Search Results (8,172)

Industrial equipment data often exhibit high dimensionality and class imbalance, which make it difficult to achieve both accurate failure detection and identification of the factors contributing to failures. To address this issue, this study proposes an explainable failure classification framework, Feature-Wise Attention Graph Convolutional Network (FWA-GCN), which combines Feature-Wise Attention (FWA) with a Graph Convolutional Network (GCN) to provide both high classification performance and variable-level interpretability. In the proposed model, tabular sensor records are treated as nodes, and a similarity-based graph is constructed to capture relationships among samples. Feature-Wise Attention learns the importance of each feature and reweights node features accordingly, and the reweighted features are then used as input to the GCN to classify failure occurrences. To alleviate the class imbalance problem, a weighted loss function is applied during training by assigning a higher weight to the failure class. Experiments conducted on the Air Pressure System (APS) dataset demonstrate that the proposed FWA-GCN achieves Precision of 79.95%, Recall of 85.07%, and F1-score of 82.43%, outperforming conventional machine learning models including Random Forest, XGBoost, CatBoost, and Multi-Layer Perceptron, as well as a standard GCN model. Furthermore, an ablation study was conducted by removing the top features selected by the attention mechanism. The results show a significant decrease in recall, confirming the effectiveness of the attention-based feature importance and supporting the interpretability of the proposed framework. Full article

This study develops a unified multiscale–machine learning framework to interpret and predict thermo-mechanical wear regime transitions in MWCNT- and nanoclay-reinforced bio-based epoxy composites. A physics-informed master wear formulation integrating real contact mechanics, geometry-dependent shear transfer, interfacial adhesion energetics, and fracture-controlled matrix detachment was combined with interpretable machine learning analytics on a unified tribological dataset. In the CNT system, increasing loading from 0.1 to 0.4 wt.% enhanced interfacial adhesion energy density from 0.00813 to 0.01906 J/m², resulting in a monotonic reduction in the wear rate from 0.00918 to 0.00613 mm³/N·m (~33% reduction). In contrast, nanoclay exhibited an optimum behavior, with a minimum wear at 0.25 wt.% (0.000093 mm³/N·m; 7.9% reduction vs. neat clay baseline), followed by deterioration at a higher loading due to dispersion loss. The unified probabilistic regime classification of low-wear conditions (k < 0.007 mm³/N·m) achieved an ROC − AUC = 0.9256 and balanced accuracy = 94.3%, with thermo-mechanical severity identified as the dominant regime-switching driver. Reinforcement identity significantly modulated regime stability, confirming distinct shear transfer (Carbon Nano Tubes(CNT)) and confinement/tribofilm (clay) mechanisms within a common mathematical framework. By enabling the durability-oriented design of bio-based tribological systems and extending component service life through predictive stability mapping, this work contributes to resource-efficient materials engineering and reduced lifecycle waste, supporting Sustainable Development Goals SDG 9 (Industry, Innovation and Infrastructure), SDG 12 (Responsible Consumption and Production), and SDG 13 (Climate Action). Full article

Magnetic resonance imaging (MRI) reconstruction from undersampled k-space data enables accelerated acquisition but leads to a severely ill-posed inverse problem. Although supervised deep learning methods have achieved strong performance, they typically rely on large paired datasets that are difficult to obtain in clinical practice. To address these limitations, we propose a dictionary-learning-inspired dAta-fRee deep generative modeling with Meta-Attention and implicit precoNditIoning for compressively sampled MRI (CS-MRI), termed ARMANI. Specifically, a meta-attention-augmented deep image prior (MA-DIP) generator performs a joint optimization over the latent input $\eta$ and the network parameter $\theta$, where $\eta$ is regularized via gradient-domain sparsity and $\theta$ is constrained by a ridge penalty, mirroring the adaptive estimation of sparse coefficients and an empirical sparsifying dictionary. Furthermore, we integrate a single-step pseudo-orthogonal projection to achieve implicit preconditioning, which modulates the loss landscape and mitigates ill-conditioning of the forward operator. Experimental results demonstrate that ARMANI consistently outperforms existing SOTA data-free and self-supervised methods, and, with limited training data, achieves performance comparable to or slightly better than the supervised benchmark MoDL, with effective artifact suppression and faithful recovery of fine structural details. Overall, ARMANI shows strong scalability and potential for practical deployment in fully data-free CS-MRI reconstruction scenarios. Full article

