Search Results (4,500)

Single-image dehazing of high-voltage power transmission lines (HPTLs) using deep learning methods confronts two critical challenges: the non-homogeneous haze distribution in HPTL images and the unavailability of paired clear images for supervised training. To overcome these issues, this paper proposes a novel dehaze neural network, named FIF-RSCT-Net, that employs a hybrid supervised-to-unsupervised iterative learning approach according to the characteristic of HPTL single images. The FIF-RSCT-Net incorporates the Spatial–Channel Feature Intersection modules and Residual Separable Convolution Transformers to enhance the feature representation capability. Crucially, this novel architecture could learn more generalized dehazing knowledge that can be transferred from the original image domain to HPTL scenarios. In the dehazing knowledge transformation, an unsupervised iterative learning mechanism based on the Line Segment Detector is designed to optimize the restoration of power transmission lines. The effectiveness of FIF-RSCT-Net on the original image domain is demonstrated in the comparative experiments of the I-Haze, O-Haze, NH-Haze, and SOTS datasets. Our methodology achieves the best average PSNR of 24.647 dB and SSIM of 0.8512. And the qualitative evaluation of unsupervised iterative learning results shows that the missed line segments are exhibited during progressive training iterations. Full article

Cryogenic propellant sloshing presents significant challenges in aerospace systems, inducing vehicle instability, structural fatigue, energy losses, and complex thermal management issues. This review synthesizes experimental, analytical, and numerical advances with an emphasis on energy dissipation and conversion efficiency in propellant storage and transfer. Recent developments in computational fluid dynamics (CFD) and AI-driven digital-twin frameworks are critically examined alongside the influences of tank materials, baffle configurations, and operating conditions. Unlike conventional fluids, cryogenic propellants in microgravity and within composite overwrapped pressure vessels (COPVs) exhibit unique thermodynamic and dynamic couplings that remain only partially characterized. Prior reviews have typically treated these factors in isolation; here, they are unified through an integrated perspective linking cryogenic thermo-physics, reduced-gravity hydrodynamics, and fluid–structure interactions. Persistent research limitations are identified in the areas of data availability, model validation, and thermo-mechanical coupling fidelity, underscoring the need for scalable multi-physics approaches. This review’s contribution lies in consolidating these interdisciplinary domains while outlining a roadmap toward experimentally validated, AI-augmented digital-twin architectures for improved energy efficiency, reliability, and propellant stability in next-generation aerospace missions. Full article

The static nature of traditional military symbology, such as MIL-STD-2525D, hinders effective real-time threat detection and response in modern cybersecurity operations. This research introduces the Dynamic Adaptive Symbol System (DASS), a novel framework enhancing cyber situational awareness in military and enterprise environments. The DASS addresses static symbology limitations by employing a modular Python 3.10 architecture that uses machine learning-driven threat detection to dynamically adapt symbol visualization based on threat severity and context. Empirical testing assessed the DASS against a MIL-STD-2525D baseline using active cybersecurity professionals. Results show that the DASS significantly improves threat identification rates by 30% and reduces response times by 25%, while achieving 90% accuracy in symbol interpretation. Although the current implementation focuses on virus-based scenarios, the DASS successfully prioritizes critical threats and reduces operator cognitive load. Full article

To address challenges such as sparse feature representation difficulties and poor robustness in detecting weak targets against sea clutter backgrounds, this study investigates the adaptability of channel modeling and sparse reconstruction techniques for target recognition. It proposes a method for detecting small sea targets that integrates OTFS with deep unfolding. Using OTFS modulation to map signals from the time domain to the Delay-Doppler domain, a sparse recovery model is constructed. Deep unfolding is employed to transform the FISTA iterative process into a trainable network architecture. A GAN model is employed for adaptive parameter optimization across layers, while the CBAM mechanism enhances response to critical regions. A multi-stage loss function design and false alarm rate control mechanism improve detection accuracy and interference resistance. Validation using the IPIX dataset yields average detection rates of 88.2%, 91.5%, 90.0%, and 83.3% across four polarization modes, demonstrating the proposed method’s robust performance. Full article

Collaborative Online International Learning (COIL) has become an innovative pedagogical strategy that promotes the internationalization of curricula and the development of transversal competencies. In architecture, its implementation is particularly relevant because there is a growing need to train professionals capable of leading and collaborating in global and interdisciplinary contexts. However, evidence of COIL’s impact during the early stages of higher education in Latin America remains limited. This study analyzed the experience of 39 architecture students from the Universidad Nacional de San Agustín de Arequipa (Peru), who collaborated with peers from Mexico in a five-week COIL project focused on design methodologies for vulnerable populations. Using a mixed-methods approach, the study assessed students’ competencies in leadership, self-regulation in virtual learning, and emotional intelligence and teamwork through pre- and post-experience questionnaires complemented with open-ended questions. Findings indicate that although students’ self-perceptions of their competencies remained at medium-to-high levels overall, changes occurred differently among groups: students with initially low self-assessment scores showed improvements, whereas those with initially high scores tended to moderate their self-assessment. Qualitative analysis highlighted barriers such as limited communication, time zone differences, and unequal participation. Overall, the results suggest that the COIL experience not only supported the development of competencies but also fostered critical reflection and a more realistic self-assessment of students’ competencies in virtual and intercultural contexts. Full article

