Search Results (10,883)

Deep learning with unmanned aerial vehicles (UAVs) is transforming maritime search and rescue (SAR) by enabling rapid object identification in challenging marine environments. This study benchmarks the performance of YOLO models for maritime SAR under diverse weather conditions using the SeaDronesSee and AFO datasets. The results show that while YOLOv7 achieved the highest mAP@50, it struggled with detecting small objects. In contrast, YOLOv10 and YOLOv11 deliver faster inference speeds but compromise slightly on precision. The key challenges discussed include environmental variability, sensor limitations, and scarce annotated data, which can be addressed by such techniques as attention modules and multimodal data fusion. Overall, the research results provide practical guidance for deploying efficient deep learning models in SAR, emphasizing specialized datasets and lightweight architectures for edge devices. Full article

Lightweight steel-framing (LSF) systems have become increasingly prominent in modern construction due to their structural efficiency, design flexibility, and sustainability. However, traditional facade materials such as stone are often cost-prohibitive, and brick veneers—despite their popularity—pose seismic performance concerns. This study introduces an innovative porcelain sheathing system for cold-formed steel (CFS) shear walls. Porcelain has no veins thus it offers integrated and reliable strength unlike granite. Four full-scale CFS shear walls incorporating screwed porcelain sheathing (SPS) were tested under combined cyclic lateral and constant gravity loading. The experimental program investigated key seismic characteristics, including lateral stiffness and strength, deformation capacity, failure modes, and energy dissipation, to calculate the system response modification factor (R). The test results showed that configurations with horizontal sheathing, double mid-studs, and three blocking rows improved performance, achieving up to 21.1 kN lateral resistance and 2.5% drift capacity. The average R-factor was 4.2, which exceeds the current design code values (AISI S213: R = 3; AS/NZS 4600: R = 2), suggesting the enhanced seismic resilience of the SPS-CFS system. This study also proposes design improvements to reduce the risk of brittle failure and enhance inelastic behavior. In addition, the results inform discussions on permissible building heights and contribute to the advancement of CFS design codes for seismic regions. Full article

This study aims to enhance the performance of an innovative steel slag–ceramsite foam concrete (SSCFC) to advance sustainable green building materials. An eco-friendly composite construction material was developed by integrating industrial by-product steel slag (SS) with lightweight ceramsite. Employing a three-factor, three-level orthogonal experimental design at a fixed density of 800 kg/m³, 12 mix proportions (including a control group) were investigated with the variables of water-to-cement (W/C) ratio, steel slag replacement ratio, and ceramsite replacement ratio. The governing mechanisms of the W/C ratio, steel slag replacement level, and ceramsite replacement proportion on the SSCFC’s fluidity and compressive strength (CS) were elucidated. The synergistic application of range analysis and analysis of variance (ANOVA) quantified the significance of factors on target properties, and partial least squares regression (PLSR)-based prediction models were established. The test results indicated the following significance hierarchy: steel slag replacement > W/C ratio > ceramsite replacement for fluidity. In contrast, W/C ratio > ceramsite replacement > steel slag replacement governed the compressive strength. Verification showed R² values exceeding 65% for both fluidity and CS predictions versus experimental data, confirming model reliability. Multi-criteria optimization yielded optimal compressive performance and suitable fluidity at a W/C ratio of 0.4, 10% steel slag replacement, and 25% ceramsite replacement. Full article

This article presents VRF-DETR, a lightweight real-time object detection framework for aerial remote sensing images, aimed at addressing the challenge of insufficient receptive fields for easily confused categories due to differences in height and perspective. Based on the RT-DETR architecture, our approach introduces three key innovations: the multi-scale receptive field adaptive fusion (MSRF²) module replaces the Transformer encoder with parallel dilated convolutions and spatial-channel attention to adjust receptive fields for confusing objects dynamically; the gated multi-scale context (GMSC) block reconstructs the backbone using Gated Multi-Scale Context units with attention-gated convolution (AGConv), reducing parameters while enhancing multi-scale feature extraction; and the context-guided fusion (CGF) module optimizes feature fusion via context-guided weighting to resolve multi-scale semantic conflicts. Evaluations were conducted on both the VisDrone2019 and UAVDT datasets, where VRF-DETR achieved the mAP₅₀ of 52.1% and the mAP_50-95 of 32.2% on the VisDrone2019 validation set, surpassing RT-DETR by 4.9% and 3.5%, respectively, while reducing parameters by 32% and FLOPs by 22%. It maintains real-time performance (62.1 FPS) and generalizes effectively, outperforming state-of-the-art methods in accuracy-efficiency trade-offs for aerial object detection. Full article

