Search Results (144)

Active methodologies place the student at the core of the teaching–learning process, with the teacher becoming a companion and guide. Among these methodologies, gamification is demonstrating great capacity to attract students and promote interest, being of particular relevance in STEM subjects. While gamification and Project-Based Learning (PBL) have been extensively studied independently, their integration into Vocational Education and Training (VET) computer science courses remains underexplored, particularly regarding approaches where students develop games themselves rather than merely incorporating game elements or playing serious games. This work presents a novel gamified PBL approach specifically designed for VET Programming education, with three distinctive features: (i) students develop a complete game based on graph theory and Object-Oriented Programming, with each student working under personalised conditions and constraints; (ii) a custom-developed software tool that simultaneously serves as a pedagogical scaffold for students to validate their solutions iteratively and as an automated evaluation platform for teachers; and (iii) empirical validation through action-research with first-year VET students, employing mixed-methods analysis including qualitative observations and descriptive quantitative comparisons. The approach was implemented with first-year Web Application Design students in the Programming subject, where students developed a game integrating graph theory algorithms, Object-Oriented Programming, and Markup Language. Despite the small sample size (10 students), qualitative observations and descriptive analysis indicated promising results, and grade distributions were comparable to those in more accessible subjects. Teacher diary observations, follow-ups, and questionnaires documented sustained engagement, peer collaboration, and strategic problem-solving throughout the project phase. These preliminary findings suggest that gamification through game development, particularly when supported by automated tools enabling personalised conditions and iterative validation, represents a promising approach for teaching and learning Programming in VET contexts. Full article

In order to solve the problem of traditional methods not being able to discover hidden attack trajectories, we propose a cyber attack path prediction approach based on a text-enhanced graph attention mechanism in this paper. Specifically, we design an ontology that captures multi-dimensional links between vulnerabilities, weaknesses, attack patterns, and tactics by integrating CVE, CWE, CAPEC, and ATT&CK into Neo4j. Then, we inject natural language descriptions into the attention mechanism to develop a text-enhanced GAT that can alleviate data sparsity. The experiment shows that compared with existing baselines, our approach improveds MRR and Hits@5 by 12.3% and 13.2%, respectively. Therefore, the proposed approach can accurately predict attack paths and support active cyber defense. Full article

Large Language Model (LLM) agents depend heavily on multiple external tools such as APIs, databases and computational services to perform complex tasks. However, these tool executions create latency and introduce costs, particularly when agents handle similar queries or workflows. Most current caching methods focus on LLM prompt–response pairs or execution plans and overlook redundancies at the tool level. To address this, we designed a multi-level caching architecture that captures redundancy at both the workflow and tool level. The proposed system integrates four key components: (1) hierarchical caching that operates at both the workflow and tool level to capture coarse and fine-grained redundancies; (2) dependency-aware invalidation using graph-based techniques to maintain consistency when write operations affect cached reads across execution contexts; (3) category-specific time-to-live (TTL) policies tailored to different data types, e.g., weather APIs, user location, database queries and filesystem and computational tasks; and (4) session isolation to ensure multi-tenant cache safety through automatic session scoping. We evaluated the system using synthetic data with 2.25 million queries across ten configurations in fifteen runs. In addition, we conducted four targeted evaluations—write intensity robustness from 4 to 30% writes, personalized memory effects under isolated vs. shared cache modes, workflow-level caching comparison and workload sensitivity across five access distributions—on an additional 2.565 million queries, bringing the total experimental scope to 4.815 million executed queries. The architecture achieved 76.5% caching efficiency, reducing query processing time by 13.3× and lowering estimated costs by 73.3% compared to a no-cache baseline. Multi-tenant testing with fifteen concurrent tenants confirmed robust session isolation and 74.1% efficiency under concurrent workloads. Our evaluation used controlled synthetic workloads following Zipfian distributions, which are commonly used in caching research. While absolute hit rates vary by deployment domain, the architectural principles of hierarchical caching, dependency tracking and session isolation remain broadly applicable. Full article

