Search Results (45)

Ship detection serves as a core foundational task for marine environmental perception. However, in real marine scenarios, dense vessel traffic often causes severe target occlusion while multi-scale targets, asymmetric vessel geometries, and harsh conditions (e.g., haze, low illumination) further degrade image quality. These factors pose significant challenges to vision-based ship detection methods. To address these issues, we propose ${\mathrm{M}}^2\mathrm{S}\text{-}\mathrm{YOLOv}8$, an improved framework based on YOLOv8, which integrates three key enhancements: First, a Multi-Scale Asymmetry-aware Parallelized Patch-wise Attention (MSA-PPA) module is designed in the backbone to strengthen the perception of multi-scale and geometrically asymmetric vessel targets. Second, a Deformable Convolutional Upsampling (DCNUpsample) operator is introduced in the Neck network to enable adaptive feature fusion with high computational efficiency. Third, a Wasserstein-Distance-Based Weighted Normalized CIoU (WA-CIoU) loss function is developed to alleviate gradient imbalance in small-target regression, thereby improving localization stability. Experimental results on the Unmanned Vessel Zhoushan Perception Dataset (UZPD) and the open-source Singapore Maritime Dataset (SMD) demonstrate that ${\mathrm{M}}^2\mathrm{S}\text{-}\mathrm{YOLOv}8$ achieves a balanced performance between lightweight design and real-time inference, showcasing strong potential for reliable deployment on edge devices of unmanned marine platforms. Full article

Wind power forecasting is critical to grid stability and renewable energy integration. However, existing deep learning methods struggle to incorporate semantic domain knowledge from textual information, exhibit limited generalization with scarce training data, and require high computational costs for extensive fine-tuning. Large language models (LLMs) offer a promising solution through their semantic representations, few-shot learning capabilities, and multimodal processing abilities. This paper proposes LLM-WPFNet, a dual-modality fusion framework that integrates frozen pre-trained LLMs with time-series analysis for wind power forecasting. The key insight is encoding temporal patterns as structured textual prompts to enable semantic guidance from frozen LLMs without fine-tuning. LLM-WPFNet employs two parallel encoding branches to extract complementary features from time series and textual prompts, unified through asymmetric multi-head attention fusion that enables selective semantic knowledge transfer from frozen LLM embeddings to enhance temporal representations. By maintaining the LLM frozen, our method achieves computational efficiency while leveraging robust semantic representations. Extensive experiments on four wind farm datasets (36–200 MW) across five prediction horizons (1–24 h) demonstrate that LLM-WPFNet consistently outperforms state-of-the-art baselines by 11% in MAE and RMSE. Notably, with only 10% of training data, it achieves a 17.6% improvement over the best baseline, validating its effectiveness in both standard and data-scarce scenarios. These results highlight the effectiveness and robustness of the dual-modality fusion design in predicting wind power under complex real-world conditions. Full article

Modern target tracking systems rely on radar as a sensor to detect targets and generate raw track points. These raw track points are affected by the radar’s own noise and the asymmetric non-Gaussian noise resulting from the nonlinear transformation from polar coordinates to Cartesian coordinates. Without effective processing, such data cannot directly support highly reliable situational awareness, early warning decisions, or weapon guidance. Track filtering, as a core component of target tracking, plays an irreplaceable foundational role in achieving real-time, accurate, and stable estimation of moving target states. Traditional deep learning filtering algorithms struggle with capturing long-term dependencies in high-dimensional spaces, often exhibiting high computational complexity, slow response to transient signals, and compromised noise suppression due to their inherent architectural asymmetries. In order to address these issues and balance the model’s high accuracy, strong real-time performance, and robustness, a new trajectory filtering algorithm based on a temporal convolutional network (TCN), Residual Gated Recurrent Unit (ResGRU), and multi-head attention (MHA) is proposed. The TCN-ResGRU-MHA hybrid structure we propose combines the parallel processing advantages and detail-capturing ability of a TCN with the residual learning capability of a ResGRU, and introduces the MHA mechanism to achieve adaptive weighting of high-dimensional features. Using the root mean square error (RMSE) and Euclidean distance to evaluate the model effect, the experimental results show that the RMSE of TCN-ResGRU-MHA is 27.4621 (m) lower than CNN-GRU, which is an improvement of 15.99% in the complex scene of high latitude, and the distance is 37.906 (m) lower than CNN-GRU, which is an improvement of 18.65%. These results demonstrate its effectiveness in filtering and tracking tasks in high-latitude complex scenarios. Full article

