Search Results (23,933)

Alkaline Water Electrolyzers (AWEs) are critical for green hydrogen production but face operational risks due to volatile renewable energy inputs. This study proposes an intelligent condition-monitoring framework that leverages a hybrid physics-informed machine learning (ML) methodology to construct Health Indicators (HIs). The core innovation lies in addressing the challenge of inaccessible internal states. First, a high-fidelity Computational Fluid Dynamics (CFD) model is developed and experimentally validated, serving as a physics-informed data generator to simulate multiphysics behavior under various operating and fault conditions. From this reliable simulation basis, a comprehensive dataset is produced, and eight key operational parameters are derived as HIs. This dataset is then used to train and benchmark three ML models for rapid health state classification. The Multilayer Perceptron (MLP) model achieves superior performance with 90.43% accuracy, effectively translating the validated physical understanding into a fast, deployable intelligent monitoring agent. This work presents a viable pathway for constructing reliable HIs and implementing AI-enhanced condition monitoring for AWEs, contributing to safer and more efficient green hydrogen production. Full article

Surface defect detection is essential for industrial quality control, but obtaining reliable labeled data remains costly due to the need for expert annotation. Semi-supervised object detection (SSOD) mitigates this need by leveraging unlabeled data through pseudo-labeling. However, industrial surface imagery presents specific challenges, including texture-ambiguous, low-contrast backgrounds that cause foreground–background confusion and strong class-dependent detection difficulty, which renders global confidence thresholds ineffective, often yielding noisy and imbalanced pseudo labels. To overcome these limitations, we propose TaDP-Det, a semi-supervised detector that improves pseudo-label quality through dual enhancements in feature representation and label filtering. We first introduce a Texture Enhance Module (TEM), designed as a texture-aware patch-level mixture-of-experts applied at shallow backbone stages, which amplifies discriminative low-level texture cues to generate more reliable pseudo labels in ambiguous regions. Second, the class-wise dynamic pseudo-label filtering (CDPF) scheme uses lightweight 1D Gaussian mixture models to adaptively determine per-class thresholds, preserving challenging defects and suppressing spurious predictions. Comprehensive evaluations on the NEU-DET, GC10-DET, and PCB-DEFECT datasets show that TaDP-Det consistently outperforms state-of-the-art SSOD baselines in mean average precision (mAP) with only modest computational overhead. The results underscore the effectiveness of our method for robust semi-supervised defect detection in industrial applications. Full article

Soybean (Glycine max) is a globally important crop valued for its high seed oil and protein content. However, lodging remains a major abiotic constraint that causes substantial yield losses. Lodging resistance is primarily determined by stem strength and toughness, which are governed by stem anatomical organization, vascular tissue development, and the composition and architecture of secondary cell walls (SCWs). This review synthesizes current knowledge on anatomical, structural, and genetic factors that are implicated in stem mechanical performance in dicotyledonous plants, with particular emphasis on vascular cambium activity, xylem and phloem differentiation, and the biosynthesis of major SCW components, including cellulose, hemicellulose, and lignin. These processes collectively determine stem rigidity, flexibility, and resistance to mechanical stress. By integrating insights from model species, especially Arabidopsis thaliana, and non-soybean dicots, this review highlights conserved regulatory pathways controlling stem development and SCW formation that are directly relevant to soybean improvement. The synthesis provides a translational framework for understanding how conserved anatomical and genetic mechanisms can be leveraged to enhance soybean stem strength, toughness, and lodging resistance. Overall, this review provides a conceptual foundation for future functional studies and breeding strategies to improve soybean yield stability and adaptability across diverse agronomic conditions. Full article

Distinct from the traditional Modular Multilevel Converter (MMC) which focuses on fundamental frequency operation, the Static Var and Filter (SVF) within the Multi-Source Line-Commutated Converter (SLCC) system is tasked with the core function of high-frequency harmonic filtering. This paper reveals a unique engineering reliability issue stemming from this functional difference: to satisfy the Nyquist sampling theorem for precise tracking and elimination of high-frequency harmonics, the update frequency of the capacitor voltage balancing algorithm in the SLCC-SVF system is forced to increase significantly. Mathematical modeling and quantitative analysis demonstrate that this strong coupling between harmonic tracking demands and the voltage sorting strategy directly drives an abnormal surge in the average switching frequency (reaching over five times that of the fundamental condition), severely threatening device safety. To address this, an optimized adaptive hybrid modulation strategy is proposed. The system operates under Nearest Level Modulation (NLM) in normal conditions and automatically transitions to Carrier Phase-Shifted PWM (CPS-PWM)—leveraging its closed-loop balancing capability—when switching frequency or junction temperature exceeds safety thresholds. Furthermore, a non-integer frequency ratio optimization theory for low-modulation indices is constructed specifically for SVF conditions to prevent low-frequency oscillations. PLECS simulation results validate the theoretical analysis, showing that the proposed strategy effectively reduces the average switching frequency by approximately 20% under complex harmonic conditions, significantly enhancing thermal stability and operational reliability while guaranteeing filtering performance. Full article

