Artificial Intelligence (AI) is transforming the biomedical domain by enabling intelligent sensing, data sharing, and decision support across connected environments. To truly integrate AI into healthcare, systems must be not only accurate and efficient but also trustworthy and privacy-preserving. This doctoral thesis proposes a unified framework that brings together three complementary paradigms — Edge Artificial Intelligence (Edge AI), Federated Learning (FL), and Fully Homomorphic Encryptio...
Visual classification depends on two fundamental factors: image structure (the relationships encoded in pixel values) and categorical organization (the labels indicating what they depict). This thesis explores how these data properties shape neural network training and responses.
First, I examine hierarchical label structures in visual datasets. While classification tasks are defined at a specific granularity, training on finer-grained labels can boost performance. I show that this benefit d...
This thesis presents the development of compact and optimized electronic systems for portable electrochemical characterization, biosensing, and electrical stimulation, aiming to advance continuous, non-invasive, and personalized healthcare monitoring. The primary objective is to design and implement low-noise, high-performance electronic interfaces that enable reliable electrochemical sensing, impedance spectroscopy, and electrical stimulation in portable or point-of-care environments. Levera...
In the era of rapid digital transformation, cybersecurity has emerged as a critical concern across diverse sectors, particularly as interconnected systems grow increasingly complex. Low- and Middle-Income Countries (LMICs) face unique challenges in this landscape, including limited resources, weak institutional frameworks, and growing systemic vulnerabilities. This dissertation seeks to address critical gaps in the understanding and management of systemic cybersecurity risks, offering a novel...
Childhood obesity is a chronic and multifactorial condition resulting from the complex interaction among genetic and environmental factors, family dynamics, lifestyle habits, and socioeconomic determinants. Its steadily increasing prevalence from the earliest stages of life calls for prevention and intervention strategies capable of targeting both eating behaviors and the psycho-physical factors that shape growth. Over the course of this PhD thesis, three projects were developed to counteract...
Stroke represents one of the most pressing global health challenges, ranking as the second leading cause of death and the third leading cause of death and disability combined. Rehabilitation is a multidisciplinary process of care aimed at managing and reducing stroke-related impairments and optimizing functional recovery. Notably, even among patients with comparable baseline motor and cognitive function, some achieve worse outcome than others. This suggests that factors beyond initial neurolo...
Increasing soil salinization poses a significant challenge to global agriculture, necessitating the identification of crop varieties with enhanced salt tolerance. This study investigates the phenotypic and molecular salt-stress response of four Italian rice varieties, Baldo, Onice, Selenio, and Vialone Nano, showing dissimilar susceptibility to salinity, aiming to identify molecular traits related to plant tolerance toward soil salinization. Phenotypic evaluations revealed Baldo and Onice as ...
This thesis explores the application of multimodal Artificial Intelligence (AI) to advance early diagnosis and understanding of Neurodevelopmental Disorders (NDD) within the framework of the neurodevelopmental cascade theory. NDD present significant diagnostic and therapeutic challenges due to their heterogeneity and overlapping symptoms, requiring new scalable and precise methodologies. By integrating AI across multiple domains and examining how motor, communicative, attentional, and socio-e...
As the age of the global population increases, the demand for innovative and practical solutions to support elderly care has attracted significant interest. Recent advances in digital technologies and computational science offer promising opportunities to extend the continuum of care at patients’ homes.
This dissertation investigates the potential role of artificial intelligence (AI) methods and technology can have in rehabilitation medicine. The hypothesis is that AI can provide solutions f...
Early Artificial Intelligence (AI) systems encoded domain-specific knowledge using knowledge representation techniques, such as expert systems. In contrast, modern AI paradigms like Deep Learning have thrived due to the abundance of data and computational resources, shifting toward a data-driven approach to decision-making. However, relying solely on this kind of approach can pose risks in certain fields, particularly in medicine and biomedical research where expert knowledge plays a crucial ...