This paper presents a pioneering and novel analysis of the synergistic relationship between China’s leadership in electric vehicle (EV) adoption and the rapid advancement of autonomous driving (AD) technologies within the nation’s mobility ecosystem. Challenging the conventional view of electrification as a parallel trend, this study introduces a new perspective by demonstrating how EV infrastructure serves as a fundamental enabler of autonomy, providing the necessary high-voltage architectures for critical AD functions like real-time sensor fusion and over-the-air updates. In doing so, it addresses the central research question: How does large-scale electrification influence the architecture, deployment, and safety development of autonomous driving vehicles, particularly in the context of China’s intelligent mobility ecosystem? Through technical analysis and industry examples, the paper offers original contributions by illustrating how EV-driven platforms overcome the inherent limitations of internal combustion engine systems, enhancing autonomous execution and system reliability. Furthermore, this research provides novel insights into China’s unique public–private innovation ecosystem, highlighting the role of vertically integrated startups and cross-sector coordination in driving AD development. By analyzing these previously overlooked systemic interactions, the paper posits that China’s EV dominance strategically amplifies its autonomous vehicle ambitions, positioning the nation to lead the next generation of intelligent transportation systems. Full article

Small surface defects in printed circuit boards (PCBs) severely affect the reliability of electronic devices, making PCB surface defect detection crucial for ensuring the quality of electronic products. However, the existing detection methods often struggle with insufficient accuracy and the inherent trade-off between detection precision and inference speed. To address these problems, we propose a novel ESDM-HNN-YOLO (EH-YOLO) network based on the improved YOLOv10 for efficient detection of small PCB defects. Firstly, an enhanced spatial-depth module (ESDM) is designed, which transforms spatial-dimensional features into depth-dimensional representations while integrating spatial attention module (SAM) and channel attention module (CAM) to highlight critical features. This dual mechanism not only effectively suppresses feature loss in micro-defects but also significantly enhances detection accuracy. Secondly, a hybrid neck network (HNN) is designed, which optimizes the speed–accuracy balance through hierarchical architecture. The hierarchical structure uses a computationally efficient weighted bidirectional feature pyramid network (BiFPN) to enhance multi-scale feature fusion of small objects in the shallow layer and uses a path aggregation network (PAN) to prevent feature loss in the deeper layer. Comprehensive evaluations on benchmark datasets (PCB_DATASET and DeepPCB) demonstrate the superior performance of EH-YOLO, achieving mAP@50-95 scores of 45.3% and 78.8% with inference speeds of 166.67 FPS and 158.73 FPS, respectively. These results significantly outperform existing approaches in both accuracy and processing efficiency. Full article

Battery Electric Vehicles (BEVs) technology is rapidly emerging as the cornerstone of sustainable transportation, driven by advancements in battery technology, power electronics, and modern drivetrains. This paper presents a comprehensive review of current and next-generation BEV powertrain architectures, focusing on five key subsystems: battery energy storage system, electric propulsion motors, energy management systems, power electronic converters, and charging infrastructure. The review traces the evolution of battery technology from conventional lithium-ion to solid-state chemistries and highlights the critical role of battery management systems in ensuring optimal state of charge, health, and safety. Recent innovations by leading automakers are examined, showcasing advancements in cell formats, motor designs, and thermal management for enhanced range and performance. The role of power electronics and the integration of AI-driven strategies for vehicle control and vehicle-to-grid (V2G) are analyzed. Finally, the paper identifies ongoing research gaps in system integration, standardization, and advanced BMS solutions. This review provides a comprehensive roadmap for innovation, aiming to guide researchers and industry stakeholders in accelerating the adoption and sustainable advancement of BEV technologies. Full article

