PhD Programme in Computer Science and Mathematics

Emanuele Colonna

Code: 39-033-02-DOT1302947-9558

CUP: H91I23000170007

Study of AI tehniques for efficient generation of digital humans and 3D environments

The research will focus on the study and development of generative AI models for creating Digital Human and modeling 3D environments. The project goal is to develop new research skills in the field of Artificial Intelligence, with a focus on the emerging field of Generative AI. The project idea aims to use generative AI techniques for both text and image generation and the creation of "Digital Human" avatars that are able to replicate human behavior in terms of features, gestures, expressions, and voice. This field of research is innovative and promising and aims to develop algorithms and models that can autonomously generate new content, such as images, videos or text. In addition, Generative AI offers opportunities for innovation and development in various fields, such as art, design, medicine, and many others.

Co-funded by: QuestIT S.r.l.

Serena Grazia De Benedictis

Code: 39-033-02-DOT1302947-9642

CUP: H91I23000170007

Topological Data Analysis and optimization for industrial processes

This research aims to explore how Topological Data Analysis (TDA) can address industrial challenges and manage diverse input data provided by industrial reality. Given TDA's versatility across research fields, its suitability for industry needs assessment. TDA is able to handle varied data types and extract significant information without relying on metrics and ensuring stability despite data noise. Integrating TDA with learning methods can enhance industrial process analysis. The objective of this research is to establish a theoretical and computational framework for devising strategies and algorithms to address data-related issues specific to industrial contexts. This approach seeks to optimize TDA's application in industry, offering insights into its efficacy and fostering innovation in solving industrial challenges.

Co-funded by: Pirelli Tyre S.p.A.

Dibenedetto Gaetano

Code: 39-033-02-DOT1302947-9752

CUP: H91I23000170007

Artificial Intelligence Approaches for Digital Healthcare through Pose Detection and Recommender Systems in eHealth

In recent years, there has been a growing interest in multimodal and multi-source data due to their ability to introduce heterogeneous information. Studies have demonstrated that combining such information enhances the performance of Recommender Systems across various scenarios. In the context of Health Recommendation Systems (HRS), different types of data are utilized, primarily focusing on patient-based information, but data from Pose Estimations (PE) are not incorporated. The objective of my Ph.D. is to investigate methods to design and develop HRS that treat the PE as one of the input sources, taking into account aspects such as privacy concerns and balancing the trade-off between system quality and responsiveness. By leveraging the combination of diverse information sources, I intend to create a new model in the area of HRS capable of providing more precise and explainable recommendations.

Co-funded by: Naps Lab S.r.l.s.

Nunzia Lomonte

Code:

CUP:

Artificial Intelligence for Advanced Digital Transformation: A Study on Next-Generation Sensors and Software Architectures for Intelligent Applications

The research thus involves the integration of IoT devices with Artificial Intelligence solutions in decision support systems. The application domain of reference encompasses the transition from conventional agriculture to sustainable agriculture, climate control, and precision medicine. Specifically, the proposed research line aims to contribute in the following contexts: • Integration of IoT technologies into cloud-based architectures for real-time control (measurement and actuation). • Simulation, digitalization, and optimization of production processes and supply chains. • Development of methods, models, and technologies for increasing biodiversity.

Co-funded by: Axians IT

Qaisar Sohail

Code:

CUP: H91I23000170007

Advancing Cybersecurity Through Adaptive User Behavioral Analytics Systems for Real-Time Threat Detection and Response

Co-funded by: Eulogic