Search Results (801)

The Dubai Government has made significant investments in digital learning through platforms such as Al Mawrid and Bayanati, enabling widespread access to employee training and upskilling. However, there remains a major gap in translating accumulated learning into intelligent workforce restructuring. This paper proposes “SkillChain DX,” a policy-driven framework that applies artificial intelligence (AI) to dynamically map employee-acquired skills to evolving job roles across departments, developed using a conceptual design science and policy analysis approach. The framework integrates blockchain to ensure secure, tamper-proof verification of skill credentials across diverse training platforms. To validate feasibility, a pilot prototype was implemented using sentence-transformer models for semantic skill inference and cryptographic hashing mechanisms for decentralized credential verification. Experimental evaluation across six controlled scenarios demonstrated an average role-matching accuracy of approximately 82%, blockchain transaction throughput exceeding 1000 operations per second, and near-instant credential verification with over 99% performance improvement compared to manual processes. The findings demonstrate that integrating AI-driven skill inference with decentralized credential verification can significantly enhance internal mobility, role alignment, and workforce planning at a policy level. The study benchmarks international practices and outlines a practical implementation path for the Dubai Government using only publicly available technologies and case studies, positioning SkillChain DX as one of the first integrated AI–blockchain policy frameworks tailored to public sector human resources (HR) transformation in Dubai. The proposed system framework bridges the current disconnect between training access and organizational transformation, supporting a proactive, transparent, and skills-first public sector, while offering actionable policy insights for future government HR modernization. Full article

Objectives: Global infertility rates are rapidly increasing. Assisted reproductive technologies combined with artificial intelligence are the next hope for overcoming infertility. In vitro fertilization (IVF) is gaining popularity owing to its increasing success rates. The success rate of IVF essentially depends on the assessment and inspection of blastocysts. Blastocysts can be segmented into several important compartments, and advanced and precise assessment of these compartments is strongly associated with successful pregnancies. However, currently, embryologists must manually analyze blastocysts, which is a time-consuming, subjective, and error-prone process. Several AI-based techniques, including segmentation, have been recently proposed to fill this gap. However, most existing methods rely only on raw grayscale intensity and do not perform well under challenging blastocyst image conditions, such as low contrast, similarity in textures, shape variability, and class imbalance. Methods: To overcome this limitation, we developed a novel and lightweight architecture, the microscopic multimodal interaction segmentation network (MiMics-Net), to accurately segment blastocyst components. MiMics-Net employs a multimodal blastocyst stem to decompose and process each frame into three modalities (photometric intensity, local textures, and directional orientation), followed by feature fusion to enhance segmentation performance. Moreover, MiMic dual-path grouped blocks have been designed, in which parallel-grouped convolutional paths are fused through point-wise convolutional layers to increase diverse learning. A lightweight refinement decoder is employed to refine and restore the spatial features while maintaining computational efficiency. Finally, semantic skip pathways are induced to transfer low- and mid-level spatial features after passing through the grouped and point-wise convolutional layers. Results/Conclusions: MiMics-Net was evaluated using a publicly available human blastocyst dataset and achieved a Jaccard index score of 87.9% while requiring only 0.65 million trainable parameters. Full article

As the global urban economy accelerates its transition from an “industrial economy” to a “service economy”, consumption has replaced investment as the core engine driving economic development. Commercial land serves as the physical foundation for consumer activities and plays a vital role in boosting urban economic vitality, enhancing residents’ quality of life, and promoting regional sustainable development when appropriately allocated. This study constructs a technical framework for analyzing the mismatch between commercial land supply and residential consumption demand, along with its impact mechanism, based on the integrated application of the multidisciplinary quantitative models such as the Boston Consulting Group Matrix (BCGM), Exploratory Spatial Data Analysis (ESDA), Decoupling Model (DM), and Explainable Machine Learning (EML). It conducts empirical research across 87 county-level cities in Gansu Province. The findings reveal that commercial land supply and consumption demand exhibit dynamic diversification, with prominent regional disparities and spatial autocorrelation characteristics. Commercial land in Gansu faces a severe mismatch, with demand exceeding supply and supply exceeding demand occurring simultaneously, and the former holding absolute dominance. The formation of mismatched relationships is influenced by many factors, exhibiting significant path nonlinearity, spatial non-stationarity, and relational interactivity. It is suggested that strategies of planning zoning and regional coordination be developed for mismatch governance, and differentiated management measures be implemented based on local conditions. This will provide a scientific basis for commercial territorial space planning and consumption policy design. Full article

