Search Results (783)

Modern battlefield operations require wearable technologies to operate reliably under harsh physical, environmental, and security conditions. This review looks at today and tomorrow’s potential for ready field-grade wearables embedded with biometric authentication systems. It details physiological, kinematic, and multimodal sensor platforms built to withstand rugged, high-stress environments, and reviews biometric modalities like ECG, PPG, EEG, gait, and voice for continuous or on-demand identity confirmation. Accuracy, latency, energy efficiency, and tolerance to motion artifacts, environmental extremes, and physiological variability are critical performance drivers. Security threats, such as spoofing and data tapping, and techniques for template protection, liveness assurance, and protected on-device processing also come under review. Emerging trends in low-power edge AI, multimodal integration, adaptive learning from field experience, and privacy-preserving analytics in terms of defense readiness, and ongoing challenges, such as gear interoperability, long-term stability of templates, and common stress-testing protocols, are assessed. In conclusion, an R&D plan to lead the development of rugged, trustworthy, and operationally validated wearable authentication systems for the current and future militaries is proposed. Full article

Weed detection algorithms based on deep learning are considered crucial for smart agriculture, with the YOLO series algorithms being widely adopted due to their efficiency. However, existing YOLO algorithms struggle to maintain high accuracy, while low parameter requirements and computational efficiency are achieved when weeds with occlusion or overlap are detected. To address this challenge, a target detection algorithm called SSS-YOLO based on YOLOv9t is proposed in this paper. First, the SCB (Spatial Channel Conv Block) module is introduced, in which large kernel convolution is employed to capture long-range dependencies, occluded weed regions are bypassed by being associated with unobstructed areas, and features of unobstructed regions are enhanced through inter-channel relationships. Second, the SPPF EGAS (Spatial Pyramid Pooling Fast Edge Gaussian Aggregation Super) module is proposed, where multi-scale max pooling is utilized to extract hierarchical contextual features, large receptive fields are leveraged to acquire background information around occluded objects, and features of weed regions obscured by crops are inferred. Finally, the EMSN (Efficient Multi-Scale Spatial-Feedforward Network) module is developed, through which semantic information of occluded regions is reconstructed by contextual reasoning and background vegetation interference is effectively suppressed while visible regional details are preserved. To validate the performance of this method, experiments are conducted on both our self-built dataset and the publicly available Cotton WeedDet12 dataset. The results demonstrate that compared to existing algorithms, significant performance improvements are achieved by the proposed method. Full article

Compared to reinforcing concrete with steel bars, rebars—made of fiber-reinforced plastic—have a high potential for resource savings in the construction industry due to their corrosion resistance. For the large-volume market of reinforcement elements, efficient manufacturing processes must be developed to ensure the best possible bond behavior between concrete and rebar. In contrast to established FRP-rebars made with thermosetting materials, the use of a thermoplastic matrix enables surface profiling without severing the edge fibers as well as subsequent bending of the bar. The rebars to be produced in this study are based on the process of reactive thermoplastic pultrusion of continuously glass fiber reinforced aPA6. Their surface must enable a mechanical interlocking between the reinforcement bar and concrete. Concepts for a profiling device have been methodically developed and evaluated. The resulting concept of a double wheel embossing unit with a variable infeed and an infrared preheating section is built as a prototype, implemented in a pultrusion line, and further optimized. For a comprehensive understanding of the embossing process, reinforcement bars are manufactured, characterized, and evaluated under parameter variation according to a statistical experimental plan. The present study demonstrates the relationship between the infeed, preheating temperature, and haul-off speed with respect to the embossing depth, which is equivalent to the rib height. No degradation of the Young’s modulus was observed as a result of the profiling process. Full article

