Search

Wideband microwave absorbers hold significant importance in both civilian and military fields. In this paper, a lightweight ultra‐wideband metasurface microwave absorber that covers a frequency range from the ultrahigh‐frequency band to Ku band is presented. The absorber consists of three layers of periodically arranged fourfold rotationally symmetric indium tin oxide (ITO) patterned structures and a reflective surface at the bottom layer separated by polymethacrylimide (PMI) spacers. Such a design enables the absorber to achieve a lightweight construction. The experimental results demonstrate that the absorber exhibits an absorptivity >90% in the 1.3–13.3 GHz band, with a corresponding fractional bandwidth of up to 164.4%. Additionally, the designed absorber features a remarkably lightweight performance with volume density relative to wavelength (VDRW) of just 6.71 mg cm−3. Furthermore, attributed to its fourfold rotationally symmetric design, the absorber also exhibits polarization insensitivity and excellent angular stability. These unique properties render the proposed wideband absorber highly suitable for a variety of practical applications after reasonable adjustment and optimization. [ABSTRACT FROM AUTHOR]

Aerogels are used to achieve lightweight heat insulation in composites. To minimize cost and ensure safety, nanocomposites must be prepared without flammable or explosive solvents at room temperature and ambient‐pressure drying. However, fabricating resin aerogel nanocomposites is challenging due to the tendency of porous structures to collapse owing to the complex surface tension in the multiphase system of fibers, resin particles, and solvent. A novel quartz fiber‐reinforced hybrid aerogel nanocomposite is successfully prepared using the sol–gel method with self‐assembly template polymerization. Two key factors in preventing aerogel collapse include the use of a cationic surfactant as a stabilizer for the initial template and as a surface tension improver during drying. The nanocomposite, with a density of 0.52 g·cm−3 and thermal conductivity of 0.046 W·m−1·K−1, exhibited a back‐face temperature rise of ≈96.4 °C after a 1500 s arc‐wind tunnel ablation test. The maximum ablation retreat is ≈0.26 mm. This novel nanocomposite shows potential for high‐temperature protection systems in extreme oxidation environments. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Considering several sources that cause global position system (GPS) interference in civil aviation and the challenges faced by interference recognition algorithms in terms of efficiency and accuracy, we propose an improved You Only Look Once (YOLO)v7‐CHS algorithm (YOLOv7‐CHS) and investigate its effectiveness in identifying GPS signals and different types of interference signals. First, continuous wavelet transform (CWT) is introduced as a method for processing and analyzing signals in the time–frequency (TF) domain to effectively obtain their temporal and spectral characteristic information. Second, the ConvNeXt structure is integrated into the YOLOv7 backbone network to create a ConvNeXtBlock (CNeB) module to enhance the classification and recognition accuracy of interference signals. Additionally, an attention mechanism is introduced to further improve model recognition accuracy. To effectively improve the capability of signal feature extraction and mitigate the impact of background noise on TF feature suppression, we have integrated the efficient channel attention (ECA) channel attention module with the convolutional block attention module (CBAM) spatial attention module, thereby proposing a hybrid CBAM and ECA (HCE) attention module. Last, to address issues arising from accidental deletion of detection frames and multipath interference negatively affecting model recognition performance, we have employed the soft nonmaximum suppression (Soft‐NMS) algorithm while selecting an optimal loss function through comparative analysis. The comparative evaluation experimental results under different circumstances show that YOLOv7‐CHS achieves recognition accuracies of 98.0% and 99.6% for various types of signals, respectively. These values represent an increase of 1.7% and 1%, respectively, compared to YOLOv7. Moreover, in terms of lightweight indicators, YOLOv7‐CHS exhibits a significant improvement in performance: the frames per second (FPS) is increased by 75.1, the number of parameters (Params) was reduced by 4.75 M, and giga floating point operations per second (GFLOPs) were reduced by 65.9 G while effectively enhancing recognition capabilities. The proposed YOLOv7‐CHS not only improves signal recognition accuracy but also reduces model Params and computational complexity, achieving a lightweight model with promising application prospects in the rapid detection and recognition of GPS interference sources in civil aviation. [ABSTRACT FROM AUTHOR]

With advancements in freeform surface design and manufacturing, applying freeform surfaces to space cameras is an effective method to further enhance imaging quality. However, existing design methods for freeform space cameras rarely consider imaging quality, system size, and manufacturing constraints simultaneously during design. This study proposes an adaptive design method for long-focal-length freeform off-axis reflective space cameras with lightweight and primary/three mirror integration, which balances system size and ease of manufacturing while ensuring good imaging quality. First, a method for adaptive configuration of the structural parameter search spaces is proposed, so that the search spaces for structural parameters are dynamically generated based on different design requirements of long-focal-length off-axis space cameras with various structures. Then, a multiple-parameter objective function is constructed, and the structural parameters for the off-axis space camera are determined through a search process to balance imaging quality, lightweight requirements and manufacturing demands. Finally, the improved Wassermann–Wolf (W-W) method is employed to optimize the mirrors into freeform surfaces, further enhancing the imaging quality of the designed space camera. Experimental results demonstrate that the proposed method can adaptively generate reasonable structural parameter search spaces while maintaining high imaging quality, facilitating the acquisition of a lightweight and easily manufacturable freeform off-axis reflective space camera. This method exhibits strong dynamic adaptability and low reliance on prior experience, providing a new insight for the design of space cameras. [ABSTRACT FROM AUTHOR]

