Search Results (23,387)

Knowledge tracing is a methodological framework focused on modeling and predicting learners’ future performance on tasks involving related concepts, while also tracking the dynamic evolution of their knowledge over time. The current study aims to assess the effectiveness of an intelligent learning system (ILS) based on the Knowledge Tracing Model in improving academic passion, self-efficacy, and achievement among 100 students enrolled in a Special Care course. A quasi-experimental design was employed via a single experimental group without a control group. Three instruments—achievement test, self-efficacy, and academic passion—were administered pre- and post-intervention. A statistically significant improvement was observed across all three domains. The findings suggest a positive association between the use of the ILS and gains in academic achievement, self-efficacy, and academic passion. In conclusion, the results support the use of knowledge-tracing-based learning systems for academic performance enhancement and university students’ motivation. Full article

Biochar supplementation has gained a lot of interest in recent years as a strategy to improve anaerobic digestion. As a result, research on the field has expanded in diverse directions, yet a clear pathway is not being followed, which can lead to unexpected or contradictory results. This review analyzed the most recent literature (2020–2024) on this topic and identified three major research trends: (i) investigating the mechanisms behind biochar enhancement of anaerobic digestion (analysis of microbial communities, interspecies electron transfer, metabolic pathways, enzymatic activity, gene expression, extracellular polymeric substances, quorum sensing, and antibiotic resistance genes); (ii) maximizing biochar applications in anaerobic digestion through the use of novel tools (biochar engineering, modeling and optimization, and integration of anaerobic digestion and other technologies); (iii) advancing towards the large-scale implementation of biochar addition to anaerobic digestion (continuous operation, biochar effects on digestate, techno-economic analysis, and life cycle assessment). By investigating these topics, key knowledge gaps and challenges to be addressed in future research were defined and discussed. This review aims to provide a clear and insightful picture of the current state and future prospects of scientific research in this field, which may be of great relevance given the current rise in this technology. Full article

Elderly patients often experience multimorbidity and long-term polypharmacy, making medication safety a critical challenge in disease management. In China, the concurrent use of Western medicines and proprietary Chinese medicines (PCMs) further complicates this issue, as potential drug interactions are often implicit, increasing risks for physiologically vulnerable older adults. Although large language model-based medical question-answering systems have been widely adopted, they remain prone to unsafe outputs in medication-related contexts. Existing retrieval-augmented generation (RAG) frameworks typically rely on static retrieval strategies, limiting their ability to appropriately allocate retrieval and verification efforts across different question types. This paper proposes FusionGraphRAG, an adaptive RAG framework for geriatric disease management. The framework employs query classification-based routing to distinguish questions by complexity and medication relevance; integrates dual-granularity knowledge alignment to connect fine-grained medical entities with higher-level contextual knowledge across diseases, medications, and lifestyle guidance; and incorporates explicit contradiction detection for high-risk medication scenarios. Experiments on the GeriatricHealthQA dataset (derived from the Huatuo corpus) indicate that FusionGraphRAG achieves a Safety Recall of 71.7%. Comparative analysis demonstrates that the framework improves retrieval accuracy and risk interception capabilities compared to existing graph-enhanced baselines, particularly in identifying implicit pharmacological conflicts. The results indicate that the framework supports more reliable geriatric medical question answering while providing enhanced safety verification for medication-related reasoning. Full article

Background/Objectives: Neurofibromatosis type 1 (NF1) is a genetic disorder characterized by various clinical manifestations, including significant neurovascular complications. This review aims to synthesize current knowledge regarding intracranial stenoses and associated vascular abnormalities in patients with NF1, emphasizing the differences between pediatric and adult populations. Methods: A narrative review was conducted, analyzing the existing literature on the epidemiology, clinical manifestations, and management of neurovascular issues related to NF1. Data were collected from a range of studies, including retrospective analyses and case series, focusing on the incidence and outcomes of intracranial vascular abnormalities. Results: The study found that intracranial vasculopathy affects between 0.4% and 6.4% of NF1 patients, with children experiencing higher rates of stenotic lesions. However, vascular issues in adults are less understood, with 3.5% of adult patients presenting vascular abnormalities. The review highlights a significant underdiagnosis of these conditions due to the lack of routine use of magnetic resonance angiography (MRA) in standard evaluations. The management of NF1-related vascular conditions, particularly in adults, remains poorly defined, particularly regarding the efficacy of antithrombotic therapies. Conclusions: The management of neurovascular complications in NF1 requires urgent attention, with a need for standardized screening protocols and further research to elucidate the natural history and optimal treatment strategies for these patients. Enhanced diagnostic practices, including routine neuroimaging, are essential to improve outcomes and reduce the risk of significant vascular events. Full article

