Search Results (22,296)

Infrared stripe noise, mainly caused by detector nonuniformity and readout inconsistencies, is a common structured degradation in infrared imaging systems, exhibiting pronounced directional bias, strong column-wise persistence, and distinctive frequency-domain characteristics. These properties make generic restoration networks prone to a trade-off between stripe suppression and detail preservation: conventional two-dimensional attention often allocates modeling capacity to stripe-irrelevant spatial dependencies, early downsampling may entangle directional stripe components with scene structures, and skip connections in U-shaped architectures can reintroduce shallow residual stripe features into the decoder. Residual stripe artifacts and restoration-induced structural distortions can further impair downstream infrared image analysis, particularly small-target detection. To address these issues, we propose a Spatio-Frequency Synergistic Progressive Restoration Network (SFPRNet) for infrared image destriping. SFPRNet progressively exploits the column-wise statistical characteristics of stripe noise, directional frequency information during early scale transformation, and selective cross-level feature refinement to enhance stripe discrimination and suppression while preserving structural details. Extensive experiments on synthetic and real infrared images demonstrate that the proposed SFPRNet achieves superior or competitive performance across most datasets and degradation settings, providing a favorable balance between destriping quality and detail preservation. Furthermore, downstream evaluation with multiple infrared small-target detectors demonstrates that SFPRNet improves subsequent small-target detection performance. Full article

Problems with power transformers reduce grid reliability and can lead to large financial losses. Traditional Dissolved Gas Analysis (DGA) methods, such as the Key Gas Method, Ratios, and Duval Triangle, often give unclear results when faults are complex or occur together. This study introduces a Statistically Guided Decision Tree (SGDT) framework, a combined approach that uses statistical DGA analysis and decision tree learning to identify transformer faults. This approach creates rule-based fault categories using advanced statistical analysis of real DGA data and tests how well these categories work with a Decision Tree model. Advanced statistical techniques such as dispersion and association metrics, confidence intervals, and distribution characteristics were used on a wide range of DGA records collected from a 275 kV transformer to define threshold values. Thereafter, fault classification rules were developed, and finally, a decision tree algorithm was developed to evaluate whether the gas concentration-based rules for fault labelling aligned with real data behaviour. The classification accuracy of 0.993 was achieved, indicating a high rate of correctly identified fault types. The F1-score, representing the harmonic mean of precision and recall, was 0.980, confirming both high precision and recall. Specifically, the recall was 0.980, meaning that 98% of real fault cases were correctly found, while the precision was 0.981, showing that 98.1% of predicted fault cases were correct. The Area Under the Curve (AUC) was 0.987, showing the model could clearly tell the difference between fault and non-fault cases. This work demonstrates the effectiveness of the current proposed SGDT framework, and this will help utilities that want to digitise their transformer maintenance and diagnostics for better decision-making. Full article

Accurate and timely monitoring of terrestrial oil spills is vital for ecological conservation and safe oilfield operations. To address the challenges of segmenting terrestrial oil spills in UAV remote sensing imagery, including blurred boundaries, irregular shapes, and complex background interference, we propose Fluid-SegFormer, a fluid-aware semantic segmentation model based on the lightweight SegFormer architecture. Fluid-SegFormer employs a Mix Transformer (MiT-B0) encoder to extract hierarchical multi-scale features and integrates a hierarchical fluid-aware optimization framework. Specifically, the Local Noise Gating (LNG) module suppresses background noise, the Horizontal–Vertical Perception Attention (HVPA) module enhances the structural representation of irregular oil spill regions, and the Fluid Soft Boundary Refinement Decoder (FSBRD) recovers fine boundary details. Experiments on a newly constructed high-resolution UAV terrestrial oil spill dataset demonstrate that Fluid-SegFormer achieves an mIoU of 87.84%, an IoU of 77.56%, and a Precision of 91.42%, effectively balancing computational efficiency and segmentation accuracy. These results demonstrate the potential of Fluid-SegFormer for practical deployment in UAV-based oil spill monitoring on edge devices. Full article

