.

Journal of Animal Science and Technology (JAST) is a peer-reviewed, open access journal publishing original research, review articles and notes in all fields of animal science. Topics covered by the journal include: genetics and breeding, physiology, nutrition of monogastric animals, nutrition of ruminants, animal products (milk, meat, eggs and their by-products) and their processing, grasslands and roughages, livestock environment, animal biotechnology, animal behavior and welfare.

The escalating demand for pork highlights the importance of swift and accurate pregnancy diagnosis in sows, a crucial factor in farm profitability. The prevalent use of low-frequency ultrasound devices in this context poses a challenge owing to the suboptimal resolution of the resultant images. This study introduces an innovative approach for sow pregnancy diagnosis using deep learning techniques to analyze low-frequency ultrasound images. Our methodology encompasses the development and comparative analysis of three distinct classification models: ViT-H, ConvNeXt-xlarge, and Xception. These models aim to improve diagnostic accuracy. AutoAugment was used to augment the data to expand the training dataset, thereby enhancing the robustness of the models under varied conditions. Results indicate a notable improvement in diagnostic performance, with the implementation of AutoAugment leading to significant achievements in the models, reflected by AUC values of 0.865, 0.856, and 0.866. These outcomes affirm the viability of deep learning in the effective management of sow pregnancies in livestock farms and suggest potential applications in broader animal husbandry contexts. This research marks a significant contribution to the evolution of agricultural technologies, presenting a scalable and efficacious solution for sow pregnancy diagnosis.

This study investigated the correlation between piglet performance and sow body weight change (BWC) during two gestational periods: 35–70, 70–105, and 35–105 days. A cohort of 70 sows was evaluated for BWC, backfat thickness change (BFC), caliper score change (CALC), feed intake, and weaning-to-estrus interval (WEI). The collected data were then analyzed according to the two specified periods. Our findings highlighted that piglet birth weight, weaning weight, and average daily weight gain (ADG) correlated with sow body characteristics, including BFC and CALC. The strongest correlation was observed with BWC. Piglet mortality was intimately associated with BFC. Piglet birth weight, weaning weight, and ADG showed a positive correlation with sow BWC, particularly during the 35–70 day period. Furthermore, sows displaying a higher BWC during the 70–105 day period, and also exhibiting a higher BW gain from 35-70 days, registered greater piglet weight gains and higher weaning weights. These trends became more apparent as the sow’s BWC increased during the 70–105 day period. Piglet mortality increased when the sow exhibited a lower BWC during both the 35–70 and 70–105 day periods. No significant observations were found concerning the number of stillborn piglets, live-born piglets, or weaned piglets, and no interaction effects were detected between these periods. In conclusion, our findings underscore the significance of sow BWC during the early stages of gestation (d 35–70) for enhancing piglet performance from birth to weaning.