Search Results (30,906)

Underwater images exhibit severe colour distortion, low contrast, and blurred details due to light absorption and scattering, which limits their practical use in marine applications. Existing methods face poor generalisation, high computational costs and weak integration of physical priors. To address these issues, this paper proposes TIDE-Net, a triple-branch illumination and detail enhancement network for underwater images. It decomposed inputs into illumination, reflectance intensity, and chromaticity branches for parallel optimisation, enabling decoupled handling of brightness, texture, and colour degradation. A piecewise colour correction module mitigated complex colour casts without introducing artefacts; a lightweight U-Net branch enhanced fine details while suppressing noise; and a local gain compensation module improved brightness uniformity and reduced halo effects. Experiments on four datasets showed that TIDE-Net outperforms some state-of-the-art methods, achieving a PSNR of 29.44 dB, an SSIM of 0.94, and competitive UIQM/UCIQE scores with only 7.74 M parameters. The results confirmed that the proposed triple-branch strategy effectively balances physical interpretability, restoration quality, and computational efficiency. In conclusion, TIDE-Net provides a robust and lightweight solution suitable for deployment on resource-limited underwater platforms, offering practical value for real-world underwater vision tasks. Full article

Europium (Eu) is a rare-earth element with unique optoelectronic properties that underpin its applications in displays and lighting, X-ray imaging, anti-counterfeiting, and biomedicine. Conventional methods typically involve the synthesis of europium-based luminescent materials in powder or crystalline form via high-temperature solid-state reactions or solution processes, followed by secondary processing such as spin coating or evaporation to fabricate films or devices. In this work, we report a direct approach to prepare trivalent europium-based luminescent materials using divalent europium bromide (EuBr₂) as the precursor via a gas-phase vacuum evaporation approach (GPVEA). This “deposition-as-synthesis” method enables the fabrication of the hybrid nanoscale films with various blending ratios, which exhibit changes in the fine structure of the emission peaks. The luminescence spectra remain nearly identical across the temperature range from 80 K to 320 K. The photoluminescence emission intensity is stronger in air than in a vacuum. The films show a maximum photoluminescence quantum yield (PLQY) of 8.27% and good photostability, with an emission decay of 3.44% over 50 min under continuous 300 nm excitation. Through patterned design, we demonstrate their value for anti-counterfeiting applications. This work thus provides guidance for the preparation of europium-based luminescent nanomaterials via GPVEA and their application in anti-counterfeiting. Full article

Affective Image Stylization (AIS) converts an emotional intent into executable artistic visual styles. Existing methods are often limited to discrete label settings and provide limited interpretability of how target emotions are realized. We propose LLaVA-Emo, an interpretable AIS framework built on multimodal Chain-of-Thought (CoT) reasoning. Our method decouples generation into two structured outputs: <reasoning> provides visual–affective causal explanations grounded in the input image evidence, and <style_prompt> expresses actionable, renderer-ready style instructions that directly condition a frozen diffusion renderer. We constructed a training set by screening ArtEmis’ sentiment interpretations and fine-tune LLaVA-1.5-7B with LoRA, where SFT mainly supervises the structured intermediate <reasoning> (and output format), while the true executability of <style_prompt> is enforced by our DPO stage via render-and-reward feedback. The rendering stage remains training-free, and we further apply DPO for preference optimization to align candidate outputs with both emotion fidelity and instruction executability. Experiments on the EmoEdit inference set demonstrate that LLaVA-Emo improves emotion alignment while providing stronger process interpretability. Full article

