Disease severity grading is the primary decision-making basis for the amount of pesticide usage in vegetable disease prevention and control. Based on deep learning, this paper proposed an integrated framework, which automatically segments the target leaf and disease spots in cucumber images using different semantic segmentation networks and then calculates the area of disease spots and the target leaf for disease severity grading. Two independent datasets of leaves and lesions were constructed, which served as the training set for the first-stage diseased leaf segmentation and the second-stage lesion segmentation models. The leaf dataset contains 1140 images, and the lesion data set contains 405 images. The proposed TRNet was composed of a convolutional network and a Transformer network and achieved an accuracy of 93.94% by fusing local features and global features for leaf segmentation. In the second stage, U-Net (Resnet50 as the feature network) was used for lesion segmentation, and a Dice coefficient of 68.14% was obtained. After integrating TRNet and U-Net, a Dice coefficient of 68.83% was obtained. Overall, the two-stage segmentation network achieved an average accuracy of 94.49% and 94.43% in the severity grading of cucumber downy mildew and cucumber anthracnose, respectively. Compared with DUNet and BLSNet, the average accuracy of TUNet in cucumber downy mildew and cucumber anthracnose severity classification increased by 4.71% and 8.08%, respectively. The proposed model showed a strong capability in segmenting cucumber leaves and disease spots at the pixel level, providing a feasible method for evaluating the severity of cucumber downy mildew and anthracnose.

The plant disease recognition model based on deep learning has shown good performance potential. However, high complexity and nonlinearity lead to the low transparency and poor interpretability of such models. These limitations greatly limit the deployment and application of such models in field scenarios. To solve the above problems, we propose a dense caption generative model, Veg DenseCap. This model takes vegetable leaf images as input and uses object detection technology to locate abnormal parts of the leaf and identify the disease results. More importantly, it can describe the disease features it sees in natural language, and users can judge whether the relevant features are semantically consistent with human cognition based on these descriptions. First of all, a dataset containing Chinese feature description statements for images of 10 leaf diseases involving two vegetables (cucumber and tomato) was established. Secondly, Faster R-CNN was used as a disease detector to extract visual features of diseases, and LSTM was used as a language generator to generate description statements for disease features. Finally, the Convolutional Block Attention Module (CBAM) and the Focal Loss function were employed to overcome the imbalance between positive and negative samples and the weak performance of Faster R-CNN in obtaining key features. According to the test results, the Intersection-over-Union (IoU) and Meteor joint evaluation index of Veg-DenseCap achieved a mean Average Precision (mAP) of 88.0% on the dense captioning dataset of vegetable leaf disease images, which is 9.1% higher than that of the classical FCLN model. The automatically generated description statements are characterized by advantages of accurate feature description, correct grammar, and high diversity.

Airborne bacterial aerosols are a significant yet understudied component of intensive poultry farming, particularly in cold climates. This study characterized the concentration, size distribution, and community composition of airborne bacteria in closed-cage broiler houses during winter in Hebei Province, China. Air sampling was conducted at three growth stages (7, 21, and 35 days) and analyzed using culture-based methods and 16S rRNA sequencing. Culturable bacterial concentrations increased significantly with broiler age, from 1.1 × 10³ to 1.6 × 10⁴ CFU/m³. The particle size distribution shifted from a predominance of large particles (≥4.7 µm) at day 7 to a dominance of small, inhalable particles (<4.7 µm) thereafter. Sequencing revealed increasing bacterial richness and diversity with age, alongside significant community structural shifts. Predominant genera included Stenotrophomonas, Lactobacillus, and Ruminococcus. Notably, potential zoonotic pathogens (Shigella and Acinetobacter) were detected in later stages. This study provides critical insights into winter bioaerosol dynamics, highlighting implications for animal welfare, occupational health, and public health.

There are some obstacles for the disabled and the elder in the urban mass transit system, such as steps, slits. Based on principles of barrier-free design, taking the elder, disabled, expectant/nursing mothers and those who carry baggage as specifically users, this paper studied their behavior and the obstacles in urban mass transit system and made the intensive study of the urban mass transit vehicle and waiting space from their physiological demand and psychological demand. Put forward plans of waiting space, wheelchair place, priority seats in urban mass transit system.