Search Results (637)

In the era of the digital food economy, high-fidelity food images are critical for applications ranging from visual e-commerce presentation to automated dietary assessment. However, developing robust computer vision systems for food analysis is often hindered by data scarcity for long-tail or regional dishes. To address this challenge, we propose a novel high-fidelity food image synthesis framework as an effective data augmentation tool. Unlike generic generative models, our method introduces an Ingredient-Aware Diffusion Model based on the Masked Diffusion Transformer (MaskDiT) architecture. Specifically, we design a Label and Ingredients Encoding (LIE) module and a Cross-Attention (CA) mechanism to explicitly model the relationship between food composition and visual appearance, simulating the “cooking” process digitally. Furthermore, to stabilize training on limited data samples, we incorporate a linear interpolation strategy into the diffusion process. Extensive experiments on the Food-101 and VireoFood-172 datasets demonstrate that our method achieves state-of-the-art generation quality even in data-scarce scenarios. Crucially, we validate the practical utility of our synthetic images: utilizing them for data augmentation improved the accuracy of downstream food classification tasks from 95.65% to 96.20%. This study provides a cost-effective solution for generating diverse, controllable, and realistic food data to advance smart food systems. Full article

Short-term load forecasting (STLF) underpins the efficient and secure operation of power systems. This study develops and evaluates a hybrid architecture that couples deep neural networks (DNNs) with support vector regression (SVR) for national-scale day-ahead STLF using Croatian load data from 2006 to 2022. The approach employs an hour-specific framework of 24 hybrid models: each DNN learns a compact nonlinear representation for a given hour, while an SVR trained on the penultimate layer activations performs the final regression. Gradient-boosting-based feature selection yields compact, informative inputs shared across all model variants. To overcome limitations of historical local measurements, the framework integrates global numerical weather prediction data from the TIGGE archive with load and local meteorological observations in an operationally realistic setup. In the held-out test year 2022, the proposed hybrid consistently reduced forecasting error relative to standalone DNN-, LSTM- and Transformer-based baselines, while preserving a reproducible pipeline. Beyond using SVR as an alternative output layer, the contributions are as follows: addressing a 17-year STLF task, proposing an hour-specific hybrid DNN–SVR framework, providing a systematic comparison with deep learning baselines under a unified protocol, and integrating global weather forecasts into a practical day-ahead STLF solution for a real power system. Full article

Accurate prediction of ultimate tensile strength (UTS) is central to the design and optimization of heat-treated steels but is traditionally achieved through costly and iterative experimental trials. This study presents a transparent, physics-aware machine learning (ML) framework for predicting UTS using an open-access steel database. A curated dataset of 1255 steel samples was constructed by combining 18 chemical composition variables with 7 processing descriptors extracted from free-text heat-treatment records and filtering them using physically justified consistency criteria. To avoid information leakage arising from repeated measurements, model development and evaluation were conducted under a group-aware validation framework based on thermomechanical states. A Random Forest (RF) regression model achieved robust, conservative test-set performance (R² ≈ 0.90, MAE ≈ 40 MPa), with unbiased residuals and realistic generalization across diverse composition–processing conditions. Performance robustness was further examined using repeated group-aware resampling and strength-stratified error analysis, highlighting increased uncertainty in sparsely populated high-strength regimes. Model interpretability was assessed using SHAP-based feature importance and partial dependence analysis, revealing that UTS is primarily governed by the overall alloying level, carbon content, and processing parameters controlling transformation kinetics, particularly bar diameter and tempering temperature. The results demonstrate that reliable predictions and physically meaningful insights can be obtained from publicly available data using a conservative, reproducible machine-learning workflow. Full article