The digital preservation of built cultural heritage requires precise documentation techniques capable of capturing complex architectural geometries often affected by occlusions and data voids. This study presents a robust multi-sensor fusion workflow integrating Terrestrial Laser Scanning (TLS) and Unmanned Aerial Vehicle (UAV) photogrammetry for the 3D reconstruction of the Hasaköy (Sasima) Church in Niğde, Türkiye. To address the limitations of traditional registration methods, specifically the susceptibility of the Iterative Closest Point (ICP) algorithm to local minima in datasets with partial overlaps, this study proposes a fine-tuning approach based on the Multi-population Based Differential Evolution (MDE) algorithm. The methodology employs a coarse-to-fine strategy, initiating with Fast Point Feature Histogram (FPFH) extraction and RANSAC (Random Sample Consensus) for global alignment, followed by TR-ICP, MDE, PSO, and Aquila Optimizer (AO) evaluation, computational-time analysis, FPFH-radius sensitivity testing, and 6-DoF transformation decomposition to characterize both accuracy and operational cost. In the 30-run fine-tuning evaluation, MDE reduced the mean bidirectional trimmed RMSE from 0.4152 m for TR-ICP to 0.3726 m. With a population parameter of 10, MDE retained a low median RMSE of 0.3718 m, while PSO exhibited a wider stochastic tail under the same bounded 6-DoF search budget. AO produced a higher mean bidirectional trimmed RMSE of 0.5233 m. The decimeter-scale bidirectional RMSE should be interpreted as a cross-source, partial-overlap distance metric rather than sensor precision; the overlapping facade objective was approximately 2.4–2.8 cm, and the UAV block was independently controlled with a 1.34 cm GCP RMSE. This study establishes a transparent and reproducible framework for heritage documentation, supporting the faithful digital preservation of endangered monuments with complex typologies. Full article

TC2 titanium alloy (Ti-4Al-1.5Mn, wt.%) is a near-α titanium alloy with promising aerospace and biomedical applications, but its limited room temperature ductility and strong texture sensitivity hinder the fabrication of high-performance sheets. In this study, the effects of hot rolling at 830 °C and 930 °C on the microstructure, macro-texture, mechanical properties, and fracture behavior of TC2 alloy were investigated. Compared with the 830 °C rolled sample, the 930 °C rolled sample exhibited finer primary α grains, a higher volume fraction of fine and dispersed secondary α_s phase, and more uniform Mn distribution, while both samples retained an α + β phase constitution. Texture and ODF (orientation distribution function) analyses revealed that increasing the rolling temperature reduced the maximum intensity of the (0001) pole figure from 6.68 to 5.23 m.r.d. (multiples of a random distribution) and increased that of the (10-10) pole figure to 9.62 m.r.d., indicating weakened basal texture, enhanced prismatic texture, and more dispersed orientation distribution. Consequently, although the tensile strength slightly decreased to approximately 730 MPa, the elongation increased from approximately 24% to 28%. The finer and denser dimples observed after 930 °C rolling further confirmed improved plastic deformation coordination. Full article

Elevated concentrations of fine particulate matter ($P{M}_{2.5}$) are a critical threat to respiratory health worldwide. Therefore, there is an urgent need for precise urban forecasting systems for public health management. Technological advancements in the domains of continuous environmental monitoring and deep learning have enabled large-scale data acquisition, processing, and modeling. Existing predictive models typically depend on auxiliary meteorological inputs, which are frequently inaccessible within standard ground-level monitoring networks. Furthermore, conventional approaches often fail to adequately capture the complex spatio-temporal interactions of pollutants. To address these limitations, this study presents the Spatio-Temporal Endogenous Attention Network (STEA-Net), a forecasting framework designed to operate exclusively without weather variables. Validated on a comprehensive multi-year historical dataset (Jan 2015–Feb 2020) from diverse monitoring stations in India, STEA-Net employs a hybrid adjacency matrix that integrates physical geographical distances with functional clustering to accurately map pollutant transport pathways. Utilizing this structural map, a Graph Attention Network dynamically evaluates the spatial influence of neighboring nodes, while a Bidirectional LSTM processes the underlying temporal sequences. Experimental results demonstrate that STEA-Net substantially surpasses traditional machine learning algorithms and provides competitive performance against advanced deep learning baselines. The proposed model achieves a peak Coefficient of Determination ($R^2$) of 0.9294 (5-seed average: $0.9273\pm 0.0023$) and a peak RMSE of 14.38 µg/m³ (5-seed average: $14.59\pm 0.23$ µg/m³), effectively adapting to the dynamic volatility of urban pollution levels. The model exhibits architectural stability with a Monte Carlo dropout verified deviation of $\pm 2.22$ µg/m³. This research provides a forecasting architecture that retains competitive predictive performance under the strict operational constraint of meteorology-free deployment in resource-constrained urban monitoring environments. Full article

