Search Results (16,427)

Defect inspection of Printed Circuit Board (PCB) is essential for maintaining the safety and reliability of electronic products. With the continuous trend toward smaller components and higher integration levels, identifying tiny imperfections on densely packed PCB structures has become increasingly difficult and remains a major challenge for current inspection systems. To tackle this problem, this study proposes the Multi-scale Edge-Aware Enhanced Detection Transformer (MEE-DETR), a deep learning-based object detection method. Building upon the RT-DETR framework, which is grounded in Transformer-based machine learning, the proposed approach systematically introduces enhancements at three levels: backbone feature extraction, feature interaction, and multi-scale feature fusion. First, the proposed Edge-Strengthened Backbone Network (ESBN) constructs multi-scale edge extraction and semantic fusion pathways, effectively strengthening the structural representation of shallow defect edges. Second, the Entanglement Transformer Block (ETB), synergistically integrates frequency self-attention, spatial self-attention, and a frequency–spatial entangled feed-forward network, enabling deep cross-domain information interaction and consistent feature representation. Finally, the proposed Adaptive Enhancement Feature Pyramid Network (AEFPN), incorporating the Adaptive Cross-scale Fusion Module (ACFM) for cross-scale adaptive weighting and the Enhanced Feature Extraction C3 Module (EFEC3) for local nonlinear enhancement, substantially improves detail preservation and semantic balance during feature fusion. Experiments conducted on the PKU-Market-PCB dataset reveal that MEE-DETR delivers notable performance gains. Specifically, Precision, Recall, and mAP_50–95 improve by 2.5%, 9.4%, and 4.2%, respectively. In addition, the model’s parameter size is reduced by 40.7%. These results collectively indicate that MEE-DETR achieves excellent detection performance with a lightweight network architecture. Full article

This study examines how different programming paradigms are associated with learning experiences and cognitive challenges as encountered by non-computer science novice learners. Using a case-study approach situated within specific instructional contexts, we integrate survey data from undergraduate students with large-scale public question-and-answer data from Stack Overflow to explore paradigm-related difficulty patterns. Four instructional contexts—C, Java, Python, and Prolog—were examined as pedagogical instantiations of imperative, object-oriented, functional-style, and logic-based paradigms using text clustering, word embedding models, and interaction-informed complexity metrics. The analysis identifies distinct patterns of learning challenges across paradigmatic contexts, including difficulties related to low-level memory management in C-based instruction, abstraction and design reasoning in object-oriented contexts, inference-driven reasoning in Prolog-based instruction, and recursion-related challenges in functional-style programming tasks. Survey responses exhibit tendencies that are broadly consistent with patterns observed in public Q&A data, supporting the use of large-scale community-generated content as a complementary source for learner-centered educational analysis. Based on these findings, the study discusses paradigm-aware instructional implications for programming education tailored to non-major learners within comparable educational settings. The results provide empirical support for differentiated instructional approaches and offer evidence-informed insights relevant to curriculum-oriented teaching and future research on adaptive learning systems. Full article

Current electrical self-sensing methods for composite structural health monitoring face significant limitations. Firstly, they often require complicated electrode layouts. Secondly, accurately determining both the location and amplitude of external loads remains a significant challenge. In this study, a deep learning-based self-sensing method is developed to identify the location and amplitude of external mechanical loads in resin-based conductive composites with a simple electrode layout. First, conductive filler-filled resin composites are prepared, and three-dimensional conductive networks are constructed within them. Subsequently, four electrodes are installed at the edges of the composite plate, and boundary electrical resistance responses are collected when applying mechanical loads at various positions on the composite plate. Finally, a residual learning-based CNN model is proposed for the accurate localization and amplitude identification of the applied loads. Research results demonstrate that the trained CNN model can accurately and effectively determine both the load amplitude and position. The obtained localization error and amplitude error are 0.91 mm and 0.13 N, respectively, surpassing the reported error values in previous studies. The research presented here opens a new avenue for achieving highly accurate and efficient prediction of load location and amplitude, which can be widely applied in composite structural health monitoring. Full article

