Deep neural networks excel in vision and language but often struggle with tabular data due to weak inductive biases and limited interpretability. While converting tabular data into synthetic images enables Convolutional Neural Networks (CNNs) to exploit spatial feature interactions, this approach typically exacerbates the models’ black-box nature. To achieve both high predictive power and transparent decision-making, we propose an interpretable Hybrid Neural Network that integrates visual reasoning (CNNs applied to synthetic images) with symbolic learning (Kolmogorov-Arnold Networks (KAN) applied to tabular data). Extensive evaluations across diverse datasets demonstrate that our CNN–KAN hybrids achieve highly competitive, and often superior, predictive performance. To audit their internal reasoning, we introduce the Global Feature Score (GFS), a unified metric that aggregates spatial saliency from Grad-CAM with symbolic attributions from the KAN branch, producing consistent feature relevance rankings. By explicitly diagnosing modality dominance, layout artifact sensitivity, and inter-branch agreement, the proposed framework significantly reduces reliance on fragile post-hoc methods. Ultimately, embedding interpretability directly into the architecture provides auditable, cross-verified explanations, establishing a robust foundation for Responsible AI-oriented tabular learning.

In recent years, the development of Natural Language Processing (NLP) text-to-face encoders and Generative Adversarial Networks (GANs) has enabled the synthesis and generation of facial images from textual description. However, most encoders have been developed for the English language. This work presents the first study of three text-to-face encoders, namely, the RoBERTa pre-trained model and the Sent2Vec and RoBERTa models, trained with the CelebA dataset in Spanish. It then introduces customised and fine-tuned conditional Deep Convolutional Generative Adversarial Networks (cDCGANs) trained with the CelebA dataset for text-to-face generation in Spanish. To validate the results obtained, a qualitative evaluation was carried out with a visual analysis and a quantitative evaluation based on the IS, FID and LPIPS metrics. Our findings show promising results with respect to the literature, improving the numerical metrics of FID and LPIPS by 5% and 37%, respectively. Our results also show, through a quantitative–qualitative comparison of the cDCGAN training epochs, that the IS metric is not a reliable objective metric to be considered in the evaluation of similar works.

Knowledge Graphs (KGs) that publish RDF data modelled using ontologies in a wide range of domains have populated the Web. The SHACL language is a W3C recommendation that has been endowed to encode a set of either value or model data restrictions that aim at validating KG data, ensuring data quality. Developing shapes is a complex and time consuming task that is not feasible to achieve manually. This article presents two resources that aim at generating automatically SHACL shapes for a set of ontologies: (1) Astrea-KG, a KG that publishes a set of mappings that encode the equivalent conceptual restrictions among ontology constraint patterns and SHACL constraint patterns, and (2) Astrea, a tool that automatically generates SHACL shapes from a set of ontologies by executing the mappings from the Astrea-KG. These two resources are openly available at Zenodo, GitHub, and a web application. In contrast to other proposals, these resources cover a large number of SHACL restrictions producing both value and model data restrictions, whereas other proposals consider only a limited number of restrictions or focus only on value or model restrictions.

Ontological requirements play a key role in ontology development as they determine the knowledge that needs to be modelled. In addition, the analysis of such requirements can be used (a) to improve ontology testing by easing the automation of requirements into tests; (b) to improve the requirements specification activity; or (c) to ease ontology reuse by facilitating the identification of patterns. However, there is a lack of openly available ontological requirements published together with their associated ontologies, which hinders such analysis. Therefore, in this work we present CORAL (Corpus of Ontological Requirements Annotated with Lexico-syntactic patterns), an openly available corpus of 834 ontological requirements annotated and 29 lexico-syntactic patterns, from which 12 are proposed in this work. CORAL is openly available in three different open formats, namely, HTML, CSV and RDF under “Creative Commons Attribution 4.0 International” license.

Terminologies in the biomedical field are one of the main resources used in the clinical practice. Keeping them up-to-date to meet real-world use cases is a critical operation that even in the case of well maintained terminologies such as SNOMED-CT involves much effort from domain experts. Pharmacological products or drugs are constantly being approved and made available in the market and their clinical information should be also updated in terminologies. Each new drug is provided with its Summary of Product Characteristics (SPC), a document in natural language that contains its essential information.

Knowledge Graphs (KG) are becoming core components of most artificial intelligence applications. Linked Data, as a method of publishing KGs, allows applications to traverse within, and even out of, the graph thanks to global dereferenceable identifiers denoting entities, in the form of IRIs. However, as we show in this work, after analyzing several popular datasets (namely DBpedia, LOD Cache, and Web Data Commons JSON-LD data) many entities are being represented using literal strings where IRIs should be used, diminishing the advantages of using Linked Data. To remedy this, we propose an approach for identifying such strings and replacing them with their corresponding entity IRIs. The proposed approach is based on identifying relations between entities based on both ontological axioms as well as data profiling information and converting strings to entity IRIs based on the types of entities linked by each relation. Our approach showed 98% recall and 76% precision in identifying such strings and 97% precision in converting them to their corresponding IRI in the considered KG. Further, we analyzed how the connectivity of the KG is increased when new relevant links are added to the entities as a result of our method. Our experiments on a subset of the Spanish DBpedia data show that it could add 25% more links to the KG and improve the overall connectivity by 17%.

Semantic Sensor Web infrastructures use ontology-based models to represent the data that they manage; however, up to now, these ontological models do not allow representing all the characteristics of distributed, heterogeneous, and web-accessible sensor data. This paper describes a core ontological model for Semantic Sensor Web infrastructures that covers these characteristics and that has been built with a focus on reusability. This ontological model is composed of different modules that deal, on the one hand, with infrastructure data and, on the other hand, with data from a specific domain, that is, the coastal flood emergency planning domain. The paper also presents a set of guidelines, followed during the ontological model development, to satisfy a common set of requirements related to modelling domain-specific features of interest and properties. In addition, the paper includes the results obtained after an exhaustive evaluation of the developed ontologies along different aspects (i.e., vocabulary, syntax, structure, semantics, representation, and context).

The W3C Semantic Sensor Network Incubator group (the SSN-XG) produced an OWL 2 ontology to describe sensors and observations — the SSN ontology, available at http://purl.oclc.org/NET/ssnx/ssn. The SSN ontology can describe sensors in terms of capabilities, measurement processes, observations and deployments. This article describes the SSN ontology. It further gives an example and describes the use of the ontology in recent research projects.