Existing methods for power load anomaly detection suffer from several limitations, including insufficient extraction of multi-scale temporal features, difficulty in capturing long-range dependencies, and inefficient fusion of heterogeneous Time-Graph information. To address these issues, this study proposes the TGCformer, an enhanced framework for Time-Graph feature fusion. First, a dual-channel feature extraction module is constructed. The temporal path utilizes Time Series Feature Extraction based on Scalable Hypothesis Tests (TSFresh) to enhance the explicit pattern representation of the load sequences, while the graph-learning path employs a Sparse Unified Graph Attention Network v2 (Sparse Unified GATv2) to model global semantic correlations among time steps. Together, these two paths provide more interpretable and structured inputs for the subsequent fusion module. Subsequently, a multi-head cross-attention mechanism is designed, where temporal features serve as the Query and graph-level embeddings as the Key and Value to guide the feature fusion process. This design ensures the effective integration of complementary information while suppressing noise. Experimental results on the public Irish CER Smart Meter Dataset demonstrate the effectiveness of the proposed model. Specifically, TGCformer consistently outperforms four classic deep learning baselines (XceptionTime, InceptionTime, FormerTime, and LSTM-GNN), demonstrating competitive detection accuracy and robustness. Full article

Visible-infrared image fusion is crucial for applications like autonomous driving and nighttime surveillance, yet it remains challenging due to the inherent limitations of existing deep learning models. Convolutional Neural Networks (CNNs) are constrained by their local receptive fields, while Transformers suffer from quadratic computational complexity. To address these issues, this paper investigates the application of the Mamba model—a novel State Space Model (SSM) with linear-complexity global modeling and selective scanning capabilities—to the task of visible-infrared image fusion. Building upon Mamba, we propose a novel fusion framework featuring two key designs: (1) A Multi-Path Mamba (MPMamba) module that orchestrates parallel Mamba blocks with convolutional streams to extract multi-scale, modality-specific features; and (2) a Dual-path Mamba Attention Fusion (DMAF) module that explicitly decouples and processes shared and complementary features via dual Mamba paths, followed by dynamic calibration with a Convolutional Block Attention Module (CBAM). Extensive experiments on the MSRS benchmark demonstrate that our framework achieves state-of-the-art performance, outperforming strong baselines such as U2Fusion and SwinFusion across key metrics including Information Entropy (EN), Spatial Frequency (SF), Mutual Information (MI), and edge-based fusion quality (Qabf). Visual results confirm its ability to produce fused images that saliently preserve thermal targets while retaining rich texture details. Full article

Accurate and real-time glottis localization is critical for ensuring intraoperative oxygenation and patient safety during nasotracheal intubation. However, representative foundation models exemplified by the Segment Anything Model exhibit notable limitations in medical applications, stemming from their rigid attention mechanisms, feature space misalignment, and insufficient generalization to complex glottal anatomies. To address these challenges, we propose Glottis-SAM, a lightweight and task-adaptive segmentation framework that integrates dynamic representation learning with multi-prior contextual modeling. Specifically, we introduce a hierarchical low-rank adaptation strategy that enables efficient fine-tuning of visual foundation models by preserving geometric priors while significantly reducing computational overhead. To further enhance semantic fusion and generalization, we design a feature aggregation module with dual-path dynamic feature pyramids, which enables complementary optimization from local textures to global semantic structures under varying anatomical conditions. Extensive experiments on three diverse datasets demonstrate that Glottis-SAM achieves state-of-the-art segmentation accuracy with 72.6% mDice, a compact 55.2 MB model size, and 44.3 FPS inference speed on clinical data. These results highlight the model’s robustness, efficiency, and potential for deployment in visual guidance systems for nasotracheal intubation. Full article

Recently, the progress of foundation models such as CLIP and SAM has shown the great potential of zero-shot anomaly detection tasks. However, existing methods usually rely on general descriptions such as “abnormal”, and the semantic coverage is insufficient, making it difficult to express fine-grained anomaly semantics. In addition, CLIP primarily performs global-level alignment, and it is difficult to accurately locate minor defects, while the segmentation quality of SAM is highly dependent on prompt constraints. In order to solve these problems, we proposed DCS, a unified framework that integrates Grounding DINO, CLIP and SAM through three key innovations. First of all, we introduced FinePrompt for adaptive learning, which significantly enhanced the modeling ability of exception semantics by building a fine-grained exception description library and adopting learnable text embeddings. Secondly, we have designed an Adaptive Dual-path Cross-modal Interaction (ADCI) module to achieve more effective cross-modal information exchange through dual-path fusion. Finally, we proposed a Box-Point Prompt Combiner (BPPC), which combines box prior information provided by DINO with the point prompt generated by CLIP, so as to guide SAM to generate finer and more complete segmentation results. A large number of experiments have proved the effectiveness of our method. On the MVTec-AD and VisA datasets, DCS has achieved the most state-of-the-art zero-shot anomaly detection results. Full article