Accurately identifying drug off-targets is essential for reducing toxicity and improving the success rate of pharmaceutical discovery pipelines. However, current deep learning approaches often struggle to fuse chemical structure, protein biology, and multi-target context. Here, we introduce HDPC-LGT (Hybrid Dual-Prompt Cross-Attention Ligand–Protein Graph Transformer), a framework designed to predict ligand binding across sixteen human translation-related proteins clinically associated with antibiotic toxicity. HDPC-LGT combines graph-based chemical reasoning with protein language model embeddings and structural priors to capture biologically meaningful ligand–protein interactions. The model was trained on 216,482 experimentally validated ligand–protein pairs from the Chemical Database of Bioactive Molecules (ChEMBL) and the Protein–Ligand Binding Database (BindingDB) and evaluated using scaffold-level, protein-level, and combined holdout strategies. HDPC-LGT achieves a macro receiver operating characteristic–area under the curve (macro ROC–AUC) of 0.996 and a micro F1-score (micro F1) of 0.989, outperforming Deep Drug–Target Affinity Model (DeepDTA), Graph-based Drug–Target Affinity Model (GraphDTA), Molecule–Protein Interaction Transformer (MolTrans), Cross-Attention Transformer for Drug–Target Interaction (CAT–DTI), and Heterogeneous Graph Transformer for Drug–Target Affinity (HGT–DTA) by 3–7%. External validation using the Papyrus universal bioactivity resource (Papyrus), the Protein Data Bank binding subset (PDBbind), and the benchmark Yamanishi dataset confirms strong generalisation to unseen chemotypes and proteins. HDPC-LGT also provides biologically interpretable outputs: cross-attention maps, Integrated Gradients (IG), and Gradient-weighted Class Activation Mapping (Grad-CAM) highlight catalytic residues in aminoacyl-tRNA synthetases (aaRSs), ribosomal tunnel regions, and pharmacophoric interaction patterns, aligning with known biochemical mechanisms. By integrating multimodal biochemical information with deep learning, HDPC-LGT offers a practical tool for off-target toxicity prediction, structure-based lead optimisation, and polypharmacology research, with potential applications in antibiotic development, safety profiling, and rational compound redesign. Full article

The development of modern vehicles faces an increase in complexity, as well as a need for shorter development cycles and a seamless cross-domain integration. In order to meet these challenges, a graph-based design language which formalizes and automates engineering workflows is presented and applied in a design case study to a Formula Student race car suspension system. The proposed method uses an ontology-based vocabulary definition and executable model transformations to compile design knowledge into a central and consistent design graph. This graph enables the automatic generation of consistent 3D CAD models, domain-specific simulations and suspension kinematic analyses, replacing manual and error-prone tool and data handover processes. The design language captures both the structural and dynamic behavior of the suspension, supports variant exploration and allows for integrated validation, such as 3D collision detection. The study illustrates how graph-based design languages can serve as ‘digital DNA’ for knowledge-based product development, offering a scalable, reusable platform for engineering automation. This approach enhances the digital consistency of data, the digital continuity of processes and the digital interoperability of tools across all relevant engineering disciplines in order to support the validation of early-stage designs and the optimization of complex systems. Full article

Entity alignment (EA) facilitates knowledge fusion by matching semantically identical entities in distinct knowledge graphs (KGs). Existing embedding-based methods rely solely on intrinsic KG facts and often struggle with long-tail entities due to insufficient information. Recently, large language models (LLMs), empowered by rich background knowledge and strong reasoning abilities, have shown promise for EA. However, most current LLM-enhanced approaches follow the in-context learning paradigm, requiring multi-round interactions with carefully designed prompts to perform additional auxiliary operations, which leads to substantial computational overhead. Moreover, they fail to fully exploit the complementary strengths of embedding-based small models and LLMs. To address these limitations, we propose HIEA, a novel hierarchical inference framework for entity alignment. By instruction-tuning a generative LLM with a unified and concise prompt and a knowledge adapter, HIEA produces alignment results with a single LLM invocation. Meanwhile, embedding-based small models not only generate candidate entities but also support the LLM through data augmentation and certainty-aware source entity classification, fostering deeper collaboration between small models and LLMs. Extensive experiments on both standard and highly heterogeneous benchmarks demonstrate that HIEA consistently outperforms existing embedding-based and LLM-enhanced methods, achieving absolute Hits@1 improvements of up to 5.6%, while significantly reducing inference cost. Full article