Accurate assessment of sleep architecture is critical for diagnosing and managing sleep disorders, which significantly impact global health and well-being. While polysomnography (PSG) remains the clinical gold standard, its inherent intrusiveness, high cost, and logistical complexity limit its utility for routine or home-based monitoring. Recent advances highlight that subtle variations in respiratory dynamics, such as respiratory rate and cycle regularity, exhibit meaningful correlations with distinct sleep stages and could serve as valuable non-invasive biomarkers. In this work, we propose a framework for estimating sleep stage distribution—specifically Wake, Light (N1+N2), Deep (N3), and REM—based on respiratory audio captured over a single sleep episode. The framework comprises three principal components: (1) a segmentation module that identifies distinct respiratory cycles in respiratory sounds using a fine-tuned Transformer-based architecture; (2) a feature extraction module that derives a suite of statistical, spectral, and distributional descriptors from these segmented respiratory patterns; and (3) stage-specific regression models that predict the proportion of time spent in each sleep stage. Experiments on the public PSG-Audio dataset (287 subjects; mean 5.3 h per subject), using subject-wise cross-validation, demonstrate the efficacy of the proposed approach. The segmentation model achieved lower RMSE and MAE in predicting respiratory rate and cycle duration, outperforming classical signal-processing baselines. For sleep stage proportion prediction, the proposed method yielded favorable RMSE and MAE across all stages, with the TabPFN model consistently delivering the best results. By quantifying interpretable respiratory features and intentionally avoiding black-box end-to-end modeling, our system may support transparent, contact-free sleep monitoring using passive audio. Full article

Early detection of network traffic anomalies is critical for cybersecurity, as a single compromised host can cause data breaches, reputational damage, and operational disruptions. However, traditional systems based on signatures and static rules are often ineffective against sophisticated and evolving threats. This study proposes a hybrid deep learning architecture for proactive anomaly detection in local and metropolitan networks. The dataset underwent an extensive process of cleaning, transformation, and feature selection, including normalization of numerical fields, encoding of ordinal variables, and derivation of behavioral metrics. The EFMS-KMeans algorithm was applied to pre-label traffic as normal or anomalous by estimating dense centers and computing centroid distances, enabling the training of a sequential CNN-GRU network, where the CNN captures spatial patterns and the GRU models temporal dependencies. To address class imbalance, the SMOTE technique was integrated, and the loss function was adjusted to improve training stability. Experimental results show a substantial improvement in accuracy and generalization compared to conventional approaches, validating the effectiveness of the proposed method for detecting anomalous traffic in dynamic and complex network environments. Full article

Mining activity has been and is one of the most important and indispensable industries for the development of society. Given its role in the provision of raw materials, advancing the development of environmentally friendly mining practices is essential for meeting the globally established goals of sustainable development. In this regard, actions and incentives are being promoted by the European Union, such as the Mine.io project presented in this research. In response to the needs identified within the mining sector, this research seeks to explore the functional and non-functional requirements across several mining contexts. The objective is to establish effective patterns that positively influence the sector activities. This effort is envisioned as a critical foundation for developing a digital architecture that addresses sector limitations and fosters the integration of Industry 4.0 principles into the mining domain. The results provide a solid basis for understanding the needs of the different mining sectors analyzed, while also demonstrating the potential advancements achievable through the project’s technological developments. They enable a comprehensive evaluation of the current technological state in relation to the broader context of global legacy practices, establishing informed guidelines for effective sector responses based on digitalization and the application of sustainable tools. Full article

Real-time lossless image compression based on the JPEG-LS algorithm is in high demand for critical missions such as satellite remote sensing and space exploration due to its excellent balance between complexity and compression rate. However, few researchers have made appropriate modifications to the JPEG-LS algorithm to make it more suitable for high-speed hardware implementation and application to Bayer pattern data. This paper addresses the current limitations by proposing a real-time lossless compression system specifically tailored for Bayer pattern images from spaceborne cameras. The system integrates a hybrid encoding strategy modified from JPEG-LS, combining run-length encoding, predictive encoding, and a non-encoding mode to facilitate high-speed hardware implementation. Images are processed in tiles, with each tile’s color channels processed independently to preserve individual channel characteristics. Moreover, potential error propagation is confined within a single tile. To enhance throughput, the compression algorithm operates within a 20-stage pipeline architecture. Duplication of computation units and the introduction of key-value registers and a bypass mechanism resolve structural and data dependency hazards within the pipeline. A reorder architecture prevents pipeline blocking, further optimizing system throughput. The proposed architecture is implemented on a XILINX XC7Z045-2FFG900C SoC (Xilinx, Inc., San Jose, CA, USA) and achieves a maximum throughput of up to 346.41 MPixel/s, making it the fastest architecture reported in the literature. Full article

