Advances towards a robust AI-based glioma grading system 

    Pitarch i Abaigar, Carla (Date of defense: 2025-03-04)

    (English) Gliomas represent the most common and aggressive form of primary brain tumors in adults, posing significant diagnostic challenges due to their heterogeneous molecular, histological, and radiological characteristics. ...

    Bio-inspired event-driven intelligence for motion estimation 

    Tian, Yi (Date of defense: 2025-05-19)

    (English) Motion estimation problems can range from low degrees of freedom (DOF) ego-motion estimation to complex, high-DOF motion, which includes dense pixel displacement or optical flow. This information is essential for ...

    Contributions on dimensionality reduction and interpretable machine learning 

    Pachón García, Cristian (Date of defense: 2025-05-08)

    (English) This thesis is divided into two parts. The first one is devoted to dimensionality reduction for large data sets, while the second one focuses on the field of Interpretable Machine Learning. Part of the material ...

    Deep learning methods for speaker verification and diarization 

    India Massana, Miquel Àngel (Date of defense: 2022-11-25)

    (English) The first part of this thesis is based on the use of attention models for speaker verification. SOTA systems for this task are based on speaker embedding extractors. These architectures are comprised by combinations ...

    End-to-end learning for wind turbine blades: from imagery data to defect repair recommendations 

    Pérez i Gonzalo, Raül (Date of defense: 2025-04-02)

    (English) The European Union's (EU) reliance on external energy sources underscores the urgent need for energy security and affordability, driving the transition to renewable energy with wind power as a key renewable ...

    Foundations of ontology-based explainable robots 

    Olivares Alarcos, Alberto (Date of defense: 2024-12-18)

    (English) A critical challenge in the design of robots that operate while interacting with humans is to ensure mutual understanding, which contributes to build reliable human-robot interactions. It is an arduous task since ...

    Highly scalable hardware architecture for real-time execution of spiking neural networks applied to neural cognitive applications 

    Vallejo Mancero, Bernardo Javier (Date of defense: 2024-11-11)

    (English) This thesis contributes to the field of neuromorphic hardware. In particular, to the significant improvement of a scalable hardware architecture, named Hardware Emulator of Evolvable Neural Spiking Systems (HEENS), ...

    Improving real-time guarantees of cache coherence and advanced interconnections in real-time systems 

    Pujol Torramorell, Roger (Date of defense: 2025-05-09)

    (English) The dissertation, research on enhancing timing predictability and performance for Critical Real-Time Embedded Systems (CRTES), focusing on Multi-Processor Systems on Chip (MPSoCs). CRTES are essential in critical ...

    Modeling and reconstruction of 3D humans under context 

    Ugrinovic Kehdy, Nicolas (Date of defense: 2025-04-04)

    (English) The study of human's and their behavior through the analysis of images and videos has long been a central topic in Computer Vision. The reconstruction and modeling of human behavior have garnered increasing ...

    Multimorbidity and frailty trajectories and explainable prediction models for health-related outcomes using longitudinal electronic health records of the ageing Catalan population 

    Carrasco Ribelles, Lucía Amalia (Date of defense: 2024-12-20)

    (English) As life expectancy rises, people over 65 years old become a larger proportion of the population. However, longer life expectancy does not imply healthy ageing. Older individuals are more likely to develop multiple ...

    Quantum analogs of classical codes 

    Vilar Algueró, Ricard (Date of defense: 2025-03-28)

    (English) The main focus of this thesis are stabilizer codes, a type of error-correcting code used to correct quantum information that has been corrupted by noise. We introduce several new general constructions of stabilizer ...

    State estimation, diagnosis and control using set-based approaches for LPV systems 

    Zhang, Shuang (Date of defense: 2025-04-25)

    (English) Considering that Linear Parameter-Varying (LPV) technique has been demonstrated as an effective way to represent nonlinear systems, results concerning the design of observers and controllers in LPV framework have ...