To address the issues of target feature blurring and increased false detections caused by high compression rates in deepfake videos, as well as the high computational resource requirements of existing face extractors, we propose a lightweight face extractor to assist deepfake detection, GCS-YOLOv8. Firstly, we employ the HGStem module for initial downsampling to address the issue of false detections of small non-face objects in deepfake videos, thereby improving detection accuracy. Secondly, we introduce the C2f-GDConv module to mitigate the low-FLOPs pitfall while reducing the model's parameters, thereby lightening the network. Additionally, we add a new P6 large target detection layer to expand the receptive field and capture multi-scale features, solving the problem of detecting large-scale faces in low-compression deepfake videos. We also design a cross-scale feature fusion module called CCFG (CNN-based Cross-Scale Feature Fusion with GDConv), which integrates features from different scales to enhance the model's adaptability to scale variations while reducing network parameters, addressing the high computational resource requirements of traditional face extractors. Furthermore, we improve the detection head by utilizing group normalization and shared convolution, simplifying the process of face detection while maintaining detection performance. The training dataset was also refined by removing low-accuracy and low-resolution labels, which reduced the false detection rate. Experimental results demonstrate that, compared to YOLOv8, this face extractor achieves the AP of 0.942, 0.927, and 0.812 on the WiderFace dataset's Easy, Medium, and Hard subsets, representing improvements of 1.1%, 1.3%, and 3.7% respectively. The model's parameters and FLOPs are only 1.68 MB and 3.5 G, reflecting reductions of 44.2% and 56.8%, making it more effective and lightweight in extracting faces from deepfake videos. [ABSTRACT FROM AUTHOR]

Technological advances have dramatically improved precision agriculture, and accurate crop classification is a key aspect of precision agriculture (PA). The flexibility and real-time nature of UAVs have led them to become an important tool for acquiring agricultural data and enabling precise crop classification. Currently, crop identification relies heavily on complex high-precision models that often struggle to provide real-time performance. Research on lightweight models specifically for crop classification is also limited. In this paper, we propose a crop classification method based on UAV visible-light images based on PP-LiteSeg, a lightweight model proposed by Baidu. To improve the accuracy, a pyramid pooling module is designed in this paper, which integrates adaptive mean pooling and CSPC (Convolutional Spatial Pyramid Pooling) techniques to handle high-resolution features. In addition, a sparse self-attention mechanism is employed to help the model pay more attention to locally important semantic regions in the image. The combination of adaptive average pooling and the sparse self-attention mechanism can better handle different levels of contextual information. To train the model, a new dataset based on UAV visible-light images including nine categories such as rice, soybean, red bean, wheat, corn, poplar, etc., with a time span of two years was created for accurate crop classification. The experimental results show that the improved model outperforms other models in terms of accuracy and prediction performance, with a MIoU (mean intersection ratio joint) of 94.79%, which is 2.79% better than the original model. Based on the UAV RGB images demonstrated in this paper, the improved model achieves a better balance between real-time performance and accuracy. In conclusion, the method effectively utilizes UAV RGB data and lightweight deep semantic segmentation models to provide valuable insights for crop classification and UAV field monitoring. [ABSTRACT FROM AUTHOR]

Underground coal gangue sorting is a critical component of modern intelligent coal mining, holding significant importance for the preservation of natural resources and the ecological environment. Traditional methods of underground coal gangue sorting suffer from issues such as low efficiency, limited applicability, and substantial resource wastage. Addressing these challenges, this paper employs multispectral technology to gather spectral data of coal and gangue in various wavelengths. Based on the identification accuracy of coal gangue images in different wavelength bands and the correlation of spectral data, the optimal three wavelengths out of 25 are selected to construct a pseudo-RGB (Red, Green, Blue) image. Furthermore, building upon YOLOv7-tiny, an improved lightweight coal gangue recognition method is proposed. Experimental results demonstrate that the improved lightweight model has a computational load of 11.5 GFLOPs, merely 88.5% of the original model's load. The model's detection rate is 77 frames per second (fps), a 23 fps increase compared to the original model. Precision, recall, and average accuracy reach 98.7%, 97.1%, and 98.8% respectively, indicating a 1.5%, 0.2%, and 0.5% improvement over the original model. The approach effectively mitigates instances of omission, enhancing model accuracy and portability. [ABSTRACT FROM AUTHOR]

Subcritical damage in sandwich panels refers to damage that occurs in the skins or core of the panel due to loading below the ultimate strength of the materials, and it can reduce the strength and durability of sandwich panels, leading to premature and unpredicted failure. In this work, a computational tool was developed for designing sandwich structures and optimizing their subcritical impact response. The model was validated experimentally on sandwich panels comprising an aluminium honeycomb core with carbon fiber reinforced epoxy skins. The study investigates subcritical damage in aluminium honeycomb and CFRP sandwich panels through mechanical experiments and finite element simulations. A novel computational tool was developed to optimize the impact response of these structures. Experimental validation was performed using standardized tests, and numerical simulations were conducted using Abaqus. Key findings indicate that the developed tool accurately predicts damage and stiffness reduction, offering significant potential for optimizing sandwich panel designs. [ABSTRACT FROM AUTHOR]

A valve block is a key component and main load-bearing structural member in the integrated installation of fluid control components and sensors, which are widely used in hydraulic systems in aerospace and other fields owing to their compact structures and ease of integration. However, hydraulic valve blocks that are manufactured using conventional processes are bulky and inefficient in terms of material use and add complexity to the configuration of vertically intersectional internal flow channels, which form eddy currents and result in potentially serious pressure losses. Moreover, their auxiliary process holes increase the risk of hydraulic oil leakage, thereby considerably decreasing the reliability of the product. This study proposes a comprehensive process for practical structural optimization and additive manufacturing process combining selective laser melting (SLM), generative design, and SLM process simulation to optimize the structure of an aerospace engine servo actuator hydraulic valve block. The weight of the hydraulic valve block was reduced by 35.9% by employing the generative design, which could reduce the cost of space transport. The actual manufacturing process of the hydraulic valve block was considered by combining SLM and post-machining. Furthermore, additive process simulations were used to evaluate printing risks and defects, optimize the printing schemes, and improve the product quality. [ABSTRACT FROM AUTHOR]

