Aiming to address the issue of low efficiency and a high false-detection rate in artificial defect detection in nitrile medical gloves, CCA-YOLO was proposed on the basis of YOLOv5 to realize the detection of tear and scratch defects. CCA-YOLO added a small-target detection layer to the YOLOv5 network backbone and further proposed an innovative channel coordinate attention mechanism. According to the different characteristics of tears and scratches, focal and efficient IoU loss and α-IoU loss functions were introduced to further improve the positioning accuracy. The data enhancement method was used to generate a dataset of nitrile gloves, which was divided into datasets for horizontal angular tear detection, vertical angular tear detection, and scratch detection. The problem of class imbalance with few defect samples was solved. Our experiments show that CCA-YOLO can effectively identify tear and scratch defects in nitrile medical gloves in the self-made datasets. Compared with YOLOv5, the mean average precision (mAP) of the three models for horizontal angular tear detection, vertical angular tear detection, and scratch detection can reach 99.3%, 99.8%, and 99.6%, showing increments of 4.2%, 5.3%, and 12.4%, respectively, thereby meeting the performance requirements of glove defect detection.

This paper considers the Modified Autonomous Van der Pol–Duffing equation subjected to dynamic state feedback, which can well characterize the dynamic behaviors of the nonlinear dynamical systems. Both the issues of local stability switches and the Hopf bifurcation versus time delay are investigated. Associating with the $\tau$ decomposition strategy and the center manifold theory, the delay stable intervals and the direction and stability of the Hopf bifurcation are all determined. Specifically, the computation of purely imaginary roots (symmetry to the real axis), the positive real root formula for cubic equation and the sophisticated bilinear form of adjoint operators are proposed, which make the calculations mentioned in our discussion unified and simple. Finally, the typical numerical examples are shown to illustrate the correctness and effectiveness of the practical technique.

The integration of unmanned aerial vehicle (UAV) networks with intelligent reflecting surface (IRS) technology offers a promising solution to enhance wireless communication by dynamically altering signal propagation. This study addresses the challenge of maximizing system energy efficiency (EE) in IRS-assisted UAV networks. The primary objective is to optimize power allocation and IRS reflection design to achieve this goal. To tackle the optimization problem, we employ a block coordinate descent (BCD) method, decomposing it into three subproblems: phase shift optimization, power allocation, and trajectory planning. These subproblems are iteratively solved using an improved particle swarm optimization (PSO) algorithm. Simulation results demonstrate that the proposed PSO algorithm effectively plans high-quality UAV trajectories in complex environments, significantly enhancing EE. The findings suggest that the IRS-assisted UAV model outperforms traditional UAV models, offering substantial improvements in wireless communication quality and EE.

Medical image segmentation acts as a foundational element of medical image analysis. Yet its accuracy is frequently limited by the scale fluctuations of anatomical targets and the intricate contextual traits inherent in medical images—including vaguely defined structural boundaries and irregular shape distributions. To tackle these constraints, we design a multi-scale feature attention network (MFA-Net), customized specifically for thyroid nodule, skin lesion, and breast lesion segmentation tasks. This network framework integrates three core components: a Bidirectional Feature Pyramid Network (Bi-FPN), a Slim-neck structure, and the Convolutional Block Attention Module (CBAM). CBAM steers the model to prioritize boundary regions while filtering out irrelevant information, which in turn enhances segmentation precision. Bi-FPN facilitates more robust fusion of multi-scale features via iterative integration of top-down and bottom-up feature maps, supported by lateral and vertical connection pathways. The Slim-neck design is constructed to simplify the network’s architecture while effectively merging multi-scale representations of both target and background areas, thus enhancing the model’s overall performance. Validation across four public datasets covering thyroid ultrasound (TNUI-2021, TN-SCUI 2020), dermoscopy (ISIC 2016), and breast ultrasound (BUSI) shows that our method outperforms state-of-the-art segmentation approaches, achieving Dice similarity coefficients of 0.955, 0.971, 0.976, and 0.846, respectively. Additionally, the model maintains a compact parameter count of just 3.05 million and delivers an extremely fast inference latency of 1.9 milliseconds—metrics that significantly outperform those of current leading segmentation techniques. In summary, the proposed framework demonstrates strong performance in thyroid, skin, and breast lesion segmentation, delivering an optimal trade-off between high accuracy and computational efficiency.

Strawberry cultivation faces significant challenges from pests and diseases, which are difficult to detect due to complex natural backgrounds and the high visual similarity between targets and their surroundings. This study proposes an advanced and lightweight detection algorithm, YOLO10-SC, based on the YOLOv10 model, to address these challenges. The algorithm integrates the convolutional block attention module (CBAM) to enhance feature representation by focusing on critical disease-related information while suppressing irrelevant data. Additionally, the Spatial and Channel Reconstruction Convolution (SCConv) module is incorporated into the C2f module to improve the model’s ability to distinguish subtle differences among various pest and disease types. The introduction of DySample, an ultra-lightweight dynamic upsampler, further enhances feature boundary smoothness and detail preservation, ensuring efficient upsampling with minimal computational resources. Experimental results demonstrate that YOLO10-SC outperforms the original YOLOv10 and other mainstream algorithms in precision, recall, mAP50, F1 score, and FPS while reducing model parameters, GFLOPs, and size. These improvements significantly enhance detection accuracy and efficiency, making the model well-suited for real-time applications in natural agricultural environments. The proposed algorithm offers a robust solution for strawberry pest and disease detection, contributing to the advancement of smart agriculture.