Associative classification models are valuable for discovering relationships within heterogeneous data systems, making them particularly useful for data integration tasks. However, they struggle with imbalanced and sparse data. This paper addresses the problem of imbalanced classification in building maintenance data by providing several updates ba...
Nuclear projects often produce and consume a large amount of knowledge. Capitalization on this knowledge constitutes a significant way to increase efficiency on subsequent projects for any stakeholder. In this study, modelling is used as a main approach to support this capitalization. It constitutes, through graphical layout, a more reliable and ro...
In this milestone, we propose a FAIR by design methodology for developing ontologies that could be extended to address other types of semantic artefacts. That is, the work developed for and reported in this milestone focuses on semantic artefacts (mostly vocabularies and ontologies) formalised in the RDF(S) and OWL representation languages mainly.
In this paper, we challenge the vision of creating a giant knowledge graph of reusable research data from multiple projects and platforms, based on Semantic Web technologies and a shared conceptualisation in the form of a commonly used ontology ecosystem, promoted by the Semantic Data for Humanities and Social Sciences project (SDHSS). Three main i...
We introduce DomainKnowledge, a system that leverages a pipeline for triple extraction from natural text and domain-specific ontologies leading to knowledge graph construction. We also address the challenge of aligning text-extracted and ontology-based knowledge graphs using the biomedical domain as use case. Finally, we derive graph metrics to eva...
In this position paper, we argue that ontologies, combined with Model-Driven Engineering (MDE) approach and the object-oriented approach, could be leveraged to produce model-driven Digital Twins. This paper presents our framework for the production of model-driven Digital Twins using the aforementioned approach. Despite the interest in existing fra...
To develop effective public health management strategies, it is necessary to account for the viewpoints of all stakeholders. Thus, anthropological approaches can potentially inform strategies for preventing and managing zoonotic diseases. Here, we use Q fever as a starting point for exploring how small ruminant farmers perceive the reality of micro...
Conducting experimental analysis on rule reasoners is a mainstream task for validating novel algorithms and systems. Nevertheless, providing robust, veriable, and reproducible experiments can still raise a sensible challenge. We propose to demonstrate B-Runner, an open library for collaborative benchmarking focusing on the deployment of articulate ...
Published in BMC bioinformatics
Traditional gene set enrichment analyses are typically limited to a few ontologies and do not account for the interdependence of gene sets or terms, resulting in overcorrected p-values. To address these challenges, we introduce mulea, an R package offering comprehensive overrepresentation and functional enrichment analysis. mulea employs a progress...
BackgroundOntologies are fundamental components of informatics infrastructure in domains such as biomedical, environmental, and food sciences, representing consensus knowledge in an accurate and computable form. However, their construction and maintenance demand substantial resources and necessitate substantial collaboration between domain experts,...