This study presents a hybrid analytical framework that enhances project selection by achieving reasonable predictive accuracy through the integration of expert judgment and modern artificial intelligence (AI) techniques. Using an enterprise-level dataset of 10,000 completed software projects with verified real-world statistical characteristics, we develop a three-step architecture for intelligent decision support. First, we introduce an extended Analytic Hierarchy Process (AHP) that incorporates organizational learning patterns to compute expert-validated criteria weights with a consistent level of reliability ($CR=0.04$), and Linear Programming is used for portfolio optimization. Second, we propose a machine learning architecture that integrates expert knowledge derived from AHP into models such as Transformers, TabNet, and Neural Oblivious Decision Ensembles through mechanisms including attention modulation, split criterion weighting, and differentiable tree regularization. Third, the hybrid AHP-Stacking classifier generates a meta-ensemble that adaptively balances expert-derived information with data-driven patterns. The analysis shows that the model achieves 97.5% accuracy, a 96.9% F1-score, and a 0.989 AUC-ROC, representing a 25% improvement compared to baseline methods. The framework also indicates a projected 68.2% improvement in portfolio value (estimated incremental value of USD 83.5 M) based on post factum financial results from the enterprise’s ventures.This study is evaluated retrospectively using data from a single enterprise, and while the results demonstrate strong robustness, generalizability to other organizational contexts requires further validation. This research contributes a structured approach to hybrid intelligent systems and demonstrates that combining expert knowledge with machine learning can provide reliable, transparent, and high-performing decision-support capabilities for project portfolio management. Full article

Given the knowledge-intensive and rapidly expanding nature of medical field, accurately synthesizing and interpreting findings remain a major challenge for clinicians and medical students. Although Large Language Models (LLMs) have advanced automated summarization or generated responses, their deployment is limited by hallucinations, outdated knowledge, and insufficient domain adaptation. Retrieval-Augmented Generation (RAG) addresses these issues by grounding LLMs in external knowledge bases. However, as the document corpus scales, maintaining RAG accuracy becomes increasingly difficult, making retrievers critical for contextual relevance. In this paper, we examined the efficiency of a modular RAG framework with a hybrid retrieval strategy that combines sparse retrieval (BM25) and dense retrieval (MedCPT) to extract the most relevant documents from the corpus, thereby providing contextual grounding for the LLM to improve medical responses. Evaluation was conducted on three benchmark healthcare datasets: PubMedQA, MedMCQA, and MedQA-US, using two LLMs, GPT-4o and BioGPT. Performance was assessed using retrieval metrics (context precision, context recall, F1-score) and generation metrics (BERTScore, RAG Assessment Score). The hybrid retriever achieved 92.14% recall, 74.36% precision, and an F1-score of 82.30%. GPT-4o with hybrid retrieval reached 89.4% faithfulness, 82.7% answer relevancy, and an ${\mathrm{F}1}_{\mathrm{BERT}}$ of 88.0% on PubMedQA. Results demonstrated that hybrid retrieval within a modular architecture substantially improves retrieval effectiveness and response quality. The proposed work offers a scalable, generalizable solution for high-stakes healthcare applications, supporting flexible retriever integration and robust evaluation to advance transparent QA systems. Full article