This study proposes a surrogate model, Graph-Structured Physics-Informed Deep Operator Network (GS-PI-DeepONet), to simulate two-dimensional hydrodynamics in a tidal river network. The model was coupled with Graph Convolutional Networks (GCNs) for spatial feature extraction and Long Short-Term Memory (LSTM) network for temporal prediction, with 2D shallow-water equations (2D SWEs) embedded as physical constraints. To handle complex river network topologies, a mapping mechanism was proposed to transform discrete irregular boundaries into differentiable neural network constraints. A dynamic weighting strategy was developed to improve model training efficiency. GS-PI-DeepONet was applied to a river network within the Pearl River Basin in Zhuhai. Trained on high-fidelity Delft3D data, it achieved precise flow field reconstruction and millisecond-level extrapolation predictions, outperforming traditional data-driven models. The model can be a valuable tool for real-time hydrodynamic simulations and flood management strategies in tidal river networks. Full article

With the widespread adoption of cloud computing technology, modern cloud platforms have become increasingly complex and dynamic, posing significant challenges for efficient resource management. Accurate forecasting of cloud resource loads has therefore become essential for improving service quality, optimizing resource utilization, and reducing operational costs. To address the intrinsic characteristics of cloud load time series, including nonlinear fluctuations, multi-scale temporal dependencies, and redundant high-dimensional features, this paper proposes the MST-iTransformer model, which integrates multi-scale temporal encoding, sparse attention, and adaptive feature selection mechanisms. Specifically, a multi-scale temporal encoding module is developed to capture and fuse temporal dependencies across multiple periodic scales. Furthermore, an adaptive feature selection module is introduced to dynamically assign importance weights to resource features, enhancing informative variables while suppressing redundant ones. Meanwhile, a sparse attention mechanism is incorporated to reduce computational overhead while maintaining forecasting accuracy. The proposed model is evaluated on the Alibaba Cluster Trace dataset. Experimental results demonstrate that MST-iTransformer achieves MSE, RMSE, and MAE values of 0.5559, 0.7456, and 0.4968, respectively. Compared with the original iTransformer, the proposed model achieves simultaneous reductions in prediction errors and inference latency, validating the effectiveness of the multi-scale temporal encoding, sparse attention mechanism, and adaptive feature selection modules in improving forecasting accuracy and computational efficiency. These improvements provide reliable prediction support for resource scheduling and elastic scaling in cloud data centers. Full article

Large Language Models (LLMs) have been rapidly evolving lately, resulting in the need for strong, explainable models to detect the difference between human-generated and machine-generated articles. Existing approaches which are mostly based on fine-tuned transformers suffer from several drawbacks such as rapid obsolescence, paraphrasing attacks, and lack of interpretability. To improve their ability to detect, this paper proposes a novel paradigm called Human vs. LLM Identification (HLI) which introduces a Retrieval-Augmented Generation (RAG)-inspired evidence-based detection strategy alongside a fine-tuned transformer classifier. Our core model, DeBERTa-Sentinel, is built on top of a fine-tuned Microsoft DeBERTa-v3-small model, which uses a disentangled attention mechanism to better capture subtle syntactic and stylistic deviations characteristic of AI-generated text. We evaluate our framework on a balanced dataset of 43,456 text samples, curated from the OpenGPTText corpus and covering AI-generated and human-authored content across diverse domains including news, education, and creative text. The experimental results show improved performance over the selected baselines, with our framework achieving an accuracy of 97.53%, precision of 95.89%, recall of 99.34%, and ROC-AUC of 99.53%. In addition, explainability is integrated into our framework through Local Interpretable Model-agnostic Explanations (LIME) analysis, providing token-level insight into classification decisions. This study establishes a benchmark for scalable, explainable AI text detection, with implications for academic integrity, content moderation, and combating misinformation. Full article

