Programa de Doctorat en Tecnologies de la Informació i les Comunicacions: Enviaments recents
Ara mostrant els elements 61-80 de 389
Natural language processing technologies in compensatory supports for people with aphasia and acquired reading impairments
Aphasia is often associated with reading impairments. Nonetheless, supports designed for people with aphasia and acquired reading impairments allowing autonomous access to written material are lacking. These individuals ...
Representation learning for music classification and retrieval: bridging the gap between natural language and music semantics
The explosion of digital music has dramatically changed our music consumption behavior. Massive digital music libraries are now available through streaming platforms. Since the amount of information available to ...
Motivations, engagement, and incentives in online communities: contributions to theory, data analytics and design
The success of an online community depends on the contributions and actions performed by the community members. This dissertation aims to understand the dynamics of participation in regulated, not-for-profit, open online ...
In-depth exploration of the syntactic capabilities of autoencoding language models for downstream applications
Pretrained Transformer-based language models have quickly replaced traditional approaches to model NLP tasks, pushing the state of the art to new levels, and will certainly continue to be very influential in the years ...
Generalized exterior-algebraic electromagnetism in (k, n)-dimensional spacetime
This doctoral thesis aims to find a connection between two different disciplines. On the one hand, the electromagnetic theory, one of the most known and most applied theories in physics, properly described by the famous ...
Interpretable machine learning through radiomics and attribute-regularized neural networks for cardiology
El diagnóstico asistido por ordenador de enfermedades cardiovasculares (CVD) con resonancia magnética cardíaca (CMR) es un campo importante de investigación para el fenotipado avanzado de imágenes cardíacas. Las mediciones ...
A machine learning approach to computer modeling of musical expression for performance learning and practice
Aquesta tesi tracta sobre el disseny i la implementació de sistemes informàtics per a l'execució musical expressiva (CSEMP), explorant diferents mètodes de l'aprenentatge automàtic i reflexionant sobre el paper de l'estructura ...
Statistical modelling of the baby face for 3D Face Reconstruction
In this thesis, we address the problem of reconstructing the 3D facial geometry of babies from uncalibrated 2D images. This topic has many different applications, but it is especially relevant for the early diagnosis of ...
Information representation and processing in neuronal networks: from biological to artificial systems and from first to second-order statistics
Neuronal networks are today hypothesized to the basis for the computing capabilities of biological nervous systems. In the same manner, artificial neuronal systems are intensively exploited for a diversity of industrial ...
Construction of injectable wireless microstimulators based on rectification of volume conducted high frequency currents
Functional neuromuscular stimulation (FNS) refers to the delivery of electrical stimuli to nerves or muscles to enhance, modify or restore motor functions. Despite their invasiveness, implantable systems for FNS offer ...
Large-scale online learning under partial feedback
La toma secuencial de decisiones con incertidumbre cubre una amplia clase de problemas. Las aplicaciones reales requieren que los algoritmos sean computacionalmente eficientes y escalables. Nosotros estudiamos un rango ...
Data-driven pitch content description of choral singing recordings
Ensemble singing is a well-established practice across cultures, found in a great diversity of forms, languages, and levels. However, it has not been widely studied in the field of Music Information Retrieval (MIR), ...
Deep learning and unsupervised machine learning for the quantification and interpretation of electrocardiographic signals
Las señales electrocardiográficas, ya sea adquiridas en la piel del paciente (electrocardiogamas de superficie, ECG) o de forma invasiva mediante cateterismo (electrocardiogramas intracavitarios, iECG) ayudan a explorar ...
Neural networks for singing voice extraction in monaural polyphonic music signals
This thesis dissertation focuses on singing voice extraction from polyphonic musical signals. In particular, we focus on two cases; contemporary popular music, which typically has a processed singing voice with instrumental ...
Studying collaborative learning space design with multimodal learning analytics
Research has provided relevant advances in evidence-based design for productive learning. For example, in the field of collaborative learning, there is extensive evidence for some key learning design elements, such as ...
Data-driven musical version identification: accuracy, scalability and bias perspectives
This dissertation aims at developing audio-based musical version identification (VI) systems for industry-scale corpora. To employ such systems in industrial use cases, they must demonstrate high performance on large-scale ...
Terahertz communications: Physical layer enablers and analysis
Undoubtedly, spectrum scarcity constitutes the main bottleneck of current wireless networks. It is therefore imperative to move beyond the sub-6 GHz band in order to overcome this limitation. Toward this direction, terahertz ...
Automating crowd simulation: from parameter tuning to dynamic context-to-policy adaptation
Computer-generated crowds are becoming more and more frequent in films, video games and safety assessment applications. Many crowd simulation algorithms exist to address the needs of this diverse range of industries. Even ...
Treatment planning in electroporation-based therapies
Diverses teràpies mèdiques es basen en l’electroporació. Entre d’altres, l’electroporació s'usa per al tractament de tumors sòlids. Com que només afecta les cèl·lules i la matriu extracel·lular queda intacta, amb ...
Training sound event classifiers using different types of supervision
The automatic recognition of sound events has gained attention in the past few years, motivated by emerging applications in fields such as healthcare, smart homes, or urban planning. When the work for this thesis started, ...