This paper gives insight into the influences of spatially varying material properties on the non-linear finite element modeling of the rectangular and square-shaped floor slabs. Modeling the properties of the concrete using spatially distributed properties instead of using constant properties is more realistic. We analyzed the influence of probabilistic concrete property modeling on the development of cracks in floor slabs. A concrete floor subjected to a shrinkage load was analyzed using the material model with randomly distributed compressive strength. Consequently, the tensile strength and elastic modulus were also randomly distributed. The concrete properties were defined by the random field generator that uses the Fast Fourier Transformation method and the guidelines given by the Joint Committee on Structural Safety Probabilistic Model Code. The obtained results are compared with the values from modeling with constant concrete properties. The comparison shows that the crack development in the slabs with and without varying material properties is statistically significantly different. Full article

Texture mapping of weft-knitted fabrics plays a crucial role in virtual try-on and digital textile design due to its computational efficiency and real-time performance. However, traditional texture mapping techniques typically adapt pre-generated textures to deformed surfaces through geometric transformations. These methods overlook the complex variations in yarn length, thickness, and loop morphology during stretching, often resulting in visual distortions. To overcome these limitations, we propose Knit-Pix2Pix, a dedicated framework for generating realistic weft-knitted fabric textures directly from knitted unit mesh maps. These maps provide grid-based representations where each cell corresponds to a physical loop region, capturing its deformation state. Knit-Pix2Pix is an integrated architecture that combines a multi-scale feature extraction module, a grid-guided attention mechanism, and a multi-scale discriminator. Together, these components address the multi-scale and deformation-aware requirements of this task. To validate our approach, we constructed a dataset of over 2000 pairs of fabric stretching images and corresponding knitted unit mesh maps, with further testing using spring-mass fabric simulation. Experiments show that, compared with traditional texture mapping methods, SSIM increased by 21.8%, PSNR by 20.9%, and LPIPS decreased by 24.3%. This integrated approach provides a practical solution for meeting the requirements of digital textile design. Full article

Underwater image enhancement remains challenging due to wavelength-dependent absorption, spatially varying scattering, and non-uniform illumination, which jointly cause severe color distortion, contrast degradation, and structural information loss. To address these issues, we propose UCS-Net, a degradation-aware dual-path framework that exploits the complementarity between global and local representations. A spatial color balance module first stabilizes the chromatic distribution of degraded inputs through a learnable gray-world-guided normalization, mitigating wavelength-induced color bias prior to feature extraction. The network then adopts a dual-branch architecture, where a hierarchical Swin Transformer branch models long-range contextual dependencies and global color relationships, while a multi-scale residual convolutional branch focuses on recovering local textures and structural details suppressed by scattering. Furthermore, a multi-scale attention fusion mechanism adaptively integrates features from both branches in a degradation-aware manner, enabling dynamic emphasis on global or local cues according to regional attenuation severity. A hue-preserving reconstruction module is finally employed to suppress color artifacts and ensure faithful color rendition. Extensive experiments on UIEB, EUVP, and UFO benchmarks demonstrate that UCS-Net consistently outperforms state-of-the-art methods in both full-reference and non-reference evaluations. Qualitative results further confirm its effectiveness in restoring fine structural details while maintaining globally consistent and visually realistic colors across diverse underwater scenes. Full article