Microalgae and cyanobacteria represent promising, sustainable resources for agricultural applications, particularly as biofertilisers, biostimulants, and biological plant protection agents. Their biomass can improve nutrient use efficiency, support plant growth and yield, and enhance soil structure and microbial activity, while cyanobacteria additionally contribute through biological nitrogen fixation, reducing reliance on synthetic fertilisers. The integration of microalgal cultivation with closed-loop systems, such as wastewater treatment plants or biogas facilities, enables nutrient recovery, production of value-added biomass, and mitigation of greenhouse gas emissions. This review synthesises current knowledge on the biochemical composition, functional properties, and mechanisms of action of microalgal and cyanobacterial biomass in relation to these established agricultural applications. In addition, prevailing research trends, selected technological and organisational constraints, and implementation challenges are discussed. Particular attention is given to emerging application contexts, including bioregenerative life support systems (BLSS) for space agriculture, where microalgae and cyanobacteria can contribute to oxygen production, nutrient recycling, and edible biomass generation. Species such as Chlorella vulgaris, Arthrospira platensis, and Scenedesmus obliquus demonstrate tolerance to microgravity, radiation, and limited light conditions, supporting their potential use in closed, self-sufficient cultivation systems. Although numerous reviews have addressed individual agricultural applications of microalgae and cyanobacteria, a more integrative perspective that connects biological functionality with broader technological, regulatory, and implementation contexts remains valuable. The present review contributes to this perspective by consolidating established agronomic uses and extending the discussion toward selected emerging applications, thereby providing a structured framework for future research and development in sustainable terrestrial and extraterrestrial agriculture. Full article

Multimodal object detection is currently a research hotspot in computer vision. However, the fusion of visible and infrared modalities inevitably increases computational complexity, making most high-performance detection models difficult to deploy on resource-constrained UAV edge devices. Although pruning and knowledge distillation are widely used for model compression, applying them independently often leads to an unstable accuracy–efficiency trade-off. Therefore, this paper proposes a hybrid lightweight algorithm named SAMKD, which combines selective activation pruning with masked knowledge distillation in a staged manner to improve efficiency while maintaining detection performance. Specifically, the selective activation network pruning model (SAPM) first reduces redundant computation by dynamically adjusting network weights and the activation state of input data to generate a lightweight student network. Then, the mask binary classification knowledge distillation (MBKD) strategy is introduced to compensate for this degradation by guiding the student network to recover missing representation patterns under masked feature learning. Moreover, MBKD reformulates classification logits into multiple foreground–background binary mappings, effectively alleviating the severe foreground–background imbalance commonly observed in UAV aerial imagery. This paper constructs a multimodal UAV aerial imagery object detection dataset, M2UD-18K, which includes 9 types of targets and over 18,000 pairs. Extensive experiments show that SAMKD performs well on the self-constructed M2UD-18K dataset, as well as the public DroneVehicle dataset, achieving a favorable trade-off between detection accuracy and detection speed. Full article

Electric energy is an essential resource in modern society; however, most current distribution systems are centralized and dependent on fossil fuels, posing risks of shortages and a potential energy crisis. The transition to renewable sources represents a sustainable alternative, though it introduces challenges associated with intermittency and generation variability. In this context, peer-to-peer (P2P) networks and artificial intelligence (AI) emerge as strategies to promote decentralization, self-management, and efficiency in energy operation. This research proposes an AI-based knowledge discovery model to predict electricity generation and consumption in a P2P network. The study was developed in four phases: exploration of AI techniques for energy prediction; analysis of the most widely used techniques in the Knowledge Discovery in Databases (KDD) process; construction of the predictive model; and validation using real energy generation and consumption data from renewable energy sources. The LSTM–CNN and Transformer models achieved an R² greater than 80% and mean absolute errors (MAE) of less than 0.02 kWh, demonstrating high prediction accuracy. The results confirm that integrating the KDD approach with deep LSTM–CNN and Transformer architectures significantly improves energy management in P2P networks, providing a solid foundation for the development of innovative and sustainable electrical systems. Full article