Curling presents a challenging continuous-control problem in which shot outcomes depend on long-horizon interactions between complex physical dynamics, strategic intent, and opponent responses. Despite recent progress in applying reinforcement learning (RL) to games and sports, curling lacks a unified environment that jointly supports stable, rule-consistent simulation, structured state abstraction, and scalable agent training. To address this gap, we introduce a comprehensive learning framework for curling AI, consisting of a full-sized simulation environment, a task-aligned Markov decision process (MDP) formulation, and a two-phase training strategy designed for stable long-horizon optimization. First, we propose a novel MDP formulation that incorporates stone configuration, game context, and dynamic scoring factors, enabling an RL agent to reason simultaneously about physical feasibility and strategic desirability. Second, we present a two-phase curriculum learning procedure that significantly improves sample efficiency: Phase 1 trains the agent to master delivery mechanics by rewarding accurate placement around the tee line, while Phase 2 transitions to strategic learning with score-based rewards that encourage offensive and defensive planning. This staged training stabilizes policy learning and reduces the difficulty of direct exploration in the full curling action space. We integrate this MDP and training procedure into a unified Curling RL Framework, built upon a custom simulator designed for stability, reproducibility, and efficient RL training and a self-play mechanism tailored for strategic decision-making. Agent policies are optimized using Soft Actor–Critic (SAC), an entropy-regularized off-policy algorithm designed for continuous control. As a case study, we compare the learned agent’s shot patterns with elite match records from the men’s division of the Le Gruyère AOP European Curling Championships 2023, using 6512 extracted shot images. Experimental results demonstrate that the proposed framework learns diverse, human-like curling shots and outperforms ablated variants across both learning curves and head-to-head evaluations. Beyond curling, our framework provides a principled template for developing RL agents in physics-driven, strategy-intensive sports environments. Full article

In complex maritime environments, the safety of path planning for Unmanned Surface Vehicles (USVs) remains a significant challenge. Existing methods for handling dynamic obstacles often suffer from inadequate predictability and generate non-smooth trajectories. To address these issues, this paper proposes a reliable hybrid path planning approach that integrates a reinforcement learning-enhanced A* algorithm with an improved Dynamic Window Approach (DWA). Specifically, the A* algorithm is augmented by incorporating a dynamic five-neighborhood search mechanism, a reinforcement learning-based adaptive weighting strategy, and a path post-optimization procedure. These enhancements collectively shorten the path length and significantly improve trajectory smoothness. While ensuring that the global path avoids dynamic obstacles smoothly, a Kalman Filter (KF) is integrated into the Long Short-Term Memory (LSTM) network to preprocess historical data. This mechanism suppresses transient outliers and stabilizes the trajectory prediction of dynamic obstacles. Moreover, the evaluation function of the DWA is refined by incorporating the International Regulations for Preventing Collisions at Sea (COLREGs) constraints, enabling compliant navigation behaviors. Simulation results in MATLAB demonstrate that the enhanced A* algorithm better conforms to the kinematic model of the USVs. The improved DWA significantly reduces collision risks, thereby ensuring safer navigation in dynamic marine environments. Full article

Teacher education represents a global strategic priority for improving educational systems and fostering inclusive, high-quality processes. Recent studies highlight the need for systematic and replicable education models capable of addressing the challenges of contemporary complexity and bridging the gap between theory and practice. Teaching professionalism is increasingly recognized as a key driver of change, requiring a balance of pedagogical, relational, and technological competences, along with strong reflective capacity. Within this framework, practicum programs play a crucial role for the development of professional identity and authentic teaching skills. Methods: This contribution adopts a theoretical–argumentative approach grounded in a critical analysis of the international scientific literature on teacher education, with specific focus on the role of practicums. The aim is to present the model implemented by Pegaso University in the context of practicum activities within initial teacher education programs to outline an interpretative framework and provide pedagogical reflections in light of the results arising from critical reflection and systematic monitoring (not covered in this specific contribution) of the effectiveness of the model implemented in the first two training cycles (academic years 23–24 and 24–25), with the involvement of 5 regions and a total of 2834 teachers in the first cycle and 10 regions and a total of 5551 teachers in the second cycle. Convenience sampling based on a non-probabilistic method was adopted, using the entire sample of teachers admitted to the training program who met the requirements of Article 7 of the Decree of the President of the Council of Ministers (DPCM). Results: This paper outlines the theoretical and methodological trajectories of the model, offering interpretative frameworks and pedagogical reflections in light of the outcomes achieved during the initial implementation phase. Conclusions: In accordance with recent national and European regulatory frameworks, the Pegaso teaching model is presented as an example of good practice for initial teacher education. It aims to foster a reflective, situated, and responsible teaching professionalism, moving beyond traditional approaches toward a continuous and transformative learning process. Full article