Effective disaster management is critical for safeguarding lives, infrastructure and economies in an era of escalating natural hazards like floods and landslides. Despite advanced early-warning systems and coordination frameworks, a persistent “last-mile” challenge undermines response effectiveness: transforming fragmented and unstructured multimodal data into timely and accountable field actions. This paper introduces ResQConnect, a human-centered, AI-powered multimodal multi-agent platform that bridges this gap by directly linking incident intake to coordinated disaster response operations in hazard-prone regions. ResQConnect integrates three key components. It uses an agentic Retrieval-Augmented Generation (RAG) workflow in which specialized language-model agents extract metadata, refine queries, check contextual adequacy and generate actionable task plans using a curated, hazard-specific knowledge base. The contribution lies in structuring the RAG for correctness, safety and procedural grounding in high-risk settings. The platform introduces an Adaptive Event-Triggered (AET) multi-commodity routing algorithm that decides when to re-optimize routes, balancing responsiveness, computational cost and route stability under dynamic disaster conditions. Finally, ResQConnect deploys a compressed, domain-specific language model on mobile devices to provide policy-aligned guidance when cloud connectivity is limited or unavailable. Across realistic flood and landslide scenarios, ResQConnect improved overall task-quality scores from 61.4 to 82.9 (+21.5 points) over a standard RAG baseline, reduced solver calls by up to 85% compared to continuous re-optimization while remaining within 7–12% of optimal response time, and delivered fully offline mobile guidance with sub-500 ms response latency and 54 tokens/s throughput on commodity smartphones. Overall, ResQConnect demonstrates a practical and resilient approach to AI-augmented disaster response. From a sustainability perspective, the proposed system contributes to Sustainable Development Goal (SDG) 11 by improving the speed and coordination of disaster response. It also supports SDG 13 by strengthening adaptation and readiness for climate-driven hazards. ResQConnect is validated using real-world flood and landslide disaster datasets, ensuring realistic incidents, constraints and operational conditions. Full article

The increasing complexity of modern electrical substations—driven by renewable integration, advanced automation, and asset aging—necessitates a transition from reactive maintenance toward intelligent, data-driven strategies. Predictive maintenance (PdM), supported by artificial intelligence, enables early fault detection and remaining useful life (RUL) estimation, while Digital Twin (DT) technology provides synchronized cyber–physical representations for situational awareness and risk-free validation of maintenance decisions. This study proposes a five-layer DT-enabled PdM architecture integrating standards-based data acquisition, semantic interoperability (IEC 61850, CIM, and OPC UA Part 17), hybrid AI analytics, and cyber-secure decision support aligned with IEC 62443. The framework is validated using utility-grade operational data from the SS1 substation of the Badra Oil Field, comprising approximately one million multivariate time-stamped measurements and 139 confirmed fault events across transformer, feeder, and environmental monitoring systems. Fault detection is formulated as a binary classification task using event-window alignment to the 1 min SCADA timeline, preserving realistic operational class imbalance. Five supervised learning models—a Random Forest, Gradient Boosting, a Support Vector Machine, a Deep Neural Network, and a stacked ensemble—were benchmarked, with the ensemble embedded within the DT core representing the operational predictive model. Experimental results demonstrate strong performance, achieving an F1-score of 0.98 and an AUC of 0.995. The results confirm that the proposed DT–AI framework provides a scalable, interoperable, and cyber-resilient foundation for deployment-ready predictive maintenance in modern substation automation systems. Full article

In the context of bearing anomaly detection, challenges such as imbalanced sample distribution and complex operational conditions present significant difficulties for data-driven deep learning models. These issues often result in overfitting and high false positive rates in complex real-world scenarios. This paper proposes a strategy that leverages multimodal fusion and Self-Adversarial Training (SAT) to construct and train a deep learning model. First, the one-dimensional bearing vibration time-series data are converted into Gramian Angular Difference Field (GADF) images, and multimodal feature fusion is performed with the original time-series data to capture richer spatiotemporal correlation features. Second, a composite data augmentation strategy combining time-domain and image-domain transformations is employed to effectively expand the anomaly samples, mitigating data scarcity and class imbalance. Finally, the SAT mechanism is introduced, where adversarial samples are generated within the fused feature space to compel the model to learn more generalized and robust feature representations, thereby significantly enhancing its performance in realistic and noisy environments. Experimental results demonstrate that the proposed method outperforms traditional baseline models across key metrics such as accuracy, precision, recall, and F1-score in abnormal bearing anomaly detection. It exhibits exceptional robustness against rail-specific interferences, offering a specialized solution strictly tailored for the unique, high-noise operational environments of intelligent railway maintenance. Full article