The emergence of highly complex generative AI and large language models represents both a significant challenge and an opportunity for multiple engineering domains. Under the Industry 4.0 paradigm, various connected automation and industrial engineering applications can leverage the inference and generative design capabilities of these models to improve control algorithms and systems. In particular, widespread deployment of mobile robotic platforms in modern industry, enhanced with LLM capabilities, can provide a substantial increase in the efficiency and cost-effectiveness of such solutions. In this study, we investigate the suitability of current-generation LLM systems for industrial mobile robot control. We present a systematic, end-to-end methodology for benchmarking four GenAI/LLMs, SmolLM2, Llama 3.2, Gemma3, and Gemma3-qat, for a typical mobile robot platform configuration. The approach is two-staged, based on both assessing the specific domain knowledge of the models in an industrial context and their integration with a robotic simulation environment based on ROS2. Reported results focus on quantitative assessment of multiple metrics (quality, coverage, speed, and reliability) and their integration in aggregated scoring mechanisms, which can help developers select and adapt the best model for a particular application, together with custom software implementation. Full article

Effective clash management is critical to the success of complex construction projects, yet BIM coordinators face severe information overload when modern detection tools generate thousands or even millions of collision reports, making interdisciplinary coordination increasingly difficult. This article presents a conceptual framework for using AI for collision triage in a Building Information Modeling (BIM) environment. Previous approaches have focused mainly on collision detection itself and simple, rule-based prioritization, rarely exploiting the potential of Artificial Intelligence (AI) methods for post-processing of results, which constitutes the main innovation of this work. The proposed framework describes a modular system in which collision detection results and data from BIM models, schedules (4D), and cost estimates (5D) are processed by a set of AI components, offering adaptive, data-driven decision support unlike static rule-based methods. These include: a classifier that filters out irrelevant collisions (noise), algorithms that group recurring collisions into single design problems, a model that assesses the significance of collisions by determining a composite ‘AI Triage Score’ indicator, and a module that assigns responsibility to the appropriate trades and process participants. The framework leverages supervised machine learning methods (gradient boosting algorithms, selected for their effectiveness with tabular data) for noise filtering, density-based clustering (HDBSCAN, chosen for its ability to detect clusters of varying densities without predefined cluster count) for clash aggregation, and multi-criteria scoring models for priority assessment. The article also discusses a potential way to integrate the framework into the existing BIM workflow and possible scenarios for its validation based on case studies and expert evaluation. The proposed conceptual framework represents a step towards moving from manual, intuitive collision triage to a data- and AI-based approach, which can contribute to increased coordination efficiency, reduced risk of errors, and better use of design resources. As a conceptual study, the framework provides a foundation for future empirical validation and its limitations include dependency on historical training data availability and the need for calibration to project-specific contexts. Full article

Identifying structurally similar ligand-binding sites in unrelated proteins can facilitate drug repurposing, reveal off-target effects, and deepen our understanding of protein function. A number of tools were developed for structural screening, but many of them suffer from limited sensitivity and scalability. Using a data bank of crystallized protein structures, we aimed to discover novel protein targets for a ligand by leveraging a known ligand-binding query protein with a resolved structure. Here, we present SLAM (Spacio-Linear Alignment of Macromolecules), a novel alignment-based algorithm that detects local 3D similarities between ligand-binding cavities or protein-exposed surfaces of query and target proteins. SLAM encodes spatial substructure neighborhoods into short linear sequences of physicochemically annotated atoms, then applies pairwise sequence alignment combined with distance-correlation scoring to identify high-fidelity structural matches. Benchmarking using the Kahraman-36 dataset demonstrated that SLAM outperforms the state-of-the-art ProBiS algorithm in true-positive rate for predicting ligand-docking compatibility. Furthermore, SLAM identifies candidate ligands that may inhibit functionally critical domains of CRISPR-Cas proteins and predicts novel binding partners of toxic per- and polyfluoroalkyl Substance (PFAS) compounds (PFOA, PFOS) with plausible mechanistic links to toxicity. In conclusion, SLAM is a robust computationally efficient and flexible structural screening tool capable of detecting subtle physicochemical compatibilities between protein surfaces, promising to accelerate target discovery in pharmacology and elucidate protein–ligand interactions in environmental toxicology. Full article