Fast charging of lithium-ion batteries requires balancing charging efficiency with electrochemical safety to minimize degradation and lithium plating. Conventional charging strategies and existing reinforcement learning approaches often lack physical consistency and model interpretability, limiting their applicability in safety-critical battery management systems. This paper proposes a physics-informed Attention-Proximal Policy Optimization (Attention-PPO) framework for intelligent battery fast charging by integrating the Single Particle Model with Electrolyte (SPMe) with a transformer-based attention mechanism. SPMe provides physically meaningful battery state transitions, while the attention-enhanced PPO dynamically learns informative electrochemical representations for charging control. To improve transparency, a monotonic XGBoost surrogate model is employed for lithium-plating risk estimation, and the learned policy is further distilled into an interpretable decision tree. Experimental results demonstrate that the proposed Attention-PPO achieves substantially faster and more stable policy convergence than the baseline PPO, reaching convergence at episode 37 compared with episode 82 for PPO, corresponding to a 54.9% reduction in training episodes. The reward standard deviation is also reduced from 0.132 to 0.041, indicating 68.9% lower reward variability. In terms of electrochemical safety, Attention-PPO achieves a mean plating overpotential of +0.023 V compared with −0.015 V for PPO, providing a 38 mV improvement and a positive safety margin against lithium plating. Compared with conventional CC-CV and CC-COP controllers, the proposed framework requires a longer charging duration because it prioritizes electrochemical safety; however, it consistently maintains positive plating overpotential while achieving reliable charging performance. Compared with conventional CC-CV, CC-COP, and standard PPO controllers, the proposed framework provides a larger electrochemical safety margin while preserving reliable charging performance. Transformer attention analysis and policy distillation provide interpretable representations of the learned charging policy, while SHAP analysis characterizes feature contributions within the auxiliary plating-risk estimator. The proposed framework provides an effective and explainable physics-informed reinforcement learning solution for safe lithium-ion battery fast charging, offering a promising approach for next-generation intelligent battery management systems. Full article

Recent studies have witnessed significant advances in unified multi-weather image restoration, which aims to handle diverse weather degradations within a single model. In this work, we observe that rain, haze, and snow restoration exhibit substantial differences in both degradation characteristics and learning dynamics, making straightforward joint optimization prone to performance imbalance and ineffective knowledge transfer. To this end, we propose UMWIR-Net, a unified multi-weather image restoration network equipped with an Asymmetric Task Collaborative Learning strategy. ATCL consists of Intra-Task Difficulty Optimization and Inter-Task Contribution Scheduling. Specifically, Intra-Task Difficulty Optimization jointly models the remaining restoration error and recent learning progress to dynamically estimate the optimization difficulty of each weather task, thereby assigning larger weights to slowly converging and under-optimized tasks. Inter-Task Contribution Scheduling measures the directional influence of a source-task update on the validation objective of a target task, constructs an asymmetric task-contribution matrix, and accordingly promotes tasks that provide stronger transferable knowledge while compensating those that benefit less from collaborative learning. In this manner, different weather restoration tasks collaborate selectively and asymmetrically, allowing the model to exploit complementary knowledge across tasks and improve overall restoration performance. Furthermore, UMWIR-Net adopts a wavelet-based Transformer backbone to capture low- and high-frequency information, enabling effective modeling of both global structures and local details for diverse weather restoration. Extensive experiments on multi-weather image restoration datasets show that UMWIR-Net achieves state-of-the-art performance and delivers more balanced restoration quality across rain, haze, and snow removal. Full article

Accurate and non-destructive assessment of drought stress is important for improving lettuce production and supporting timely crop management. This study presents a detection-guided deep learning framework for plant-level drought-stress assessment in hydroponically grown lettuce using bird’s-eye-view RGB images. The study further investigates whether canopy segmentation can improve classification performance by reducing irrelevant background information. The framework was evaluated using 2190 images collected across three independent cultivation cycles in which drought stress was induced by isolating the plant root zones from the nutrient solution. In the first stage, YOLO-based object detection was used to localize individual plants, with YOLO26m achieving the highest detection performance of 99.4% mAP@0.5. The detected regions were subsequently used as spatial prompts for zero-shot canopy segmentation using the Segment Anything Model (SAM), with SAM ViT-B achieving a mean IoU of 0.9864. Six convolutional, transformer-based, and hybrid classification architectures were then evaluated independently using YOLO-cropped and SAM-segmented plant images. Segmented inputs consistently improved classification performance, with MaxViT-S achieving the highest binary test accuracy of 96.3%. The framework further distinguished time-defined pre-stress, early-stress, and late-stress periods with an accuracy of 92.4%. Plant-level generalization was further assessed using six-fold leave-one-plant-out cross-validation, resulting in a mean test accuracy of 90.25 ± 1.78% on unseen plants. These findings demonstrate that RGB-based plant-level analysis can support non-destructive drought-stress assessment and that canopy segmentation improves classification by reducing background influence. Full article