Medical image semantic segmentation is a crucial technique in medical imaging processing, providing essential diagnostic support by precisely delineating different tissue structures and pathological areas within an image. However, the pursuit of higher accuracy has led to increasingly complex architectures in existing networks, resulting in significant training overhead. In response, this study introduces a flattened, minimalist design philosophy and constructs the shallow super convolution U-shaped Net (SSCU-Net) based on this concept. Compared to the traditional four-layer U-shaped networks, SSCU-Net has a simplified two-layer structure, adhering to a lightweight research objective. On one hand, to address the issue of insufficient semantic feature extraction caused by the shallow network architecture, a parallel multi-branch feature extraction module called the super convolution block is designed to thoroughly extract diverse semantic information. On the other hand, to facilitate the transfer of critical semantic information between encoding and decoding, as well as across layers, the spatial convolution path, along with feature enhanced downsample and feature resolution upsample, are constructed. The performance of SSCU-Net was validated against 18 comparison models across seven metrics on five datasets. Results from metric analysis, image comparisons, and ablation tests collectively demonstrate that SSCU-Net achieves an average improvement of 15.9792% in the Dice coefficient compared to other models, confirming the model's advantages in both lightweight design and accuracy. The network code is available at https://github.com/YF-W/SSCU-Net. [ABSTRACT FROM AUTHOR]

Copyright of Automobile Technology & Material is the property of Automobile Technology & Material Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Craniocerebral injuries represent the primary cause of fatalities among riders involved in two-wheeler accidents; nevertheless, the prevalence of helmet usage among these riders remains alarmingly low. Consequently, the accurate identification of riders who are wearing safety helmets is of paramount importance. Current detection algorithms exhibit several limitations, including inadequate accuracy, substantial model size, and suboptimal performance in complex environments with small targets. To address these challenges, we propose a novel lightweight detection algorithm, termed GL-YOLOv5, which is an enhancement of the You Only Look Once version 5 (YOLOv5) framework. This model incorporates a Global DualPooling NoReduction Blend Attention (GDPB) module, which optimizes the MobileNetV3 architecture by reducing the number of channels by half and implementing a parallelized channel and spatial attention mechanism without dimensionality reduction. Additionally, it replaces the conventional convolutional layer with a channel shuffle approach to overcome the constraints associated with the Squeeze-and-Excitation (SE) attention module, thereby significantly improving both the efficiency and accuracy of feature extraction and decreasing computational complexity. Furthermore, we have optimized the Variable Normalization and Attention Channel Spatial Partitioning (VNACSP) within the C3 module of YOLOv5, which enhances sensitivity to small targets through the application of a lightweight channel attention mechanism, substituting it for the standard convolution in the necking network. The Parameter-Free Spatial Adaptive Feature Fusion (PSAFF) module is designed to adaptively modify the weights of each spatial position through spatial pooling and activation functions, thereby effectively enhancing the model's ability to perceive contextual information over distances. Ultimately, GL-YOLOv5 performs remarkably in the custom dataset, achieving a model parameter count of 922,895 M, a computational load of 2.9 GFLOPS, and a mean average precision (mAP) of 92.1%. These advancements significantly improve the model's detection capabilities and underscore its potential for practical applications. [ABSTRACT FROM AUTHOR]

Combining light metals like aluminum to produce lightweight structures offers a high weight‐saving and contributes to a circular economy in automotive car body construction. Compound casting is a promising process for producing car body parts. Difficulties arise in creating metallic continuity between insert and casting. Insert coatings are used to remove the oxide layer and thereby improve the wettability of the melt. This study uses a hybrid joining method to improve the metallic bond between insert and casting. Induction heating differently influences the strength properties of age‐ and nonage‐hardenable inserts. Compression shear tests characterize the metallic bond strength. Microscopic images show the influence of the process variables on the compound quality. Reproducible sound metallic bonding with low scattering is achieved by enhancing the compound casting process through induction and no insert coating. Cast wall thicknesses down to 4 mm contribute to further lightweight potential as they have the same strength level as the reference sample. A decisive factor is the insert temperature in the compound zone. Thereby, insert preheating conditions play a crucial role. Additional heat treatment of hardenable compounds leads to a further increase in metallic bond strength. [ABSTRACT FROM AUTHOR]

Copyright of Cotton Textile Technology is the property of Cotton Textile Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The problems of electromagnetic wave (EMW) pollution in X and Ku bands (8–18 GHz) are becoming more and more serious. Therefore, it is urgent to design EMW absorbing materials with high-efficiency such as thin thickness, lightweight, wide bandwidth and strong EMW absorption. Inspired by the biomorph of sea cucumber, Nb2CTx MXene@Co nitrogen-doped carbon nanosheet arrays@carbon fiber aerogels (Nb2CTx@Co-NC@CFA, Nb2CTx = niobium carbide) were constructed by self-assembly, in-situ chemical deposition and subsequent pyrolysis. The carbon fiber aerogel, as the basic skeleton of sea cucumber, forms lightweight three-dimensional interconnected conductive network, enhances the dielectric loss and extends the multiple reflection and absorption paths of EMW. As the tentacles of sea cucumber surface, Nb2CTx MXene and Co nitrogen-doped carbon nanosheet arrays exist rich heterogeneous interfaces, which play an important role in improving EMW polarization loss and optimizing impedance matching. The minimum reflection loss (RLmin) of Nb2CTx@Co-NC@CFA reaches −54.7 dB at 9.84 GHz (2.36 mm) with a low filling ratio of 10 wt.% and the effective absorption bandwidth (EAB) of Nb2CTx@Co-NC@CFA reaches 2.96 GHz (8.48–11.44 GHz) with 2.36 mm and 5.2 GHz (12.8–18 GHz) with 1.6 mm, covering most of X and Ku bands by adjusting thickness. The radar cross section (RCS) value of Nb2CTx@Co-NC@CFA is 26.64 dB·m2, which is lower than that of the perfect electrical conductor (PEC), indicating that Nb2CTx@Co-NC@CFA can effectively decrease the probability of the target being detected by the radar detector. This work provides ideas for design and development of EMW absorbing materials with high-efficiency EMW absorption in X and Ku bands. [ABSTRACT FROM AUTHOR]

