Welcome to my research space, where I bridge the gap between fragmented data and meaningful AI by ethically distilling the world’s digital chaos into responsible knowledge that empowers more intuitive, human-centered intelligent systems.

---

My work explores a fundamental question:

How can knowledge be formalised, understood, and transformed into intelligent systems that remain aligned with human reasoning and values?

A Research Vision: NOESIS

My research is structured around the concept of NOESIS, understood as the act of intellectual understanding through which intelligence apprehends truth.

NOESIS is both a philosophical foundation and a scientific framework. It articulates six complementary principles that describe the emergence of knowledge:

At the center of these principles lies empathy, ensuring that knowledge remains human-oriented, interpretable, and meaningful.

This vision can be expressed as a progression:

Knowledge → Understanding → Empathy → Action

It reflects the ambition to design systems that do not merely compute, but interpret, explain, and support human decision-making.

Scientific Trajectory and Research Axes
My research trajectory, formalised through my HDR and developed in national and international projects, is structured around three interrelated axes.

1 – Knowledge Formalisation and Semantic Interoperability
I develop formal approaches to structure heterogeneous knowledge through:
• ontology engineering and semantic web technologies
• formal concept analysis and relational concept analysis
• knowledge graphs and reasoning frameworks
These methods aim to ensure interoperability, traceability, and explainability in complex systems.

2 – Knowledge Extraction from Complex Data
Modern systems generate large volumes of heterogeneous and often fragmented data. A central challenge is to reveal the underlying structures that transform data into knowledge.
My work focuses on:
• extracting structured knowledge from heterogeneous sources
• integrating expert knowledge with data-driven approaches
• enabling semantic interpretation of complex environments
This corresponds to the principle of Aletheia, where knowledge is understood as a process of unveiling.

3 – Cognitive AI and Digital Twins
A key direction of my research is the development of knowledge-driven cognitive systems that integrate:
• symbolic reasoning (ontologies, formal models)
• subsymbolic approaches (machine learning, AI)
This leads to the concept of Cognitive Digital Twins, systems that combine data, models, and knowledge to support reasoning, simulation, and decision-making in complex environments.
As highlighted in my recent research and projects, these systems enable:
• explainable and traceable decision support
• simulation and exploration of alternative scenarios
• preservation and transmission of expert knowledge in industrial systems

Toward Human-Centric Artificial Intelligence
Contemporary artificial intelligence is largely driven by data and optimisation. While effective, such approaches often lack:
• explicit knowledge representation
• interpretability and transparency
• alignment with human reasoning
My research contributes to addressing these limitations through hybrid cognitive architectures, combining formal knowledge models and machine learning.
The objective is to develop human-centric, explainable, and resilient intelligent systems, aligned with the principles of Industry 5.0, where artificial intelligence augments human expertise rather than replaces it.