Many complex engineering problems can be formulated as mathematical optimization tasks, for which bio-inspired metaheuristic algorithms have demonstrated outstanding effectiveness. Drawing inspiration from snake behavior, the Snake Optimizer (SO) algorithm provides a promising framework but suffers from random population initialization, insufficient global search capability, and slow convergence. To address these drawbacks, the study proposes a Modified Snake Optimizer (MSO) that integrates three key strategies: a dual mapping strategy based on Latin hypercube sampling and logistic mapping for population initialization; an opposition-based learning mechanism with scaling factors for exploration; and integration of the soft-rime search strategy from RIME optimization during exploitation. The performance of MSO was benchmarked against nine representative algorithms using the CEC2017 and further validated on three engineering application problems—pressure vessel, tension/compression spring, and hydrostatic thrust bearing design, and two UAV path planning scenarios. Experimental results show that MSO achieves faster convergence speed, stronger robustness and greater stability, effectively extending the biomimetic principles of the original SO and confirming its superiority for solving optimization problems. Full article

Accurate cropland parcel mapping is essential for food security and sustainable land management in arid Africa, yet it remains challenging in Egypt due to edge blurring, spectral confusion, and fragmented fields in medium-resolution imagery. A novel dual-encoder deep learning method that integrates multi-scale axial attention and boundary constraints (MAA-BCNet) is proposed for the precise extraction of croplands in Egypt from Sentinel-2 multispectral images. A dual-path encoder is designed to fuse CNN-based local textures with an RMT global branch using spatial decay attention for complementary feature extraction. A multi-scale axial attention module is introduced to capture anisotropic parcel structures for improved spectral–spatial discrimination, and a multi-directional gradient edge enhancement module is developed for explicitly preserving boundary integrity. A U-Net++ decoder is employed for dense multi-scale aggregation. Experimental results in Egypt demonstrate that MAA-BCNet achieves superior performance in delineating cropland parcels, particularly for irregular or fragmented croplands with complex landscapes and fuzzy boundaries. Compared with the widely used segmentation models such as DeepLabV3_plus, PSPnet, Link_net, FCN_resnet101, and U-Net++ under the same training and evaluation settings, our model has the best performance, with Recall, Precision, IoU, and F1-Score reaching 94.92%, 90.77%, 86.57%, and 92.80%, respectively. These advancements make MAA-BCNet suitable for cropland mapping of large areas of Egypt, with applications in precision agriculture and sustainable land management. Full article

Artificial intelligence (AI) has the potential to transform healthcare by supporting more accurate diagnoses and personalized treatments. However, its adoption in practice remains constrained by fragmented data sources, strict privacy rules, and the technical complexity of building reliable clinical systems. To address these challenges, we introduce a model-driven engineering (MDE) framework designed specifically for healthcare AI. The framework relies on formal metamodels, domain-specific languages (DSLs), and automated transformations to move from high-level specifications to running software. At its core is the Medical Interoperability Language (MILA), a graphical DSL that enables clinicians and data scientists to define queries and machine learning pipelines using shared ontologies. When combined with a federated learning architecture, MILA allows institutions to collaborate without exchanging raw patient data, ensuring semantic consistency across sites while preserving privacy. We evaluate this approach in a multi-center cancer immunotherapy study. The generated pipelines delivered strong predictive performance, with best-performing models achieving up to 98.5% accuracy on selected prediction tasks, while substantially reducing manual coding effort. These findings suggest that MDE principles—metamodeling, semantic integration, and automated code generation—can provide a practical path toward interoperable, reproducible, and reliable digital health platforms. Full article

The multi-jet polishing process (MJP) demonstrates high shape accuracy and surface quality in the machining of nonlinear and complex surfaces, and it achieves precise and adjustable material removal rates through computer control. However, there are still challenges in terms of machining efficiency, system complexity, and stability. In particular, maintaining the polishing quality presents a greater challenge when working conditions change. To overcome these issues, this paper conceptually proposes a digital twin (DT)-driven, human-centric design framework that integrates key factors of MJP, such as jet kinetic energy, nozzle structure, abrasive type, and machining path. Within this framework, a feature-encoded transfer learning-based model is introduced to enhance surface roughness prediction accuracy and robustness under varying working conditions. The effectiveness of the proposed model was verified by conducting experiments on 3D printed workpieces under two different MJP working conditions. The results show that our proposed method yields better predictive performance and cross-condition adaptability. Overall, this work provides a predictive modeling component that supports DT-driven process design, offering a practical and extensible perspective for optimizing complex ultra-precision manufacturing processes under data-scarce and uncertainty-dominated conditions. Full article