Organic–inorganic hybrid perovskites are quite promising candidates in the field of electromagnetic wave (EMW) absorption due to their unique physicochemical properties. However, it is still a considerable challenge to satisfy the light weight, broad bandwidth, and strong absorption properties simultaneously. Herein, the solution of methylammonium lead iodide (MAPbI3) perovskites was infiltrated into the pores of reduced graphene oxide (rGO) aerogels. After drying, a series of MAPbI3/rGO composite aerogel (MGA) materials were synthesized by anchoring the MAPbI3 perovskite nanoparticles to rGO sheets with the assistance of rGO templates. Through the adjustment of component ratios, excellent EMW absorption properties are obtained with the synergistic effects of polarization loss, conduction loss, and multiple reflection and scattering of MAPbI3 and rGO. The porous structure of the aerogel and the suitable group distribution ratio allowed the MGA-4 samples to obtain excellent impedance matching and ultra-low density of ∼ 7.69 mg·cm−3. At a low filling ratio of 15 wt.%, the MGA-4 sample simultaneously achieves highly efficient and broadband EMW absorption performance at a thin thickness. The MGA-4 sample obtained a minimum reflection loss value of −64.35 dB and the effective absorption bandwidth (EAB) value of 5.4 GHz at a thickness of 2.08 mm and a maximum EAB (EABmax) value of 6.2 GHz under 2.22 mm. The MGA-5 sample obtained a maximum EAB value of 6.4 GHz with the thinckness of 2.16 mm. Furthermore, the simulation results of the radar cross-section (RCS) verified the component-optimized composites are capable of achieving excellent EMW attenuation. This paper provides a new approach and valuable reference for the development of hybrid perovskite-based microwave absorption materials with lightweight, ultra-broadband, and strong absorption properties. [ABSTRACT FROM AUTHOR]

Because of the special way an unmanned aerial vehicle (UAV) acquires aerial photography, UAV images have the characteristics of large coverage area, complex background, and a large proportion of small targets, which exacerbate the difficulty of object detection. Additionally, UAV-based aerial image detection needs to meet lightweight and real-time capabilities. To address these issues, this paper proposes a lightweight model YOLOv7-P that is based on YOLOv7 but has a stronger detection capability for small targets. First, partial convolution (PConv) is used to reduce redundant parameters and computation in YOLOv7. Second, an optimal combination of detection heads is determined that can significantly improve the detection performance of small objects. Third, a novel lightweight convolution called PConv-wide is proposed to replace RepConv in the network, thus simplifying the network without affecting detection accuracy. Finally, the normalized wasserstein distance loss is reasonably combined with the complete intersection over union loss to further improve the sensitivity of the network to small targets. The proposed YOLOv7-P model strikes a delicate balance between precision and parameter count. Compared with the baseline YOLOv7 network, it reduces parameter count by 47.1% without increasing computational complexity and boosts AP50 by 8% and mAP by 5.4% on the VisDrone dataset. [ABSTRACT FROM AUTHOR]

Copyright of Paint & Coatings Industry (0253-4312) is the property of Paint & Coatings Industry Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Liquid crystal polymer (LCP) composites are presented as lightweight, high-strength, thermoplastic composites. Fumed silica (FS), carbon black (CB), carbon nanostructures (CNS), and boron nitride (BN) added to the polyphenylene sulfide (PPS) increased the viscosity ratio of the PPS to the LCP. PPS filled with 5 wt.% FS was used to optimize injection molding conditions and had a viscosity ratio ranging from 2 to 13. Increasing fill time to 5 s brought about the highest tensile strength of 99 MPa and modulus of 12.5 GPa, while the tool and melt temperatures imparted no significant effect. Mechanical and thermal properties of select LCP materials processed using molding conditions optimized for the experimental materials are presented. Mechanical properties in the crossflow direction were lower than in the flow direction, which could be overcome with tool design and placement of valve gates to tailor the flow patterns. BN filled composites increased the thermal conductivity to a value of 0.26 W/mK at 16 wt.% loading. [ABSTRACT FROM AUTHOR]

Due to the limited onboard resources on Micro Aerial Vehicles (MAVs), the poor real-time performance has always been an urgent problem to be solved in the practical applications of visual inertial odometry (VIO). Therefore, a lightweight omnidirectional visual-inertial odometry (LOVIO) for MAVs based on improved keyframe tracking and marginalization was proposed. In the front-end processing of LOVIO, wide field-of-view (FOV) images are captured by an omnidirectional camera, frames are tracked by semi-direct method combining of direct method with rapidity and feature-based method with accuracy. In the back-end optimization, the Hessian matrix corresponding to the error optimization equation is stepwise marginalized, so the high-dimensional matrix is decomposed and the operating efficiency is improved. Experimental results on the dataset TUM-VI show that LOVIO can significantly reduce running time consumption without loss of precision and robustness, that means LOVIO has better real-time and practicability for MAVs. [ABSTRACT FROM AUTHOR]

Currently, lightweight small object detection algorithms for unmanned aerial vehicles (UAVs) often employ group convolutions, resulting in high Memory Access Cost (MAC) and rendering them unsuitable for edge devices that rely on parallel computing. To address this issue, we propose the SOD-YOLO model based on YOLOv7, which incorporates a DSDM-LFIM backbone network and includes a small object detection branch. The DSDM-LFIM backbone network, which combines Deep-Shallow Downsampling Modules (DSD Modules) and Lightweight Feature Integration Modules (LFI Modules), avoids excessive use of group convolutions and element-wise operations. The DSD Module focuses on extracting both deep and shallow features from feature maps using fewer parameters to obtain richer feature representations. The LFI Module, is a dual-branch feature integration module designed to consolidate feature information. Experimental results demonstrate that the SOD-YOLO model achieves an AP50 of 50.7% and a FPS of 72.5 on the VisDrone validation set. Compared to YOLOv7, our model reduces computational costs by 20.25% and decreases the number of parameters by 17.89%. After scaling the number of channels in the model, it achieves an AP50 of 33.4% with an inference time of 27.3ms on the Atlas 200I DK A2. These experimental results indicate that the SOD-YOLO model can effectively perform small object detection tasks in a large number of aerial images captured by UAVs. [ABSTRACT FROM AUTHOR]

