Programa de Doctorat en Tecnologies de la Informació i les Comunicacions: Envíos recientes
Mostrando ítems 1-20 de 411
Analyzing singing voice expressivity: Focus on singing voice musical dynamics
Musical dynamics, a key expressive dimension of the singing voice, play a vital role in shaping phrasing and conveying the desired emotional impact. Despite their importance, their formalization and standardization remain ...
Novel geometric representations and optimized frameworks for deep learning models of interatomic potentials
Aquesta tesi explora avenços en potencials de xarxes neuronals per a simulacions atomístiques, abordant el doble repte de la precisió i l'eficiència. Mitjançant noves representacions geomètriques i marcs optimitzats, té ...
A deep cascaded, biomechanics-driven framework for medical image registration
Aquesta tesi presenta un marc que combina una xarxa neuronal profunda en cascada amb un modelatge biomecànic per millorar el registre d’imatges mèdiques, amb aplicacions en la imatge cerebral perinatal i l’anàlisi de ...
Compositionality for hierarchical reinforcement learning
Recent breakthroughs in AI have proven that reinforcement learning can be used successfully to solve complex sequential decision problems to achieve near-optimal solutions. However, despite the successful applications ...
The Role of constraints in coputation exploring optimality through limited resources and intrinsic motivation
When interacting with the world, agents take actions they consider optimal, that is, best. Typically, this optimality is evaluated over the entire space of possibilities. However, agents are inherently bounded -- for ...
Business innovation strategies
En l’entorn empresarial accelerat d’avui, la innovació és reconeguda com a essencial per mantenir un avantatge competitiu, però moltes organitzacions s'enfronten a grans reptes per incorporar-la als seus marcs estratègics. ...
Music identification with audio fingerprinting an industrial perspective
Music identification is a mature and well-studied field in the Music Information Retrieval community. In the music industry, it ensures fair distribution of royalties, which are allocated based on usage, such as plays ...
Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks
Reinforcement learning (RL) provides a unique framework for addressing sequential decision-making problems. Despite the numerous software frameworks proposed to accelerate the development of new algorithms and applications, ...
Provably efficient large-scale reinforcement learning via primal-dual stochastic optimization
Real-world sequential decision-making tasks are often characterized by large state spaces and unknown dynamics. In this setting, an efficient method is tasked to learn a near-optimal decision-making policy under a given ...
Lesion morphology and cell death mechanisms in high frequency pulsed field ablation in cardiac tissue
A novel technique for the ablation of cardiac arrhythmias based on irreversible electroporation, Pulsed Field Ablation (PFA), has been developed over the last years. Despite PFA is already in clinical use, there are many ...
Facilitating interpersonal synchrony in children: designing embodied mixed reality experiences to facilitate and assess prosocial behaviours in neurodiverse children
This thesis is focused on how full-body interactive design in multi-user Mixed Reality environments can support Interpersonal Synchrony (IPS) strategies to promote prosocial attitudes and behaviors in children. This ...
Multi-link operation for low-latency
Next generation applications will have strict network requirement, such as higher throughput and low latency. As Wi-Fi continues to grow, it needs to adapt to these new requirements. This thesis focuses on latency reduction ...
The Cost of sybils
This thesis explores Sybil strategies in decentralized and anonymous systems, focusing on blockchain technology. Combining blockchain insights with game theory, mechanism design, and machine learning, the research analyzes ...
Optimization of transportation services for persons with reduced mobility
Aquesta tesi aborda l'optimització dels serveis de transport per a persones amb mobilitat reduïda, centrant-se en el Servei Municipal de Transport Especial de Barcelona. Els sistemes de transport accessibles són essencials ...
A High-performance computational framework for multiscale and multiphysics modelling of the intervertebral disc
This thesis develops a multiscale and multiphysics model of the intervertebral disc (IVD); it focuses on three main axes regarding: Mechanical response: It introduces a compatible porohyperelastic framework capable of ...
Design, development, and deployment of real-time drum accompaniment systems
This dissertation examines the generation of real-time symbolic drum accompaniments, with a particular focus on live improvisation contexts. While the research does occasionally focus on the audio domain, the majority of ...
Empowering educators' inspiration during the learning design process with citizen science data and technology-enhanced learning
The creation of learning designs (LD) represents a pivotal aspect of pedagogical practice, as it entails the integration of subject-matter knowledge with the pedagogical expertise of individual educators. Furthermore, ...
High resolution 3D modelling of lumbar spine from MRI using deep learning
This thesis addresses the growing problem of degenerative disorders of the intervertebral discs (IVD). Intervertebral Disc Degeneration (IDD) represents a progressive degradation of the IVDs compromising their biomechanical ...
Industrial augmented reality prototypes in the field of art authoring, dissemination, and consumption tools for artistic content on mobile devices with a focus generation Z
The advent of spatial content and increasingly advanced mixed reality devices is set to revolutionise the manner in which we interact with digital content, becoming the predominant human-computer interface in the ...
Deep audio representation learning for music using weak supervision
Music audio tagging is the Music Information Retrieval task of assigning one or multiple labels to an audio signal. Current state-of-the-art music taggers rely on deep learning approaches, which offer high performance ...