Wideband spectrum sensing is a crucial technology for the efficient utilization of limited frequency resources in cognitive radio. While deep learning models have yielded promising results, they typically rely on either time-domain (I/Q) or frequency-domain (FFT) data alone, which can limit their performance. This study proposes IPFSCNN (IQ-Parallel FFT-Serial CNN), a novel asymmetric hybrid architecture that synergistically fuses both data representations. The key idea of its design is an asymmetric architecture that employs two specialized streams: a parallelized branch to efficiently capture temporal features from I/Q data, and a deep serial branch to extract spectral patterns from FFT data. These complementary features are fused to perform a multi-label classification task. Experiments on an LTE-M dataset demonstrate that the proposed IPFSCNN achieves a higher detection performance than state-of-the-art models, including DeepSense and ParallelCNN, particularly in low signal-to-noise ratio conditions. Furthermore, IPFSCNN achieves this superior accuracy while maintaining high computational efficiency, requiring 15% fewer parameters and only one-third of the multiply-accumulate (MAC) operations compared to the DeepSense model. Crucially, a comprehensive ablation study validates this asymmetric design, proving that the proposed ‘IQ-Parallel FFT-Serial’ combination is demonstrably superior to other hybrid configurations. Full article

Acute hypoxemic respiratory failure is a critical challenge in intensive care. A substantial proportion of patients present with asymmetric acute lung injury (ALI), complicating management due to heterogeneous lung involvement. While lung-protective mechanical ventilation represents the standard of care, the optimal approach to positive end-expiratory pressure (PEEP) titration remains unclear. This study investigated the effects of transpulmonary pressure (TPP)-guided PEEP titration vs. a fixed PEEP strategy in a porcine model of unilateral ALI. A total of 14 pigs underwent ALI induction via unilateral surfactant depletion and were randomized to receive either a fixed PEEP of 5 cmH₂O or a PEEP targeting a slightly positive TPP at end-expiration. Over six hours, respiratory mechanics, high-resolution computed tomography (HRCT), histological lung injury scores (LIS), and plasma protein biomarkers were assessed. TPP-guided PEEP titration significantly lowered driving pressure and improved compliance compared to fixed low PEEP, suggesting more homogeneous tidal volume distribution. HRCT revealed less collateral injury in the initially non-injured lung in the TPP-guided group. However, histopathological LIS did not differ between groups. Exploratory cytokine profiling showed systemic inflammatory activation—including pro- and anti-inflammatory responses—only in the TPP-guided group. These findings indicate that TPP-guided PEEP titration may optimize ventilation by balancing alveolar recruitment and overdistension in asymmetric ALI, with clear effects on physiological and imaging parameters, but without parallel effects on cytokine responses. Further research is needed to assess its long-term impact and clinical relevance. Full article

This paper presents a comparative mathematical analysis of electrode configurations used in active fog water harvesting systems based on electrostatic ionization. The study begins with a brief overview of fog formation and typology. It also addresses the global relevance of fog as a decentralized water resource. It also outlines the main methods and collector designs currently employed for fog water capture, both passive and active. The core of the work involves solving the Laplace equation for various electrode geometries to compute electrostatic field distributions and analyze field line density patterns as a proxy for potential water collection efficiency. The evaluated configurations include centered rod–cylinder, symmetric parallel multi-rod, and asymmetric wire–plate layouts, with emphasis on identifying spatial regions of high field line convergence. These regions are interpreted as likely trajectories of charged droplets under Coulombic force influence. The modeling approach enables preliminary assessment of design efficiency without relying on time-consuming droplet-level simulations. The results serve as a theoretical foundation prior to the construction of electrode layouts in the portable HygroCatch experimental harvester and provide insight into how field structure correlates with fog water harvesting performance. Full article

