Open Science is based on a collaborative network to develop transparent, accessible, and shared knowledge. Open Research Data Platforms (ORDPs) are deployed to fulfill the needs for data sharing of a specific community and/or scientific discipline. The high variety of research areas creates a barrier to data sharing between research entities. To enable this research data to be found by the research entities that need it, it is necessary to establish access to different ORDPs that are unknown to these research entities. The goal of this article is to provide a quantitative analysis showing the current limitations of data sharing between ORDPs in Open Science. We then propose a solution to improve data access and sharing based on theoretical foundations and an experimental approach. We propose to extend our theoretical interoperability model, which helps us to define the necessary steps to interoperate ORDPs. We present and discuss a quantitative evaluation of ORDPs’ interoperability. Based on this exploratory study, we propose a solution that enables research entities to discover unknown ORDPs, thereby facilitating access to relevant data. This solution is the Open Science Data Network (OSDN), a decentralized, distributed, and federated network of ORDPs that integrates a query propagation process and robustness features. To enable the deployment of OSDN at an Open Science scale, we designed our solution by considering its adoption cost relative to a non-organized interoperability approach. With two ORDPs integrated into the OSDN, the adoption cost is estimated to be reduced by at least 17%. This reduction approaches 100% as the number of integrated ORDPs increases. To demonstrate the feasibility of the solution, we developed a Proof of Concept (POC) and applied it to two research projects from different domains and involving distinct research communities. For the first research project, we measured a 7% increase in the volume of accessed data and an 80% reduction in the time needed to find this data. In addition, researcher from this experiment was able to formulate new intra- and interdisciplinary research questions thanks to the newly accessed data. In the second research project, we observed an increase in data volume of up to a factor of 3968. More importantly, this process led to the discovery of new essential data that was previously missing.

Federated Learning (FL) is a decentralized paradigm that enables a client-server architecture to collaboratively train a global Artificial Intelligence model without sharing raw data, thereby preserving privacy. A key challenge in FL is Non-IID data. Quantity Skew (QS) is a particular problem of Non-IID, where clients hold highly heterogeneous data volumes. Clustered Federated Learning (CFL) is an emergent variant of FL that presents a promising solution to Non-IID problem. It improves models' performance by grouping clients with similar data distributions into clusters. CFL methods generally fall into two operating strategies. In the first strategy, clients select the cluster that minimizes the local training loss. In the second strategy, the server groups clients based on local model similarities. However, most CFL methods lack systematic evaluation under QS but present significant challenges because of it.

Attention Deficit Hyperactivity Disorder is a neurodevelopmental disorder whose manifestations vary significantly depending on the context. This situational variability poses major challenges for assessing and understanding symptoms, particularly outside clinical environments. In this work, we propose a framework that integrates a contextual vision to enrich medical information. The framework is composed of three main components: a modular ontology that formalizes both medical and contextual dimensions of ADHD; a multi-agent system powered by large language models for automatically extracting and populating knowledge from heterogeneous data sources; and a clinical rule-based reasoning mechanism capable of inferring high-level interpretations from instantiated data. Experimental results demonstrate the framework’s ability to generate accurate, context-sensitive interpretations of symptom manifestations. This approach lays the groundwork for more personalized, explainable, and context-aware patient monitoring, with promising applications in intelligent healthcare systems.

Data lakes are supposed to enable analysts to perform more efficient and efficacious data analysis by crossing multiple existing data sources, processes and analyses. However, it is impossible to achieve that when a data lake does not have a metadata governance system that progressively capitalizes on all the performed analysis experiments. The objective of this paper is to have an easily accessible, reusable data lake that capitalizes on all user experiences. To meet this need, we propose an analysis-oriented metadata model for data lakes. This model includes the descriptive information of datasets and their attributes, as well as all metadata related to the machine learning analyzes performed on these datasets. To illustrate our metadata solution, we implemented a web application of data lake metadata management. This application allows users to find and use existing data, processes and analyses by searching relevant metadata stored in a NoSQL data store within the data lake. To demonstrate how to easily discover metadata with the application, we present two use cases, with real data, including datasets similarity detection and machine learning guidance.

Data lakes are supposed to enable analysts to perform more efficient and efficacious data analysis by crossing multiple existing data sources, processes and analyses. However, it is impossible to achieve that when a data lake does not have a metadata governance system that progressively capitalizes on all the performed analysis experiments. The objective of this paper is to have an easily accessible, reusable data lake that capitalizes on all user experiences. To meet this need, we propose an analysis-oriented metadata model for data lakes. This model includes the descriptive information of datasets and their attributes, as well as all metadata related to the machine learning analyzes performed on these datasets. To illustrate our metadata solution, we implemented an application of data lake metadata management. This application allows users to find and use existing data, processes and analyses by searching relevant metadata stored in a NoSQL data store within the data lake. To demonstrate how to easily discover metadata with the application, we present two use cases, with real data, including datasets similarity detection and machine learning guidance.

The identification of alignments between heterogeneous ontologies is one of the main research issues in the semantic web.The manual matching of the ontologies is a complex, time consuming and an error prone task.Therefore, ontology matching systems aims to automate this process.Usually, these systems perform the matching process by combining element and structural level matchers.Selecting the optimal string similarity measure associated with its threshold is an important issue in order to enhance the effectiveness of the element level matcher, which in turn will improve the whole ontology system results.In this paper, we present POMap, an ontology matching system based on a syntactic study covering element and structural levels.For the element level matcher we have adopted the best configuration based on the analysis of the performances of many string similarity measures associated with their thresholds.For the structural level, we have performed a syntactic study on both subclasses and siblings in order to infer the structural similarity.Our proposed matching system is validated and evaluated on the Anatomy, the Conference and the Large Biomedical tracks provided by the benchmark of OAEI 2016 ontology matching campaign.

Data warehouses use a multidimensional model. Based on this model, OLAP cubes enable users to analyze data. For correct OLAP analysis, multidimensional models should be checked. In particular, these models should ensure summarizability. Checking multidimensional models and their summarizability is complex and error-prone. To perform this task, formal reasoning is appropriate. In this paper, we propose and illustrate an approach to represent a multidimensional model as an OWL-DL ontology, and reason on this ontology to check the multidimensional model and its summarizability. Beyond the reasoning capabilities of description logic, representing multidimensional models as OWL-DL ontologies is a means to move multidimensional modeling to the semantic Web. To illustrate this, we investigate the complementarities between our approach and the RDF Data Cube vocabulary, and suggest how they could be combined.