The ecological network serves as a vital spatial strategy for addressing climate change, biodiversity loss, and habitat fragmentation. Addressing limitations in existing ecological network studies—such as strong subjectivity and insufficient accuracy in structural element identification, cross-regional integration, and resistance surface weighting—this research uses the Zhengzhou–Kaifeng–Luoyang region (ZKLR) as a case study. It introduces the self-organizing map (SOM) model to identify ecological sources and employs the XGBoost-SHAP model to optimize resistance surface weights, thereby reducing subjective weighting biases. Subsequently, the Linkage Mapper tool is utilized to construct the regional ecological network. The superiority of the SOM model for identifying ecological sources was confirmed by comparison with a traditional network based on morphological spatial pattern analysis (MSPA). Further integrating complex network topology theory, nodes attack the simulations-assessed network resilience and proposed optimization strategies. The results indicate the following: (1) The area of ecological sources identified by the SOM model is three times that of the MSPA model; (2) SHAP feature importance analysis revealed that elevation (DEM) exerted the greatest influence on the composite resistance surface, contributing over 40%, followed by land use and slope, with each contributing approximately 15%. High-resistance areas were primarily distributed in western and central mountainous regions and built-up urban areas, while low-resistance areas were concentrated in the central and eastern plains; (3) topological analysis indicates that the integrated ecological network (IEN) exhibits superior robustness compared to the structural ecological network (SEN). The edge-adding strategy generated 22 additional ecological corridors, significantly enhancing the overall resilience of the integrated ecological network; and (4) based on ecological network construction and optimization results, a territorial spatial protection strategy of “one belt, two cores, two zones, and three corridors” is proposed. This study provides a novel methodological framework for ecological network construction, with findings offering reference for ecological conservation and spatial planning in the ZKLR and similar areas. Full article

The piston pin operates under severe mechanical and thermal conditions, making accurate lubrication prediction essential for engine durability. This study presents a comprehensive digital engineering framework for piston pin bearings, built upon a fully coupled thermo-elasto-hydrodynamic (TEHD) formulation. The framework integrates: (1) a Reynolds-equation hydrodynamic solver with temperature-/pressure-dependent viscosity and cavitation; (2) elastic deformation obtained from FEA (finite element analysis)-based compliance matrices; (3) a break-in module that iteratively adjusts surface profiles before steady-state simulation; (4) a three-body heat transfer model resolving heat conduction, convection, and solid–liquid interfacial heat exchange. Applied to a heavy-duty diesel engine, the framework reproduces experimentally observed behaviors, including bottom-edge rounding at the small end and the slow unidirectional drift of the floating pin. By integrating multi-physics modeling with design-level flexibility, this work aims to provide a robust digital twin for the piston-pin system, enabling virtual diagnostics, early-stage failure prediction, and data-driven design optimization for engine development. Full article

Pediatric pneumonia detection faces the challenge of pathological asymmetry, where immature lung tissues present blurred boundaries and lesions exhibit extreme scale variations (e.g., small viral nodules vs. large bacterial consolidations). Conventional detectors often fail to address these imbalances. In this study, we propose YOLO-SMD, a detection framework built upon a symmetrical design philosophy to enforce balanced feature representation. We introduce three architectural innovations: (1) DySample (Content-Aware Upsampling): To address the blurred boundaries of pediatric lesions, this module replaces static interpolation with dynamic point sampling, effectively sharpening edge details that are typically smoothed out by standard upsamplers; (2) SAC2f (Cross-Dimensional Attention): To counteract background interference, this module enforces a symmetrical interaction between spatial and channel dimensions, allowing the model to suppress structural noise (e.g., rib overlaps) in low-contrast X-rays; (3) SDFM (Adaptive Gated Fusion): To resolve the extreme scale disparity, this unit employs a gated mechanism that symmetrically balances deep semantic features (crucial for large bacterial shapes) and shallow textural features (crucial for viral textures). Extensive experiments on a curated subset of 2611 images derived from the Chest X-ray Pneumonia Dataset demonstrate that YOLO-SMD achieves competitive performance with a focus on high sensitivity, attaining a Recall of 86.1% and an mAP@0.5 of 84.3%, thereby outperforming the state-of-the-art YOLOv12n by 2.4% in Recall under identical experimental conditions. The results validate that incorporating symmetry principles into feature modulation significantly enhances detection robustness in primary healthcare settings. Full article

