In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds...In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.展开更多
The neuroinflammatory response mediated by microglial activation plays an important role in the secondary nerve injury of traumatic brain injury.The post-transcriptional modification of N^(6)-methyladenosine is ubiqui...The neuroinflammatory response mediated by microglial activation plays an important role in the secondary nerve injury of traumatic brain injury.The post-transcriptional modification of N^(6)-methyladenosine is ubiquitous in the immune response of the central nervous system.The fat mass and obesity-related protein catalyzes the demethylation of N^(6)-methyladenosine modifications on mRNA and is widely expressed in various tissues,participating in the regulation of multiple diseases’biological processes.However,the role of fat mass and obesity in microglial activation and the subsequent neuroinflammatory response after traumatic brain injury is unclear.In this study,we found that the expression of fat mass and obesity was significantly down-regulated in both lipopolysaccharide-treated BV2 cells and a traumatic brain injury mouse model.After fat mass and obesity interference,BV2 cells exhibited a pro-inflammatory phenotype as shown by the increased proportion of CD11b^(+)/CD86^(+)cells and the secretion of pro-inflammatory cytokines.Fat mass and obesity-mediated N^(6)-methyladenosine demethylation accelerated the degradation of ADAM17 mRNA,while silencing of fat mass and obesity enhanced the stability of ADAM17 mRNA.Therefore,down-regulation of fat mass and obesity expression leads to the abnormally high expression of ADAM17 in microglia.These results indicate that the activation of microglia and neuroinflammatory response regulated by fat mass and obesity-related N^(6)-methyladenosine modification plays an important role in the pro-inflammatory process of secondary injury following traumatic brain injury.展开更多
基金funded by the Joint Funds of the National Natural Science Foundation of China(U2341223)the Beijing Municipal Natural Science Foundation(No.4232067).
文摘In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.
基金supported by grants from the Major Projects of Health Science Research Foundation for Middle-Aged and Young Scientist of Fujian Province,China,No.2022ZQNZD01010010the National Natural Science Foundation of China,No.82371390Fujian Province Scientific Foundation,No.2023J01725(all to XC).
文摘The neuroinflammatory response mediated by microglial activation plays an important role in the secondary nerve injury of traumatic brain injury.The post-transcriptional modification of N^(6)-methyladenosine is ubiquitous in the immune response of the central nervous system.The fat mass and obesity-related protein catalyzes the demethylation of N^(6)-methyladenosine modifications on mRNA and is widely expressed in various tissues,participating in the regulation of multiple diseases’biological processes.However,the role of fat mass and obesity in microglial activation and the subsequent neuroinflammatory response after traumatic brain injury is unclear.In this study,we found that the expression of fat mass and obesity was significantly down-regulated in both lipopolysaccharide-treated BV2 cells and a traumatic brain injury mouse model.After fat mass and obesity interference,BV2 cells exhibited a pro-inflammatory phenotype as shown by the increased proportion of CD11b^(+)/CD86^(+)cells and the secretion of pro-inflammatory cytokines.Fat mass and obesity-mediated N^(6)-methyladenosine demethylation accelerated the degradation of ADAM17 mRNA,while silencing of fat mass and obesity enhanced the stability of ADAM17 mRNA.Therefore,down-regulation of fat mass and obesity expression leads to the abnormally high expression of ADAM17 in microglia.These results indicate that the activation of microglia and neuroinflammatory response regulated by fat mass and obesity-related N^(6)-methyladenosine modification plays an important role in the pro-inflammatory process of secondary injury following traumatic brain injury.