Data-centric approaches are increasingly shaping wireless communication research, where the availability and quality of datasets directly influence the reliability of learning-based and model-driven methods. In this context, unmanned aerial vehicle (UAV) communication poses unique challenges, as it requires datasets that jointly capture geometric information, propagation conditions, and diverse link configurations. This work introduces a geometry-aware UAV communication dataset designed to support research on controlled UAV communication link directions and propagation scenarios. The dataset is generated using standardized 3GPP and ITU-R channel models across multiple urban, suburban, and rural regions, accounting for variations in altitude, carrier frequency, and node distribution. The dataset provides spatially resolved channel parameters along with geometry-rich files containing environmental features, which can be used to extract relevant parameters for UAV communication studies. These data support reproducible research in geometry-aware channel modelling, path-loss prediction, LOS/NLOS analysis, delay-related modelling, and trajectory-conditioned link-quality analysis. Full article

Laser Powder Bed Fusion for metals (PBF-LB/M) is a complex additive manufacturing process in which metal powder is selectively melted layer-by-layer to fabricate 3D parts. Process parameters critically influence the resulting microstructure in nickel alloys, with features such as melt pool marks, grain size and orientation, porosity, and cracks serving as key process signatures. These features are typically analyzed post-process to identify suboptimal conditions. This research aims to develop automated post-process measurement and analysis techniques using image processing, pattern recognition, and statistical learning to correlate process parameters with part quality. Optical microscopy images of build surfaces are analyzed using machine learning algorithms to evaluate porosity, grain size, and relative density in fabricated test coupons. Effect plots are generated to identify trends related to increasing energy density. A novel deep learning approach based on Mask R-CNN is used to detect and segment melt pool regions in optical microscopy images. From the segmented regions, melt pool dimensions—such as width, depth, and area—are extracted using bounding geometry coordinates. Manually labeled images (Type I and Type II) are used to train the model. A comparison between ResNet-50 and ResNet-101 backbones shows that the ResNet-50-based model (Model 2) achieves superior performance, with lower training loss (0.1781 vs. 0.1907) and validation loss (8.6140 vs. 9.4228). Quantitative evaluation using the Jaccard index, precision, and recall metrics shows that the ResNet-101 backbone outperforms ResNet-50, achieving about 4% higher mean Intersection-over-Union, with values of 0.85 for Type I and 0.82 for Type II melt pools, where Type I is detected more accurately due to its more regular morphology and clearer boundaries. By extending Faster R-CNNs with a mask prediction branch, the method allows for precise melt pool measurements, providing valuable insights into process quality and dimensional accuracy, and aiding in the detection of defects in PBF-LB-fabricated parts. Full article

Remote sensing images acquired by UAVs under nighttime or low-illumination conditions suffer from insufficient illumination, leading to degraded image quality, detail loss, and noise, which restrict their application in public security and disaster emergency scenarios. Although existing machine learning-based enhancement methods can recover part of the missing information, they often cause color distortion and texture inconsistency. This study proposes an improved low-illumination image enhancement method based on a Weakly Paired Image Dataset (WPID), combining the Hierarchical Deep Convolutional Generative Adversarial Network (HDCGAN) with a low-rank image fusion strategy to enhance the quality of low-illumination UAV remote sensing images. First, YCbCr color channel separation is applied to preserve color information from visible images. Then, a Low-Rank Representation Fusion Network (LRRNet) is employed to perform structure-aware fusion between thermal infrared (TIR) and visible images, thereby enabling effective preservation of structural details and realistic color appearance. Furthermore, a weakly paired training mechanism is incorporated into HDCGAN to enhance detail restoration and structural fidelity. To achieve objective evaluation, a structural consistency assessment framework is constructed based on semantic segmentation results from the Segment Anything Model (SAM). Experimental results demonstrate that the proposed method outperforms state-of-the-art approaches in both visual quality and application-oriented evaluation metrics. Full article