The informal learning spaces (ILSs), as the core carrier supporting students’ autonomous learning and social interaction, have become an indispensable component of modern campuses. However, existing research still has limitations, including the ambiguous definition of ILSs and the lack of analysis of the synergy between social and physical dimension factors and students’ performance. To further explore the above problems, this review conducted a systematic review, in which all included literature was analysed following the PRISMA guidelines. This review retrieved 33 empirical studies from multiple databases in the fields of education, architecture and library science published from 2000 to 2025. The results of this review show that ILSs can be defined as dynamic ecosystems primarily designed to support self-directed and collaborative learning. The ecosystem integrates technological infrastructure, flexible layouts and social interaction to accommodate diverse learning needs. Meanwhile, ILSs’ design needs to coordinate and balance the multiple influencing factors across the social and physical dimensions. Although synthesising findings inevitably involves subjective judgement, this review can provide design guidelines for educators, architects, and policymakers that account for both students’ needs and adaptive functional configurations, thereby offering a practical path to achieving inclusive learning environments and sustainable campus development. Full article

Edge artificial intelligence (AI) workloads generate bursty, heterogeneous traffic on Networks-on-Chip (NoCs) under tight energy and latency constraints. Hybrid NoCs that overlay electronic meshes with silicon photonic express links can reduce long-path latency via wavelength-division multiplexing, but thermal drift and intermittent optical availability complicate routing. This study introduces a decentralized, photonic-aware controller based on Deep Reinforcement Learning (DRL) with Proximal Policy Optimization (PPO). The policy uses router-local observables—per-port buffer occupancy with short histories, hop distance, a local injection estimate, and a per-cycle optical validity signal—and applies action masking so chosen outputs are always feasible; the controller is co-designed with the router pipeline to retain single-cycle decisions and a modest memory footprint. Cycle-accurate simulations with synthetic traffic and benchmark-derived traces evaluate mean packet latency, throughput, and energy per delivered bit against deterministic, adaptive, and recent DRL baselines; ablation studies isolate the roles of optical validity cues and locality. The results show consistent improvements in congestion-forming regimes and on long electronic paths bridged by photonic links, with robustness across mesh sizes and wavelength concurrency. Overall, the evidence indicates that photonic-aware PPO provides a practical, thermally robust control plane for hybrid NoCs and a scalable routing solution for AI-centric manycore and edge systems. Full article

The growing interest in precision agriculture has led, in recent years, to an increase in the adoption of Internet of Things (IoT) technologies in the service of smart agriculture to optimize agricultural production processes through the monitoring of environmental conditions and prevent food loss. This work stems from research conducted as part of the Tech4You project, where the enabling digital technologies developed in Spoke 6 contribute to the advanced solutions envisaged by Spoke 3 to facilitate the transition to a sustainable agrifood system. In particular, we present the design and evaluation of a multi-hop Device-to-Device (D2D) communication architecture that leverages Long Range (LoRa) technology, specifically designed for monitoring vineyards in the context of passito wine production. The proposed framework addresses the challenge of monitoring mobile containers for grapes during the drying phase, a critical stage in which inadequate temperatures and humidity can promote the growth of fungi and the formation of mycotoxins. The integration of simulation-based performance evaluation with a multi-layer system architecture is presented in this work. The objective is to compare the performance of different routing strategies in choosing data forwarding paths to the gateway. The simulation results show that the proposed routing strategy, which is based on learning but also focuses on energy consumption, offers good performance. In particular, it achieves packet delivery rates of over $92\%$ and preserves over $95\%$ of active nodes after 2 h of operation. Energy-aware routing strategies also perform well compared to those that only consider the distance from the destination, but overall, the proposed strategy achieves a better trade-off on the metrics analyzed. Full article

This study examines the pricing dynamics of Non-Fungible Tokens (NFTs) in the secondary market using advanced machine-learning techniques. We construct a large dataset of Ethereum-based NFT transactions initially comprising over 500,000 raw blockchain observations spanning multiple NFT segments, including art, collectibles, gaming, metaverse, and utility assets, over the period from November 2018 to March 2023. Following data preprocessing, synchronization across data sources, and the construction of history-dependent features, the analysis focuses on a final analytical sample of approximately 70,000 transactions. To address the challenges of non-fungibility, thin trading, and high price dispersion, we develop an interpretable predictive framework that integrates domain-informed manual feature engineering, automated Deep Feature Synthesis, and dimensionality reduction via Principal Component Analysis. Three non-linear models—Random Forest, XGBoost, and a Multilayer Perceptron—are trained and evaluated using both random and time-aware validation strategies. The results indicate that XGBoost consistently achieves the highest predictive accuracy, both overall and across individual NFT segments, while historical transaction prices emerge as the dominant predictor of future prices. Segment-level analysis reveals substantial heterogeneity in predictability, with art and collectible NFTs exhibiting more stable pricing patterns than gaming and metaverse assets. Overall, the findings highlight strong path dependence and reputation-driven valuation in NFT markets and demonstrate that carefully designed machine-learning models can deliver high predictive performance without sacrificing economic interpretability. Full article