Search Results (80)

Structural timber is an important building material, but surface defects such as cracks and knots seriously affect its load-bearing capacity, dimensional stability, and long-term durability, posing a significant risk to structural safety. Conventional inspection methods are unable to address the issues of multi-scale defect characterization, inter-class confusion, and morphological diversity, thus limiting reliable construction quality assurance. To overcome these challenges, this study proposes WDNET-YOLO: an enhanced deep learning model based on YOLOv8n for high-precision defect detection in structural wood. First, the RepVGG reparameterized backbone utilizes multi-branch training to capture critical defect features (e.g., distributed cracks and dense clusters of knots) across scales. Second, the ECA attention mechanism dynamically suppresses complex wood grain interference and enhances the discriminative feature representation between high-risk defect classes (e.g., cracks vs. knots). Finally, CARAFE up-sampling with adaptive contextual reorganization improves the sensitivity to morphologically variable defects (e.g., fine cracks and resin irregularities). The analysis results show that the mAP50 and mAP50-95 of WDNET-YOLO are improved by 3.7% and 3.5%, respectively, compared to YOLOv8n, while the parameters are increased by only 4.4%. The model provides a powerful solution for automated structural timber inspection, which directly improves building safety and reliability by preventing failures caused by defects, optimizing material utilization, and supporting compliance with building quality standards. Full article

Pollen allergy has emerged as a critical global health challenge. Proactive pollen monitoring is imperative for safeguarding susceptible populations through timely preventive interventions. Current manual detection methods suffer from inherent limitations: notably, suboptimal accuracy and delayed response times, which hinder effective allergy management. Therefore, we present an automated pollen concentration detection system integrated with a novel GGD-YOLOv8n model (Ghost-generalized-FPN-DualConv-YOLOv8), which was specifically designed for allergenic pollen species identification. The methodological advancements comprise three components: (1) combining the C2f convolution in Backbone with the G-Ghost module, this module generates features through half-convolution operations and half-symmetric linear operations, enhancing the extraction and expression capabilities of detailed feature information. (2) The conventional neck network is replaced with a GFPN architecture, facilitating cross-scale feature aggregation and refinement. (3) Standard convolutional layers are substituted with DualConv, thereby reducing model complexity by 22.6% (parameters) and 22% GFLOPs (computational load) while maintaining competitive detection accuracy. This systematic optimization enables efficient deployment on edge computing platforms with stringent resource constraints. The experimental validation substantiates that the proposed methodology outperforms the baseline YOLOv8n model, attaining a 5.4% increase in classification accuracy accompanied by a 4.7% enhancement in mAP@50 metrics. When implemented on Jetson Nano embedded platforms, the system demonstrates computational efficiency with an inference latency of 364.9 ms per image frame, equating to a 22.5% reduction in processing time compared to conventional implementations. The empirical results conclusively validate the dual superiority in detecting precision and operational efficacy when executing microscopic pollen image analysis on resource-constrained edge computing devices; they establish a feasible algorithm framework for automated pollen concentration monitoring systems. Full article

To address key challenges in clothing trademark quality inspection—namely, insufficient defect samples, unstable performance in complex industrial environments, and low detection efficiency—this paper proposes DLF-YOLO, an enhanced YOLOv11-based model optimized for industrial deployment. To mitigate the problem of limited annotated data, an unsupervised generative network, CycleGAN, is employed to synthesize rare defect patterns and simulate diverse environmental conditions (e.g., rotation, noise, and contrast variations), thereby improving data diversity and model generalization. To reduce the impact of industrial noise, a novel multi-scale dynamic synergy attention (MDSA) attention mechanism is introduced, which utilizes dual attention in both channel and spatial dimensions to focus more accurately on key regions of the trademark, effectively suppressing false detections caused by lighting variations and fabric textures. Furthermore, the high-level selective feature pyramid network (HS-FPN) module is adopted to make the neck structure more lightweight, where the feature selection sub-module enhances the perception of fine edge defects, while the feature fusion sub-module achieves a balance between model lightweighting and detection accuracy through the aggregation of hierarchical multi-scale context information. In the backbone, DWConv replaces standard convolutions before the C3k2 module to reduce computational complexity, and HetConv is integrated into the C3k2 module to simultaneously reduce computational cost and enhance feature extraction capabilities, achieving the goal of maintaining model accuracy. Experimental results on a custom-built dataset demonstrate that DLF-YOLO achieves an mAP@0.5:0.95 of 80.2%, with a 49.6% reduction in parameters and a 25.6% reduction in computational load compared to the original YOLOv11. These results highlight the potential of DLF-YOLO as a scalable and efficient solution for lightweight, industrial-grade defect detection in clothing trademarks. Full article