The development of small UAV technology has led to the emergence of new challenges in UAV countermeasures. The timely detection of UAVs can effectively prevent potential infringements on airspace and privacy. Currently, methods based on deep learning demonstrate excellent performance in target detection. However, in complex scenes, there is a tendency for false alarms (FAs) and misdetections to occur at a higher rate. To solve these problems, we propose a lightweight infrared small target detection algorithm LDHD‐Net. First, we design a novel Ghost‐Shuffle module in the backbone network to enhance the network feature extraction capability. Meanwhile, we remove redundant layers from the network to make the backbone network more lightweight. Second, we design a hierarchical attention enhancement module in the neck network to improve the saliency of UAV targets and reduce background noise interference. In addition, we design a novel small target detection structure and prediction heads in the shallow layers of the network to improve small target detection accuracy. Finally, we design a novel attention dual‐branch head to reduce interference between different tasks and improve the real‐time performance of algorithm detection. The experimental results show that compared with the original model, inference time remains essentially the same, LDHD‐Net parameters are only 3.9 M and AP improves by 12.6%. Compared to SOTA methods, LDHD‐Net shows better performance on SIDD and Anti‐UAV410 datasets. The algorithm effectively improves the accuracy and real‐time detection of UAVs in complex scenes. [ABSTRACT FROM AUTHOR]

Highlights The realization of lightweight insulation materials is often accompanied by a decrease in ablation performance. Coordinating the contradiction between lightweight and ablation resistance is the key to the development of thermal protection technology. Addressing the need for high‐performance insulation materials within solid rocket motors (SRMs) combustion chambers, we designed three multilayer composite structural insulation materials and studied their properties. The results show that among these constructed multilayer composites, the bilayer structure exhibited the lowest density at a mere 0.72 g/cm3, marking a 27% reduction compared to the basic structure. Remarkably, the bilayer configuration demonstrated superior ablation resistance, showcasing a 25% decrease in the line ablation rate in contrast to the basic structure after oxygen‐acetylene test. This achievement embodies the successful harmonization of lightweight properties with ablation resistance. Furthermore, based on the performance and microstructure of the char layer, a further analysis revealed the enhancement mechanism of ablative performance by the multilayer composite structure. It was found that the synergistic effect of the compact/porous structure of the char layer grants the bilayer structure thermal insulation material optimal ablative performance. This work provides strong support for improving the performance of SRMs. Insulation materials with multilayer composite structures are designed. The materials exhibit both lightweight and superior ablation resistance. Compact/porous char layers enhance material ablation performance. [ABSTRACT FROM AUTHOR]

Light field (LF) image super-resolution (SR) is a technique designed to enhance the details and clarity of low-resolution (LR) light field images by leveraging the additional information and structure present within the LF data. With the rise of deep learning, the performance of LF image super-resolution has been significantly improved, but it has led to an increase in model parameters and computational complexity, resulting in a phenomenon of excessive reliance on computational resources. To address this problem, this paper proposes a lightweight but effective model. In our approach, we employ Swin Attention to extract features from LF images. Window and Shifted Window are the main components of Swin Attention. Therefore, the local features of the LF images are captured using Window, and feature correlations are established through Shifted Window. Furthermore, we introduce Extensive Attention (EA) blocks to capture the global features of the LF image. In addition to the aforementioned configurations, we have also engineered an iteration of the Low Computation Convolution (LCC) that is capable of eliminating redundant information prior to the feature extraction process in LF images. This design aims to mitigate superfluous computations, thereby enhancing computational efficiency. Experimental results show that our approach achieves suboptimal performance compared to other state-of-the-art models, while having fewer parameters, lower computational complexity, and faster inference speed. [ABSTRACT FROM AUTHOR]

Sea workover machine is used as the necessary equipment for the whole workover operation, its derrick is the most critical bearing part of workover machine, with large load and serious accidents are often caused due to insufficient strength and stability. Based on the static performance of the derrick is mainly used as the design criterion, and it does not consider the small modularity and lightweight requirements of the derrick. There is a huge material waste only by adding the materials of the rod material to ensure the safety and reliability of the derrick. So it provides very important engineering significance while the safety and reliability of the derrick are ensured, in order to realize the lightweight design of offshore workover rig and reduce the material consumption. The simulation annealing algorithm was used to investigate the lightweight of the derrick. The results show that the industry standard is met by the statics, dynamics and stability of the lightweight derrick. It can be seen that the accuracy of light weight study of offshore workover rig is high. The theoretical basis and data reference can be provided by the research methods and results for the structural optimization of derrick of workover rig. [ABSTRACT FROM AUTHOR]

In the intricate and dynamic infrared imaging environment, the detection of infrared dim and small targets becomes notably challenging due to their feeble radiation intensity, intricate background noise, and high interference characteristics. To tackle this issue, this paper introduces a lightweight detection and recognition algorithm, named YOLOv5-IR, and further presents an even more lightweight version, YOLOv5-IRL. Firstly, a lightweight network structure incorporating spatial and channel attention mechanisms is proposed. Secondly, a detection head equipped with an attention mechanism is designed to intensify focus on small target information. Lastly, an adaptive weighted loss function is devised to improve detection performance for low-quality samples. Building upon these advancements, the network size can be further compressed to create the more lightweight YOLOv5-IRL version, which is better suited for deployment on resource-constrained mobile platforms. Experimental results on infrared dim and small target detection datasets with complex backgrounds indicate that, compared to the baseline model YOLOv5, the proposed YOLOv5-IR and YOLOv5-IRL detection algorithms reduce model parameter counts by 42.9% and 45.6%, shorten detection time by 13.6% and 16.9%, and enhance mAP0.5 by 2.4% and 1.8%, respectively. These findings demonstrate that the proposed algorithms effectively elevate detection efficiency, meeting future demands for infrared dim and small target detection. [ABSTRACT FROM AUTHOR]