Timely and accurate identification of surface damage in hydraulic structures is essential for maintaining structural integrity and ensuring operational safety. Traditional manual inspections are time-consuming, labor-intensive, and prone to subjectivity, especially for large-scale or inaccessible infrastructure. Leveraging advancements in aerial imaging, unmanned aerial vehicles (UAVs) enable efficient acquisition of high-resolution visual data across expansive hydraulic environments. However, existing deep learning (DL) models often lack architectural adaptations for the visual complexities of UAV imagery, including low-texture contrast, noise interference, and irregular crack patterns. To address these challenges, this study proposes a lightweight, robust, and high-precision segmentation framework, called LFPA-EAM-Fast-SCNN, specifically designed for pixel-level damage detection in UAV-captured images of hydraulic concrete surfaces. The developed DL-based model integrates an enhanced Fast-SCNN backbone for efficient feature extraction, a Lightweight Feature Pyramid Attention (LFPA) module for multi-scale context enhancement, and an Edge Attention Module (EAM) for refined boundary localization. The experimental results on a custom UAV-based dataset show that the proposed damage detection method achieves superior performance, with a precision of 0.949, a recall of 0.892, an F1 score of 0.906, and an IoU of 87.92%, outperforming U-Net, Attention U-Net, SegNet, DeepLab v3+, I-ST-UNet, and SegFormer. Additionally, it reaches a real-time inference speed of 56.31 FPS, significantly surpassing other models. The experimental results demonstrate the proposed framework’s strong generalization capability and robustness under varying noise levels and damage scenarios, underscoring its suitability for scalable, automated surface damage assessment in UAV-based remote sensing of civil infrastructure. Full article

Atmospheric and oceanic turbulence can severely degrade the orbital angular momentum (OAM) mode purity of vortex beams in cross-media optical links. Here, we propose a hybrid correction framework that fuses multiscale phase-screen modeling with a lightweight U-Net predictor for phase-distortion—driven solely by measured optical intensity—and augments it with a feed-forward, Gaussian-reference subtraction scheme for iterative compensation. In our experiments, this approach boosts the l = 3 mode purity from 38.4% to 98.1%. Compared to the Gerchberg–Saxton algorithm, the Gaussian-reference feed-forward method achieves far lower computational complexity and greater robustness, making real-time phase recovery feasible for OAM-based communications over heterogeneous channels. Full article

In engineering design, optimization is crucial for achieving sustainable goals. This involves creating environmentally responsible structures. Optimizing the design is the first step in reducing the environmental impact of construction. Topology optimization (TO) is one way to do this. TO is the process of designing the material layout in the design domain according to selected criteria. The criteria can be explicitly defined to promote sustainability. As a result, a new structure topology is proposed to make the structure both lightweight and durable, with the aim of improving its functionality and reducing its environmental impact. In optimal engineering design, it is particularly important to take into account the structure’s special operating conditions, e.g., loads subject to random changes. Predicting topologies under such conditions is important since random load changes can significantly affect the resulting topologies. In this paper, an easy to implement numerical method for this kind of problem is proposed. The basic idea is to transform a random loads case into the deterministic problem of multiple loads. A heuristic method of Cellular Automata is proposed as a numerical optimization tool. The examples of topology optimization have been performed to illustrate the concept, confirming the efficiency, versatility, and ease of its implementation. Full article

Work-related musculoskeletal disorders (WMSDs) are a leading concern in industrial ergonomics, often stemming from sustained non-neutral postures and repetitive tasks. This paper presents a vision-based framework for real-time, frame-level ergonomic risk classification using a lightweight Vision Transformer (ViT). The proposed system operates directly on raw RGB images without requiring skeleton reconstruction, joint angle estimation, or image segmentation. A single ViT model simultaneously classifies eight anatomical regions, enabling efficient multi-label posture assessment. Training is supervised using a multimodal dataset acquired from synchronized RGB video and full-body inertial motion capture, with ergonomic risk labels derived from RULA scores computed on joint kinematics. The system is validated on realistic, simulated industrial tasks that include common challenges such as occlusion and posture variability. Experimental results show that the ViT model achieves state-of-the-art performance, with F1-scores exceeding 0.99 and AUC values above 0.996 across all regions. Compared to previous CNN-based system, the proposed model improves classification accuracy and generalizability while reducing complexity and enabling real-time inference on edge devices. These findings demonstrate the model’s potential for unobtrusive, scalable ergonomic risk monitoring in real-world manufacturing environments. Full article