This study introduces a multi-mechanism entity–relation extraction model designed to address persistent challenges in natural language processing, including syntactic complexity, long-range dependency modeling, and suboptimal utilization of contextual information. The proposed architecture integrates several complementary components. First, a pre-trained Chinese-RoBERTa-wwm-ext encoder with a whole-word masking strategy is employed to preserve lexical semantics and enhance contextual representations for multi-character Chinese text. Second, BiLSTM-based sequential modeling is incorporated to capture bidirectional contextual dependencies, facilitating the identification of distant entity relations. Third, the combination of multi-head attention and gated attention mechanisms enables the model to selectively emphasize salient semantic cues while suppressing irrelevant information. To further improve global prediction consistency, a Conditional Random Field (CRF) layer is applied at the output stage. Building upon this multi-mechanism framework, an adaptive dynamic network is introduced to enable input-dependent activation of feature modeling modules based on sentence-level semantic complexity. Rather than enforcing a fixed computation pipeline, the proposed mechanism supports flexible and context-aware feature interaction, allowing the model to better accommodate heterogeneous sentence structures. Experimental results on benchmark datasets demonstrate that the proposed approach achieves strong extraction performance and improved robustness, making it a flexible solution for downstream applications such as knowledge graph construction and semantic information retrieval. Full article

Wind power forecasting is critical to renewable energy generation, as accurate predictions are essential for the efficient and reliable operation of power systems. However, wind power output is inherently unstable and is strongly affected by meteorological factors such as wind speed, wind direction, and atmospheric pressure. Weather conditions and wind power data are recorded by sensors installed in wind turbines, which may be damaged or malfunction during extreme or sudden weather events. Such failures can lead to inaccurate, incomplete, or missing data, thereby degrading data quality and, consequently, forecasting performance. To address these challenges, we propose a method that integrates a pre-trained large-scale language model (LLM) with the spatiotemporal characteristics of wind power networks, aiming to capture both meteorological variability and the complexity of wind farm terrain. Specifically, we design a spatiotemporal graph neural network based on multi-view maps as an encoder. The resulting embedded spatiotemporal map sequences are aligned with textual representations, concatenated with prompt embeddings, and then fed into a frozen LLM to predict future wind turbine power generation sequences. In addition, to mitigate anomalies and missing values caused by sensor malfunctions, we introduce a novel frequency-domain learning-based interpolation method that enhances data correlations and effectively reconstructs missing observations. Experiments conducted on real-world wind power datasets demonstrate that the proposed approach outperforms state-of-the-art methods, achieving root mean square errors of 17.776 kW and 50.029 kW for 24-h and 48-h forecasts, respectively. These results indicate substantial improvements in both accuracy and robustness, highlighting the strong practical potential of the proposed method for wind power forecasting in the renewable energy industry. Full article

This interdisciplinary pilot study examines the use of Natural Language Processing (NLP) techniques, specifically Large Language Models (LLMs) with Prompt Engineering (PE), to analyze economic vulnerability from qualitative self-narratives. Seventy narratives from twenty-five women in the Palk Bay coastal region of Rameshwaram, India were analyzed using a schema adapted from a contextual empowerment framework. The study operationalizes theoretical constructs into structured Information Extraction (IE) templates, enabling systematic identification of multiple vulnerability aspects, contributing factors, and experiential expressions. Prompt templates were iteratively refined and validated through dual-annotator review, achieving an F1-score of 0.78 on a held-out subset. Extracted elements were examined through downstream analysis, including pattern grouping and graph-based visualization, to reveal co-occurrence structures and recurring vulnerability configurations across narratives. The findings demonstrate that LLMs, when aligned with domain-specific conceptual models and supported by human-in-the-loop validation, can enable interpretable and replicable analysis of self-narratives. While findings are bounded by the pilot scale and community-specific context, the approach supports translation of narrative evidence into community-level program design and targeted grassroots outreach, with planned expansion to multi-site, multilingual datasets for broader applicability. Full article