In the context of edge environments with constrained resources, realizing real-time and robust crosswalk and guide arrow detection poses a significant challenge for autonomous driving systems. This paper proposes a crosswalk and guide arrow detection network (CGADNet), a lightweight visual neural network derived from YOLOv8. Specifically designed for the swift and accurate detection of crosswalks and guide arrows within the field of view of the vehicle, the CGADNet can seamlessly be implemented on the Jetson Orin Nano device to achieve real-time processing. In this study, we incorporated a novel C2f_Van module based on VanillaBlock, employed depth-separable convolution to reduce the parameters efficiently, utilized partial convolution (PConv) for lightweight FasterDetect, and utilized a bounding box regression loss with a dynamic focusing mechanism—WIoUv3—to enhance the detection performance. In complex scenarios, the proposed method in the stability of the mAP@0.5 was maintained, resulting in a 4.1% improvement in the mAP@0.5:0.95. The network parameters, floating point operations (FLOPs), and weights were reduced by 63.81%, 70.07%, and 63.11%, respectively. Ultimately, a detection speed of 50.35 FPS was achieved on the Jetson Orin Nano. This research provides practical methodologies for deploying crosswalk and guide arrow detection networks on edge computing devices. [ABSTRACT FROM AUTHOR]

Pathological myopia is a major cause of blindness among people under 50 years old and can result in severe vision loss in extreme cases. Currently, its detection primarily relies on manual methods, which are slow and heavily dependent on the expertise of physicians, making them impractical for large-scale screening. To tackle these challenges, we propose SMLS-YOLO, an instance segmentation method based on YOLOv8n-seg. Designed for efficiency in largescale screenings, SMLS-YOLO employs an extremely lightweight model. First, StarNet is introduced as the backbone of SMLS-YOLO to extract image features. Subsequently, the StarBlock from StarNet is utilized to enhance the C2f, resulting in the creation of the C2f-Star feature extraction module. Furthermore, shared convolution and scale reduction strategies are employed to optimize the segmentation head for a more lightweight design. Lastly, the model incorporates the Multi-Head Self-Attention (MHSA) mechanism following the backbone to further refine the feature extraction process. Experimental results on the pathological myopia dataset demonstrate that SMLS-YOLO outperforms the baseline YOLOv8n-seg by reducing model parameters by 46.9%, increasing Box mAP@0.5 by 2.4%, and enhancing Mask mAP@0.5 by 4%. Furthermore, when compared to other advanced instance segmentation and semantic segmentation algorithms, SMLS-YOLO also maintains a leading position, suggesting that SMLS-YOLO has promising applications in the segmentation of pathological myopia images. [ABSTRACT FROM AUTHOR]

Recently, there have been significant developments in the realm of novel view synthesis relying on radiance fields. By incorporating the Splatting technique, a new approach named Gaussian Splatting has achieved superior rendering quality and real-time performance. However, the training process of the approach incurs significant performance overhead, and the model obtained from training is very large. To address these challenges, we improve Gaussian Splatting and propose Frequency-Importance Gaussian Splatting. Our method reduces the performance overhead by extracting the frequency features of the scene. First, we analyze the advantages and limitations of the spatial sampling strategy of the Gaussian Splatting method from the perspective of sampling theory. Second, we design the Enhanced Gaussian to more effectively express the high-frequency information, while reducing the performance overhead. Third, we construct a frequency-sensitive loss function to enhance the network's ability to perceive the frequency domain and optimize the spatial structure of the scene. Finally, we propose a Dynamically Adaptive Density Control Strategy based on the degree of reconstruction of the background of the scene, which adaptive the spatial sample point generation strategy dynamically according to the training results and prevents the generation of redundant data in the model. We conducted experiments on several commonly used datasets, and the results show that our method has significant advantages over the original method in terms of memory overhead and storage usage and can maintain the image quality of the original method. [ABSTRACT FROM AUTHOR]

In order to solve the security risks caused by UAV “ black flight”, aiming at the problems of large model parameters and long training time of the existing UAV target detection algorithm based on deep learning, a lightweight real-time object detection algorithm for UAV based on YOLOv5 (ED-YOLOv5s) was proposed. Firstly, the feature extraction part of YOLOv5 backbone network was reconstructed by combining the lightweight model efficient model (EMO) . Secondly, normalized gaussian wasserstein distance (NWD) and scale factor were introduced to calculate the similarity between candidate boxes to partially replace IoU. Then, SimAM was introduced to optimize the weight distribution and improved the detection accuracy, so as to achieved the effect of optimizing the Backbone and Head of YOLOv5 network. Finally, the model size is 4. 57 M. ED-YOLOv5s lightweight UAV detection algorithm with floating point computation of 26. 1 (GFLOPs). The experimental data shows that the improved algorithm improves the detection accuracy and realizes the model lightweight. The proposed algorithm achieves 96. 7% AP@ 50 value on the DUT Anti-UAV dataset, and the detection speed reaches 37 frame / s on the RTX2060 GPU. [ABSTRACT FROM AUTHOR]

In recent years, significant progress has been made in single-image super-resolution with the advancements of deep convolutional neural networks (CNNs) and transformer-based architectures. These two techniques have led the way in the field of super-resolution technology research. However, performance improvements often come at the cost of a substantial increase in the number of parameters, thereby limiting the practical applications of super-resolution methods. Existing lightweight super-resolution methods, which primarily focus on single-scale feature extraction, lead to the issue of missing multi-scale features. This results in incomplete feature acquisition and poor reconstruction of the image. In response to these challenges, this paper proposed a lightweight multi-scale feature cooperative enhancement network (MFCEN). The network consists of three parts: shallow feature extraction, deep feature extraction, and image reconstruction. In the deep feature extraction part, a novel integrated multi-level feature module was introduced. Compared to existing CNN and transformer hybrid super-resolution networks, MFCEN significantly reduced the number of parameters while maintaining performance. This improvement was particularly evident at a scale factor of 3. The network introduced a novel comprehensive integrated multi-level feature module, leveraging the strong local perceptual capabilities of CNNs and the superior global information processing of transformers. It was designed with depthwise separable convolutions for extracting local information and a block-scale and global feature extraction module based on vision transformers (ViTs). While extracting the three scales of features, a satisfiability attention mechanism with a feed-forward network that can control the information was used to keep the network lightweight. Experiments demonstrated that the proposed model surpasses the reconstruction performance of the 498K-parameter SPAN model with a mere 488K parameters. Extensive experiments on commonly used image super-resolution datasets further validated the effectiveness of the network. [ABSTRACT FROM AUTHOR]

