This paper presents a web-based platform designed to support dialogical learning through a Retrieval-Augmented Generation (RAG) architecture. The system integrates retrieval grounding, context-aware dialogue management, and a modular, model-agnostic design to enable controlled and pedagogically aligned learning supported by Artificial Intelligence (AI) and based on instructor-verified educational materials. The proposed approach supports multilingual interaction, including operation in lower-resource languages such as Bulgarian, and models learning as a continuous dialogue rather than a sequence of isolated queries. To ensure reliable knowledge access, the system employs a hybrid retrieval strategy combining semantic embeddings with lexical matching within a two-stage indexing and retrieval framework. The approach is supported by an empirical evaluation based on a manually constructed question set with human-validated relevance assessment. The results demonstrate that the selected configuration achieves 90% retrieval accuracy at TOP-5 and up to 91.4% at TOP-6, providing a reliable contextual basis for response generation. A complementary manual evaluation of generated responses further indicated strong practical usefulness and generally grounded answer quality. The platform is further designed in alignment with European regulatory principles, emphasizing transparency, traceability, and controlled use of AI in educational environments. Overall, the study demonstrates that integrating retrieval precision with pedagogical structure enables the development of AI systems that support structured and contextually grounded learning processes.

Large language models (LLMs) face difficulties in leveraging the syntactic structures and entity relations embedded in text for long-document information extraction. To address this issue, this paper proposes a generative extraction method integrating heterogeneous topology awareness and spatial alignment. The method first extracts syntactic and coreference information to construct a heterogeneous document graph and employs a mixture-of-experts network to decouple and encode multi-type topological features. A component orthogonal projection mechanism and a graph-text contrastive learning strategy are then utilized to align the extracted graph features to the underlying semantic space of the language model with high fidelity. Furthermore, Topology-Aware Encoder compresses the global features into fixed-length structural prompts to guide text generation. Experiments on the ACE2005, WikiEvents, and DuEE datasets demonstrated that the proposed method achieved state-of-the-art performance on information extraction tasks. Consequently, these results suggest that the proposed framework is a promising approach for complex information extraction across base LLMs of different scales.

Extracting causal relations from complex dynamic systems has become an appealing topic for decades, especially for machine design engineering, industrial manufacturing, and equipment maintenance, which usually suffer from a large number of tangled relationships. Although many causality detection methods have been utilized, evaluating and choosing appropriate methods, and developing proper workflow remain challenges. In this paper, a causal analysis workflow designed to detect hidden patterns involved with mechanical mechanisms is presented. In particular, various causality measures are ensembled, enabling the search for refined causal mechanisms, the impact of constitutive law, and spatial distribution of causality from the entangled raw network. Based on numerical experiments, several beneficial conclusions can be drawn: Separating typical stages is necessary for a complex process; The constitutive property has a great impact on causal inference; The discrepancy of causality among different locations of monitor points mainly depends on whether it is near the fixed boundary, near to the load, or in contact with friction; Granger Causality is suitable for discovering linear dependencies among material, load, and geometry, while constraint-based and score-based algorithms excel in identifying nonlinear causality in metal plasticity, severe discontinuity in contact, impulsive dynamic load, or damping phenomenon.