Globally, grasslands, savannas, and wetlands are degrading rapidly and increasingly being replaced by woody vegetation. Woody Plant Encroachment (WPE) disrupts natural landscapes and has significant consequences for biodiversity, ecosystem functioning, and key ecosystem services. This review synthesizes findings from 159 peer-reviewed studies identified through a PRISMA-guided systematic literature review to evaluate the drivers of WPE, its ecological impacts, and the remote sensing (RS) approaches used to monitor it. The drivers of WPE are multifaceted, involving interactions among climate variability, topographic and edaphic conditions, hydrological change, land use transitions, and altered fire and grazing regimes, while its impacts are similarly diverse, influencing land cover structure, water and nutrient cycles, carbon and nitrogen dynamics, and broader implications for ecosystem resilience. Over the past two decades, RS has become central to WPE monitoring, with studies employing classification techniques, spectral mixture analysis, object-based image analysis, change detection, thresholding, landscape pattern and fragmentation metrics, and increasingly, machine learning and deep learning methods. Looking forward, emerging advances such as multi-sensor fusion (optical– synthetic aperture radar (SAR), Light Detection and Ranging (LiDAR)–hyperspectral), cloud-based platforms including Google Earth Engine, Microsoft Planetary Computer, and Digital Earth, and geospatial foundation models offer new opportunities for scalable, automated, and long-term monitoring. Despite these innovations, challenges remain in detecting early-stage encroachment, subcanopy woody growth, and species-specific patterns across heterogeneous landscapes. Key knowledge gaps highlighted in this review include the need for long-term monitoring frameworks, improved socio-ecological integration, species- and ecosystem-specific RS approaches, better utilization of SAR, and broader adoption of analysis-ready data and open-source platforms. Addressing these gaps will enable more effective, context-specific strategies to monitor, manage, and mitigate WPE in rapidly changing environments. Full article

Students with learning disabilities (LD) often struggle to develop deep, transferable conceptual understanding in mathematics due to cognitive and processing challenges, underscoring the relevance of instruction grounded in strong teacher pedagogical content knowledge (PCK). This issue is critical given widening post-pandemic achievement gaps and increased expectations for conceptual understanding in inclusive classrooms. Although many studies document effective mathematics interventions for students with LD, relatively few examine how teachers’ PCK functions in these classrooms. In contrast, general education research highlights the importance of PCK for conceptual learning. This manuscript bridges these studies by examining how insights from broader PCK research may inform instruction for students with LD. This manuscript presents a practice-based conceptual synthesis of research on mathematics teachers’ PCK, integrating findings from special education and mathematics intervention literature with classroom vignettes and practitioner examples. The synthesis highlights how core PCK components—content knowledge, understanding of student thinking and misconceptions, and instructional strategies—may support early conceptual understanding in students with LD, emphasizing multiple representations, error analysis, and routines that promote generalization through distributed practice. Implications for practice, professional development, and future research are discussed, offering practice-informed pathways to support inclusive mathematics instruction for students with LD. Full article

With the rapid advancement of smart grids driven by renewable energy integration and the extensive deployment of supervisory control and data acquisition (SCADA) and phasor measurement units (PMUs), addressing the escalating alarm flooding via intelligent analysis of large-scale alarm data is pivotal to safeguarding the safe and stable operation of power grids. To tackle these challenges, this study introduces a pioneering alarm optimization framework based on symmetry-driven crowdsourced active learning and interpretable deep reinforcement learning (DRL). Firstly, an anomaly alarm annotation method integrating differentiated crowdsourcing and active learning is proposed to mitigate the inherent asymmetry in data distribution. Secondly, a symmetrically structured DRL-based hierarchical attention deep Q-network is designed with a dual-path encoder to balance the processing of multi-scale alarm features. Finally, a SHAP-driven interpretability framework is established, providing global and local attribution to enhance decision transparency. Experimental results on a real-world power alarm dataset demonstrate that the proposed method achieves a Fleiss’ Kappa of 0.82 in annotation consistency and an F1-Score of 0.95 in detection performance, significantly outperforming state-of-the-art baselines. Additionally, the false positive rate is reduced to 0.04, verifying the framework’s effectiveness in suppressing alarm flooding while maintaining high recall. Full article