This paper presents an artificial intelligence (AI)-assisted multi-objective topology optimization of a 48 V interior permanent magnet synchronous motor (PMSM) intended for mid-drive e-bike applications. The machine features a 48-slot, 8-pole stator–rotor combination with $\Delta$-shaped three buried magnets per pole, and is coupled to a multi-stage gearbox that adapts its high-speed, low-torque output to a human-scale crank speed. The design problem simultaneously maximizes average torque and efficiency while minimizing torque ripple by varying key stator slot dimensions and magnet geometries. A modular MATLAB–ANSYS Maxwell framework is developed in which finite element simulations are driven by a Bayesian optimization (BO) loop augmented by a large language model (LLM) with retrieval-augmented generation (RAG). The LLM acts as a memory-based agent that proposes candidates, shapes Gaussian Process priors, and incorporates natural language rules expressing qualitative design knowledge. Two AI-assisted trials are compared against a multi-objective Artificial Hummingbird Algorithm benchmark, RAG + BO with and without natural language input. All three methods converge to a similar Pareto region with average torque around 5.4–5.7 Nm, torque ripple of approximately 12.8–14.2%, and efficiency near 93.3–93.6%, suitable for geared e-bike drives. The LLM-guided trial achieves this performance with a 20.1% reduction in simulation expenses relative to the BO baseline and by about 48% compared to the Artificial Hummingbird Algorithm. The results demonstrate that integrating LLM guidance into Bayesian optimization improves sample efficiency while providing interpretable design trends for PMSM topologies tailored for light electric vehicles. Full article

Laboratories across educational levels have traditionally required in-person attendance, limiting practical activities to specific times and physical spaces. This paper presents a technological architecture based on a system-on-chip (SoC) and a connectivist model, grounded in Connectivism Learning Theory, for implementing a remote laboratory in digital logic design using FPGA devices. The architecture leverages an Internet-of-Things (IoT) environment to provide applications and servers that enable remote access, programming, manipulation, and visualization of FPGA-based development boards located in the institution’s laboratory, from anywhere and at any time. The connectivist model allows learners to interact with multiple nodes for attending synchronous classes, performing laboratory exercises, managing the remote laboratory, and accessing educational resources asynchronously. This approach aims to enhance learning, knowledge transfer, and skills development. A four-year evaluation was conducted, including one experimental group using an e-learning approach and three in-person control groups from a Digital Logic Design course. The experimental group achieved an average performance score of 9.777, surpassing the control groups, suggesting improved academic outcomes with the proposed system. Additionally, a Technology Acceptance Model-based survey showed very high acceptance among learners. This paper presents a novel connectivist model, which we call the Massive Open Online Laboratory. Full article

Background/Objectives: Whole food, plant-based (WFPB) diets have been associated with reduced cardiovascular risk and enhanced overall health. However, nutrition education in medical training remains limited. This study evaluated an experiential WFPB intervention known as the “Plant Plunge.” Methods: A total of 64 medical student participants attended weekly one-hour nutrition seminars on campus led by a local nonprofit, received complimentary WFPB lunches, and were encouraged to eat a WFPB diet for four weeks. Semi-structured interviews explored program perceptions. Pre- and post-intervention assessments measured nutrition knowledge, and a post-program survey assessed attitudes toward the intervention. Results: We analyzed a total of 14 interviews, 25 pre- and post-intervention knowledge assessments, and 49 post-intervention surveys. Qualitative analysis identified seven major themes: (1) improved physical health outcomes; (2) increased awareness of nutrition’s role in medicine; (3) concerns about feasibility and accessibility of WFPB diets; (4) personal empowerment and behavioral change; (5) educational value of seminars; (6) social engagement and peer support; and (7) relevance to future clinical practice. Mean scores on the knowledge assessment significantly improved from 73.3% to 87.0% (p = 0.045) following the Plant Plunge. Survey responses revealed that 65% of participants agreed that they increased knowledge of food ingredients, 54% indicated increased likelihood of selecting plant-based options, and 43% agreed that finding WFPB foods was easy, with 16% disagreeing. Conclusions: The Plant Plunge improved medical students’ nutrition knowledge, dietary attitudes, and perceived readiness for lifestyle counseling while offering an experiential model of nutrition education. Short, experiential nutrition programs may serve as scalable approaches to strengthen nutrition training and support chronic disease prevention. Full article