To address the limitations of Retrieval-Augmented Generation (RAG) systems in handling long policy documents, mitigating information dilution, and reducing hallucinations in engineering-oriented applications, this paper proposes SPR-RAG, a retrieval-augmented framework designed for knowledge-intensive vertical domains such as electric power policy analysis. With practicality and interpretability as core design goals, SPR-RAG introduces a Semantic Parsing Retriever (SPR), which integrates community detection–based entity disambiguation and transforms natural language queries into logical forms for structured querying over a domain knowledge graph, thereby retrieving verifiable triple-based evidence. To further resolve retrieval bias arising from diverse policy writing styles and inconsistencies between user queries and policy text expressions, a question-repository–based indirect retrieval mechanism is developed. By generating and matching latent questions, this module enables more robust retrieval of non-structured contextual evidence. The system then fuses structured and unstructured evidence into a unified dual-source context, providing the generator with an interpretable and reliable grounding signal. Experiments conducted on real electric power policy corpora demonstrate that SPR-RAG achieves 90.01% faithfulness—representing a 5.26% improvement over traditional RAG—and 76.77% context relevance, with a 5.96% gain. These results show that SPR-RAG effectively mitigates hallucinations caused by ambiguous entity names, textual redundancy, and irrelevant retrieved content, thereby improving the verifiability and factual grounding of generated answers. Overall, SPR-RAG demonstrates strong deployability and cross-domain transfer potential through its “Text → Knowledge Graph → RAG” engineering paradigm. The framework provides a practical and generalizable technical blueprint for building high-trust, industry-grade question–answering systems, offering substantial engineering value and real-world applicability. Full article

Antimicrobial resistance (AMR) has become a major health crisis worldwide, and it is expected to surpass cancer as one of the leading causes of death by 2050. Conventional antibiotics are struggling to keep pace with the rapidly evolving resistance trends, underscoring the urgent need for novel antimicrobial therapeutic strategies. Antimicrobial peptides (AMPs) function through diverse, often membrane-disrupting mechanisms that can address the latest challenges to resistance. However, the identification, prediction, and optimization of novel AMPs can be impeded by several issues, including extensive sequence spaces, context-dependent activity, and the higher costs associated with wet laboratory screenings. Recent developments in artificial intelligence (AI) have enabled large-scale mining of genomes, metagenomes, and quantitative species-resolved activity prediction, i.e., MIC, and de novo AMPs designed with integrated stability and toxicity filters. The current review has synthesized and highlighted progress across different discriminative models, such as classical machine learning and deep learning models and transformer embeddings, alongside graphs and geometric encoders, structure-guided and multi-modal hybrid learning approaches, closed-loop generative methods, and large language models (LLMs) predicted frameworks. This review compares models’ benchmark performances, highlighting AI-predicted novel hybrid approaches for designing AMPs, validated by in vitro and in vivo methods against clinical and resistant pathogens to increase overall experimental hit rates. Based on observations, multimodal paradigm strategies are proposed, focusing on identification, prediction, and characterization, followed by design frameworks, linking active-learning lab cycles, mechanistic interpretability, curated data resources, and uncertainty estimation. Therefore, for reproducible benchmarks and interoperable data, collaborative computational and wet lab experimental validations must be required to accelerate AI-driven novel AMP discovery to combat multidrug-resistant Gram-negative pathogens. Full article

Construction sites are complex environments where traditional safety monitoring methods often suffer from low detection accuracy and limited interpretability. To address these challenges, this study proposes a modular multimodal agent framework that integrates computer vision, knowledge representation, and large language model (LLM)–based reasoning. First, the CLIP model fine-tuned with Low-Rank Adaptation (LoRA) is combined with YOLOv10 to achieve precise recognition of construction activities and personal protective equipment (PPE). Second, a construction safety knowledge graph integrating Retrieval-Augmented Generation (RAG) is constructed to provide structured domain knowledge and enhance contextual understanding. Third, the FusedChain prompting strategy is designed to guide large language models (LLMs) to perform step-by-step safety risk reasoning. Experimental results show that the proposed approach achieves 97.35% accuracy in activity recognition, an average F1-score of 0.84 in PPE detection, and significantly higher performance than existing methods in hazard reasoning. The modular design also facilitates scalable integration with more advanced foundation models, indicating strong potential for real-world deployment in intelligent construction safety management. Full article