In this study, we present a sponge-like lipophilic gel crosslinked with a branched crosslinker as an absorbent for VOC removal. The gel was synthesized by crosslinking the monomer 3-(trimethoxysilyl)propyl methacrylate (TMSPMA) with the branched crosslinker poly(2-propyl aspartamide) grafted methacrylate (PPA-g-MA). The grafted crosslinker, PPA-g-MA, was prepared by introducing acrylate groups as crosslinking moieties to the poly(succinimide) precursor for poly(2-propyl aspartamide) (PPA), which serves as a hydrophobic backbone. Lipophilic gels were synthesized with varying TMSPMA monomer concentrations and freeze-dried to form a porous structure. To evaluate VOC absorption, the toluene removal efficiency of the sponge-like lipophilic gel was tested in a continuous gas flow system. As a result, the optimal TMSPMA monomer content for maximizing toluene removal efficiency was determined. This result suggests that while an increase in silicon content generally enhances VOC removal efficiency, the porous structure of sponge-like lipophilic gels plays a more crucial role in absorption capacity. The collapse of the porous structure, caused by excessive silicon content making the material more rubber-like, explains why there exists an optimal monomer content for effective VOC absorption. Overall, these findings provide valuable insights for developing high-performance VOC absorbents. Full article

The accurate detection of road defects is crucial for enhancing the safety and efficiency of road maintenance. This study focuses on six common types of pavement defects: transverse cracks, longitudinal cracks, alligator cracking, oblique cracks, potholes, and repair marks. In real-world scenarios, key challenges include effectively distinguishing between the foreground and background, as well as accurately identifying small-sized (e.g., fine cracks, dense alligator cracking, and clustered potholes) and overlapping defects (e.g., intersecting cracks or clustered damage areas where multiple defects appear close together). To address these issues, this paper proposes a Pavement-DETR model based on the Real-Time Detection Transformer (RT-DETR), aiming to optimize the overall accuracy of defect detection. To achieve this goal, three main improvements are proposed: (1) the introduction of the Channel-Spatial Shuffle (CSS) attention mechanism in the third (S3) and fourth (S4) stages of the ResNet backbone, which correspond to mid-level and high-level feature layers, enabling the model to focus more precisely on road defect features; (2) the adoption of the Conv3XC structure for feature fusion enhances the model’s ability to differentiate between the foreground and background, which is achieved through multi-level convolutions, channel expansion, and skip connections, which also contribute to improved gradient flow and training stability; (3) the proposal of a loss function combining Powerful-IoU v2 (PIoU v2) and Normalized Wasserstein Distance (NWD) weighted averaging, where PIoU v2 focuses on optimizing overlapping regions, and NWD targets small object optimization. The combined loss function enables comprehensive optimization of the bounding boxes, improving the model’s accuracy and convergence speed. Experimental results show that on the UAV-PDD2023 dataset, Pavement-DETR improves the mean average precision (mAP) by 7.7% at IoU = 0.5, increases mAP by 8.9% at IoU = 0.5–0.95, and improves F1 Score by 7%. These results demonstrate that Pavement-DETR exhibits better performance in road defect detection, making it highly significant for road maintenance work. Full article

Accurate shoreline extraction is critical for coastal engineering applications, including erosion monitoring, disaster response, and sustainable management of island ecosystems. However, traditional methods face challenges in large-scale monitoring due to high costs, environmental interference (e.g., cloud cover), and poor performance in complex terrains (e.g., bedrock coastlines). This study developed an optimized DeepLabV3+ model for the extraction of island shorelines, which improved model performance by replacing the backbone network with MobileNetV2, introducing a strip pooling layer into the ASPP module, and adding CBAM modules in both the shallow and deep stages of feature extraction from the backbone network. The model accuracy was verified using a self-built drone dataset of the shoreline of Koh Lan, Thailand, and the results showed: (1) Compared with the control model, the improved DeepLabV3+ model performs excellently in pixel accuracy (PA), recall, F1 score, and intersection over union (IoU), reaching 98.7%, 97.7%, 98.0%, and 96.2%, respectively. Meanwhile, the model has the lowest number of parameters and floating-point operations, at 6.61 M and 6.7 GFLOPS, respectively. (2) In terms of pixel accuracy (PA) and intersection over union (IoU), the CBAM attention mechanism outperforms the SE-Net and CA attention mechanisms. Compared with the original DeepLabV3+ network, PA increased by 3.1%, and IoU increased by 8.2%. (3) The verification results of different types of coastlines indicate that the improved model can effectively distinguish between shadows and water bodies, reducing the occurrence of false negatives and false positives, thereby lowering the risk of misclassification and obtaining better extraction results. This work provides a cost-effective tool for dynamic coastal management, particularly in data-scarce island regions. Full article

