Search Results (2,410)

High-Performance Computing (HPC) has become essential for training medium- and large-scale Artificial Intelligence (AI) models, yet two bottlenecks remain under-exploited: the semantic coherence of training data and the interaction between distributed deep learning runtimes and heterogeneous HPC architectures. Existing work tends to optimise multi-node, multi-GPU training in isolation from data semantics or to apply semantic technologies to data curation without considering the constraints of large-scale training on modern clusters. This paper introduces SemanticHPC, an experimental framework that integrates ontology and Resource Description Framework (RDF)-based semantic preprocessing with distributed AI training (Horovod/PyTorch Distributed Data Parallel) and hardware-aware optimisations for Non-Uniform Memory Access (NUMA), multi-GPU and high-speed interconnects. The framework has been evaluated on 1–8 node configurations (4–32 GPUs) on a production-grade cluster. Experiments on a medium-size Open Images V7 workload show that semantic enrichment improves validation accuracy by 3.5–4.4 absolute percentage points while keeping the additional end-to-end overhead below 8% and preserving strong scaling efficiency above 79% on eight nodes. We argue that bringing semantic technologies into the training workflow—rather than treating them as an offline, detached phase—is a promising direction for large-scale AI on HPC systems. We detail an implementation based on standard Python libraries, RDF tooling and widely adopted deep learning runtimes, and we discuss the limitations and practical hurdles that need to be addressed for broader adoption. Full article

Accurate estimation of internal temperature is essential for safe operation and state estimation of lithium-ion batteries, yet it usually cannot be measured directly and requires physically grounded electro-thermal models. High fidelity 3D simulations capture geometry-dependent heat transfer behavior but are too computationally intensive for real-time use, whereas common lumped models cannot represent internal gradients. This work presents an integrated geometry-resolved workflow that combines detailed 3D finite volume thermal modeling with systematic reduction to a compact multi-node thermal network and its coupling with an equivalent circuit electrical model. A realistic 3D model of the Panasonic NCR18650B cell was reconstructed from computed tomography data and literature parameters and validated against published axial and radial thermal conductivity measurements. The automated reduction yields a five-node thermal network preserving radial temperature distribution, which was coupled with five parallel Battery Table-Based blocks in MATLAB/Simulink R2024b to capture spatially distributed heat generation. Experimental validation under dynamic loading is performed using measured surface temperature and terminal voltage, showing strong agreement (surface temperature MAE ≈ 0.43 °C, terminal voltage MAE ≈ 16 mV). The resulting model enables physically informed estimation of internal thermal behavior, is interpretable, computationally efficient, and suitable for digital twin development. Full article

In this paper, we present a novel method for background estimation and updating in video sequences, utilizing an innovative approach that combines an intelligent truncated mean, the stationary wavelet transform (SWT), and advanced thresholding techniques. This method aims to significantly enhance the accuracy of moving object detection by mitigating the impact of outliers and adapting background estimation to dynamic scene conditions. The proposed approach begins with a robust initial background estimation, followed by moving object detection through frame subtraction and gamma correction. Segmentation is then performed using SWT, coupled with adaptive thresholding methods, including hard and soft thresholding. These techniques work in tandem to effectively reduce noise while preserving critical details. Finally, the background is selectively updated to integrate new information from static regions while excluding moving objects, ensuring a precise and robust detection system. Experimental evaluation on the CDnet 2014 and SBI 2015 datasets demonstrates that the proposed method improves the F1 score by 12.5 percentage points (from 0.7511 to 0.8765), reduces false positives by up to 65%, and achieves higher PSNR values compared to GMM_Zivk, SuBSENSE, and SC_SOBS. These results confirm the robustness of the hybrid approach based on truncated mean and SWT in dynamic and challenging environments. Full article