Robotically selective broccoli harvesting requires precise lightweight detection models to efficiently detect broccoli heads. Therefore, this study introduces a lightweight and high-precision detection model named LBDC-YOLO (Lightweight Broccoli Detection in Complex Environment—You Look Only Once), based on the improved YOLOv8 (You Look Only Once, Version 8). The model incorporates the Slim-neck design paradigm based on GSConv to reduce computational complexity. Furthermore, Triplet Attention is integrated into the backbone network to capture cross-dimensional interactions between spatial and channel dimensions, enhancing the model's feature extraction capability under multiple interfering factors. The original neck network structure is replaced with a BiFPN (Bidirectional Feature Pyramid Network), optimizing the cross-layer connection structure, and employing weighted fusion methods for better integration of multi-scale features. The model undergoes training and testing on a dataset constructed in real field conditions, featuring broccoli images under various influencing factors. Experimental results demonstrate that LBDC-YOLO achieves an average detection accuracy of 94.44% for broccoli. Compared to the original YOLOv8n, LBDC-YOLO achieves a 32.1% reduction in computational complexity, a 47.8% decrease in parameters, a 44.4% reduction in model size, and a 0.47 percentage point accuracy improvement. When compared to models such as YOLOv5n, YOLOv5s, and YOLOv7-tiny, LBDC-YOLO exhibits higher detection accuracy and lower computational complexity, presenting clear advantages for broccoli detection tasks in complex field environments. The results of this study provide an accurate and lightweight method for the detection of broccoli heads in complex field environments. This work aims to inspire further research in precision agriculture and to advance knowledge in model-assisted agricultural practices. [ABSTRACT FROM AUTHOR]

Lotus leaf diseases and pests have seriously threatened the yield and quality of lotus seeds, such as rhizome rot, leaf spot, virus disease, and Spodoptera litura. The detection of diseased leaves has been the most important measure to prevent and control the lotus leaf diseases and pests. However, manual detection cannot fully meet the large-scale production in recent years, due to the subjective and inefficient experience. It is still lacking in professional knowledge, easily leading to missed or false detection. Therefore, automatic detection can be expected to improve the planting quality in the actual environment of lotus fields. In this study, a lightweight detection model was proposed for the lotus leaf disease and pest using improved YOLOv8. The detection accuracy was improved to reduce the calculation scale for the better deployability of the model. At the same time, a new dataset of lotus leaf disease and pests was established to consider the different environmental conditions. Firstly, the convolution module (Conv) in the YOLOv8 neck network was replaced with GSConv. The C2f module was replaced with the VoV-GSCSP to form a slim-neck architecture, in order to reduce the computational complexity of the model for the high recognition accuracy. The C2f_EMA module was integrated with the EMA efficient multi-scale attention mechanism. The C2f module was then replaced in the backbone network, in order to extract the features of lotus leaf pests and diseases in the complex environments. The experimental results show that the improved YOLOv8 detection model effectively detected the lotus leaf pests and diseases. The mean average precision (mAP) was achieved at 89.3%, which was 1.6% higher than the baseline model; The number of parameters of the model was reduced by 0.2M, compared with the baseline model. The model size was only 5.6 MB. A comparison was performed on several mainstream one-stage target detection models: Faster RCNN, SSD, YOLOv3, YOLOv4, YOLOv5, YOLOv7, YOLOv8, and YOLOv9. The results show that the improved YOLOv8 model shared significant advantages in the detection accuracy, number of parameters, and model size, compared with the rest mainstream models. Finally, the improved YOLOv8 model was deployed on the Jetson Xavier NX and Raspberry Pi 4B edge computing devices, where the frame rates were 27 and 0.7 frames/s, respectively. Compared with the YOLOv5 model, the frame rates increased by 8.9 and 0.3 frames/s, respectively. In terms of actual deployment performance, the improved YOLOv8 model performed better than the classic YOLOv5 model, indicating a better prospect for the mobile terminal deployment. The accurate identification can provide support to the automatic prevention and control of lotus leaf diseases and pests. [ABSTRACT FROM AUTHOR]

Strip steel surface defect detection has become a crucial step in ensuring the quality of strip steel production. To address the issues of low detection accuracy and long detection times in strip steel surface defect detection algorithms caused by varying defect sizes and blurred images during acquisition, this paper proposes a lightweight strip steel surface defect detection network, YOLO-SDS, based on an improved YOLOv8. Firstly, StarNet is utilized to replace the backbone network of YOLOv8, achieving lightweight optimization while maintaining accuracy. Secondly, a lightweight module DWR is introduced into the neck and combined with the C2f feature extraction module to enhance the model's multi-scale feature extraction capability. Finally, an occlusion-aware attention mechanism SEAM is incorporated into the detection head, enabling the model to better capture and process features of occluded objects, thus improving performance in complex scenarios. Experimental results on the open-source NEU-DET dataset show that the improved model reduces parameters by 34.4% compared with the original YOLOv8 algorithm while increasing average detection accuracy by 1.5%. And it shows good generalization performance on the deepPCB dataset. Compared with other defect detection models, YOLO-SDS offers significant advantages in terms of parameter count and detection speed. Additionally, ablation experiments validate the effectiveness of each module. [ABSTRACT FROM AUTHOR]