Face super-resolution (FSR) has made great progress thanks to deep learning and facial priors. However, many existing methods do not fully exploit landmark heatmaps and lack effective multi-scale texture modeling, which often leads to texture loss and artifacts under large upscaling factors. To address these problems, we propose a Multi-Scale Residual Stacking Network (MRSNet), which integrates multi-scale texture enhancement with multi-stage heatmap fusion. The MRSNet is built upon Residual Attention-Guided Units (RAGUs) and incorporates a Face Detail Enhancer (FDE), which applies edge, texture, and region branches to achieve differentiated enhancement across facial components. Furthermore, we design a Multi-Scale Texture Enhancement Module (MTEM) that employs progressive average pooling to construct hierarchical receptive fields and employs heatmap-guided attention for adaptive texture refinement. In addition, we introduce a multi-stage heatmap fusion strategy that injects landmark priors into multiple phases of the network, including feature extraction, texture enhancement, and detail reconstruction, enabling deep sharing and progressive integration of prior knowledge. Extensive experiments on CelebA and Helen demonstrate that the proposed method achieves superior detail recovery and generates perceptually realistic high-resolution face images. Both quantitative and qualitative evaluations confirm that our approach outperforms state-of-the-art methods. Full article

This study addresses the challenges of early recognition of fruit and vegetable diseases and pests in facility horticultural greenhouses and the difficulty of real-time deployment on edge devices, and proposes a lightweight cross-scale intelligent recognition network, Light-HortiNet, designed to achieve a balance between high accuracy and high efficiency for automated greenhouse pest and disease detection. The method is built upon a lightweight Mobile-Transformer backbone and integrates a cross-scale lightweight attention mechanism, a small-object enhancement branch, and an alternative block distillation strategy, thereby effectively improving robustness and stability under complex illumination, high-humidity environments, and small-scale target scenarios. Systematic experimental evaluations were conducted on a greenhouse pest and disease dataset covering crops such as tomato, cucumber, strawberry, and pepper. The results demonstrate significant advantages in detection performance, with mAP@50 reaching $0.872$, mAP@50:95 reaching $0.561$, classification accuracy reaching $0.894$, precision reaching $0.886$, recall reaching $0.879$, and F1-score reaching $0.882$, substantially outperforming mainstream lightweight models such as YOLOv8n, YOLOv11n, MobileNetV3, and Tiny-DETR. In terms of small-object recognition capability, the model achieved an mAP-small of $0.536$ and a recall-small of $0.589$, markedly enhancing detection stability for micro pests such as whiteflies and thrips as well as early-stage disease lesions. In addition, real-time inference performance exceeding 20 FPS was achieved on edge platforms such as Jetson Nano, demonstrating favorable deployment adaptability. Full article

The intersection of edge computing, Large Language Models (LLMs), and the Transformer architecture is a very active and fascinating area of research. The core tension is that LLMs, which are built on the Transformer architecture, are massive and computationally intensive, while edge devices are resource-constrained in terms of power, memory, and processing capabilities. Therefore, LLMs based on the Transformer architecture are inherently unsuitable for edge computing in their original, full-sized form. They were designed for powerful, resource-rich cloud data centers. However, there is a massive and growing effort to make them suitable for edge devices. Implementing Transformer-based LLMs on edge computing devices is a complex but crucial task that requires a multi-faceted strategy. This paper reviews LLM deployment strategies for Transformer models on edge computing devices, examines the challenges, and estimates future directions. To address these challenges, researchers are exploring methods to compress LLMs and optimize their inference capabilities, making them more efficient for edge environments. Recent advancements in compact LLMs have shown promise in enhancing their deployment on edge devices, enabling improved performance while addressing the limitations of traditional models. This approach not only reduces computational costs but also enhances user privacy and security. Full article