Sanghuangporus baumii, a fungus used in traditional Chinese medicine, produces important pharmacological compounds such as triterpenoids, but at levels significantly lower than those required for medical use. This study investigated the effects of various concentrations of Ca²⁺ on S. baumii mycelial growth and the heterologous biosynthesis of S. baumii triterpenoids. Under induction by 10 mM Ca²⁺, the growth rate (0.39 cm/d) and biomass (4.48 g/L) of S. baumii mycelia were 1.03% and 10.05% higher than those in the 0 mM Ca²⁺-treatment group, respectively. In contrast, 200 mM Ca²⁺ significantly inhibited the growth rate and biomass of the mycelia. Notably, the total triterpenoid content reached its peak (17.71 mg/g) in the 200 mM Ca²⁺-treatment group, with a significant increase in the Ca²⁺ content (3869.97 µg/g) in the mycelia. Subsequently, the differential metabolic pathways and related genes between the S. baumii groups were examined using transcriptomic analysis. The results indicated that the increase in the growth rate and biomass of S. baumii mycelia was primarily due to elevated soluble sugar content, whereas the growth inhibition was associated with the toxic effects of H₂O₂. The observed differences in triterpenoid content were mainly attributed to the activation of the terpenoid backbone biosynthesis pathway and the AACT gene. Finally, the AACT gene was cloned and transformed into yeast cells, thus creating strain Sc-AA1. Upon treatment at the optimal Ca²⁺ concentration, the squalene content of strain Sc-AA1 reached 0.78 mg/g, 2.89-fold higher than that in the control group. These findings are significant for the heterologous biosynthesis of triterpenoids from S. baumii. Our study demonstrates the feasibility of producing triterpenoids in Saccharomyces cerevisiae and provides a foundation for future optimization toward achieving industrially relevant yields. Full article

In drone countermeasure systems, drone tracking is commonly conducted using object detection methods, which are typically limited to identifying the presence of a drone. To enhance the performance of such systems and improve the accuracy of drone flight posture prediction—while precisely capturing critical components such as rotors, mainboards, and flight trajectories—this paper introduces a novel drone key point detection model, UVPose, built upon the MMpose framework. First, we design an innovative backbone network, MDA-Net, based on the CSPNet architecture. This network improves multi-scale feature extraction and strengthens connections between low- and high-level features. To further enhance key point perception and pose estimation accuracy, a parallel attention mechanism, combining channel and spatial attention, is integrated. Next, we propose an advanced neck structure, RFN, which combines high-level semantic features from the backbone with rich contextual information from the neck. For the head, we adopt the SimCC method, optimized for lightweight, efficient, and accurate key point localization. Experimental results demonstrate that UVPose outperforms existing models, achieving a PCK of 79.2%, an AP of 67.2%, and an AR of 73.5%, with only 15.8 million parameters and 3.3 G of computation. This balance between accuracy and resource efficiency makes UVPose well suited for deployment on edge devices. Full article

To address the critical need for collision risk warning at unsignalized intersections, this study proposes an advanced predictive system combining YOLOv8 for object detection, Deep SORT for tracking, and Bi-LSTM networks for trajectory prediction. To adapt YOLOv8 for complex intersection scenarios, several architectural enhancements were incorporated. The RepLayer module replaced the original C2f module in the backbone, integrating large-kernel depthwise separable convolution to better capture contextual information in cluttered environments. The GIoU loss function was introduced to improve bounding box regression accuracy, mitigating the issues related to missed or incorrect detections due to occlusion and overlapping objects. Furthermore, a Global Attention Mechanism (GAM) was implemented in the neck network to better learn both location and semantic information, while the ReContext gradient composition feature pyramid replaced the traditional FPN, enabling more effective multi-scale object detection. Additionally, the CSPNet structure in the neck was substituted with Res-CSP, enhancing feature fusion flexibility and improving detection performance in complex traffic conditions. For tracking, the Deep SORT algorithm was optimized with enhanced appearance feature extraction, reducing the identity switches caused by occlusions and ensuring the stable tracking of vehicles, pedestrians, and non-motorized vehicles. The Bi-LSTM model was employed for trajectory prediction, capturing long-range dependencies to provide accurate forecasting of future positions. The collision risk was quantified using the predictive collision risk area (PCRA) method, categorizing risks into three levels (danger, warning, and caution) based on the predicted overlaps in trajectories. In the experimental setup, the dataset used for training the model consisted of 30,000 images annotated with bounding boxes around vehicles, pedestrians, and non-motorized vehicles. Data augmentation techniques such as Mosaic, Random_perspective, Mixup, HSV adjustments, Flipud, and Fliplr were applied to enrich the dataset and improve model robustness. In real-world testing, the system was deployed as part of the G310 highway safety project, where it achieved a mean Average Precision (mAP) of over 90% for object detection. Over a one-month period, 120 warning events involving vehicles, pedestrians, and non-motorized vehicles were recorded. Manual verification of the warnings indicated a prediction accuracy of 97%, demonstrating the system’s reliability in identifying potential collisions and issuing timely warnings. This approach represents a significant advancement in enhancing safety at unsignalized intersections in urban traffic environments. Full article

