Related Events & Projects

The Darwinist project aims to streamline the creation of reliable and adaptable digital transformation (DT) technologies across various domains. DT presents a promising frontier in digital technology, offering improved services, enhanced security, and increased reliability. With the rapid advancement of AI, big data processing, cloud computing, sensor technologies, and the Internet of Everything (IoE), the development of DT has accelerated over the past two decades.

DT deployment in critical infrastructure provides benefits such as process optimization. Real-time analysis of production processes enables the identification of inefficiencies and performance enhancements, while predictive maintenance strategies help preempt equipment failures, reducing downtime.

Despite the reliability of DT environments for exploring optimal operational scenarios, there's a lack of systematic methodologies in the literature for developing scalable, reusable, interoperable, and extensible DT solutions. The Darwinist project addresses this gap by investigating and defining solutions for DT implementation in various sectors, including railways, healthcare, and aerospace. Additionally, the project adapts to emerging opportunities, as evidenced by its exploration of new domains like aerospace based on positive results from initial studies.

Dissemination:

• Merging Model-Based and Data-Driven Approaches for Resilient Systems Digital Twins Design 

• Supporting the Development of Digital Twins in Nuclear Waste Monitoring Systems 

• Inferring Emotional Models from Human-Machine Speech Interactions 

• A Petri net oriented approach for advanced building energy management systems 

• CaseID detection for Process Mining: a heuristic-based methodology 

The project proposal focuses on the definition and implementation of a decision support system aimed at facilitating the early diagnosis and monitoring of pediatric patients with posterior urethral valves (PUV). This condition is often difficult to diagnose accurately without resorting to invasive examinations. Moreover, it increases the risk of chronic kidney disease, a condition associated with high morbidity and mortality.

The proposed system will integrate clinical, anthropometric, anamnestic, and instrumental data through a multimodal analysis, allowing for an accurate and timely prediction—prior to surgical intervention—of which patients may be affected by PUV and which patients may be at an increased risk of developing chronic kidney disease during subsequent follow-up.

The combined analysis of different data sources will not only enhance the accuracy and reliability of the proposed tool but, thanks to the use of Explainable Artificial Intelligence (XAI) techniques, will also provide medical specialists with a clear understanding of the diagnostic decision-making processes. This will be crucial in supporting healthcare professionals in the patient care process.