Accurate identification of sheep is important for achieving precise animal management and welfare farming in large farms. In this study, a sheep face detection method based on YOLOv3 model pruning is proposed, abbreviated as YOLOv3-P in the text. The method is used to identify sheep in pastures, reduce stress and achieve welfare farming. Specifically, in this study, we chose to collect Sunit sheep face images from a certain pasture in Xilin Gol League Sunit Right Banner, Inner Mongolia, and used YOLOv3, YOLOv4, Faster R-CNN, SSD and other classical target recognition algorithms to train and compare the recognition results, respectively. Ultimately, the choice was made to optimize YOLOv3. The mAP was increased from 95.3% to 96.4% by clustering the anchor frames in YOLOv3 using the sheep face dataset. The mAP of the compressed model was also increased from 96.4% to 97.2%. The model size was also reduced to 1/4 times the size of the original model. In addition, we restructured the original dataset and performed a 10-fold cross-validation experiment with a value of 96.84% for mAP. The results show that clustering the anchor boxes and compressing the model using this dataset is an effective method for identifying sheep. The method is characterized by low memory requirement, high-recognition accuracy and fast recognition speed, which can accurately identify sheep and has important applications in precision animal management and welfare farming.

Background: Lung radiation injury is a critical complication of radiotherapy (RT) for thoracic esophageal carcinoma (EC). Therefore, the goal of this study was to investigate the feasibility and dosimetric effects of reducing the lung tissue irradiation dose during RT for thoracic EC by applying volumetric modulated arc radiotherapy (VMAT) combined with active breathing control (ABC) for moderate deep inspiration breath-hold (mDIBH). Methods: Fifteen patients with thoracic EC were randomly selected to undergo two series of computed tomography (CT) simulation scans with ABC used to achieve mDIBH (representing 80% of peak DIBH value) versus free breathing (FB). Gross tumor volumes were contoured on different CT images, and planning target volumes (PTVs) were obtained using different margins. For PTV_-FB, intensity-modulated radiotherapy (IMRT) was designed with seven fields, and VMAT included two whole arcs. For PTV_-DIBH, VMAT with three 135° arcs was applied, and the corresponding plans were named: IMRT_-FB, VMAT_-FB, and VMAT_-DIBH, respectively. Dosimetric differences between the different plans were compared. Results: The heart volumes decreased by 19.85%, while total lung volume increased by 52.54% in mDIBH, compared to FB (p < 0.05). The mean conformality index values and homogeneity index values for VMAT_-DIBH (0.86, 1.07) were slightly worse than those for IMRT_-FB (0.90, 1.05) and VMAT_-FB (0.90, 1.06) (p > 0.05). Furthermore, compared to IMRT_-FB and VMAT_-FB, VMAT_-DIBH reduced the mean total lung dose by 18.64% and 17.84%, respectively (p < 0.05); moreover, the V₅, V₁₀, V₂₀, and V₃₀ values for IMRT_-FB and VMAT_-FB were reduced by 10.84% and 10.65% (p > 0.05), 12.5% and 20% (p < 0.05), 30.77% and 33.33% (p < 0.05), and 50.33% and 49.15% (p < 0.05), respectively. However, the heart dose-volume indices were similar between VMAT_-DIBH and VMAT_-FB which were lower than IMRT_-FB without being statistically significant (p > 0.05). The monitor units and treatment time of VMAT_-DIBH were also the lowest (p < 0.05). Conclusions: VMAT combined with ABC to achieve mDIBH is a feasible approach for RT of thoracic EC. Furthermore, this method has the potential to effectively reduce lung dose in a shorter treatment time and with better targeting accuracy.