Accurate prediction of effluent quality indicators is essential for ensuring stable operation and regulatory compliance in wastewater treatment plants. However, the inherent spatial distribution and temporal fluctuations of wastewater processes present significant challenges for modeling. In this study, we propose a dynamic multi-scale spatio-temporal Transformer (DMST-Transformer) with a symmetric architecture to enhance prediction accuracy in complex wastewater systems. Unlike conventional asymmetric designs, the DMST-Transformer extracts spatial and temporal features in parallel using a spatial graph convolutional network and a multi-scale self-attention mechanism coupled with a dynamic self-tuning module. The model is evaluated on a full-process dataset collected from a municipal wastewater treatment plant, with biochemical oxygen demand selected as the target indicator. Experimental results on test data show that the DMST-Transformer achieves a coefficient of determination of 0.93, root mean square error of 1.40 mg/L, and mean absolute percentage error of 6.61%, outperforming classical models such as linear regression, partial least squares, and graph convolutional networks, as well as advanced deep learning baselines including Transformer and ST-Transformer. Ablation studies confirm the complementary effectiveness of the spatial and temporal modules, and computational time comparisons demonstrate the model’s suitability for real-time applications. These results validate the practical potential of the DMST-Transformer for robust effluent quality monitoring in wastewater treatment plants. Future research will focus on scaling the model to larger and more diverse datasets, extending it to predict additional water quality indicators, and deploying it in real-time environmental monitoring systems to support intelligent water resource management. Full article

Synthetic nanopores were recently demonstrated with memristive and nonlinear voltage-current behaviors, akin to ion channels in a cell membrane. Such ionic devices are considered a promising candidate for the development of brain-inspired neuromorphic computing techniques. In this work, we show the composite behavior of nanopore-array large memristors, formed with different membrane materials, pore sizes, electrolytes, and device arrangements. Anodic aluminum oxide (AAO) membranes with 5 nm and 20 nm diameter pores and track-etched polycarbonate (PCTE) membranes with 10 nm diameter pores are tested and shown to demonstrate memristive and nonlinear behaviors with approximately 10⁷–10¹⁰ pores in parallel when electrolyte concentration across the membranes is asymmetric. Ion diffusion through the large number of channels induces time-dependent electrolyte asymmetry that drives the system through different memristive states. The behaviors of series composite memristors with different configurations are also presented. In addition to helping understand fluidic devices and circuits for neuromorphic computing, the results also shed light on the development of field-assisted ion-selection-membrane filtration techniques as well as the investigations of large neurons and giant synapses. Further work is needed to de-embed parasitic components of the measurement setup to obtain intrinsic large memristor properties. Full article

Many challenges in solving large graph coloring through parallel strategies remain unresolved. Previous algorithms based on Pregel-like frameworks, such as Apache Giraph, encounter parallelism bottlenecks due to sequential execution and the need for a full graph traversal in certain stages. Additionally, GPU-based algorithms face the dilemma of costly and time-consuming processing when moving complex graph applications to GPU architectures. In this study, we propose Spardex, a novel parallel and distributed graph coloring optimization algorithm designed to overcome and avoid these challenges. We design a symmetry-driven optimization approach wherein the EdgePartition1D strategy in GraphX induces partitioning asymmetry, leading to overlapping locally symmetric regions. This structure is leveraged through asymmetric partitioning and symmetric reassembly to reduce the search space. A two-stage pipeline consisting of partitioned repaint and core conflict detection is developed, enabling the precise correction of conflicts without traversing the entire graph as in previous algorithms. We also integrate symmetry principles from combinatorial optimization into a distributed computing framework, demonstrating that leveraging locally symmetric subproblems can significantly enhance the efficiency of large-scale graph coloring. Combined with Spark-specific optimizations such as AQE skew join optimization, all these techniques contribute to an efficient parallel graph coloring optimization in Spardex. We conducted experiments using the Aliyun Cloud platform. The results demonstrate that Spardex achieves a reduction of 8–72% in the number of colors and a speedup of 1.13–10.27 times over concurrent algorithms. Full article