Unmanned Aerial Vehicle (UAV) swarms operating in contested environments face a critical “semantic gap” between raw, high-velocity network traffic and high-level mission security constraints, compounded by the risk of privacy leakage during collaborative learning. Existing deep learning (DL)-based Network Intrusion Detection Systems (NIDSs) suffer from opacity, prohibitive resource consumption, and vulnerability to gradient leakage attacks in federated settings, while traditional rule-based systems fail to handle encrypted payloads and evolving attack patterns. To bridge this gap, we present NeSySwarm-IDS (Neuro-Symbolic Swarm Intrusion Detection System), an end-to-end differentiable neuro-symbolic framework that simultaneously achieves high accuracy, strong privacy guarantees, and built-in interpretability under resource constraints. NeSySwarm-IDS integrates an extremely lightweight 1D convolutional neural network with a differentiable Łukasiewicz fuzzy logic reasoner incorporating attack-specific rules. By aggregating only low-dimensional logic rule weights with calibrated differential privacy noise, we drastically reduce communication overhead while providing $(ϵ,\delta )$-DP guarantees with negligible utility loss. Extensive experiments on the UAV-NIDD dataset and our self-collected dataset demonstrate that NeSySwarm-IDS achieves near-perfect detection accuracy, significantly outperforming traditional machine learning baselines despite using limited training data. A detailed case study on GPS spoofing confirms the interpretability of our approach, providing axiomatic explanations suitable for autonomous mission verification. These results establish that end-to-end neuro-symbolic learning can effectively bridge the semantic gap in UAV swarm security while ensuring privacy and interpretability, offering a practical pathway for deploying trustworthy AI in contested environments. Full article

Reliable estimation of the State of Health (SOH) in lithium-ion batteries is critical to battery system security and dependability. However, existing Physics-Informed Neural Networks (PINNs) have drawbacks like single-feature physical constraints, rigid fixed-weight fusion of multi-feature constraints and insufficient time-series degradation modeling. To solve these problems, this study proposes an Adaptive-Weight PINN (AW-PINN) optimized by the Grey Wolf Optimizer (GWO) algorithm, which features a dual-LSTM parallel structure and takes incremental capacity peaks and charged capacity as dual physical constraints. A weight generator LSTM adaptively learns weights for monotonicity losses without manual intervention, and GWO globally optimizes physical loss weights to balance data fitting accuracy and prediction physical consistency. Validated on ${\mathrm{LiCoO}}_2$, NCA, and NCM batteries from CALCE and Tongji University datasets via comparative, ablation, and small-sample experiments, AW-PINN shows superior predictive performance (average RMSE = 0.0076; MAE = 0.0065; MAPE = 0.0072), robustness, and generalization. It integrates battery degradation physics with deep learning, retaining strong fitting capability while enabling physical interpretability. Full article

Accurate and physically consistent state prediction is essential for shipboard power systems (SPS) operating under dynamic conditions. However, purely data-driven models often exhibit degraded robustness and physically inconsistent outputs when exposed to transient disturbances or limited data coverage. To address these limitations, this paper proposes a physics-constrained hybrid prediction model that integrates a convolutional neural network–bidirectional long short-term memory (CNN–BiLSTM) architecture with wide residual connections (WRC) and a physics-constrained loss (PCL). The proposed modeling approach combines real operational measurement data with high-resolution simulation data to enhance data diversity and improve generalization capability. The CNN–BiLSTM structure captures nonlinear temporal dependencies, while the WRC preserves critical low-level transient electrical features during deep temporal modeling. In addition, multiple physical constraints, including power balance, voltage conversion relationships, and battery state-of-charge (SOC) dynamics, are incorporated into the training process to enforce physically consistent predictions. The model is validated using charging and discharging experiments on a laboratory-scale SPS under both steady-state and transient conditions. Comparative results demonstrate that the proposed approach achieves higher prediction accuracy, improved dynamic stability, and faster recovery following disturbances compared with conventional data-driven models. These results indicate that physics-constrained deep learning provides an effective and interpretable modeling framework for SPS state prediction, supporting digital twin-oriented monitoring and real-time prediction applications. Full article