In the trend of large-scale and intensive livestock farming, it has become difficult to monitor the physical health and breeding performance of animals accurately, quickly, and comprehensively in the traditional feeding management mode, and with the development of computer technology, machine vision has been widely used as a non-contact sensor technology. In this work, it reviews the current automatic behavior detection methods. The chapters are summarized with machine vision technology as the core and classical behavior detection techniques are added for comparison. It is classified into three aspects: breeding performance, disease and health, and social behavior, and then discusses in detail daily behaviors (lying, drinking, feeding, lameness, etc.) and complex behaviors (mounting, aggression, tail biting, etc.).

This study aimed to compare fixed‐field, intensity‐modulated radiotherapy (f‐IMRT) with intensity‐modulated arc therapy (IMAT) treatment plans in dosimetry and practical application for cervical esophageal carcinoma. For ten cervical esophageal carcinoma cases, f‐IMRT plan (seven fixed‐fields) and two IMAT plans, namely RA (coplanar 360° arcs) and RAx (coplanar 360° arcs without sectors from 80° to 110°, and 250° to 280°), were generated. DVHs were adopted for the statistics of above parameters, as well as conformal index (CI), homogeneity index (HI), dose‐volumetric parameters of normal tissues, total accelerator output MUs and total treatment time. There were differences between RAx and f‐IMRT, as well as RA in PTV parameters such as HI, and , but not in CI. RAx reduced lung from ( in f‐IMRT and ( in RA to ( in RAx . However, lung and MLD increased in RAx. There was no difference in the mean heart dose in three plans. Total MU was reduced from in f‐IMRT to in RA and in RAx . Compared with f‐IMRT, IMAT reduced low dose volumes of lung and total MU on the basis of meeting clinical requirements.PACS numbers: 87.55.D, 87.55.dk, 87.55.ne

Rice diseases can adversely affect both the yield and quality of rice crops, leading to the increased use of pesticides and environmental pollution. Accurate detection of rice diseases in natural environments is crucial for both operational efficiency and quality assurance. Deep learning-based disease identification technologies have shown promise in automatically discerning disease types. However, effectively extracting early disease features in natural environments remains a challenging problem. To address this issue, this study proposes the YOLO-CRD method. This research selected images of common rice diseases, primarily bakanae disease, bacterial brown spot, leaf rice fever, and dry tip nematode disease, from Tianjin Xiaozhan. The proposed YOLO-CRD model enhanced the YOLOv5s network architecture with a Convolutional Channel Attention Module, Spatial Pyramid Pooling Cross-Stage Partial Channel module, and Ghost module. The former module improves attention across image channels and spatial dimensions, the middle module enhances model generalization, and the latter module reduces model size. To validate the feasibility and robustness of this method, the detection model achieved the following metrics on the test set: mean average precision of 90.2%, accuracy of 90.4%, F1-score of 88.0, and GFLOPS of 18.4. for the specific diseases, the mean average precision scores were 85.8% for bakanae disease, 93.5% for bacterial brown spot, 94% for leaf rice fever, and 87.4% for dry tip nematode disease. Case studies and comparative analyses verified the effectiveness and superiority of the proposed method. These research findings can be applied to rice disease detection, laying the groundwork for the development of automated rice disease detection equipment.

To improve the classification of pig vocalization using vocal signals and improve recognition accuracy, a pig vocalization classification method based on multi-feature fusion is proposed in this study. With the typical vocalization of pigs in large-scale breeding houses as the research object, short-time energy, frequency centroid, formant frequency and first-order difference, and Mel frequency cepstral coefficient and first-order difference were extracted as the fusion features. These fusion features were improved using principal component analysis. A pig vocalization classification model with a BP neural network optimized based on the genetic algorithm was constructed. The results showed that using the improved features to recognize pig grunting, squealing, and coughing, the average recognition accuracy was 93.2%; the recognition precisions were 87.9%, 98.1%, and 92.7%, respectively, with an average of 92.9%; and the recognition recalls were 92.0%, 99.1%, and 87.4%, respectively, with an average of 92.8%, which indicated that the proposed pig vocalization classification method had good recognition precision and recall, and could provide a reference for pig vocalization information feedback and automatic recognition.