This article introduces a framework for scientific and professional language training tailored for STEM (Science, Technology, Engineering and Mathematics) specialists, emphasising the integration of digital technologies and artificial intelligence (AI) in language education. The framework aims to develop students’ research communication skills and digital competencies, which are essential for effective participation in both national and international scientific discourse. The article discusses contemporary trends in STEM education, emphasising the importance of interdisciplinary approaches, project-based learning, and the utilisation of digital tools to boost language skills and scientific literacy. The article outlines the development and deployment of a digital platform aimed at supporting personalised and adaptive learning experiences, integrating various educational technologies and approaches. Empirical research conducted through a pedagogical experiment demonstrates the effectiveness of the framework, showing significant improvements in students’ academic and linguistic competencies across multiple modules. The findings highlight the importance of combining language training with STEM education to equip future engineers for the challenges of a globalised and digitalised professional world. This work reports on the “Enhancing Scientific and Professional Language Learning for Engineering Students in Kazakhstan through Digital Technologies” project conducted at Saginov Technical University (STU) in Kazakhstan and funded by the Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan (Grant No. AP19678460). The research contributes to the ongoing discussion on improving language teaching in STEM fields, offering a framework that aligns with current educational demands and technological progress. Full article

Eutrophication remains a persistent challenge in the Romanian Black Sea coastal zone, driven by excess nutrient inputs from riverine and coastal sources and further intensified by climate change. This study assesses eutrophication dynamics and explores mitigation options using an integrated framework that combines in situ observations, satellite-derived chlorophyll a data, machine learning, and system dynamics modelling. Water samples collected during two field campaigns (2023–2024) were analyzed for nutrient concentrations and linked with chlorophyll a products from the Copernicus Marine Service. Random Forest analysis identified dissolved inorganic nitrogen, phosphate, salinity, and temperature as the most influential predictors of chlorophyll a distribution. A system dynamics model was subsequently used to explore relative ecosystem responses under multiple management scenarios, including nutrient reduction, enhanced zooplankton grazing, and combined interventions. Scenario-based simulations indicate that nutrient reduction alone produces a moderate decrease in chlorophyll a (45% relative to baseline conditions), while restoration of grazing pressure yields a comparable response. The strongest reduction is achieved under the combined scenario, which integrates nutrient reduction with biological control and lowers normalized chlorophyll a levels by approximately two thirds (71%) relative to baseline. In contrast, a bloom-favourable scenario results in a several-fold increase in chlorophyll a of 160%. Spatial analysis highlights persistent eutrophication hotspots near the Danube mouths and urban discharge areas. These results demonstrate that integrated strategies combining nutrient source control with ecological restoration are substantially more effective than single-measure interventions. The proposed framework provides a scenario-based decision-support tool for ecosystem-based management and supports progress toward achieving Good Environmental Status under the Marine Strategy Framework Directive. Full article

Camellia oleifera, a woody oil crop unique to China, plays a crucial role in alleviating the global pressure of edible oil supply and maintaining ecological security. However, it remains challenging to accurately forecast Camellia oleifera yield in complex landscapes using only remote sensing data. The aim of this study is to develop an interpretable deep learning model, namely Shapley Additive Explanations–guided Attention–long short-term memory (SALSTM), for estimating Camellia oleifera yield by integrating an improved spectral bloom index and environmental parameters. The study area is located in Hengyang City in Hunan Province. Sentinel-2 imagery, meteorological observation from 2019 to 2023, and topographic data were collected. First, an improved spectral bloom index (ISBI) was constructed as a proxy for flowering density, while average temperature, precipitation, accumulated temperature, and wind speed were selected to represent environmental regulation variables. Second, a SALSTM model was designed to capture temporal dynamics from multi-source inputs, in which the LSTM module extracts time-dependent information and an attention mechanism assigns time-step-wise weights. Feature-level importance derived from SHAP analysis was incorporated as a guiding prior to inform attention distribution across variable dimensions, thereby enhancing model transparency. Third, model performance was evaluated using root mean square error (RMSE) and coefficient of determination (R²). The result show that the constructed SALSTM model achieved strong predictive performance in predicting Camellia oleifera yield in Hengyang City (RMSE = 0.5738 t/ha, R² = 0.7943). Feature importance analysis results reveal that ISBI weight > 0.26, followed by average temperature and precipitation from flowering to fruit stages, these features are closely associated with C. oleifera yield. Spatially, high-yield zones were mainly concentrated in the central–southern hilly regions throughout 2019–2023, In contrast, low-yield zones were predominantly distributed in the northern and western mountainous areas. Temporally, yield hotspots exhibited a gradual increasing while low-yield zones showed mild fluctuations. This framework provides an effective and transferable approach for remote sensing-based yield estimation of flowering and fruit-bearing crops in complex landscapes. Full article