In recent years, numerous advanced lightweight models have been proposed for salient object detection (SOD) in optical remote sensing images (ORSI). However, most methods still face challenges such as performance limitations and imbalances between accuracy and computational cost. To address these issues, we propose SggNet, a novel semantic- and graph-guided lightweight network for ORSI-SOD. The SggNet adopts a classical encoder-decoder structure with MobileNet-V2 as the backbone, ensuring optimal parameter utilization. Furthermore, we design an Efficient Global Perception Module (EGPM) to capture global feature relationships and semantic cues through limited computational costs, enhancing the model’s ability to perceive salient objects in complex scenarios, and a Semantic-Guided Edge Awareness Module (SEAM) that leverages the semantic consistency of deep features to suppress background noise in shallow features, accurately predict object boundaries, and preserve the detailed shapes of salient objects. To further efficiently aggregate multi-level features and preserve the integrity and complexity of overall object shape, we introduce a Graph-Based Region Awareness Module (GRAM). This module incorporates non-local operations under graph convolution domain to deeply explore high-order relationships between adjacent layers, while utilizing depth-wise separable convolution blocks to significantly reduce computational cost. Extensive quantitative and qualitative experiments demonstrate that the proposed model achieves excellent performance with only 2.70 M parameters and 1.38 G FLOPs, while delivering an impressive inference speed of 108 FPS, striking a balance between efficiency and accuracy to meet practical application needs. Full article

AlN-based bulk acoustic wave (BAW) filters have emerged as crucial components in 5G communication due to their high frequency, wide bandwidth, high power capacity, and compact size. This paper mainly reviews the basic principles and recent research advances of AlN-based BAW resonators, which are the backbone of BAW filters. We begin by summarizing the epitaxial growth of single-crystal, polycrystalline, and doped AlN films, with a focus on single-crystal AlN and ScAlN, which are currently the most popular. The discussion then extends to the structure and fabrication of BAW resonators, including the basic solidly mounted resonator (SMR) and the film bulk acoustic resonator (FBAR). The new Xtended Bulk Acoustic Wave (XBAW) technology is highlighted as an effective method to enhance filter bandwidth. Hybrid SAW/BAW resonators (HSBRs) combine the benefits of BAW and SAW resonators to significantly reduce temperature drift. The paper further explores the application of BAW resonators in ladder and lattice BAW filters, highlighting advancements in their design improvements. The frequency-reconfigurable BAW filter, which broadens the filter’s application range, has garnered substantial attention from researchers. Additionally, optimization algorithms for designing AlN-based BAW filters are outlined to reduce design time and improve efficiency. This work aims to serve as a reference for future research on AlN-based BAW filters and to provide insight for similar device studies. Full article

This paper proposes mathematical optimization models for solving the network planning problem using millimeter wave technology for 5G wireless communications networks. To this end, it is assumed that a set of users, $M=\{1,\dots ,m\}$, and a set of base stations, $N=\{1,\dots ,n\}$, are deployed randomly in a square area. In particular, the base stations should be connected, forming a star backbone so that users can connect to their nearest active base stations forming the backbone where the connections are symmetric. In particular, the first two models maximize the number of users connected to the backbone and minimize the distance costs of connecting users to the base stations, and distances of connecting the base stations themselves. Similarly, the last two models maximize and minimize the same objectives and the number of base stations to be activated to form the star backbone. Each user is allowed to connect to a unique active base station. In general, the millimeter wave technology presents a high path loss. Consequently, the transmission distances should be no larger than 300 m at most for different radial transmissions. Thus, a direct line of sight between users and base stations is assumed. Finally, we propose local search-based algorithms that allow finding near-optimal solutions for all our tested instances. Our numerical results indicate that we can solve network instances optimally with up to $k=100$, $n=200$, and $m=5000$ users. Full article