The authentication of wood species is of paramount significance to market regulation and product quality control in the construction industry. While classification based on microscopic wood cell structures serves as a critical reference for this task, the high inter-class similarity of cell structures and the inherent biological anisotropy of fine textures pose significant challenges to existing methods. Due to their generic design, standard deep learning models often struggle to capture these fine-grained directional features and suffer from catastrophic feature loss during global pooling, particularly under limited sample conditions. To bridge this gap between general-purpose architectures and the specific demands of wood texture analysis, this paper proposes CM-EffNet, a lightweight fine-grained classification framework based on an improved EfficientNetV2 architecture. Firstly, a data augmentation strategy is employed to expand a collected dataset of 226 wood species from 3673 to 29,384 images, effectively mitigating overfitting caused by small sample sizes. Secondly, a Coordinate Attention (CA) mechanism is integrated to embed positional information into channel attention. This allows the network to precisely capture long-range dependencies between cell walls and vessels cavities, successfully decoding the challenge of textural anisotropy. Thirdly, a MixPooling strategy is introduced to replace traditional global average pooling, enabling the collaborative extraction of background context and salient fine-grained details to prevent the loss of critical micro-features. Systematic experiments demonstrate that CM-EffNet achieves a recognition accuracy of 96.72% and a training accuracy of 98.18%. Comparative results confirm that the proposed model offers superior learning efficiency and classification precision with a compact parameter size. This makes it highly suitable for deployment on mobile terminals connected to portable microscopes, providing a rapid and accurate solution for on-site timber market regulation and industrial quality control. Full article

Infrared and visible image fusion (IVIF) integrates the thermal saliency of infrared images (IRs) with the structural details of visible images (VIs) to produce comprehensive scene representations. Existing methods often overemphasize one modality, leading to loss of temperature readability or visual details. To address this, we propose Wave-Cross, a wavelet-based fusion framework. Using the discrete wavelet transform (DWT), IR low-frequency sub-bands encode thermal distribution, while VI high-frequency sub-bands capture textural details. Cross-attention adaptively recombines these sub-bands, suppressing modality-specific noise and balancing complementary features. Additionally, we introduce a Heat-Consistency Loss, which enforces pixel-wise thermal ordering and local energy preservation in a self-supervised manner, ensuring the fused image retains IR interpretability while enhancing VI sharpness. Experiments on the TNO, MSRS, and M3FD datasets demonstrate the effectiveness of the proposed method. Compared with state-of-the-art baselines, Wave-Cross achieves superior performance on objective metrics such as SD, AG, SCD, SF, CC, EN, NABF, and MS-SSIM yielding clearer details and more stable thermal saliency under challenging interference conditions. These results highlight the framework’s potential for practical applications in surveillance, autonomous driving, and fault diagnosis. Full article

To address the challenges in detecting surface damage on general aviation aircraft skin—such as feature degradation under varying imaging distances, significant target scale variations, and low recognition accuracy—this paper proposes GAD-YOLO, a sight-distance adaptive detection algorithm. First, a P2 small-target detection layer is integrated into the shallow network to enhance the capture of fine damage details. Second, an HMFHead detection head is introduced to mitigate scale variation effects through progressive semantic fusion and edge-aware constraints. Third, an LDown downsampling module is designed to construct a multi-scale feature fusion architecture. This module reduces redundancy via cross-level interaction and a lightweight kernel design, thereby decreasing the number of parameters and computational cost. Additionally, a DySample-based dynamic sampling operator is proposed to preserve local details through proximity-aware sampling while enriching the contextual semantics of distant damage features, effectively improving recognition performance. Experiments on a self-constructed general aviation aircraft skin damage dataset show that GAD-YOLO achieves 87.4% precision, 80.4% recall, 86.6% mAP@0.5, and 59.7% mAP@0.5:0.95. These results outperform the YOLOv11n baseline by 2.0%, 9.4%, 6.7%, and 7.6%, respectively. The proposed method significantly improves detection performance and provides a valuable reference for intelligent inspection and maintenance in general aviation. Full article