This work develops a zero-trust, physics-constrained mathematical framework for detecting stealthy drift perturbations in power system dynamical models. Such perturbations constitute adversarial, statistical deviations that preserve first-order operating trends, making them difficult to identify using classical residual-based estimators or unconstrained data-driven models. We introduce ZETWIN, a spatio-temporal learning architecture formulated as a constrained optimization problem in which the nodal admittance matrix $Y_{bus}$ acts as a graph-structured linear operator embedded directly into the loss functional. This construction enforces Kirchhoff-consistent latent representations and yields a mathematically grounded zero-trust decision rule that flags any trajectory violating physical feasibility, independent of prior attack signatures. The proposed framework is evaluated using a PyPSA-based AC–DC meshed network, demonstrating an AUROC = 0.994, and F1 = 0.969. The formulation highlights how physics-informed constraints, graph operators, and spatio-temporal approximation theory can be combined to construct mathematically interpretable zero-trust detectors for complex dynamical systems. Full article

The global rise in electronic waste (e-waste), especially in semiconductor components such as circuit boards and microchips, underscores a critical need for improved recycling technology. Current industrial sorters often miss small, high-value components. This leads to the loss of precious metals and inefficient recycling processes. This paper introduces an automated detection framework for detecting semiconductor components in e-waste. It assesses ensemble learning methods that leverage the strengths of multiple YOLO (You Only Look Once) object detection models, including YOLOv5, YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLOv12. Three ensemble fusion strategies are systematically compared: standard Non-Maximum Suppression (NMS), voting-based strategies (Affirmative, Consensus, Unanimous), and Weighted Box Fusion (WBF) with both static and dynamic weight optimization. Our simulations demonstrate that using multiple models together is far more effective than a single model for the following reasons. 1. Higher Accuracy: The best configuration, Top-4 Consensus Voting ensemble strategy, achieved an mAP@0.5 of 59.63%, a 10.3% improvement over the best individual model (YOLOv8s, 54.04%); 2. Greater Reliability: It significantly reduced “false negatives” (missed detections), even in cluttered or crowded e-waste scenarios; 3. Enhanced Detection: While the individual YOLOv8 model is fast (taking only 62.6 ms), supporting real-time detection, the best ensemble configuration (Consensus Top-4) takes 384.9 ms, creating a trade-off between detection accuracy and speed; 4. Well-Balanced Performance: Some fusion strategies showed slight trade-offs in mAP for certain parts, but collectively achieved a 7% rise in F1-score, indicating a better balance between precision and recall. This research marks significant progress in smart recycling. Improved component identification allows for more efficient recovery of high-purity materials. This promotes a circular economy by ensuring that rare and strategic materials in electronics are reused instead of discarded. Full article

To address traditional beer detection limitations, this study proposes a rapid NIRS-based method for detecting key indicators and verifying authenticity. Designing Single-task (STL) and Multi-task learning (MTL) strategies, it employs Variable Importance in Projection for wavelength selection. Deep spectral features were extracted utilizing a Multi-Head Attention (MHA)-fused Convolutional Neural Network (CNN-MHA), Long Short-Term Memory (LSTM-MHA), and hybrid CNN-LSTM-MHA networks. To further enhance model performance, the Bayesian Optimization Algorithm globally optimized network hyperparameters in STL, alongside hyperparameters and multi-task loss weights in MTL. Partial least squares regression, support vector machine regression, and partial least squares discriminant analysis models were established using these features. Results indicate that the MTL-based CNN-LSTM-MHA network effectively learns shared features across multiple tasks, significantly improving model generalization. Specifically, the coefficients of determination ($R^2$) for alcohol content and original wort concentration in the validation set were 0.996 and 0.997, respectively, with relative root mean square errors (rRMSE) of 2.024% and 2.515%. In the independent test set, the $R^2$ were 0.995 and 0.991, with rRMSE of 2.515% and 2.087%, respectively. Furthermore, 100% classification accuracy was achieved across all datasets. This method provides an efficient technical solution for beer market regulation and real-time detection in production processes. Full article

