Recently, the growing demand for meat has increased interest in precision livestock farming (PLF), wherein monitoring livestock behavior is crucial for assessing animal health. We introduce a novel cattle behavior detection model that leverages data from 2D RGB cameras. It primarily employs you only look once (YOLO)v7-E6E, which is a real-time object detection framework renowned for its efficiency across various applications. Notably, the proposed model enhances network performance without incurring additional inference costs. We primarily focused on performance enhancement and evaluation of the model by integrating AutoAugment and GridMask to augment the original dataset. AutoAugment, a reinforcement learning algorithm, was employed to determine the most effective data augmentation policy. Concurrently, we applied GridMask, a novel data augmentation technique that systematically eliminates square regions in a grid pattern to improve model robustness. Our results revealed that when trained on the original dataset, the model achieved a mean average precision (mAP) of 88.2%, which increased by 2.9% after applying AutoAugment. The performance was further improved by combining AutoAugment and GridMask, resulting in a notable 4.8% increase in the mAP, thereby achieving a final mAP of 93.0%. This demonstrates the efficacy of these augmentation strategies in improving cattle behavior detection for PLF.

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.

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.

Accurate pregnancy diagnosis is important for reproductive management in pig farming. This study evaluated a computer-aided diagnosis workflow using portable low-frequency ultrasound videos from 1895 sows at two sites. Xception frame predictions were aggregated into video-level decisions. Original, Preprocessing (wavelet denoising and contrast-limited adaptive histogram equalization), Mixup, and their combination (Combined) were compared across ten repeated sow-level splits. Combined achieved mean accuracies of 84.5% and 85.3% in Datasets A and B, respectively, with pregnant-sow videos restricted to days 18–25 post-insemination. Compared with Original, mean specificity increased by 1.3 and 2.4 percentage points and Youden’s index by 1.7 and 2.3 points, while mean sensitivity was numerically similar. Paired 95% confidence intervals for specificity and Youden’s index differences excluded zero only in Dataset B, without adjustment for multiple comparisons. Paired comparisons of the area under the curve (AUC) did not establish improved discrimination. Mixup yielded the highest mean specificity and AUC, whereas Combined yielded higher mean sensitivity than Mixup. This trade-off varied across partition subsets. Cross-site and leave-one-session-out evaluations showed performance variability across acquisition settings, with no consistently best condition. These comparisons identify configuration-dependent trade-offs requiring further evaluation for diagnostic support.