In industrial applications, robotic arm grasp detection tasks frequently suffer from inadequate accuracy and success rates, which result in reduced operational efficiency. Although existing methods have achieved some success, limitations remain in terms of detection accuracy, real-time performance, and generalization ability. To address these challenges, this paper proposes an enhanced grasp detection model, G-RCenterNet, based on the CenterNet framework. First, a channel and spatial attention mechanism is introduced to improve the network’s capability to extract target features, significantly enhancing grasp detection performance in complex backgrounds. Second, an efficient attention module search strategy is proposed to replace traditional fully connected layer structures, which not only increases detection accuracy but also reduces computational overhead. Additionally, the GSConv module is incorporated during the prediction decoding phase to accelerate inference speed while maintaining high accuracy, further improving real-time performance. Finally, ResNet50 is selected as the backbone network, and a custom loss function is designed specifically for grasp detection tasks, which significantly enhances the model’s ability to predict feasible grasp boxes. The proposed G-RCenterNet algorithm is embedded into a robotic grasping system, where a structured light depth camera captures target images, and the grasp detection network predicts the optimal grasp box. Experimental results based on the Cornell Grasp Dataset and real-world scenarios demonstrate that the G-RCenterNet model performs robustly in grasp detection tasks, achieving accurate and efficient target grasp detection suitable for practical applications. Full article

PCBs (printed circuit boards) are the core components of modern electronic devices, and inspecting them for defects will have a direct impact on the performance, reliability and cost of the product. However, the performance of current detection algorithms in identifying minor PCB defects (e.g., mouse bite and spur) still requires improvement. This paper presents the MDD-DETR algorithm for detecting minor defects in PCBs. The backbone network, MDDNet, is used to efficiently extract features while significantly reducing the number of parameters. Simultaneously, the HiLo attention mechanism captures both high- and low-frequency features, transmitting a broader range of gradient information to the neck. Additionally, the proposed SOEP neck network effectively fuses scale features, particularly those rich in small targets, while INM-IoU loss function optimization enables more effective distinction between defects and background, further improving detection accuracy. Experimental results on the PCB_DATASET show that MDD-DETR achieves a 99.3% mAP, outperforming RT-DETR by 2.0% and reducing parameters by 32.3%, thus effectively addressing the challenges of detecting minor PCB defects. Full article

Background/Objectives: Hemophilia B is a hereditary bleeding disorder due to the production of liver malfunctional factor IX (FIX). Gene therapy with viral vectors offers a cure. However, applications are limited due to pre-existing antibodies, eligibility for children under 12 years of age, hepatotoxicity, and excessive costs. Lipid nanoparticles are a potential alternative owing to their biocompatibility, scalability, and non-immunogenicity. However, their therapeutic applications are still elusive due to the poor transfection efficiencies in delivering plasmid DNA into primary cells and target organs in vivo. To develop efficient liver-targeted lipid nanoparticles, we explored galactosylated lipids to target asialoglycoprotein receptors (ASGPRs) abundantly expressed on hepatocytes. Methods: We developed 12 novel liposomal formulations varying the galactose lipid Gal-LNC 5, cationic lipid MeOH16, DOPE, and cholesterol. We evaluated their physicochemical properties, toxicity profiles, and transfection efficiencies in hepatic cell lines. Among the formulations, Gal-LNC 5 could efficiently transfect the reporter plasmid eGFP in hepatic cell lines and specifically distribute into the liver in vivo. Toward developing functional factor IX, we cloned Padua mutant FIX-L in a CpG-free backbone to enhance the expression and duration. Results: We demonstrated superior expression of FIX with our galactosylated lipid nanoparticle system. Conclusions: The current research presents a specialized lipid nanoparticle system viz. Gal-LNC which is a specialized lipid nanoparticle system for liver-targeted gene therapy in hemophilia B patients that has potential for clinical use. The Gal-LNC successfully delivers a CpG-free Padua FIX gene to liver cells, producing therapeutically relevant levels of FIX protein. Among its benefits are the ideal qualities of stability, targeting the liver specifically, and maximizing efficiency of transfection. Optimization of liver-targeting lipid nanoparticle systems and function FIX plasmids will pave the way for novel lipid nanoparticle-based gene therapy products for hemophilia B and other monogenic liver disorders. Full article