As Large Language Models (LLMs) are core components in Retrieval-Augmented Generation (RAG) systems for knowledge-intensive tasks, concerns regarding hallucinations, redundancy, and unverifiable outputs have intensified, particularly in high-stakes domains, such as e-government. This study proposes a modular, multi-pipeline framework for statement-level faithfulness evaluation for characterizing hallucination and redundancy across both simple and agentic RAG pipelines. Using GPT-4.1, Claude Sonnet-4.0, and Gemini 2.5 Pro as LLM-based judges, this study examines how tool-specific attribution within agentic multi-tool architectures influences the interpretability and traceability of the generated content. By using a modular agentic RAG framework combining symbolic (GraphRAG), semantic (embedding), and real-time (web) retrieval, we benchmark hallucination and redundancy patterns, using state-of-the-art LLM judges. The study examines RAG and agent-based pipelines that attribute outputs to distinct tools, in contrast to traditional single-source RAG systems that rely on aggregated retrieval. Using e-government data sourced from the European Commission’s Press Corner, our evaluation framework assesses not only the frequency, but also the source-aware detectability of hallucinated content. The findings provide actionable insights into how source granularity and retrieval orchestration impact faithfulness evaluation across different pipeline architectures, while also suggesting new directions for explainability-aware RAG design. The study contributes a reproducible, modular framework for automated faithfulness assessment, with implications for transparency, governance compliance, and trustworthy AI deployment. Full article

Large Language Models (LLMs) are increasingly used for rubric-based assessment, yet reliability is limited by instability, bias, and weak diagnostics. We present EvalCouncil, a committee-and-chief framework for rubric-guided grading with auditable traces and a human adjudication baseline. Our objectives are to (i) characterize domain structure in Human–LLM alignment, (ii) assess robustness to concordance tolerance and panel composition, and (iii) derive a domain-adaptive audit policy grounded in dispersion and chief–panel differences. Authentic student responses from two domains–Computer Networks (CNs) and Machine Learning (ML)–are graded by multiple heterogeneous LLM evaluators using identical rubric prompts. A designated chief arbitrator operates within a tolerance band and issues the final grade. We quantify within-panel dispersion via MPAD (mean pairwise absolute deviation), measure chief–panel concordance (e.g., absolute error and bias), and compute Human–LLM deviation. Robustness is examined by sweeping the tolerance and performing leave-one-out perturbations of panel composition. All outputs and reasoning traces are stored in a graph database for full provenance. Human–LLM alignment exhibits systematic domain dependence: ML shows tighter central tendency and shorter upper tails, whereas CN displays broader dispersion with heavier upper tails and larger extreme spreads. Disagreement increases with item difficulty as captured by MPAD, concentrating misalignment on a relatively small subset of items. These patterns are stable to tolerance variation and single-grader removals. The signals support a practical triage policy: accept low-dispersion, small-gap items; apply a brief check to borderline cases; and adjudicate high-dispersion or large-gap items with targeted rubric clarification. EvalCouncil instantiates a committee-and-chief, rubric-guided grading workflow with committee arbitration, a human adjudication baseline, and graph-based auditability in a real classroom deployment. By linking domain-aware dispersion (MPAD), a policy tolerance dial, and chief–panel discrepancy, the study shows how these elements can be combined into a replicable, auditable, and capacity-aware approach for organizing LLM-assisted grading and identifying instability and systematic misalignment, while maintaining pedagogical interpretability. Full article

Virtual assistants in academic environments often lack comprehensive multimodal integration and specialized role-based architecture. This paper presents NAIA (Nimble Artificial Intelligence Assistant), a robust artificial intelligence framework designed for multi-role virtual academic assistance through a modular monolithic approach. The system integrates Large Language Models (LLMs), Computer Vision, voice processing, and animated digital avatars within five specialized roles: researcher, receptionist, personal skills trainer, personal assistant, and university guide. NAIA’s architecture implements simultaneous voice, vision, and text processing through a three-model LLM system for optimized response quality, Redis-based conversation state management for context-aware interactions, and strategic third-party service integration with OpenAI, Backblaze B2, and SerpAPI. The framework seamlessly connects with the institutional ecosystem through Microsoft Graph API integration, while the frontend delivers immersive experiences via 3D avatar rendering using Ready Player Me and Mixamo. System effectiveness is evaluated through a comprehensive mixed-methods approach involving 30 participants from Universidad del Norte, employing Technology Acceptance Model (TAM2/TAM3) constructs and System Usability Scale (SUS) assessments. Results demonstrate strong user acceptance: 93.3% consider NAIA useful overall, 93.3% find it easy to use and learn, 100% intend to continue using and recommend it, and 90% report confident independent operation. Qualitative analysis reveals high satisfaction with role specialization, intuitive interface design, and institutional integration. The comparative analysis positions NAIA’s distinctive contributions through its synthesis of institutional knowledge integration with enhanced multimodal capabilities and specialized role architecture, establishing a comprehensive framework for intelligent human-AI interaction in modern educational environments. Full article