Megaplatypus mutatus, a major poplar pest in South America, tunnels into the xylem, weakening trunks and reducing wood quality. Volatile organic compounds (VOCs) are key mediators of plant–insect interactions and may reflect genotype-specific defence strategies. This study analysed VOC profiles of young and adult Populus deltoides cv. Harvard and P. × canadensis cv. Conti 12 under natural M. mutatus infestation. Gas chromatography–mass spectrometry putatively annotated 31 VOCs, including green leaf volatiles (GLVs), pentyl leaf volatiles (PLVs), terpenes, alcohols, aromatics and phenolics, 12 of which, to our knowledge, have not been previously reported in Populus VOC profiles. Harvard trees showed ~14.5-fold higher total VOC abundance than Conti trees. In Conti, constitutive VOC emissions remained stable regardless of infestation status or age. In contrast, under infestation, Harvard trees emitted10-fold higher constitutive VOCs than non-infested Harvard trees and ~52-fold higher than Conti, a pattern consistent with increased defensive activity. GLVs and PLVs relatively dominated both genotypes, although Harvard showed higher emissions. Terpenes were not detected in young Conti trees under our analytical conditions but were abundant and diverse in infested Harvard trees, which may indicate a stronger terpene-associated response in this clone. Several compounds were detected only under specific genotype–condition combinations in our dataset and therefore represent candidate volatiles for future behavioural and functional studies. These results are consistent with differences in VOC emission patterns between genotypes and age classes, improve our understanding of putative chemical cues in the interaction between Populus and M. mutatus, and provide a basis for future work towards sustainable pest management strategies. Full article

Power-line presence recognition technology for unmanned aerial vehicles (UAVs) is one of the key research directions in the field of UAV remote sensing. With the rapid development of UAV technology, the application of UAVs in various fields has become increasingly widespread. However, when flying in urban and rural areas, UAVs often face the danger of obstacles such as power lines, posing challenges to flight safety and stability. To address this issue, this study proposes a novel method for presence recognition in UAVs for power lines using an improved GhostNet v2 knowledge distillation dual-attention mechanism convolutional neural network. The construction of a real-time UAV power-line presence recognition system involves three aspects: dataset acquisition, a novel network model, and real-time presence recognition. First, by cleaning, enhancing, and segmenting the power-line data collected by UAVs, a UAV power-line presence recognition image dataset is obtained. Second, through comparative experiments with multi-attention modules, the dual-attention mechanism is selected to construct the CNN, and the UAV real-time power-line presence recognition training is conducted using the SGD optimiser and Hard-Swish activation function. Finally, knowledge distillation is employed to transfer the knowledge from the dual-attention mechanism-based CNN to the nonlinear function and Mamba-enhanced GhostNet v2 network, thereby reducing the model’s parameter count and achieving real-time recognition performance suitable for mobile device deployment. Experiments demonstrate that the UAV-based real-time power-line presence recognition method proposed in this paper achieves real-time recognition accuracy rates of over 91.4% across all regions, providing a technical foundation for advancing the development and progress of UAV-based real-time power-line presence recognition. Full article

Objective: This study characterized Spanish occupational therapists’ knowledge of the national Code of Ethics and perceptions of professional ethics and examined associations with sociodemographic and educational variables. It quantified knowledge of key Code elements (approving body and professional values), described ethics education and participation in formal ethical support structures, and identified resources used to manage ethical conflicts in routine practice. Methods: A descriptive cross-sectional online survey was administered between March and September 2022. The analytical sample included 596 occupational therapists practicing in Spain. The questionnaire assessed participant characteristics, ethics education, knowledge and perceived importance of the Code, participation in ethics committees or similar structures, experience of ethical conflicts, and conflict-management strategies. Descriptive and bivariate analyses were conducted (p < 0.05). Results: Respondents were mostly women (86.6%) and aged 20–40 years. Although 65.3% reported university ethics education and 73.2% rated the Code as important/very important, 11.4% were unaware of its existence. Only 28.2% identified the approving body, and 16.3% correctly identified the professional values included in the Code. Ethical conflicts were reported by 43.1%. When conflicts occurred, respondents most often consulted the interdisciplinary team (25.5%) or occupational therapy colleagues (24.3%), whereas few consulted the Code (4.5%) or an ethics committee (2.7%). Ethics education and greater professional experience were associated with higher Code knowledge. Conclusions: Occupational therapists in Spain endorse professional ethics, yet actionable knowledge and use of the Code and engagement with formal support structures remain limited. Strengthening practice-oriented ethics education and accessible deliberation mechanisms may improve ethical decision-making. Full article