Global decarbonization and the rapid growth of distributed energy resources increase the need for information-centric mechanisms that can support secure, scalable, cross-border coordination under heterogeneous technical and regulatory conditions. This paper proposes a Global Virtual Prosumer (GVP) framework that integrates IoT sensing, multi-agent coordination, and permissioned blockchain smart contracts to operationalize cross-border energy services as auditable service commitments rather than physical power exchange. Building on prior work that validated MAS-based power management and blockchain-secured operation within individual Virtual Prosumers, the present contribution lies in the cross-border coordination layer and its associated contractual and evaluation mechanisms, not in the constituent technologies themselves. A layered IoT–AI–blockchain architecture is introduced, where off-chain optimization produces allocations and admissibility indicators and on-chain contracts enforce identity, feasibility guards, delegation and partner-assignment rules, oracle verification, and settlement time compliance outcomes. The contractual lifecycle is formalized through four smart-contract algorithms covering trade registration, conditional delegation, cooperative fulfillment, and cross-border settlement with explicit failure semantics and event-based audit trails. The framework is evaluated on a global case study with seven Virtual Prosumers and quantified using contract-centric KPIs that capture registration time rejections, settlement success versus non-compliance, oracle-driven failure attribution, and full lifecycle traceability. The results demonstrate internal consistency of the proposed lifecycle and the practical value of KPI-driven accountability for cross-border energy service coordination. At the same time, the evaluation is based on synthetic parameterization and an emulated contract environment; realistic deployment constraints—including consensus latency, cross-region communication reliability, and regulatory overlap—are discussed as explicit limitations and directions for future empirical validation.

Adaptive reuse of industrial heritage from a tourism perspective presents a complex design challenge requiring a balance between heritage preservation, functional innovation, and diverse stakeholder expectations. However, current practices often face issues such as ambiguous demand interpretation and a disconnect between design generation and systematic evaluation. Addressing these limitations, this paper proposes and illustrates a human–machine collaborative design paradigm that integrates generative AI into a closed-loop process of “demand analysis–intelligent generation–comprehensive evaluation.” The method first employs Kansei Engineering and the KANO model to qualitatively extract and quantitatively prioritise heterogeneous user needs, translating subjective perceptions into structured design constraints and optimisation objectives. Next, these needs are encoded as text prompts to drive targeted spatial exploration by the generative AI tool Nano Banana AI. Finally, the TOPSIS method is applied for multi-criteria performance evaluation and solution selection. A case study of Shanghai Libo Brewery suggests that this paradigm can enhance design efficiency and show potential to outperform traditional methods across dimensions such as historical preservation, public accessibility, ecological integration, social inclusivity, and formal innovation. The research offers a quantifiable and systematically documented intelligent design methodology for industrial heritage renewal, while acknowledging the exploratory nature of the generative phase. Furthermore, it provides a visitor-demand-driven innovation pathway for developing industrial heritage tourism destinations, thereby potentially enhancing cultural experiences and tourism appeal at heritage sites. This research illustrates a move from an experience-driven paradigm toward a data- and value-driven approach, contributing theoretical methodologies to the intersection of cultural tourism and artificial intelligence.

Advances in Generative Artificial Intelligence have enabled the development of models capable of generating text, images, and audio that are similar to what humans can create. These models often have valuable general knowledge thanks to their training on large datasets. Through fine-tuning or prompt-based adaptation, this knowledge can be applied to specific tasks. In this work, we propose a modular approach to automated news generation using Large Language Models, composed of an information retrieval module and a text generation module. The proposed system leverages both publicly available (open-weight) and proprietary Large Language Models, enabling a comparative evaluation of their behavior within the proposed news generation pipeline. We describe the experiments carried out with a total of five representative Large Language Models spanning both categories, detailing their configurations and performance. The results demonstrate the feasibility of using Large Language Models to automate this task and identify systematic differences in behavior across model categories, as well as the problems that remain to be solved to enable fully autonomous news generation.

The traditional craft of Buddha statue carving represents an important form of cultural heritage in many Asian societies, yet the transmission of this knowledge is increasingly threatened by modernization and the declining number of skilled artisans. This study explores the use of Virtual Reality (VR) as an innovative tool for preserving and teaching the cultural knowledge associated with Salah Lanna stone Buddha carving. A VR-based learning environment was developed to simulate traditional carving techniques, tools, and cultural narratives related to Lanna Buddhist art. The system was designed using Unity 3D and integrated hand-tracking interaction to enable immersive practice of carving procedures. The prototype was evaluated through expert review involving ten specialists in Buddha carving, art education, and VR technology. The evaluation assessed five dimensions: usability, authenticity, cultural relevance, immersion, and perceived learning potential. Results indicate high levels of expert evaluation results regarding the effectiveness of the system, with average scores of 4.6 for usability, 4.8 for authenticity, 4.7 for cultural relevance, 4.5 for immersion, and 4.9 for perceived learning potential on a five-point scale. The findings suggest that VR technology can provide a promising platform for preserving traditional craftsmanship and supporting immersive cultural learning. By integrating technical training with cultural narratives, the system demonstrates potential for enhancing access to traditional craft education while contributing to the digital preservation of Salah Lanna cultural heritage.