Accurate identification of visually similar targets in Unmanned Aerial Vehicle (UAV) imagery is hindered by significant inter-class ambiguity and viewpoint variability. While hierarchical deep learning mitigates these challenges, existing architectures relieve manual design, introducing subjectivity and limiting cross-domain scalability. In this work, we propose an objective, data-driven method for the automated synthesis of hierarchical classification structures. Our approach uses a hybrid inter-class proximity metric that integrates geometric distances between latent-feature-space centroids with empirical misclassification probabilities. Using a hierarchical agglomerative clustering algorithm optimized via an inconsistency coefficient, we synthesize a coarse-to-fine cascade that deploys YOLOv11 for feature extraction and FT-Transformers for specialized identification. Experimental validation on the VisDrone2019 and UAV123 datasets demonstrates that the automatically generated hierarchy achieves a peak F1-score of 94.9%, outperforming the monolithic YOLOv11 model by 0.8% and matching human-designed cascades. Sensitivity analysis indicates an optimal hybrid weight range of 0.4–0.6. The findings confirm that our automated synthesis provides high adaptability and reliability for real-time edge AI deployments, ensuring robust performance in dynamic monitoring environments without requiring manual redesign. Full article

Epileptic seizure prediction using an Electroencephalogram (EEG) can improve patient safety by enabling early intervention, yet most existing approaches focus on short prediction horizons with limited personalization or computational efficiency. This study presents a unified deep learning framework evaluated across ten pre-ictal prediction windows up to 300 min before seizure onset, using recordings from 161 patients and 1023 seizure events. At the 5 min horizon, the generalized model achieved 96.30% accuracy and 91.62% sensitivity. Two complementary personalization strategies are introduced: incremental transfer learning, which progressively fine-tunes the generalized model using patient-specific data, and Dynamic Time Warping (DTW)-based similarity personalization, which constructs a morphology-aware training cohort from a single reference seizure. Personalized models consistently outperform generalized baselines, particularly at longer horizons, with the DTW-based approach achieving 89.68% accuracy using only 70 similar patients. Reliable prediction is demonstrated up to 60 min prior to onset, while model optimization reduces computational complexity with minimal performance loss, supporting deployment in resource-constrained clinical environments. Full article

The practical application of Brain–Computer Interface (BCI) technology is frequently challenged by significant inter-individual variability in electroencephalogram (EEG) signals. This variability makes it extremely difficult to decode the brain activity of new subjects using pre-recorded data from previous subjects. To address these issues, this study presents an EEG decoding approach based on four-stage domain generalization. We start by preprocessing the data and then dividing it into source and target domains. The source domain data are then passed through four sequential modules: Feature Extraction, Feature Augmentation, Feature Optimization, and Domain Adaptation, where we adjust the parameters using the source domain loss function. Next, the target domain data go through the same four stages while we fine-tune the parameters together with the domain adaptation loss, ultimately obtaining the decoding results for the target domain. The proposed method achieves the highest classification accuracy of 72.61%, outperforming EEGTransferNet by 7.22% and surpassing all classical and deep learning baselines by improvements ranging from 5.97% to 23.86%. Overall, the proposed method significantly enhances cross-subject generalization in motor imagery decoding, offering practical value for plug-and-play BCI applications. Full article

This paper presents a multidimensional analysis of Historic Building Information Modeling (HBIM) segmentation, offering a roadmap towards standardization, a key dimension towards broader adoption within the Cultural Heritage (CH) sector. HBIM faces multiple challenges related to the lack of standardized protocols and varying definitions of Level of Detail (LOD) across applications. Amid the advancements of the fourth industrial revolution, integrating Building Information Modeling (BIM) improves sustainability and digital governance, aligning with the sustainable development agenda. Despite increasing academic interest, the implementation of HBIM remains limited, primarily due to the complexities and heterogeneities inherent in CH artifacts. This study begins with a purely qualitative strategy. Then, it introduces multidimensional and hierarchical clustering analysis to classify the unique characteristics of various HBIM applications such as segmentation, input, and data-capturing media. At the same time, it is a tool for fine-tuning keyword-based selection criteria, which is crucial in systematic or semi-systematic surveys in HBIM segmentation. The thematic analysis output is interrupted just before the conceptualization step, and theme extraction is diverted to correspondence analysis implemented in R, an open-source statistical package. Among the key findings of this paper is the classification of four distinct HBIM application clusters, revealing how specific workflows align with data acquisition methods, input formats, and Level of Detail (LOD) requirements. The analysis exposes critical standardization bottlenecks hindering wider-scale industry adoption, highlighting that challenges are domain-specific. Strong evidence shows that 3D modeling has not reached the required maturity level, with persisting challenges distributed non-uniformly within the applications spectrum. Finally, AI-driven automation relates with poor LOD outcome. Full article