Wireless Body Area Networks (WBANs) enable real-time data collection for medical monitoring, sports tracking, and environmental sensing, driven by Internet of Things advancements. Their layered architecture supports efficient sensing, aggregation, and analysis, but energy constraints from transmission (over 60% of consumption), idle listening, and dynamic conditions like body motion hinder adoption. Challenges include minimizing energy waste while ensuring data reliability, Quality of Service (QoS), and adaptation to channel variations, alongside algorithm complexity and privacy concerns. This paper reviews recent power control mechanisms in WBANs, encompassing feedback control, dynamic and convex optimization, graph theory-based path optimization, game theory, reinforcement learning, deep reinforcement learning, hybrid frameworks, and emerging architectures such as federated learning and cell-free massive MIMO, adopting a systematic review approach with a focus on healthcare and IoT application scenarios. Achieving energy savings ranging from 6% (simple feedback control) to 50% (hybrid frameworks with emerging architectures), depending on method complexity and application scenario, with prolonged network lifetime and improved reliability while preserving QoS requirements in healthcare and IoT applications. Full article

Background/Objectives: Diagnosing Rotator Cuff Tears (RCTs) via Magnetic Resonance Imaging (MRI) is clinically challenging due to complex 3D anatomy and significant interobserver variability. Traditional slice-centric Convolutional Neural Networks (CNNs) often fail to capture the necessary volumetric context for accurate grading. This study aims to develop and validate the Patient-Aware Vision Transformer (Pa-ViT), an explainable deep-learning framework designed for the automated, patient-level classification of RCTs (Normal, Partial-Thickness, and Full-Thickness). Methods: A large-scale retrospective dataset comprising 2447 T2-weighted coronal shoulder MRI examinations was utilized. The proposed Pa-ViT framework employs a Vision Transformer (ViT-Base) backbone within a Weakly-Supervised Multiple Instance Learning (MIL) paradigm to aggregate slice-level semantic features into a unified patient diagnosis. The model was trained using a weighted cross-entropy loss to address class imbalance and was benchmarked against widely used CNN architectures and traditional machine-learning classifiers. Results: The Pa-ViT model achieved a high overall accuracy of 91% and a macro-averaged F1-score of 0.91, significantly outperforming the standard VGG-16 baseline (87%). Notably, the model demonstrated superior discriminative power for the challenging Partial-Thickness Tear class (ROC AUC: 0.903). Furthermore, Attention Rollout visualizations confirmed the model’s reliance on genuine anatomical features, such as the supraspinatus footprint, rather than artifacts. Conclusions: By effectively modeling long-range dependencies, the Pa-ViT framework provides a robust alternative to traditional CNNs. It offers a clinically viable, explainable decision support tool that enhances diagnostic sensitivity, particularly for subtle partial-thickness tears. Full article

Reliable monitoring of pesticide residues is essential for ensuring food safety. Conventional chromatographic and spectrometric techniques remain labor-intensive, time-consuming, and costly. Recent progress in Machine Learning (ML) provides computational tools that improve the precision and efficiency of pesticide residue detection in diverse food matrices. This review presents a comprehensive analysis of current ML-based approaches for pesticide analysis, with particular attention to supervised learning algorithms such as support vector machines, random forests, boosting methods, and deep neural networks. These models have been integrated with chromatographic, spectroscopic, and electrochemical platforms to achieve enhanced signal interpretation and more reliable prediction from existing analytical data, and more robust data processing in complex food systems. The review also discusses methodologies for feature extraction, model validation, and the management of heterogeneous datasets, while examining ongoing challenges that include limited training data, matrix variability, and regulatory constraints. Emerging advances in deep learning architectures, transfer learning strategies, and portable sensing technologies are expected to support the development of real-time, field-ready monitoring systems. The findings highlight the potential of ML to advance food quality assurance and strengthen public health protection through more efficient and accurate pesticide residue detection. Full article