To enhance the performance of super-resolution models, neural networks frequently employ module stacking. However, this approach inevitably results in an excessive proliferation of parameter counts and information redundancy, ultimately constraining the deployment of these models on mobile devices. To surmount this limitation, this study introduces the application of Dual-path Large Kernel Learning (DLKL) to the task of image super-resolution. Within the DLKL framework, we harness a multiscale large kernel decomposition technique to efficiently establish long-range dependencies among pixels. This network not only maintains excellent performance but also significantly mitigates the parameter burden, achieving an optimal balance between network performance and efficiency. When compared with other prevalent algorithms, DLKL exhibits remarkable proficiency in generating images with sharper textures and structures that are more akin to natural ones. It is particularly noteworthy that on the challenging texture dataset Urban100, the network proposed in this study achieved a significant improvement in Peak Signal-to-Noise Ratio (PSNR) for the ×4 upscaling task, with an increase of 0.32 dB and 0.19 dB compared with the state-of-the-art HAFRN and MICU networks, respectively. This remarkable result not only validates the effectiveness of the present model in complex image super-resolution tasks but also highlights its superior performance and unique advantages in the field. [ABSTRACT FROM AUTHOR]

In this article, the numerical and experimental free vibration analyses of PLA-based composite plates with different filling geometries were carried out. Firstly, the natural frequencies and modal shapes were obtained from finite element (FE) methods to characterize the vibration behavior of the plates. The obtained results were compared with experimental testing of the three-dimensional (3D) produced plates. In the comparison, it was seen that the finite element analysis and the experimental results were quite close to each other. It was also observed that the highest frequencies are measured by a triangle, then the grid and honeycomb. Moreover, higher frequencies and lower weights are possible with the triangle pattern fill. On the other hand, it is noted that the types of filling structures do not affect the modal shapes of the 3D plates. Thus, the results of this paper are of utmost importance for getting light structure and high frequencies. [ABSTRACT FROM AUTHOR]

In the scenario of industrial gas leakage, traditional object detection models face challenges such as high computational complexity, large parameter count, and slow detection speed, making it difficult to deploy them on terminal hardware devices with limited computational resources. Meanwhile, existing lightweight object detection models also encounter difficulties in balancing detection accuracy and real-time requirements. To address this issue, this paper proposes a lightweight object detection algorithm, P-YOLOv7-TFD, based on the YOLOv7-tiny model. Firstly, the YOLOv7-TFD algorithm is constructed, which utilizes FasterNet as the backbone network, reducing the computational complexity and improving feature representation capability through the application of rapid feature fusion and efficient upsampling modules, while maintaining accuracy and enhancing detection speed. Secondly, the network's head layer is reconstructed based on the diverse branch block module to enrich the diversity of feature space, thereby improving model performance without sacrificing inference speed. Finally, the YOLOv7-TFD model is pruned using the Network Slimming channel pruning algorithm to obtain the P-YOLOv7-TFD model, further reducing the model's parameter count. Experimental results show that, compared to the original YOLOv7-tiny model, the average precision of the P-YOLOv7-TFD object detection model decreases by only 1.6% on a self-built dataset, while the parameter count and computational load decrease by 75.7% and 71.8% respectively. The computation inference time is decreased by 88.3%, and the model weight size is only 4.4 MB, representing a reduction of 62.4%. [ABSTRACT FROM AUTHOR]

In engineering practice, deep learning is commonly used for small-sample fault diagnosis of mechanical equipment under heavy noise interference. In recent years, many researchers have used attentional neural operators based on CNNs to extract feature representations from complex data. However, the current attentional neural operator-based fault diagnosis method still has the following limitations: (1) CNN performs poorly in global feature extraction and is unable to capture the global dependencies of long sequential signals. (2) Neural operators have a serious information loss problem in multi-level feature computation, which is unfavorable for processing sensor signals that are long and contain complex noise. To address these problems, we innovatively design an efficient attentional neural operator, and also propose a new lightweight model called CSDANet. Firstly, the spatial interaction between local and global in vibration signals is facilitated by introducing a multi-level convolution and layer scaling strategies; secondly, We designed a feature channel with long-term memory capacity to cope with the adverse effects of information loss on the model; Finally, a vibration signal feature extractor is proposed to obtain richer feature mapping from the original one-dimensional sensor signals, which significantly improves the ability of the attention module to perceive multi-frequency domain noise features while consuming less computational resources. The results of two experiments demonstrate that the proposed approach accommodates advantages of lightweight and robustness in small-sample fault diagnosis tasks, compared to the existing mainstream Transformer and CNN fault diagnosis frameworks. [ABSTRACT FROM AUTHOR]

The civil aviation transportation has sustained rapid growth, which poses significant challenges in ensuring airport safety and efficiency of use. Persons and vehicles are tiny targets in airport surveillance. Existing detection methods are difficult to detect accurately. Enhancing small target detection by only the method of adding enhancement modules inevitably leads to increased network parameters. To address the above issues, this article proposes a lightweight airport surveillance detection based on YOLOv7 named LAS-YOLO. Firstly, we design the lightweight basic module, which significantly reduces network parameters while retaining certain local features. Secondly, we replace the SPPCSPC module with the spatial pyramid pooling-fast module with fewer parameters, further reducing the quantity of network parameters. Finally, the attention mechanism and small object detection layer are introduced to enhance small object detection accuracy. The efficient channel attention module is selected among three attention methods by experiments. We simulate the application process of object detection methods in airport surveillance, training on high-performance computers and testing on lower-performance computer. This article verifies the performance of the proposed method on the public ASS dataset consisting of the airport surface surveillance dataset (ASS1) and panoramic surveillance dataset (ASS2). The experiment shows that the parameters of LAS-YOLO are 12.5 M, which is 34.2 % of the original model. The mean average precision is 89.8 % on the ASS1. This proposed method enhances the average precision for airplane and vehicle detection by 14.5 % and 22.7 % compared to YOLOv7 on the ASS2. In order to reflect the robustness of the model in airport surveillance, we conduct another experiment using airplane data from the ROSD. The experiment demonstrates the superiority of the proposed method over other models in airport surveillance. Code is available at https://zenodo.org/records/10969930. [ABSTRACT FROM AUTHOR]