Thermal facial imaging enables non-contact measurements of face heat patterns that are valuable for healthcare and affective computing, but common occluders (glasses, masks, scarves) and the single-channel, texture-poor nature of thermal frames make robust landmark localisation and visibility estimation challenging. We propose M³MSTL, a multi-modal, multi-stage, multi-task framework for occlusion-aware landmarking on thermal faces. M³MSTL pairs a ResNet-50 backbone with two lightweight heads: a compact fully connected landmark regressor and a Vision Transformer occlusion classifier that explicitly fuses per-landmark temperature cues. A three-stage curriculum (mask-based backbone pretraining, head specialisation with a frozen trunk, and final joint fine-tuning) stabilises optimisation and improves generalisation from limited thermal data. On the TFD68 dataset, M³MSTL substantially improves both visibility and localisation: the occlusion accuracy reaches 91.8% (baseline 89.7%), the mean NME reaches 0.246 (baseline 0.382), the ROC–AUC reaches 0.974, and the AP is 0.966. Paired statistical tests confirm that these gains are significant. Our approach aims to improve the reliability of temperature-based biometric and clinical measurements in the presence of realistic occluders. Full article

Many denoising methods model noise as Gaussian noise. However, the realistic noise captured by camera devices does not satisfy Gaussian distribution. Hence, those methods do not perform well when being applied to real-world image denoising tasks. In this work, we indicate that the spatial correlation in noise and the variation of noise intensity are the main factors that impact the performance of Gaussian noise-based methods, and accordingly propose an extension of the method based on the weighted, mixed non-convex ${\mathsf{\ell }}_p$ norm. The proposed method first strengthens the intensity of the noise pattern in the original denoising result through the Guided Filter, then removes the over-amplified frequency in the local area by the proposed regularization term. We prove that the optimal solution can be achieved through the sub-gradient-based iterative optimization scheme, and further reduce the computational cost by optimizing the initial values. Numerical experiments show that the proposed extending method can balance well texture preservation and noise removal, and the PSNR of the extending method’s results are greatly improved, even outperforming the recently proposed realistic noise removal methods which also include deep learning based methods. Full article

The rapid deterioration of global infrastructure necessitates precise and automated crack detection technologies for proactive maintenance. However, deep learning-based segmentation models often suffer from a scarcity of diverse, high-quality labeled datasets. This study proposes StyleSPADE, a novel conditional image generation model that integrates semantic masks and style images to synthesize realistic crack data with diverse background textures while preserving precise geometric morphology. To validate the effectiveness of the generated data, we conducted extensive semantic segmentation tasks using Transformer-based (Mask2Former, Swin-UPerNet) and CNN-based (K-Net) models. Experimental results demonstrate that StyleSPADE-based augmentation significantly outperforms baseline models, achieving a Crack IoU of 0.6376 and an F1-score of 0.7586. Furthermore, we implemented a Stacking Ensemble strategy combining high-recall and high-precision models, which further improved performance to a Crack IoU of 0.6452. Our findings confirm that StyleSPADE effectively mitigates the data scarcity problem and enhances the robustness of crack detection in complex environmental conditions. This framework contributes to improving the efficiency and safety of infrastructure management by enabling reliable damage assessment in data-limited environments. Full article

This article studies practical argumentation in the context of designing application problems and transforming them into modelling problems. To this end, the practical arguments developed by prospective primary education teachers were analysed, using a scheme for structuring and representing these arguments and a modelling cycle for representing the solution plans proposed to these problems. This is a case study with three groups of prospective teachers who were taking a course on mathematical reasoning and activity in primary education, where problem solving and mathematical modelling were the two most relevant topics. For data collection, a questionnaire was applied to and an interview was conducted with the study subjects, thus identifying nine episodes of practical argumentation based on the justification of their pedagogical decisions made on the design and transformation of problems. Also, the written reports prepared by the study subjects were reviewed to analyse their solution plans proposed to the problems. The results showed that the study subjects developed practical arguments to justify the design of motivating learning situations and problems for students in realistic contexts close to their environment and the transformation of application problems into modelling problems by eliminating data from their statements and formulating an open-ended question. Full article