As core infrastructure of power transmission networks, power towers require high-precision 3D models, which are critical for intelligent inspection and digital twin applications of power transmission lines. Traditional reconstruction methods, such as LiDAR scanning and oblique photogrammetry, suffer from issues including high operational risks, low modeling efficiency, and loss of fine details. To address these limitations, this paper proposes a 3D Gaussian Splatting (3DGS)-based method for power tower 3D reconstruction to enhance reconstruction efficiency and detail preservation capability. First, a multi-view data acquisition scheme combining “unmanned aerial vehicle + oblique photogrammetry” was designed to capture RGB images acquired by Unmanned Aerial Vehicle (UAV) platforms, which are used as the primary input for 3D reconstruction. Second, a sparse point cloud was generated via Structure from Motion. Finally, based on 3DGS, Gaussian model initialization, differentiable rendering, and adaptive density control were performed to produce high-precision 3D models of power towers. Taking two typical power tower types as experimental subjects, comparisons were made with the oblique photogrammetry + ContextCapture method. Experimental results demonstrate that 3DGS not only achieves high model completeness (with the reconstructed model nearly indistinguishable from the original images) but also excels in preserving fine details such as angle steels and cables. Additionally, the final modeling time is reduced by over 70% compared to traditional oblique photogrammetry. 3DGS enables efficient and high-precision reconstruction of power tower 3D models, providing a reliable technical foundation for digital twin applications in power transmission lines. By significantly improving reconstruction efficiency and reducing operational costs, the proposed method supports sustainable power infrastructure inspection, asset lifecycle management, and energy-efficient digital twin applications. Full article

Current management strategies for sorghum aphids heavily rely on indiscriminate chemical application, leading to severe environmental consequences and impacting food safety. While precision spraying offers a viable remediation for pesticide overuse, its effectiveness depends on accurately locating and classifying pests. To address the critical challenge of segmenting small, swarming aphids in complex field environments, we propose FESW-UNet, a dual-domain attention network that integrates Fourier-enhanced attention, spatial attention, and wavelet-based downsampling into a UNet backbone. We introduce an efficient multi-scale attention (EMA) module between the encoder and decoder to enhance global context perception, enabling the model to capture more accurate relationships between global and local features in the field. In the feature extraction stage, we embed a simple attention module (SimAM) to target key infestation regions while suppressing background noise, thereby enhancing pixel-level discrimination. Furthermore, we replace conventional downsampling with Haar wavelet downsampling (HWD) to reduce resolution while preserving structural edge details. Finally, a Fourier-enhanced attention module (FEAM) is added to the skip-connection layers. By using complex-valued weights to regulate frequency-domain features, FEAM effectively fuses global low-frequency structures with local high-frequency details, thereby enhancing feature representation diversity. Experiments on the Aphid Cluster Segmentation dataset demonstrate that FESW-UNet outperforms other models, achieving an mIoU of 68.76%, mPA of 78.19%, and mF1 of 79.01%. The model also demonstrated strong adaptability on the AphidSeg-Sorghum dataset, achieving an mIoU of 81.22%, mPA of 87.97%, and mF1 of 88.60%. The proposed method offers an efficient and feasible technical solution for monitoring and controlling sorghum aphids through image segmentation, demonstrating broad application potential. Full article

Small-object detection in UAV remote sensing faces common challenges such as tiny target size, blurred features, and severe background interference. Furthermore, single imaging modalities exhibit limited representation capability in complex environments. To address these issues, this paper proposes CTU-YOLO, a UAV-based small-object detection algorithm built upon cross-modal feature fusion and lightweight upsampling. The algorithm incorporates a dynamic and adaptive cross-modal feature fusion (DCFF) module, which achieves efficient feature alignment and fusion by combining frequency-domain analysis with convolutional operations. Additionally, a lightweight upsampling module (LUS) is introduced, integrating dynamic sampling and depthwise separable convolution to enhance the recovery of fine details for small objects. Experiments on the DroneVehicle and LLVIP datasets demonstrate that CTU-YOLO achieves 73.9% mAP on DroneVehicle and 96.9% AP on LLVIP, outperforming existing mainstream methods. Meanwhile, the model possesses only 4.2 MB parameters and 13.8 GFLOPs computational cost, with inference speeds reaching 129.9 FPS on DroneVehicle and 135.1 FPS on LLVIP. This exhibits an excellent lightweight design and real-time performance while maintaining high accuracy. Ablation studies confirm that both the DCFF and LUS modules contribute significantly to performance gains. Visualization analysis further indicates that the proposed method can accurately preserve the structure of small objects even under nighttime, low-light, and multi-scale background conditions, demonstrating strong robustness. Full article