Increased food production demands, labor shortages, and environmental concerns are driving the need for innovative agricultural technologies. However, effective adoption depends critically on aligning robot innovations with the needs of farmers. This paper examines the alignment between the needs of farmers and the robotic systems used in row crop farming. We review current commercial agricultural robots and research, and map these to the needs of farmers, as expressed in the literature, to identify the key issues holding back large-scale adoption. From initial pool of 184 research articles, 19 survey articles, and 82 commercial robotic solutions, we selected 38 peer-reviewed academic studies, 12 survey articles, and 18 commercially available robots for in-depth review and analysis for this study. We identify the key challenges faced by farmers and map them directly to the current and emerging capabilities of agricultural robots. We supplement the data gathered from the literature review of surveys and case studies with in-depth interviews with nine farmers to obtain deeper insights into the needs and day-to-day operations. Farmers reported mixed reactions to current technologies, acknowledging efficiency improvements but highlighting barriers such as capital costs, technical complexity, and inadequate support systems. There is a notable demand for technologies for improved plant health monitoring, soil condition assessment, and enhanced climate resilience. We then review state-of-the-art robotic solutions for row crop farming and map these technological capabilities to the farmers’ needs. Only technologies with field validation or operational deployment are included, to ensure practical relevance. These mappings generate insights that underscore the need for lightweight and modular robot technologies that can be adapted to diverse farming practices, as well as the need for farmers’ education and simpler interfaces to robotic operations and data analysis that are actionable for farmers. We conclude with recommendations for future research, emphasizing the importance of co-creation with the farming community to ensure the adoption and sustained use of agricultural robotic solutions. Full article

Synthetic aperture radar (SAR), as an active microwave imaging system, has the capability of all-weather and all-time observation. In response to the challenges of aircraft detection in SAR images due to the complex background interference caused by the continuous scattering of airport buildings and the demand for real-time processing, this paper proposes a YOLOv7-MTI recognition model that combines the attention mechanism and involution. By integrating the MTCN module and involution, performance is enhanced. The Multi-TASP-Conv network (MTCN) module aims to effectively extract low-level semantic and spatial information using a shared lightweight attention gate structure to achieve cross-dimensional interaction between “channels and space” with very few parameters, capturing the dependencies among multiple dimensions and improving feature representation ability. Involution helps the model adaptively adjust the weights of spatial positions through dynamic parameterized convolution kernels, strengthening the discrete strong scattering points specific to aircraft and suppressing the continuous scattering of the background, thereby alleviating the interference of complex backgrounds. Experiments on the SAR-AIRcraft-1.0 dataset, which includes seven categories such as A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and others, show that the mAP and mRecall of YOLOv7-MTI reach 93.51% and 96.45%, respectively, outperforming Faster R-CNN, SSD, YOLOv5, YOLOv7, and YOLOv8. Compared with the basic YOLOv7, mAP is improved by 1.47%, mRecall by 1.64%, and FPS by 8.27%, achieving an effective balance between accuracy and speed, providing research ideas for SAR aircraft recognition. Full article

We introduce I-fp convergence (ideal convergence in fuzzy paranormed spaces) and develop its core theory, including stability results and an equivalence to $I^{*}$-fp convergence under the AP Property. Building on this foundation, we design an adaptive base-stock policy for a single-echelon inventory system in which weekly demand is expressed as triangular fuzzy numbers while holiday or promotion weeks are treated as ideal-small anomalies. The policy is updated by a simple learning rule that can be implemented in any spreadsheet, requires no optimisation software, and remains insensitive to tuning choices. Extensive simulation confirms that the method simultaneously lowers cost, reduces average inventory and raises service level relative to a crisp benchmark, all while filtering sparse demand spikes in a principled way. These findings position I-fp convergence as a lightweight yet rigorous tool for blending linguistic uncertainty with anomaly-aware decision making in supply-chain analytics. Full article

In manufacturing environments, the proper use of Personal Protective Equipment (PPE) is essential to prevent workplace accidents. Despite this need, existing PPE monitoring methods remain largely manual and suffer from limited coverage, significant errors, and inefficiencies. This article focuses on addressing this deficiency by designing a computer vision desktop application for automated monitoring of PPE use. This system uses lightweight YOLOv8 models, developed to run on the local system and operate even in industrial locations with limited network connectivity. Using a Lean UX approach, the development of the system involved creating empathy maps, assumptions, product backlog, followed by high-fidelity prototype interface components. C4 and physical diagrams helped define the system architecture to facilitate modifiability, scalability, and maintainability. Usability was verified using the System Usability Scale (SUS), with a score of 87.6/100 indicating “excellent” usability. The findings demonstrate that a user-centered design approach, considering user experience and technical flexibility, can significantly advance the utility and adoption of AI-based safety tools, especially in small- and medium-sized manufacturing operations. This article delivers a validated and user-centered design solution for implementing machine vision systems into manufacturing safety processes, simplifying the complexities of utilizing advanced AI technologies and their practical application in resource-limited environments. Full article

