To address the challenge of detecting small defects in Printed Circuit Boards (PCBs), a YOLO-HDEW model based on the enhanced YOLOv8 architecture is proposed. A high-resolution detection layer is introduced at the P2 feature level to improve sensitivity to small targets. Depthwise Separable Convolution (DSConv) is used for downsampling, reducing parameter complexity. An Edge-enhanced Multi-scale Parallel Attention mechanism (EMP-Attention) is integrated to capture multi-scale and edge features. The EMP mechanism is incorporated into the C2f module to form the C2f-EMP module, and dynamic non-monotonic Wise-IoU (W-IoU) loss is employed to enhance bounding box regression. The model is evaluated on the PKU-Market-PCB, DeepPCB, and NEU-DET datasets, with experimental results showing that YOLO-HDEW achieves 98.1% accuracy, 91.6% recall, 90.3% mAP@0.5, and 61.7% mAP@0.5:0.95, surpassing YOLOv8 by 1.5%, 2.3%, 1.2%, and 1.9%, respectively. Additionally, the model demonstrates strong generalization performance on the DeePCB and NEU-DET datasets. These results indicate that YOLO-HDEW significantly improves detection accuracy while maintaining a manageable model size, offering an effective solution for PCB defect detection.

With the development of wireless communication technology, the number of devices accessing the communication network is increasing. This paper addresses critical issues such as low spectrum resource utilization and the energy constraints of devices. The investigation focuses on the system performance of the shared relay Cognitive Radio Non-Orthogonal Multiple Access (CR-NOMA) network based on Simultaneous Wireless Information and Power Transfer (SWIPT) network model. Unlike the existing CR-NOMA model in which the secondary network user do not participate in the transmission of information from the primary network, we consider the secondary network near user as shared relay. The shared relay utilizes SWIPT technology to harvest energy using a nonlinear energy harvesting model. Additionally, the shared relay assists in transmitting information from the primary network base station to primary user, as well as from the secondary network base station to far user of the secondary network. Subsequently, we conduct a series of simulations to analyze the effects of Signal-to-Noise Ratio (SNR), power distribution factor, interference threshold, and time-switching (TS) factor on system performance. Furthermore, we compare and analyze the performance of our proposed network model against CR-NOMA network across three dimensions: outage probability, throughput, and energy efficiency. Our results demonstrate that the proposed network model exhibits superior outage performance and enhances user throughput compared to the CR-NOMA network. Additionally, it demonstrates improved energy efficiency compared to the shared relay CR-NOMA network, leading to an overall improvement in network performance.

The increasing demands for high-precision semantic segmentation in applications such as autonomous driving, unmanned aerial vehicles, and robotics has made improving segmentation accuracy a major research focus. In this paper, we propose MPNet, (multi-scale progressive network) a novel semantic segmentation model based on the DeepLabV3+ architecture. First, a lightweight MobileNetV2 was employed as the backbone network, and a new multi-scale feature fusion structure was constructed by integrating the backbone with the centralized feature pyramid network (CFPNet). Then, based on the ASPP module, a progressive dilated atrous spatial pyramid pooling (PDASPP) module was designed to further enhance feature extraction. Extensive experiments were conducted on the Cityscapes and PASCAL VOC 2012 Augmented. The experimental results show that MPNet achieved 75.23% mIoU and 83.54% mPA on the Cityscapes dataset, outperforming DeepLabV3+ by 3.01% and 3.31%, respectively. On the PASCAL VOC 2012 Augmented dataset, MPNet achieved 72.70% mIoU and 83.57% mPA, with improvements of 1.59% and 1.30% over DeepLabV3+, respectively. These results demonstrate that MPNet significantly improves segmentation accuracy while maintaining model complexity under control, providing an effective solution for semantic segmentation in road scene understanding.