This study addresses inlet flow distribution and pressure pulsation-induced vibration in LNG dual-pump parallel systems. We investigate an LNG dual-submerged pump tower system. Our approach combines computational fluid dynamics with vortex dynamics theory. We examine inlet flow characteristics under different flow conditions. Pressure pulsation propagation patterns are analyzed. System stability mechanisms are investigated. A 3D model incorporates inducers, impellers, guide vanes, outlet sections, and base structures. The SST k-ω turbulence model and Q-criterion vortex identification reveal key features. Results show minimal head differences during parallel operation. The inlet flow field remains uniform without significant vortices. However, local low-velocity zones beneath the base may cause flow separation at low flows. Pressure pulsations are governed by guide vane rotor–stator interactions. These disturbances propagate backward to impellers and inducers. Outlet sections show asymmetric pressure fluctuations. This asymmetry results from spatial positioning differences. Complex base geometries generate low-intensity vortices. Vortex intensity stabilizes at higher flows. These findings provide theoretical foundations for vibration suppression. Full article

This research introduces an innovative probabilistic method for examining torsional stress behavior in spherical shell structures through Monte Carlo simulation techniques. The spherical geometry of these components creates distinctive computational difficulties for conventional analytical and deterministic numerical approaches when solving torsion-related problems. The authors develop a comprehensive mesh-free Monte Carlo framework built upon the Feynman–Kac formula, which maintains the geometric symmetry of the domain while offering a probabilistic solution representation via stochastic processes on spherical surfaces. The technique models Brownian motion paths on spherical surfaces using the Euler–Maruyama numerical scheme, converting the Saint-Venant torsion equation into a problem of stochastic integration. The computational implementation utilizes the Fibonacci sphere technique for achieving uniform point placement, employs adaptive time-stepping strategies to address pole singularities, and incorporates efficient algorithms for boundary identification. This symmetry-maintaining approach circumvents the mesh generation complications inherent in finite element and finite difference techniques, which typically compromise the problem’s natural symmetry, while delivering comparable precision. Performance evaluations reveal nearly linear parallel computational scaling across up to eight processing cores with efficiency rates above 70%, making the method well-suited for multi-core computational platforms. The approach demonstrates particular effectiveness in analyzing torsional stress patterns in thin-walled spherical components under both symmetric and asymmetric boundary scenarios, where traditional grid-based methods encounter discretization and convergence difficulties. The findings offer valuable practical recommendations for material specification and structural design enhancement, especially relevant for pressure vessel and dome structure applications experiencing torsional loads. However, the probabilistic characteristics of the method create statistical uncertainty that requires cautious result interpretation, and computational expenses may surpass those of deterministic approaches for less complex geometries. Engineering analysis of the outcomes provides actionable recommendations for optimizing material utilization and maintaining structural reliability under torsional loading conditions. Full article

Electric vertical take-off and landing (eVTOL) aircraft are transforming urban air mobility (UAM) by providing efficient, low-emission, and rapid transit in congested cities. However, ensuring safe and stable landings remains a critical challenge, particularly in constrained urban environments with variable wind conditions. This study investigates the landing aerodynamics of a multi-rotor eVTOL using the lattice Boltzmann method (LBM), a computational approach well-suited to complex boundary conditions and parallel processing. This analysis examines the ground effect, descent speed, and crosswind influence on lift distribution and stability. A rooftop landing scenario is also explored, where half of the rotors operate over a rooftop while the rest remain suspended in open air. Results indicate that rooftop landings introduce asymmetric lift distribution due to crosswind and roof-induced flow circulation, significantly increasing rolling moment compared to ground landings. These findings underscore the role of descent speed, crosswinds, and landing surface geometry in eVTOL aerodynamics, particularly the heightened risk of rollover in rooftop scenarios. Full article