To address the problems of traditional methods that rely on destructive sampling, the poor adaptability of fixed equipment, and the susceptibility of single-view angle measurements to occlusions, a non-destructive and portable device for three-dimensional phenotyping and biomass detection in lettuce was developed. Based on the Structure-from-Motion Multi-View Stereo (SFM-MVS) algorithms, a high-precision three-dimensional point cloud model was reconstructed from multi-view RGB image sequences, and 12 phenotypic parameters, such as plant height, crown width, were accurately extracted. Through regression analyses of plant height, crown width, and crown height, and the R² values were 0.98, 0.99, and 0.99, respectively, the RMSE values were 2.26 mm, 1.74 mm, and 1.69 mm, respectively. On this basis, four biomass prediction models were developed using Adaptive Boosting (AdaBoost), Support Vector Regression (SVR), Gradient Boosting Decision Tree (GBDT), and Random Forest Regression (RFR). The results indicated that the RFR model based on the projected convex hull area, point cloud convex hull surface area, and projected convex hull perimeter performed the best, with an R² of 0.90, an RMSE of 2.63 g, and an RMSEn of 9.53%, indicating that the RFR was able to accurately simulate lettuce biomass. This research achieves three-dimensional reconstruction and accurate biomass prediction of facility lettuce, and provides a portable and lightweight solution for facility crop growth detection. Full article

Multimodal object detection leverages the complementary characteristics of visible (RGB) and infrared (IR) imagery, making it well-suited for challenging scenarios such as low illumination, occlusion, and complex backgrounds. However, most existing fusion-based methods rely on static or heuristic strategies, limiting their adaptability to dynamic environments. To address this limitation, we propose CLSANet, a cognitive learning-based self-adaptive network that enhances detection performance by dynamically selecting and integrating modality-specific features. CLSANet consists of three key modules: (1) a Dominant Modality Identification Module that selects the most informative modality based on global scene analysis; (2) a Modality Enhancement Module that disentangles and strengthens shared and modality-specific representations; and (3) a Self-Adaptive Fusion Module that adjusts fusion weights spatially according to local scene complexity. Compared to existing methods, CLSANet achieves state-of-the-art detection performance with significantly fewer parameters and lower computational cost. Ablation studies further demonstrate the individual effectiveness of each module under different environmental conditions, particularly in low-light and occluded scenes. CLSANet offers a compact, interpretable, and practical solution for multimodal object detection in resource-constrained settings. Full article

In marine engineering applications, substituting conventional crushed stone coarse aggregates with coral aggregates offers dual advantages: reduced terrestrial quarrying operations and minimized construction material transportation costs. However, the inherent characteristics of coral aggregates—low bulk density, high porosity, and elevated water absorption capacity—adversely influence concrete workability and mechanical performance. To address these limitations, this investigation employed microbial-induced carbonate precipitation (MICP) for aggregate modification. The experimental design systematically evaluated the impacts of substrate concentration (1 mol/L) and mineralization period (14 days) on three critical parameters, mass gain percentage, water absorption reduction, and apparent density enhancement, across distinct particle size fractions (4.75–9.5 mm, 9.5–20 mm) and density classifications. Subsequent application trials assessed the performance of MICP-treated aggregates in marine concrete formulations. Results indicated that under a substrate concentration of 1 mol/L and mineralization period of 14 days, lightweight coral aggregates and coral aggregates within the 4.75–9.5 mm size fraction exhibited favorable modification effects. Specifically, their mass gain rates reached 11.75% and 11.22%, respectively, while their water absorption rates decreased by 32.22% and 34.75%, respectively. Apparent density increased from initial values of 1764 kg/m³ and 1930 kg/m³ to 2050 kg/m³ and 2207 kg/m³. Concrete mixtures incorporating modified aggregates exhibited enhanced workability and strength improvement at all curing ages. The 28-day compressive strengths reached 62.1 MPa (11.69% increment), 46.2 MPa (6.94% increment), and 60.1 MPa (14.91% increment) for the 4.75–9.5 mm, 9.5–20 mm, and continuous grading groups, respectively, compared to untreated counterparts. Full article