The Internet of Things generates vast data volumes via diverse sensors, yet its potential remains unexploited for innovative data-driven products and services. Limitations arise from sensor-dependent data handling by manufacturers and user companies, hindering third-party access and comprehension. Initiatives like the European Data Act aim to enable high-quality access to sensor-generated data by regulating accuracy, completeness, and relevance while respecting intellectual property rights. Despite data availability, interoperability challenges impede sensor data reusability. For instance, sensor data shared in HTML formats requires an intricate, time-consuming processing to attain reusable formats like JSON or XML. This study introduces a methodology aimed at converting raw sensor data extracted from web portals into structured formats, thereby enhancing data reusability. The approach utilises large language models to derive structured formats from sensor data initially presented in non-interoperable formats. The effectiveness of these language models was assessed through quantitative and qualitative evaluations in a use case involving meteorological data. In the proposed experiments, GPT-4, the best performing LLM tested, demonstrated the feasibility of this methodology, achieving a precision of 93.51% and a recall of 85.33% in converting HTML to JSON/XML, thus confirming its potential in obtaining reusable sensor data.

The growing significance of sensor data in the development of information technology services finds obstacles due to disparate data presentations and non-adherence to FAIR principles. This paper introduces a novel approach for sensor data gathering and retrieval. The proposal leverages large language models to convert sensor data into FAIR-compliant formats and to provide word embedding representations of tabular data for subsequent exploration, enabling semantic comparison. The proposed system comprises two primary components. The first focuses on gathering data from sensors and converting it into a reusable structured format, while the second component aims to identify the most relevant sensor data to augment a given user-provided dataset. The evaluation of the proposed approach involved comparing the performance of various large language models in generating representative word embeddings for each table to retrieve related sensor data. The results show promising performance in terms of precision and MRR (0.90 and 0.94 for the best-performing model, respectively), indicating the system’s ability to retrieve pertinent sensor data that fulfil user requirements.

DCAT-based data ecosystems, such as open data portals and data spaces, have shown their potential to foster data economy by supporting the FAIR (Findability, Accessibility, Interoperability, Reusability) principles. Nevertheless, there are domains where metadata are tailored to specific semantics of the domain, resulting in the absence of DCAT-based catalogs that adhere to FAIR principles. A particularly relevant case is that of the digital humanities, where texts encoded in TEI (Text Encoding Initiative) constitute a consolidated standard in the field of literature. However, TEI metadata are not always well aligned with the FAIR principles, nor easily integrated into interoperable catalogs that enable seamless combination with external datasets. To address this gap, our approach aims to (i) generate DCAT catalogs derived from TEI by identifying which metadata can be mapped and how, and (ii) explore the use of Large Language Models (LLMs) to assist in the generation and enrichment of metadata when transforming TEI to DCAT. Our approach contributes to catalog-level harmonization, enabling domain-specific standards such as TEI to be aligned with cross-domain standards like DCAT, thus facilitating adherence to FAIR principles.

In this paper, we propose a data-driven decision-support approach for conceptual trail planning and management in protected natural areas, where environmental awareness (particularly climatic comfort and noise levels) is critical to ensuring a sustainable and enjoyable visitor mobility. Our case study is the Natural Park of La Mata and Torrevieja in Spain. The paper begins by identifying climate refuges in this park (areas offering shelter from heat and other adverse conditions based on meteorological data). We extend this with a novel comfort indicator that incorporates ambient noise levels, using acoustic data from sensors. A key challenge is the integration of heterogeneous data sources (climatic data and noise data from the park’s digital twin infrastructure). To demonstrate the potential of this approach for trail planning, we implement an A* pathfinding algorithm to explore comfort-oriented routing alternatives, guided by our combined climate-noise comfort index. The algorithm is applied to trail management in the Natural Park of La Mata and Torrevieja, enabling the identification of indicative high-comfort routes that can inform future trail design and management decisions, while accounting for ecological constraints and visitor well-being. Results show that the proposed comfort-aware routing improves average environmental comfort by 66.3% with only an additional 344 m of walking distance. Finally, this work constitutes a first step toward a data space use case, showcasing interoperable, AI-ready environmental data usage and aligning with the European Green Deal.

Data spaces facilitate sovereignty-preserving data sharing within federated ecosystems; however, dataset discovery is often constrained by catalogs that rely primarily on high-level metadata standards such as DCAT-AP. These models typically lack structural and content-level details, which impedes fine-grained relevance assessment and complicates both internal dataset discovery and the federation of external open data into data spaces. This paper introduces cbmDCAT-AP, a backward-compatible extension of DCAT-AP that integrates content-based metadata as primary catalog elements. The proposed extension augments dataset descriptions with field-level semantics, and representative sample values, thereby enabling content-informed discovery without disclosing entire datasets. Furthermore, a clustering-based reduction technique is proposed to generate representative samples values through the use of word embeddings and K-means clustering. Finally, an end-to-end evaluation across two scenarios (internal dataset discovery and external open data selection) has been conducted to evaluate and validate our proposed extension of DCAT-AP.