Deep learning-based hyperspectral image (HSI) classification methods, such as Transformers and Mambas, have attracted considerable attention. However, several challenges persist, e.g., (1) Transformers suffer from quadratic computational complexity due to the self-attention mechanism; and (2) both the local and global feature extraction capabilities of large kernel convolutional neural networks (LKCNNs) need to be enhanced. To address these limitations, we introduce a multi-scale large kernel asymmetric CNN (MSLKACNN) with the large kernel sizes as large as $1\times 17$ and $17\times 1$ for HSI classification. MSLKACNN comprises a spectral feature extraction module (SFEM) and a multi-scale large kernel asymmetric convolution (MSLKAC). Specifically, the SFEM is first utilized to suppress noise, reduce spectral bands, and capture spectral features. Then, MSLKAC, with a large receptive field, joins two parallel multi-scale asymmetric convolution components to extract both local and global spatial features: (C1) a multi-scale large kernel asymmetric depthwise convolution (MLKADC) is designed to capture short-range, middle-range, and long-range spatial features; and (C2) a multi-scale asymmetric dilated depthwise convolution (MADDC) is proposed to aggregate the spatial features between pixels across diverse distances. Extensive experimental results on four widely used HSI datasets show that the proposed MSLKACNN significantly outperforms ten state-of-the-art methods, with overall accuracy (OA) gains ranging from 4.93% to 17.80% on Indian Pines, 2.09% to 15.86% on Botswana, 0.67% to 13.33% on Houston 2013, and 2.20% to 24.33% on LongKou. These results validate the effectiveness of the proposed MSLKACNN. Full article

In this study, we conducted experimental and numerical investigations of a Darrieus rotor with asymmetrical blades, which has two structural configurations—with and without horizontal parallel plates. Experimental tests were conducted in a wind tunnel at various air flow velocities (ranging from 3 m/s to 15 m/s), measuring rotor rotation frequency, torque, and thrust force. The computational simulation used the ANSYS 2022 R2 Fluent software package, where CFD simulations of air flow around both rotor configurations were performed. The calculations employed the Realizable k-ε turbulence model, while an unstructured mesh with local refinement in the blade–flow interaction zones was used for grid generation. The study results showed that the rotor with horizontal parallel plates exhibits higher aerodynamic efficiency at low wind velocities compared to the no-plates rotor. The experimental findings indicated that at wind speeds of 3–6 m/s, the rotor with plates demonstrates 18–22% higher torque, which facilitates the self-start process and stabilizes turbine operation. The numerical simulations confirmed that horizontal plates contribute to stabilizing the air flow by reducing the intensity of vortex structures behind the blades, thereby decreasing aerodynamic drag and minimizing energy losses. It was also found that the presence of plates creates a directed flow effect, increasing the lift force on the blades and improving the power coefficient (Cp). In the case of the rotor without plates, the CFD simulations identified significant low-pressure zones and high turbulence regions behind the blades, leading to increased aerodynamic losses and reduced efficiency. Thus, the experimental and numerical modeling results confirm that the Darrieus rotor with horizontal parallel plates is a more efficient solution for operation under low and variable wind conditions. The optimized design with plates ensures more stable flow, reduces energy losses, and increases the turbine’s power coefficient. These findings may be useful for designing small-scale wind energy systems intended for areas with low wind speeds. Full article

Flight tests and wind tunnel experiments face difficulties in investigating the impact of aircraft carrier air-wake on the landing process. Meanwhile, numerical methods generally exhibit low overall computational efficiency in solving such problems. To address the computational challenges posed by the disparate spatiotemporal scales of the ship air-wake and aircraft motion, a domain precursor inflow method is developed to efficiently generate unsteady inflow boundary conditions from precomputed full-domain air-wake simulations. This study investigates the aerodynamic variability of carrier-based aircraft during landing through the turbulent air-wake generated by an aircraft carrier, employing a hybrid RANS-LES methodology on dynamic unstructured overset grids. The numerical framework integrates a delayed detached-eddy simulation (DDES) model with a parallel dynamic overset grid approach, enabling high-fidelity simulations of coupled aircraft carrier interactions. Validation confirms the accuracy of the precursor inflow method in reproducing air-wake characteristics and aerodynamic loads compared to full-domain simulations. Parametric analyses of 15 distinct landing trajectories reveal significant aerodynamic variability, particularly within 250 m of the carrier, where interactions with island-generated vortices induce fluctuations in lift (up to 25%), drag (18%), and pitching moments (30%). Ground effects near the deck further amplify load variations, while lateral deviations in landing paths generate asymmetric forces and moments. The proposed methodology demonstrates computational efficiency for multi-scenario analysis, providing critical insights into aerodynamic uncertainties during carrier operations. Full article