Fine-grained image classification under few-shot learning conditions remains a significant challenge due to limited labeled data and high intra-class similarity. This paper proposes a novel cross-modal framework that integrates Contrastive Language-Image Pretraining (CLIP) embeddings within a Siamese similarity network to enable robust and label-efficient classification. By leveraging the semantic alignment between textual class descriptions and visual representations, the model forms hybrid similarity pairs of image-to-image and image-to-text within a shared latent space, facilitating discriminative learning under low-shot scenarios. The architecture employs a dual-branch CLIP encoder and a contrastive loss function to optimize intra-class compactness and inter-class separability. Experiments conducted on benchmark datasets including miniImageNet and CUB-200-2011 demonstrate substantial improvements over zero-shot and few-shot baselines, achieving 70.32% accuracy, 71.15% F1-score, and 68.47% mAP on 5-way 1-shot and 78.41% accuracy, 79.02% F1-score, and 76.83% mAP on 5-way 5-shot tasks (averaged over 600 episodes with 95% confidence intervals on the CUB-200-2011 dataset). Extended evaluations under 10-way settings show similarly strong performance. Ablation studies further validate the critical roles of contrastive learning, normalization, and cross-modal embeddings in enhancing generalization. This work presents a scalable and interpretable paradigm for fine-grained classification in data-scarce domains. Full article

Edge intelligence enables significant latency reduction and enhances the timeliness of model-based fault diagnosis. However, existing deep learning-driven bearing fault diagnosis models are ill-suited for deployment on edge devices, primarily due to three critical limitations: (1) Lightweight models typically exhibit inadequate anti-noise performance, failing to meet the reliability requirements of real-world engineering scenarios. (2) Models with superior anti-noise capabilities often demand high-performance hardware for operation, thereby restricting their deployment on resource-constrained edge devices. (3) These models adopt a fixed input length, which makes it difficult to guarantee diagnostic accuracy across diverse application scenarios—attributed to variations in sampling frequencies, bearing parameters, and other relevant factors. To address these challenges, this paper proposes a lightweight anti-noise diagnostic framework (LADF) for edge-intelligent bearing fault diagnosis in complex engineering environments. The LADF comprises three core modules: a dynamic input module (DIM), a lightweight network module (LNM), and a denoising branch. Specifically, the DIM is designed based on the envelope spectrum, leveraging its inherent demodulation characteristics to dynamically adapt to input signals across diverse scenarios. Group convolution and layer normalization are employed to construct the LNM, ensuring robust diagnostic performance while achieving efficient computation. The denoising branch constrains the feature extractor via a loss function, enabling it to learn generalized fault features under varying noise environments and thereby enhancing the anti-noise capability of the framework. Finally, the proposed LADF is validated through test rig experiments on two datasets of train axle box bearings. Comparative analysis with state-of-the-art models demonstrates that the LADF achieves superior diagnostic stability and anti-noise performance while maintaining a more lightweight architecture, making it well-suited for edge deployment in railway bearing fault diagnosis. Full article

Ultra-High-Performance Concrete (UHPC) is increasingly used in slender and prestressed structural members due to its superior strength and durability. However, inaccurate or incomplete prediction of creep deformation may lead to excessive long-term deflection, prestress loss, cracking, and potential serviceability or safety risks in buildings and infrastructure. Therefore, reliable prediction methods for UHPC creep are essential for both structural design and long-term performance assessment. In this study, a database containing 60 literature-derived UHPC creep records was compiled to investigate the creep coefficient at approximately 100 days. Pearson correlation analysis revealed strong interdependence among predictors and weak single-variable linear relationships, indicating that creep behavior is governed by nonlinear interactions. A feedforward backpropagation neural network (BPNN) trained using the Levenberg–Marquardt algorithm was developed to predict the creep coefficient. To maintain engineering interpretability, the fib Model Code 2020 (MC2020) formulation was adopted as a code-based benchmark and further calibrated using ridge regression. Results show that the calibrated MC2020 model improves prediction consistency, while the BPNN model provides the highest predictive accuracy. The proposed framework integrates machine-learning prediction with interpretable code-based calibration, contributing to the development of creep modeling approaches for UHPC and providing practical support for the safe design of UHPC structures. Full article