The accelerating global demand for renewable heating, cooling and electricity, driven by climate change and rising living standards, presents both a challenge and an opportunity for sustainable energy transitions. This paper introduces the Initial-Aid Cashback (IAC) model, an innovative business model designed to finance renewable energy solutions, with a focus on space cooling, by leveraging citizen participation and collaborative financing mechanisms. The model incentivizes private investors through discounted energy prices, while system operators benefit from reduced upfront capital requirements and minimised financial risk. Through two case studies, an office building in Romania (small-scale case) and the application of the REGEN-BY-2 technology in a mixed housing–office area (large-scale case), the paper demonstrates the model’s potential to accelerate the adoption of renewable cooling technologies, enhance profitability for operators, and provide attractive returns for investors. The findings highlight the model’s adaptability to diverse stakeholder needs, its scalability, and its role in fostering the clean energy transition (CET). However, challenges such as the need for a minimum number of investors, legal complexities, and trust-building among stakeholders are identified as critical barriers to implementation. The paper concludes that the IAC model offers a promising pathway to integrate citizens and small investors into the CET, while emphasising the importance of supportive policies, clear governance structures, and practical testing to ensure its success. Full article

With production growth and improvements in production speed in modern industries, accurate anomaly detection is becoming increasingly important to improve quality inspection efficiency and help minimize production costs. Existing reconstruction-based methods achieve promising anomaly detection results in some scenarios. However, when large-scale anomalies exist, the generalization ability of these methods is limited, and it is difficult to reconstruct the anomalies effectively into normal areas, which may lead to unsatisfactory results. To address this issue, this paper proposes a novel network architecture called SeRNet, which comprises three components: a segmentation sub-network, a reconstruction sub-network, and a repair module. SeRNet addresses the challenge of large-scale anomaly reconstruction by utilizing the segmentation sub-network for pre-segmentation, the repair module for repairing the large-scale anomalies using normal images similar to the test images, and the reconstruction sub-network for processing small-scale anomalies and anomalies in the repaired splices. Additionally, this paper introduces two methods for generating pseudo-anomalies at different scales. SeRNet leverages the advantages of both the segmentation sub-network, which is effective at segmenting large-scale anomalies, and the reconstruction sub-network, which can effectively reconstruct small-scale anomalies. Experiments on the MVTec AD industrial dataset demonstrate that SeRNet delivers outstanding performance, achieving an image-level AUROC score of 99.6. Full article

The maritime industry is experiencing significant growth due to globalized trade, but this expansion has led to increasing environmental concerns. Studies project that shipping emissions could reach 90–130% of 2008 levels by 2050 without intervention potentially contributing up to 17% of global CO₂ emissions by 2050, thereby posing a major environmental challenge. Stringent environmental regulations from international organizations and government agencies necessitate the maritime industry to find effective solutions to reduce its greenhouse gas (GHG) emissions and improve energy efficiency. This research proposes a methodology for dynamically calculating optimal ship speed to enhance energy efficiency and reduce GHG emissions. By leveraging real-time environmental data (e.g., weather forecasts, sea state information) and operational parameters (e.g., ship characteristics, cargo load), the study utilizes an Adaptive Particle Swarm Optimization based on Velocity Information (APSO-VI) to predict optimal speed over ground (SOG) in real time. The study utilizes the Energy Efficiency Operational Index (EEOI) as a performance metric. EEOI is a widely employed measure in the maritime industry that quantifies the grams of CO₂ emitted per tonne-nautical mile (g CO₂/t nm) of transport work. The effectiveness of the proposed dynamic optimization model (APSO-VI) is assessed by comparing its performance with constant velocity models through extensive simulations, showing a 5–12% reduction in EEOI with the optimized speed model. The results demonstrate significant reductions in fuel consumption and emissions, supporting the adoption of such technologies for a more sustainable maritime industry. Future research may explore integrating machine learning techniques and advanced weather forecasting models for even more robust optimization strategies. Full article

Single-cell RNA sequencing (scRNA-seq) provides a comprehensive understanding of cellular complexity; however, its requirement for fresh or frozen samples limits its flexibility. To overcome this limitation to effectively leverage clinical samples, Chromium Fixed RNA Profiling on formalin-fixed paraffin-embedded (FFPE) tissue blocks (scFFPE-seq) was developed to perform single-nucleus RNA sequencing from nuclei isolated from FFPE. In this study, we utilized fresh tissue samples from colon, ileum, and skin to assess the viability of scFFPE-seq compared to these fresh samples. We were able to recover unique cell types from challenging FFPE tissues and validated scFFPE-seq findings through Hematoxylin and Eosin (H&E) images. The results demonstrated that scFFPE-seq effectively captured the single-cell transcriptome in FFPE tissues, obtaining comparable cell abundance, cell type annotation, and pathway characterization to those in fresh tissues. Overall, the study presents strong evidence of the potential of scFFPE-seq to enhance scientific knowledge by enabling the generation of high-quality, sensitive single-nucleus RNA-seq data from preserved tissue samples. This technique unlocks the vast archives of FFPE samples for extensive retrospective genomic studies. Full article