This study examined how duct inclination influences particle removal in a hybrid acoustic–electrostatic filtration system operating at low airflow velocities. The experiments were carried out in a 150 mm diameter air duct at airflow speeds of 0.50 and 0.75 m/s, with duct inclinations of 45° and 90°. Aerosol particles with properties similar to marine diesel exhaust, spanning a size range of 0.2–10 µm, were introduced at stable concentrations. Electrostatic voltages of 17.5 and 20 kV were applied, together with acoustic voltages between 100 and 200 V. Particle removal was evaluated using both size-resolved and overall collection efficiencies. The results show that duct inclination mainly affects the removal of fine and medium-sized particles. The largest differences were observed for particles around 1 µm in diameter, where the vertical duct increased collection efficiency by up to 27 percentage points at an airflow speed of 0.75 m/s. For larger particles in the 5–10 µm size range, high removal efficiency was achieved under all tested conditions, and duct orientation had a smaller influence on collection performance. Overall, the results confirm that duct inclination has a clear and measurable effect on the performance of hybrid acoustic–electrostatic filtration systems operating at low airflow velocities. Full article

Automatic Modulation Classification (AMC) is essential for waveform-level signal characterization. It supports spectrum sensing, signal identification, and adaptive resource allocation in cognitive radio and next-generation wireless systems. However, channel impairments such as multipath propagation, frequency offset, fast fading, and noise degrade modulation signatures, making reliable AMC challenging. Existing deep learning-based approaches often rely on purely data-driven learning, leading to insufficient modeling of modulation-relevant features, loss of transient characteristics, and limited exploitation of hierarchical relationships among modulation types. To address these issues, this paper proposes PHM-Net, a physics-informed hierarchical multi-scale network for robust AMC. The model employs a hierarchical backbone with residual encoder blocks. A Transient Feature Gating (TFG) module enhances modulation-relevant representations, a Cross-Resolution Signal Aggregation (CRSA) module fuses multi-stage features, and a Physics-Informed Hierarchical Loss (PI-HL) enforces consistency between coarse- and fine-grained predictions. Experimental results on three benchmark datasets (RML2016.10a, RML2016.10b, and RML2018.01a) show that PHM-Net consistently achieves the highest average accuracy among all compared models. On RML2018.01a, which contains 1024-sample sequences and 24 classes, PHM-Net achieves an average accuracy of 64.59% and a best-case accuracy of 98.42%, surpassing AMC_Net by 11.14 and 17.09 percentage points and CNN-Transformer by 9.43 and 11.15 percentage points, respectively. PHM-Net provides a robust and interpretable solution for AMC under complex channel conditions. Full article

Laser powder bed fusion (LPBF) of high-strength aluminum alloy 7075 (AA7075) is severely limited by hot cracking. However, the underlying mechanisms, particularly the coupling between thermal fields, solidification microstructure, and cracking behavior, remain insufficiently clarified. This study elucidates these mechanisms by integrating experimental characterization with thermal simulation to investigate the temperature field, microstructure, and cracking relationships in both AA7075 and a crack-resistant 7075-Er-Zr alloy. Results show that coarse hot crack morphology is highly dependent on linear energy density E_L. In AA7075, E_L < 450 J/m promotes laterally inclined cracks (short, narrow cracks extending from the melt pool boundary toward the track center), whereas E_L higher than that value leads to the continuous centerline cracks (long, wide cracks along the track center). Fine microcracks are also observed at melt pool boundaries. The 7075-Er-Zr alloy demonstrates superior crack resistance. At E_L = 600 J/m, longitudinal centerline cracks still penetrate along the track, but the alloy achieves crack-free tracks at 200 W with scanning speeds above 1000 mm/s, otherwise exhibiting only short discontinuous cracks. Microcracks at melt pool boundaries are markedly suppressed in the modified alloy. The enhanced crack resistance is attributed to Er/Zr-induced grain refinement and a transition to an equiaxed grain structure, which disrupts intergranular gaps. Critically, thermal simulations identify an annular region with a peak temperature gradient. In AA7075, this region develops aligned columnar grains that facilitate both microcracks and centerline cracks. In the 7075-Er-Zr alloy, microcracks are fully eliminated within this region. However, a residual crystallographic texture persists in the annular region, which promotes the continued occurrence of centerline cracks under high energy density (e.g., E_L = 600 J/m). The annular region remains a critical weak link, and its microstructural control determines the prevailing crack type. This work provides a fundamental understanding of the thermal-microstructural origins of cracking and offers a theoretical foundation for developing crack-resistant aluminum alloys via LPBF. Full article