To address the high incidence of work-related musculoskeletal disorders (WMSDs) at manual edge-banding workstations in furniture factories, and in an effort to tackle the existing research challenges of poor cumulative risk quantification and inconsistent evaluations, this paper proposes a three-stage system for continuous, automated, non-invasive WMSD risk monitoring. First, MediaPipe 0.10.11 is used to extract 33 key joint coordinates, compute seven types of joint angles, and resolve missing joint data, ensuring biomechanical data integrity for subsequent analysis. Second, joint angles are converted into graded parameters via RULA, REBA, and OWAS criteria, enabling automatic calculation of posture risk scores and grades. Third, an Adaptive Pooling Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) dual-branch hybrid model based on the Efficient Channel Attention (ECA) mechanism is built, which takes nine-dimensional features as the input to predict expert-rated fatigue states. For validation, 32 experienced female workers performed manual edge-banding tasks, with smartphones capturing videos of the eight work steps to ensure authentic and representative data. The results show the following findings: (1) system ratings strongly correlate with expert evaluations, verifying its validity for posture risk assessment; (2) the hybrid model successfully captures the complex mapping of expert-derived fatigue patterns, outperforming standalone CNN and LSTM models in fatigue prediction—by integrating CNN-based spatial feature extraction and LSTM-based temporal analysis—and accurately maps fatigue indexes while generating intervention recommendations. This study addresses the limitations of traditional manual evaluations (e.g., subjectivity, poor temporal resolution, and inability to capture cumulative risk), providing an engineered solution for WMSD prevention at these workstations and serving as a technical reference for occupational health management in labor-intensive industries. Full article

With the growing deployment of Flying Ad hoc Networks (FANETs) in military and civilian applications, constructing a stable and efficient communication backbone has become a critical challenge. This paper tackles the Cluster Head (CH) optimization problem in large-scale and highly dynamic FANETs by formulating it as a Minimum Connected Dominating Set (MCDS) problem. However, since MCDS is NP-complete on general graphs, existing heuristic and exact algorithms suffer from limited coverage, poor connectivity, and high computational cost. To address these issues, we propose TGN-MCDS, a novel algorithm built upon the Temporal Graph Network (TGN) architecture, which leverages graph neural networks for cluster head selection and efficiently learns time-varying network topologies. The algorithm adopts a multi-objective loss function incorporating coverage, connectivity, size control, centrality, edge penalty, temporal smoothness, and information entropy to guide model training. Simulation results demonstrate that TGN-MCDS rapidly achieves near-optimal CH sets with full node coverage and strong connectivity. Compared with Greedy, Integer Linear Programming (ILP), and Branch-and-Bound (BnB) methods, TGN-MCDS produces fewer and more stable CHs, significantly improving cluster stability while maintaining high computational efficiency for real-time operations in large-scale FANETs. Full article

To investigate the in situ irradiation effects of gallium nitride at varying temperatures, we combined ion beam-induced luminescence spectroscopy with variable-temperature irradiation using a home-built IBIL system and a GIC4117 2 × 1.7 MV tandem accelerator. Unlike previous static studies—limited to post-irradiation or single-temperature luminescence—we in situ tracked dynamic luminescence changes throughout irradiation, directly capturing the real-time responses of luminescent centers to coupled temperature-dose variations—a rare capability in prior work. To clarify how irradiation and temperature affect the luminescent centers of GaN, we integrated density functional theory (DFT) calculations with literature analysis, then resolved the yellow luminescence band into three emission centers via Gaussian deconvolution: 1.78 eV associated with C/O impurities, 1.94 eV linked to VGa, and 2.2 eV corresponding to CN defects. Using a single-exponential decay model, we further quantified the temperature- and dose-dependent decay rates of these centers under dual-variable temperature and dose conditions. Experimental results show that low-temperature irradiation such as at 100 K suppresses the migration and recombination of V_Ga/C_N point defects, significantly enhancing the radiation tolerance of the 1.94 eV and 2.2 eV emission centers; meanwhile, it reduces non-radiative recombination center density, stabilizing free excitons and donor-bound excitons, thereby improving near-band-edge emission center resistance. Notably, the 1.94 eV emission center linked to gallium vacancies exhibits superior cryogenic radiation tolerance due to slower defect migration and more stable free exciton/donor-bound exciton states. Collectively, these findings reveal a synergistic regulation mechanism of temperature and radiation fluence on defect stability, addressing a key gap in static studies, providing a basis for understanding degradation mechanisms of gallium nitride-based devices under actual operating conditions (coexisting temperature fluctuations and continuous radiation), and offering theoretical/experimental support for optimizing radiation-hardened gallium nitride devices for extreme environments such as space or nuclear applications. Full article