Existing video inpainting methods typically combine optical flow propagation with Transformer architectures, achieving promising inpainting results. However, they lack adaptive inpainting strategy optimization in diverse scenarios, and struggle to capture high-level temporal semantics, causing temporal inconsistencies and quality degradation. To address these challenges, we make one of the first attempts to introduce reinforcement learning into the video inpainting domain, establishing a closed-loop framework named CLIP-RL that enables adaptive strategy optimization. Specifically, video inpainting is reformulated as an agent–environment interaction, where the inpainting module functions as the agent’s execution component, and a pre-trained inpainting detection module provides real-time quality feedback. Guided by a policy network and a composite reward function that incorporates a weighted temporal alignment loss, the agent dynamically selects actions to adjust the inpainting strategy and iteratively refines the inpainting results. Compared to ProPainter, CLIP-RL improves PSNR from 34.43 to 34.67 and SSIM from 0.974 to 0.986 on the YouTube-VOS dataset. Qualitative analysis demonstrates that CLIP-RL excels in detail preservation and artifact suppression, validating its superiority in video inpainting tasks. Full article

This study examines the high-temperature degradation of Hastelloy C276, a corrosion-resistant nickel-based alloy, during exposure to combustion products generated by methane and 99% cracked ammonia. Using a high-pressure optical combustor (HPOC) at 4 bar and exhaust temperatures of 815–860 °C, standard tensile specimens were exposed for five hours to fully developed post-flame exhaust gases, simulating real industrial turbine or burner conditions. The surfaces and subsurface regions of the samples were analysed using scanning electron microscopy (SEM; Zeiss Sigma HD FEG-SEM, Carl Zeiss, Oberkochen, Germany) and energy-dispersive X-ray spectroscopy (EDX; Oxford Instruments X-MaxN detectors, Oxford Instruments, Abingdon, United Kingdom), while mechanical properties were evaluated by tensile testing, and the gas-phase compositions were tracked in detail for each fuel blend. Results show that exposure to methane causes moderate oxidation and some grain boundary carburisation, with localised carbon enrichment detected by high-resolution EDX mapping. In contrast, 99% cracked ammonia resulted in much more aggressive selective oxidation, as evidenced by extensive surface roughening, significant chromium depletion, and higher oxygen incorporation, correlating with increased NO_x in the exhaust gas. Tensile testing reveals that methane exposure causes severe embrittlement (yield strength +41%, elongation −53%) through grain boundary carbide precipitation, while cracked ammonia exposure results in moderate degradation (yield strength +4%, elongation −24%) with fully preserved ultimate tensile strength (870 MPa), despite more aggressive surface oxidation. These counterintuitive findings demonstrate that grain boundary integrity is more critical than surface condition for mechanical reliability. These findings underscore the importance of evaluating material compatibility in low-carbon and hydrogen/ammonia-fuelled combustion systems and establish critical microstructural benchmarks for the anticipated mechanical testing in future work. Full article

Coronary artery disease (CAD) remains a leading cause of mortality worldwide, and accurate coronary artery segmentation in X-ray coronary angiography (XCA) is challenged by low contrast, structural ambiguity, and anisotropic vessel trajectories, which hinder quantitative coronary angiography. We propose HR-UMamba++, a U-Mamba-based framework centered on a rotation-aligned multi-directional state-space scan for modeling long-range vessel continuity across multiple orientations. To preserve thin distal branches, the framework is equipped with (i) a persistent high-resolution bypass that injects undownsampled structural details and (ii) a UNet++-style dense decoder topology for cross-scale topological fusion. On an in-house dataset of 739 XCA images from 374 patients, HR-UMamba++ is evaluated using eight segmentation metrics, fractal-geometry descriptors, and multi-view expert scoring. Compared with U-Net, Attention U-Net, HRNet, U-Mamba, DeepLabv3+, and YOLO11-seg, HR-UMamba++ achieves the best performance (Dice 0.8706, IoU 0.7794, HD95 16.99), yielding a relative Dice improvement of 6.0% over U-Mamba and reducing the deviation in fractal dimension by up to 57% relative to U-Net. Expert evaluation across eight angiographic views yields a mean score of 4.24 ± 0.49/5 with high inter-rater agreement. These results indicate that HR-UMamba++ produces anatomically faithful coronary trees and clinically useful segmentations that can serve as robust structural priors for downstream quantitative coronary analysis. Full article