There is increasing interest in structured layered double hydroxide (LDH)-based catalysts because they combine tunable acid–base/redox chemistry with reactor architectures that can reduce diffusion lengths, improve heat management, and lower pressure-drop penalties. This review evaluates LDH, LDH-derived oxide (LDO/MMO), reduced metal/LDO, reconstructed hydroxide-rich, and mixed dynamic states integrated into honeycomb monoliths, open-cell foams, meshes/felts, thin films, washcoats, coated plates, microchannels, capillaries, and additively manufactured lattices. To move beyond descriptive comparison, the literature is assessed using unified evaluation dimensions: operative active state, support architecture, coating/integration route, active-phase loading, coating thickness and uniformity, reactor-volume-normalized productivity or STY, ΔP/L, axial/radial thermal gradients, time-on-stream, coating loss, regeneration recovery, and pilot-readiness. Representative benchmarks illustrate both the promise and reporting gaps of the field: NiFe-LDH-derived monoliths for CO₂ methanation have reached ~70% CO₂ conversion at 300 °C with >90% CH₄ selectivity and only 0.7% post-test mass loss; NiFe-LDH/iron-foam monoliths retained 85% ozone conversion after 168 h; high-entropy LDH-derived oxides showed T50/T90 values of 246/254 °C for toluene oxidation; and Au/LDH capillary films achieved 31.9% glycerol carbonate yield and 3.78 g h⁻¹ g⁻¹ productivity. The strongest current cases are pollution abatement and CO₂ methanation, whereas biomass upgrading, fine-chemical flow, high-entropy coatings, and photo/electrocatalytic films require deeper module-level validation. Overall, structured LDH catalysts should be treated as coupled chemistry–coating–reactor systems whose performance must be judged simultaneously by activity, accessible catalyst inventory, transport efficiency, pressure drop, thermal profile, durability, regeneration, and manufacturability. Full article

This study presents numerical and experimental investigations of a voltage-controlled active preload adjustment system for an ultrasonic traveling wave piezoelectric motor intended for potential use in space-related systems. The proposed preload system consists of two ring-shaped piezoceramic elements driven by a DC voltage of up to 300 V_DC. The passive conical spring provides the nominal rotor preload, while the piezoelectric ring stack enables open-loop remote fine adjustment of the stator–rotor contact force by modifying the axial compression of the spring. Finite element simulations were performed over a temperature range from −25 °C to 55 °C to evaluate the electromechanical response and thermal sensitivity of the preload system. The numerical results indicated that the active preload system can generate a simulated preload force variation of approximately 0.47 N at 300 V_DC, corresponding to approximately 21.4% of the nominal initial preload force of 2.2 N. Experimental tests were conducted in a thermal vacuum chamber at a pressure of 5.6 × 10⁻⁶ mbar. The measured displacement of the piezoceramic preload stack ranged from 0.33 µm to 2.36 µm and showed good agreement with the numerical displacement results. Motor speed measurements demonstrated that increasing the preload-control voltage from 0 to 300 V_DC resulted in an average angular speed increase of approximately 17–20 RPM, depending on temperature. The results demonstrate that the proposed system can provide compact open-loop preload fine adjustment under thermal vacuum conditions, with preload force variation supported by FEM estimation and experimentally validated displacement response. Full article