This study investigates performance overheads and security threats in 6th Generation Mobile Communication (6G) roaming environments, which are expected to enable services such as autonomous driving, smart cities, and remote healthcare that demand ultra-low latency and high reliability. To bridge the gap between standardization and real-world deployment, we built a realistic roaming testbed by separating the home and visited public land mobile networks (H-PLMN and V-PLMN) and simulating user equipment (UE) interactions. In this environment, we defined and measured roaming cost by comparing non-roaming and roaming procedures, and reproduced two Subscription Concealed Identifier (SUCI)-based denial-of-service (DoS) attacks: random generation and replay. Our experiments showed that intermediary functions such as the Security Edge Protection Proxy (SEPP) and Service Communication Proxy (SCP) introduced CPU/memory overhead and latency, highlighting performance degradation unique to roaming. Moreover, random SUCI generation concentrated load on the Authentication Server Function (AUSF) in the H-PLMN, whereas replay attacks distributed it across both the H-PLMN and the V-PLMN, consistently identifying the AUSF as a bottleneck. These findings demonstrate that roaming enlarges the attack surface and exposes vulnerabilities not fully addressed in current standards. We conclude that secure and reliable 6G roaming requires multi-layered defense strategies with inter-operator cooperation, providing empirical evidence to guide standardization and operational practice. Full article

For UAVs, the industry currently relies on expensive sensors for obstacle avoidance. A significant challenge arises from the scarcity of high-quality depth estimation datasets tailored for low-altitude environments, which hinders the advancement of self-supervised learning methods in these settings. Furthermore, mainstream depth estimation models capable of achieving obstacle avoidance through image recognition are built upon convolutional neural networks or hybrid Transformers. Their high computational costs make deployment on resource-constrained edge devices challenging. While existing lightweight convolutional networks reduce parameter counts, they struggle to simultaneously capture essential features and fine details in complex scenes. In this work, we introduce LFP-Mono as a lightweight self-supervised monocular depth estimation network. In the paper, we will detail the Pooling Convolution Downsampling (PCD) module, Continuously Dilated and Weighted Convolution (CDWC) module, and Cross-level Feature Integration (CFI) module. All results show that LFP-Mono outperforms existing lightweight methods on the KITTI benchmark, and by evaluating with the Make3D dataset, show that our method generalizes outdoors. Finally, by training and testing on the Syndrone dataset, baseline work shows that LFP-Mono exceeds state-of-the-art methods for low-altitude drone performance. Full article

Low-altitude Unmanned Aerial Vehicle (UAV) detection using LiDAR range images faces persistent challenges. These include sparse features for long-range targets, large scale variations caused by viewpoint changes, and severe interference from complex backgrounds. To address these issues, we propose an improved detection framework based on YOLOv10. First, we design a Swin-Conv hybrid module that combines sparse attention with deformable convolution. This module enables the network to focus on informative regions and adapt to target geometry. These capabilities jointly strengthen feature extraction for sparse, long-range targets. Second, we introduce Attentional Feature Fusion (AFF) in the neck to replace naïve feature concatenation. AFF employs multi-scale channel attention to softly select and adaptively weight features from different levels, improving robustness to multi-scale targets. In addition, we systematically study how the viewpoint distribution in the training set affects performance. The results show that moderately increasing the proportion of low-elevation-view samples significantly improves detection accuracy. Experiments on a self-built simulated LiDAR range-image dataset demonstrate that our method achieves 88.96% mAP at 54.2 FPS, which is 4.78 percentage points higher than the baseline. Deployment on the Jetson Orin Nano edge device further validates the model’s potential for real-time applications. The proposed method remains robust under noise and complex backgrounds. The proposed approach achieves an effective balance between detection accuracy and computational efficiency, providing a reliable solution for real-time target detection in complex low-altitude environments. Full article