This study examines the relationship between digitalisation and eco-innovation across countries, with a particular focus on the role of digital government and digital standardisation. Using cross-country data for 2022, eco-innovation is proxied by environment-related patenting activity, while digitalisation is measured using the United Nations E-Government Development Index (EGDI). Employing a combination of ordinary least squares, population-weighted regressions, spline specifications, and quantile regressions, we document three main findings. First, digitalisation is positively and robustly associated with eco-innovation across countries. Second, the relationship is non-linear, with marginal effects that strengthen at higher levels of digital development, suggesting important complementarities between digital capabilities and national innovation systems. Third, the association between digitalisation and eco-innovation is heterogeneous across the distribution of eco-innovation, with particularly strong associations observed among countries with intermediate levels of innovative activity. Taken together, these findings suggest that digitalisation is systematically associated with eco-innovation across countries and indicate the potential relevance of digital governance and digital standardisation to sustainable technological change.

Scarcity of healthcare resources requires prioritisation decisions that raise complex ethical, economic, and social challenges. While normative frameworks provide guidance on how such decisions ought to be made, growing evidence suggests that individuals differ substantially in how they approach morally charged allocation choices. This study investigates heterogeneity in decision-making styles and support for healthcare prioritisation criteria using an interdisciplinary approach that integrates health economics, social psychology, and computational methods to identify latent decision-making profiles among a sample of adults residing in Portugal. Data were collected from adults residing in Portugal using a structured online questionnaire comprising socio-demographic characteristics, decision-making styles, and preferences elicited through twenty hypothetical healthcare rationing scenarios. The results reveal three meaningful decision-making profiles characterised by different combinations of cognitive styles and ethical prioritisation patterns: analytically oriented decision-makers prioritising health gains; intuitive, context-sensitive decision-makers balancing clinical and social criteria; heuristic-driven decision-makers relying on simpler or less differentiated heuristics. These findings demonstrate that, within this sample, healthcare prioritisation preferences are shaped by systematic variations in decision style rather than a single moral or rational framework. By linking behavioural heterogeneity with ethical decision-making, this study contributes to theoretical debates on healthcare rationing and demonstrates the value of clustering techniques for uncovering latent structures in complex decision data. The results provide insights relevant for the design of decision-support systems and rationing policies, which may be adapted to accommodate heterogeneous decision styles in comparable settings.

Digital Twins (DTs) are increasingly recognized as a strategic technology for enhancing cybersecurity in industrial environments, particularly in the face of rising threats targeting Operational Technology (OT). After comparatively examining closely related DT–cybersecurity frameworks to position the contribution within the existing research landscape, this paper presents a systematic literature review and comparative analysis of 19 recent DT-based cybersecurity studies, focusing on their relevance to incident detection and response in sectors such as Industrial Internet of Things (IIoT), manufacturing, and energy. The analysis evaluates each study across multiple dimensions, including attack types, detection and response mechanisms, DT integration, and technology stacks. From this review, we derive a consolidated set of requirements, categorized as functional, non-functional, security-specific, and domain-specific. These requirements serve as the foundation for a novel, cybersecurity-focused, ISO 23247-based framework. The proposed architecture formalizes a DT-enabled incident detection and response lifecycle aligned with ISO 23247. It is explicitly mapped to the derived requirements and detailed with practical implementation considerations. This work contributes a structured, evidence-based approach to DT-based security engineering and offers a reference design for researchers and practitioners aiming to build resilient, adaptive cybersecurity solutions in industrial settings.