With the rapid advancement of Generative Adversarial Networks (GANs), diffusion models, and other deep generative techniques, AI-generated images have achieved unprecedented levels of visual realism, posing severe challenges to the authenticity, security, and credibility of digital content. This paper proposes a novel hybrid transformer model that integrates spatial and frequency domains. It leverages CLIP to extract semantic inconsistencies in the image’s spatial domain while employing wavelet transforms to capture multi-scale frequency anomalies in AI-generated images. After cross-domain feature fusion, global modeling is performed within the Swin-Transformer architecture, enabling robust authenticity detection of AI-generated images. Extensive experiments demonstrate that our detector maintains high accuracy across diverse datasets. Full article

Carotid plaque classification based on ultrasound echogenicity and quantification of plaque burden are crucial in stroke risk assessment. In this work, we propose a framework that leverages the synergy between classification and segmentation by sharing plaque location information to enhance the performance of both tasks. Our cascaded framework integrates a ResNet-based classifier (Masked-ResNet-DS) with MedSAM, a medically adapted version of the Segment Anything Model for joint classification and segmentation of carotid plaques from 2D ultrasound images. Ground truth boundaries are used to guide region-specific feature pooling in the classifier, helping it focus on plaques during training. Since ground truth boundaries are unavailable at inference, we introduce a two-iteration strategy: the first generates a class activation map (CAM), which is then used for focused pooling in the second iteration to predict plaque type. The CAM is also used as a prompt to guide MedSAM for segmentation. To ensure accurate localization, the CAM is supervised during training using a Dice loss against the segmentation ground truth. Masked-ResNet-DS achieves a mean F1-score of 96.7% in plaque classification, at least 3.2% higher than competing methods. Ablation studies confirm that ground truth-based pooling and CAM supervision both improve classification. CAM-guided MedSAM achieves a Dice similarity coefficient (DSC) of 86.6%, outperforming U-Net and nnU-Net by 5.9% and 3.6%, respectively. In addition, CAM prompts improve MedSAM’s DSC by 2.2%. By sharing plaque location between classification and segmentation, the proposed method improves both tasks and provides a more accurate tool for stroke risk stratification. Full article

Nowadays, longitudinal data are common—typically high-dimensional, large, complex, and collected using various methods, with repeated outcomes. For example, the growing elderly population experiences health deterioration, including limitations in Instrumental Activities of Daily Living (IADLs), thereby increasing demand for long-term care. Understanding the risk of repeated IADLs and estimating the trajectory risk by identifying significant predictors will support effective care planning. Such data analysis requires a complex modeling framework. We illustrated a regressive modeling framework employing statistical and machine learning (ML) models on the Health and Retirement Study data to predict the trajectory of IADL risk as a function of predictors. Based on the accuracy measure, the regressive logistic regression (RLR) and the Decision Tree (DT) models showed the highest prediction accuracy: 0.90 to 0.93 for follow-ups 1–6; and 0.89 and 0.90 for follow-up 7, respectively. The Area Under the Curve and Receiver Operating Characteristics curve also showed similar findings. Depression scores, mobility score, large muscle score, and Difficulties of Activities of Daily Living (ADLs) score showed a significant positive association with IADLs (p < 0.05). The proposed modeling framework simplifies the analysis and risk prediction of repeated outcomes from complex datasets and could be automated by leveraging Artificial Intelligence (AI). Full article

AI-driven network security relies increasingly on Large Language Models (LLMs) to detect sophisticated threats; however, their deployment on resource-constrained edge devices is severely hindered by immense parameter scales. While unstructured pruning offers a theoretical reduction in model size, commodity Graphics Processing Unit (GPU) architectures fail to efficiently leverage element-wise sparsity due to the mismatch between fine-grained pruning patterns and the coarse-grained parallelism of Tensor Cores, leading to latency bottlenecks that compromise real-time analysis of high-volume security telemetry. To bridge this gap, we propose SPARTA (Sparse Parallel Architecture for Real-Time Threat Analysis), an algorithm–architecture co-design framework. Specifically, we integrate a hardware-based address remapping interface to enable flexible row-offset access. This mechanism facilitates a novel graph-based column vector merging strategy that aligns sparse data with Tensor Core parallelism, complemented by a pipelined execution scheme to mask decoding latencies. Evaluations on Llama2-7B and Llama2-13B benchmarks demonstrate that SPARTA achieves an average speedup of 2.35× compared to Flash-LLM, with peak speedups reaching 5.05×. These findings indicate that hardware-aware microarchitectural adaptations can effectively mitigate the penalties of unstructured sparsity, providing a viable pathway for efficient deployment in resource-constrained edge security. Full article