A Unified Geometric Deep Learning Framework for Financial Time Series: Integrating Temporal, Graph, and Signature-Based Representations

Financial time series exhibit complex statistical properties, in- cluding nonlinear dependencies, non-stationarity, and evolv- ing relationships among assets. Traditional econometric mod- els and purely temporal machine learning approaches often struggle to capture these characteristics as they focus mainly on sequential dynamics while overlooking the underlying ge- ometric structure of financial data. This thesis investigates the role of geometric representations in financial time series ...

Mind, Media, and Networks

The increasing complexity of psychological phenomena in digital environments calls for innovative theoretical and methodological approaches. While psychology offers a rich body of established theories to study and interpret human behavior, it is not clear how they apply to contemporary digital contexts. In this thesis, I combine established frameworks with emerging approaches to examine how traditional concepts apply to the new, digital world. Across three empirical studies, I explore key mec...

How visual experience shapes sleep physiology and phenomenology in blind and sighted individuals

Uncovering Neuropsychiatric Susceptibility Through Reliable and Harmonized Sulcal Morphometry : A Framework for Reproducible Neuroimaging Analysis

Magnetic resonance imaging (MRI) has transformed the study of human brain structure by enabling quantitative analysis of cortical anatomy. However, conventional morphometric measures, such as cortical thickness and volumetry, often lack sensitivity to subtle structural alterations and are vulnerable to scanner- and site-related variability in large, multisite studies. Sulcal morphometry, which characterizes fine- grained aspects of cortical folding geometry, offers a biologically grounded a...

Essays on Pro-Environmental Behaviors and Plant-Based Food Choices

Climate crisis requires individual and collective actions to be modified in order to reduce human environmental pressures. This means that consumers’ behavior should change to be- come compatible with ecosystem preservation. Among the Pro-Environmental Behaviors (PEBs) that humans can under- take, more plant-based food choices represent a viable strat- egy to mitigate the climate crisis through the reduction of pol- lutant emissions, soil depletion, and biodiversity loss. This dissertation...

Fine-grained symbolic verification of heterogeneous systems: systematic exploration and formal analysis of “what-if” attack scenarios

Arbitrage in the Bitcoin ecosystem: an investigation of the Mt. Gox exchange platform

Shipwrecking Probability in Mediterranean Territorial Waters: A Cultural Approach to Archaeological Predictive Modelling

In questa tesi viene presentato un modello predittivo, sviluppato utilizzando sistemi informativi geografici (GIS), il cui scopo è di stimare la probabilità di naufragio nelle acque territoriali del Mediterraneo. L’obiettivo è quello di compensare lo scarso sviluppo ed utilizzo di modelli predittivi in ambito archeologico subacqueo -soprattutto nel bacino Mediterraneo- il cui uso ottimizzerebbe invece le indagini archeologiche marine. Dal momento che i modelli predittivi vengono spesso critic...

Thermoelastic and Fracture Responses of Periodic Materials: Theory and Applications to Laminates and Triply Periodic Minimal Surfaces

In order to provide better quality on a variety of equipment, services and new technologies to the community, periodic materials as laminates and periodic structures as foams are constantly gaining more attention world- wide, due to the fact that these structures present suitable mechanical behaviours, enhanced physical properties and are yet low-cost. There- fore, it is crucial to understand how these structures respond for different physical and mechanical problems. The present thesis ex...