Vibration signals of planetary gearboxes under variable-speed conditions exhibit strong non-stationarity and modulation, so a single feature representation cannot comprehensively describe intricate fault patterns, and distribution discrepancies across rotating speeds degrade the cross-condition generalization of diagnostic models. To address these limitations, this paper proposes an adaptive domain-aligned multi-modal feature fusion network (ADAMFFN). Three parallel branches extract complementary features from dual-channel vibration signals: spatial coupling features from orbit images, time–frequency energy features from continuous wavelet transform (CWT) representations, and frequency-domain statistical (FreqStat) features from power and envelope spectra. Heterogeneous features are mapped into a shared latent subspace through a unified projection layer, deep cross-modal interaction is realized by a progressive fusion network, and a domain alignment mechanism based on a domain-adversarial neural network (DANN) is introduced to eliminate source–target distribution gaps via adversarial training. On eight leave-one-speed-out (LOSO) cross-speed tasks constructed on the public WT-Planetary Gearbox dataset, ADAMFFN achieves an average accuracy of 99.25%, outperforming the best single-branch and dual-branch schemes by 2.63 and 0.40 percentage points, respectively; ablation experiments verify the complementarity of the three modalities and the effectiveness of domain alignment. Cross-condition external validation on the Southeast University (SEU) gearbox dataset further demonstrates its generalization capability under a different test rig and acquisition conditions. Full article

Accurate and up-to-date information is essential for environmental monitoring, particularly in regions characterized by complex topography and heterogeneous landscapes. This study presents a multisource remote sensing–based approach for forest vegetation classification on La Palma Island (Canary Islands, Spain), which was further used to illustrate its potential for monitoring the temporal dynamics of different forest habitat types. Very high-resolution multispectral data from the WorldView-2/3 satellites were used, complemented by multispectral and LiDAR data acquired by an unmanned aerial vehicle (UAV). Four target forest vegetation types were mapped within a six-class classification scheme that also included “Other vegetation” and “Soil/Others” as non-target/background classes. The performance of ten supervised classification algorithms was evaluated, including Minimum Distance, Mahalanobis Distance, Parallelepiped, Spectral Angle Mapper, Maximum Likelihood, Naïve Bayes, K-Nearest Neighbors, Random Forest, Support Vector Machine, and the transformer-based deep learning model SegFormer. The results indicate that Random Forest achieved the highest overall accuracy, while Support Vector Machine and SegFormer also showed competitive performance, particularly when spectral information was integrated with vegetation indices and topographic variables. The study provides practical evidence on the selection of input data and classifiers for detailed forest vegetation mapping in a large and topographically complex island. Full article

Reliable battery prognostics for electric vertical take-off and landing (eVTOL) aircraft require models that preserve phase-dependent electrothermal information while generalizing to cells absent from training. This study reconstructs the public CMU eVTOL battery dataset and establishes a leakage-safe benchmark for state of charge (SOC), five-mission-ahead state of health (SOH), and threshold-based remaining useful life (RUL). A protocol-based screen identified 441 valid C/5 reference-performance-test anchors across 22 cells; three cells with non-monotone diagnostic-capacity trajectories were excluded from the primary health benchmark, leaving 19 cells. Predictors were restricted to telemetry-derived phase and mission features, with cell identity and target- or future-derived quantities excluded. All health models were evaluated using outer leave-one-cell-out validation with matched 20-mission histories. Random Forest achieved the lowest SOH MAE of 0.620 percentage points, compared with 1.252 for the mission-phase Transformer and 1.471 for Attention-LSTM-MoE. The best RUL MAEs were 24.067, 46.527, and 122.198 missions at the 90%, 85%, and 80% SOH thresholds. Cell-bootstrap uncertainty showed that model differences were threshold-dependent. Row-random splitting produced substantially more optimistic errors than cell-held-out evaluation. These results show that rigorous target construction and leakage-safe validation are critical and that increased sequence-model complexity does not guarantee superior unseen-cell generalization. Full article