Coal gangue, as a predominant solid byproduct of the global coal industry, poses severe environmental challenges because of its massive accumulation and low utilization rate. This review systematically synthesizes and analyzes published experimental and analytical studies on the dual-pathway utilization of coal gangue in concrete, including Pathway 1 (aggregate substitution) and Pathway 2 (cementitious activity activation). While the application of coal gangue aggregates is traditionally limited by their inherent high porosity and lower mechanical strength than those of natural aggregates, this review demonstrates that performance barriers can be effectively overcome. Through multiscale modification strategies—including surface densification, biological mineralization (MICP), and matrix synergy—the interfacial defects are significantly mitigated, allowing for feasible substitution in structural concrete. Conversely, for the mineral admixture pathway, controlled thermal activation is identified as a key process to optimize the phase transformation of kaolinite, thereby significantly enhancing pozzolanic reactivity and long-term durability. According to reported studies, the partial replacement of natural aggregates or cement with coal gangue can reduce CO₂ emissions by approximately tens to several hundreds of kilograms per ton of coal gangue utilized, depending on the substitution level and activation strategy, highlighting its considerable potential for carbon reduction in the construction sector. Nevertheless, challenges related to energy-intensive activation processes and variability in raw gangue composition remain. These limitations indicate the need for future research focusing on low-carbon activation technologies, standardized classification of coal gangue resources, and long-term performance validation under realistic service environments. Based on the synthesized literature, this review discusses hierarchical utilization concepts and low-carbon activation approaches as promising directions for promoting the sustainable transformation of coal gangue from an environmental liability into a carbon-reduction asset in the construction industry. Full article

Pollen identification is critical for melissopalynology (honey authentication), ecological monitoring, and allergen tracking, yet manual microscopic analysis remains labor-intensive, subjective, and error-prone when multiple grains overlap in realistic samples. Existing automated approaches often fail to address multi-grain scenarios or lack systematic comparison across classical and deep learning paradigms, limiting their practical deployment. This study proposes a subinstance-based classification framework combining YOLOv12n object detection for grain isolation, independent classification via classical machine learning (ML), convolutional neural networks (CNNs), or Vision Transformers (ViTs), and majority voting aggregation. Five classical classifiers with systematic feature selection, three CNN architectures (ResNet50, EfficientNet-B0, ConvNeXt-Tiny), and three ViT variants (ViT-B/16, ViT-B/32, ViT-L/16) are evaluated on four datasets (full images vs. isolated grains; raw vs. CLAHE-preprocessed) for four berry pollen species (Ribes nigrum, Ribes uva-crispa, Lonicera caerulea, and Amelanchier alnifolia). Stratified image-level splits ensure no data leakage, and explainable AI techniques (SHAP, Grad-CAM++, and gradient saliency) validate biological interpretability across all paradigms. Results demonstrate that grain isolation substantially improves classical ML performance (F1 from 0.83 to 0.91 on full images to 0.96–0.99 on isolated grains, +8–13 percentage points), while deep learning excels on both levels (CNNs: F1 = 1.000 on full images with CLAHE; ViTs: F1 = 0.99). At the instance level, all paradigms converge to near-perfect discrimination (F1 ≥ 0.96), indicating sufficient capture of morphological information. Majority voting aggregation provides +3–5% gains for classical methods but only +0.3–4.8% for deep models already near saturation. Explainable AI analysis confirms that models rely on biologically meaningful cues: blue channel moments and texture features for classical ML (SHAP), grain boundaries and exine ornamentation for CNNs (Grad-CAM++), and distributed attention across grain structures for ViTs (gradient saliency). Qualitative validation on 211 mixed-pollen images confirms robust generalization to realistic multi-species samples. The proposed framework (YOLOv12n + SVC/ResNet50 + majority voting) is practical for deployment in honey authentication, ecological surveys, and fine-grained biological image analysis. Full article