Background: Healthcare 5.0 represents a shift toward intelligent, human-centric care systems. Intensive care units generate vast amounts of data that require real-time decisions, but current decision support systems lack comprehensive frameworks for safe integration of artificial intelligence. Objective: We developed and validated the Learn–Predict–Monitor–Detect–Correct (LPMDC) framework as a methodology for systematic artificial intelligence integration across the critical care workflow. The framework improves predictive analytics, continuous patient monitoring, intelligent alerting, and therapeutic decision support while maintaining essential human clinical oversight. Methods: Framework development employed systematic theoretical modeling integrating Healthcare 5.0 principles, comprehensive literature synthesis covering 2020–2024, clinical workflow analysis across 15 international ICU sites, technology assessment of mature and emerging AI applications, and multi-round expert validation by 24 intensive care physicians and medical informaticists. Each LPMDC phase was designed with specific integration requirements, performance metrics, and safety protocols. Results: LPMDC implementation and aggregated evidence from prior studies demonstrated significant clinical improvements: 30% mortality reduction, 18% ICU length-of-stay decrease (7.5 to 6.1 days), 45% clinician cognitive load reduction, and 85% sepsis bundle compliance improvement. Machine learning algorithms achieved an 80% sensitivity for sepsis prediction three hours before clinical onset, with false-positive rates below 15%. Additional applications demonstrated effectiveness in predicting respiratory failure, preventing cardiovascular crises, and automating ventilator management. Digital twins technology enabled personalized treatment simulations, while the integration of the Internet of Medical Things provided comprehensive patient and environmental surveillance. Implementation challenges were systematically addressed through phased deployment strategies, staff training programs, and regulatory compliance frameworks. Conclusions: The Healthcare 5.0-enabled LPMDC framework provides the first comprehensive theoretical foundation for systematic AI integration in critical care while preserving human oversight and clinical safety. The cyclical five-phase architecture enables processing beyond traditional cognitive limits through continuous feedback loops and system optimization. Clinical validation demonstrates measurable improvements in patient outcomes, operational efficiency, and clinician satisfaction. Future developments incorporating quantum computing, federated learning, and explainable AI technologies offer additional advancement opportunities for next-generation critical care systems. Full article

Glazed components in ancient Chinese architecture hold profound historical and cultural value. However, over time, environmental erosion, physical impacts, and human disturbances gradually lead to various forms of damage, severely impacting the durability and stability of the buildings. Therefore, preventive protection of glazed components is crucial. The key to preventive protection lies in the early detection and repair of damage, thereby extending the component’s service life and preventing significant structural damage. To address this challenge, this study proposes a Restoration-Scale Identification (RSI) method that integrates depth information. By combining RGB-D images acquired from a depth camera with intrinsic camera parameters, and embedding a Convolutional Block Attention Module (CBAM) into the backbone network, the method dynamically enhances critical feature regions. It then employs a scale restoration strategy to accurately identify damage areas and recover the physical dimensions of glazed components from a global perspective. In addition, we constructed a dedicated semantic segmentation dataset for glazed tile damage, focusing on cracks and spalling. Both qualitative and quantitative evaluation results demonstrate that, compared with various high-performance semantic segmentation methods, our approach significantly improves the accuracy and robustness of damage detection in glazed components. The achieved accuracy deviates by only ±10 mm from high-precision laser scanning, a level of precision that is essential for reliably identifying and assessing subtle damages in complex glazed architectural elements. By integrating depth information, real scale information can be effectively obtained during the intelligent recognition process, thereby efficiently and accurately identifying the type of damage and size information of glazed components, and realizing the conversion from two-dimensional (2D) pixel coordinates to local three-dimensional (3D) coordinates, providing a scientific basis for the protection and restoration of ancient buildings, and ensuring the long-term stability of cultural heritage and the inheritance of historical value. Full article

Optimal airfoil design remains a critical challenge in aerodynamic engineering, with traditional methods requiring extensive computational resources and iterative processes. This paper presents GEO-DSGA, a novel framework integrating hybrid geometric neural networks with deep symbiotic genetic algorithms for enhanced airfoil optimization. The methodology employs graph-based representations of airfoil geometries through a hybrid architecture combining graph convolutional networks with traditional deep learning, enabling precise capture of spatial geometric relationships. The parametric modeling stage utilizes CST, Bézier curves, and PARSEC methods to generate mathematically robust airfoil representations, subsequently transformed into graph structures preserving local and global shape characteristics. The optimization framework incorporates a deep symbiotic genetic algorithm enhanced with dominant feature phenotyping, applying biological symbiotic principles where design parameters achieve superior performance through mutual enhancement rather than independent optimization. This systematic exploration maintains geometric feasibility and aerodynamic validity throughout the design space. Experimental results demonstrate an 88.6% reduction in computational time while maintaining prediction accuracy within 1.5% error margin for aerodynamic coefficients across diverse operating conditions. The methodology successfully identifies airfoil geometries outperforming baseline NACA profiles by up to 12% in lift-to-drag ratio while satisfying manufacturing and structural constraints, establishing GEO-DSGA as a significant advancement in computational aerodynamic design optimization. Full article