Degraded tax forms and other legal–administrative documents require restoration methods that impose strict constraints on content fidelity. This paper presents a structure-aware restoration framework for degraded tax documents that combines geometric normalization, canonical template guidance, and supervised image restoration within a common alignment space. Documents are first mapped to a canonical layout through homography estimation based on Scale-Invariant Feature Transform (SIFT) and Random Sample Consensus (RANSAC), using the canonical visual template as the reference. Restoration is then performed using template priors and masked constraints designed to preserve the fixed document structure while recovering variable content. Under a fixed-budget comparative protocol, U-Net with template priors achieved the highest visual and structural quality, whereas the proposed hybrid model obtained the best functional OCR performance on synthetic data, reaching a Character Error Rate (CER) of 0.1091 and a Word Error Rate (WER) of 0.3495. As a complementary evaluation on 37 real-world documents with human-generated textual ground truth, restoration increased full-page word coverage across all three OCR engines evaluated, yielding absolute improvements ranging from 4.15 to 18.05 percentage points. Full article

Accurate identification of multiphase flow patterns in vertical pipelines is critical for operational safety and efficiency in the oil and gas industry. Yet, conventional methods struggle with subjectivity and transitional regimes. This study develops and integrates three neural network architectures: a convolutional neural network (CNN) for spatial features, a transformer neural network (TNN) for long-range dependencies, and a physics-encoding network (PEN) for embedding physical constraints. These are combined into a hybrid framework trained on an experimental dataset of 2131 images from a wire mesh sensor, annotated using a semi-automated pipeline. Results show the hybrid model achieved 95.91% test accuracy with a macro F1-score of 0.96, the highest of the four models evaluated, with its main advantage in transitional regimes. A multi-seed ablation shows that the convolutional branch provides the dominant discriminative signal, while the transformer and physics-inspired branches added complementary improvements that are consistent across runs. This hybridisation mitigates individual model weaknesses, with the physics-inspired branch acting as a spatial regulariser that improves interpretability, providing a robust and objective tool for reliable pipeline monitoring. Full article

Background/Objectives: Nonsurgical treatment for pancreatolithiasis is widely performed. However, treatment success remains difficult to predict before treatment initiation, complicating the selection of an appropriate treatment strategy. This study aimed to predict pancreatic stone clearance after nonsurgical treatment for pancreatolithiasis associated with chronic pancreatitis by integrating pretreatment computed tomography (CT) images and clinical information using deep learning and machine learning models. Methods: Of 195 patients with pancreatolithiasis associated with chronic pancreatitis who underwent nonsurgical treatment, including extracorporeal shock wave lithotripsy, at our institution between 1992 and 2024, only 91 (47%) had extractable pretreatment noncontrast abdominal CT images and were included in the AI analysis. Multiple deep learning models (VGG16/19, InceptionV3, ResNet50, DenseNet121/169/201, Vision Transformer, and Swin Transformer) were trained using CT images, and their predictive performance was compared. Imaging-derived and clinical predictors selected using only the training data in each patient-level cross-validation fold were combined and used as inputs for conventional machine learning models, including random forest, support vector machine, naïve Bayes, neural network, and gradient boosting. Results: Successful pancreatic stone clearance was achieved in 54 of 91 patients (59%). Compared with the 104 patients without extractable CT data, the analyzed cohort had a higher proportion of asymptomatic pancreatolithiasis (43% vs. 15%) and a markedly lower pancreatic stone clearance rate (59% vs. 88%), indicating potential selection bias. Asymptomatic pancreatolithiasis and a pancreatic stone size of ≥15 mm, defined using a data-derived exploratory cutoff, were significantly associated with unsuccessful stone clearance. Among the deep learning models, ResNet50 achieved the highest performance (area under the receiver operating characteristic curve [AUC], 0.718), followed by Vision Transformer (Large model, 16 × 16 patches) (AUC, 0.700). When image-derived features were combined with clinical features, the neural network achieved the best performance, with a mean AUC of 0.757, a median sensitivity of 0.568, a median specificity of 0.704, and a median accuracy of 0.659. Conclusions: A neural network integrating CT-derived image features with clinical information showed moderate internal predictive performance for pancreatic stone clearance. Because this was a single-center retrospective study without external validation, the present model should be regarded as a preliminary predictive model requiring validation in independent cohorts before clinical application. Full article