Introduction: Overweight and obesity are becoming increasingly prevalent. Incretin-based obesity treatments—glucagon-like peptide-1 receptor agonists (GLP-1 RAs) and dual glucagon-like peptide-1 receptor/glucose-dependent insulinotropic polypeptide receptor agonists (GIP/GLP-1 RAs or dual agonists)—are a major stride in the evolution of obesity management. However, like weight loss with other means, they are associated with an inadvertent significant loss of lean body mass, including muscle. This has led to a resurgence in research for the preservation of lean body mass, the loss of which occurs with weight loss. The purpose of this narrative review is to discuss the mechanisms involved with lean body loss and capture the research landscape of the different classes of pharmacological agents being developed to address this problem. Methodology: We queried PubMed, Medline, and Scopus for randomized controlled trials and phase II or phase III trials using key words to capture the breath of this topic—obesity, weight loss, muscle loss, lean mass, and muscle preservation. Animal studies were excluded. We analyzed the studies conducted to date. Results: Weight loss, regardless of the method used to achieve it, is inadvertently accompanied by lean body mass loss, to varying degrees. There are several mechanisms that govern the loss of lean body mass and, more specifically, the loss of muscle mass; as such, several classes of medications have been explored, targeting different pathways and receptors—including bimagrumab (activin receptor agonist), tesamorelin (growth hormone releasing hormone agonists), and enobosarm (selective androgen receptor modulator). Most of these drugs are in the early phases of research development, but some show great promise. Conclusion: This narrative review attempts to detail the physiology of muscle mass loss when accompanied by weight loss and identify pharmacological targets that can be utilized to minimize it with mechanisms, effects, side effects, and research developmental progress. Full article

Underwater images frequently suffer from color casts, low illumination, and blur due to wavelength-dependent absorption and scattering. We present a practical two-stage, modular, and degradation-aware framework designed for real-time enhancement, prioritizing deployability on edge devices. Stage I employs a lightweight CNN to classify inputs into three dominant degradation classes (color cast, low light, blur) with 91.85% accuracy on an EUVP subset. Stage II applies three scene-specific lightweight enhancement pipelines and fuses their outputs using two alternative learnable modules: a global Linear Fusion and a LiteUNetFusion (spatially adaptive weighting with optional residual correction). Compared to the three single-scene optimizers (average PSNR = 19.0 dB; mean UCIQE ≈ 0.597; mean UIQM ≈ 2.07), the Linear Fusion improves PSNR by +2.6 dB on average and yields roughly +20.7% in UCIQE and +21.0% in UIQM, while maintaining low latency (~90 ms per 640 × 480 frame on an Intel i5-13400F (Intel Corporation, Santa Clara, CA, USA). The LiteUNetFusion further refines results: it raises PSNR by +1.5 dB over the Linear model (23.1 vs. 21.6 dB), brings modest perceptual gains (UCIQE from 0.72 to 0.74, UIQM 2.5 to 2.8) at a runtime of ≈125 ms per 640 × 480 frame, and better preserves local texture and color consistency in mixed-degradation scenes. We release implementation details for reproducibility and discuss limitations (e.g., occasional blur/noise amplification and domain generalization) together with future directions. Full article

Modern power systems have become increasingly complex, making the detailed modeling and analysis of large-scale networks computationally demanding and often impractical. Therefore, network reduction techniques are essential for representing a smaller area of interest while preserving the electrical behavior of the complete system. For electromagnetic transient (EMT) studies, such as load rejection analysis, reduced networks are commonly derived using classical methods like Kron reduction under maximum power transfer conditions. However, this approach can lead to discrepancies in load flow and short-circuit levels between the reduced and complete systems. In addition, Kron reduction may introduce negative resistances in the reduced-order model, compromising system stability by producing non-passive equivalents and potentially causing unrealistic or numerically unstable EMT simulations. To address these limitations, this paper proposes an optimization-based approach, termed PSO-OPF-Kron, which integrates Optimal Power Flow (OPF) with the Particle Swarm Optimization (PSO) algorithm to refine the equivalent network parameters. The method optimally determines power injections, bus voltages, transformer tap settings, and impedances to align the reduced model with the full system’s operating point and short-circuit levels. Validation on the IEEE 39-bus system demonstrates that the proposed method significantly improves accuracy and numerical stability, ensuring reliable EMT simulations for load rejection studies. Full article