Now showing items 172-191 of 376

    Identification of versions of the same musical composition by processing audio descriptions 

    Serrà Julià, Joan (Date of defense: 2011-02-23)

    This work focuses on the automatic identification of musical piece versions (alternate renditions of the same musical composition like cover songs, live recordings, remixes, etc.). In particular, we propose two core ...

    Image analysis and deep learning to support endovascular repair of abdominal aortic aneurysms 

    López-Linares, Karen (Date of defense: 2019-06-11)

    An abdominal aortic aneurysm (AAA) is a focal dilation of the aorta that may lead to its rupture. The most common treatment for AAAs is endovascular aneurysm repair (EVAR). EVAR implies lifelong postoperative surveillance ...

    Image based analysis and modeling of the detailed cardiac ventricular anatomy 

    Paun, Bruno (Date of defense: 2017-07-24)

    The role of trabeculations and their normal morphological expression in the human heart is still unclear. Clinical studies have shown that excessive trabeculation can cause heart failure due to diastolic and systolic ...

    Image processing algorithms as artistic tools in digital cinema 

    Zabaleta Razquin, Itziar (Date of defense: 2021-10-01)

    The industry of cinema has experienced a radical change in the last decades: the transition from film cinematography to its digital format. As a consequence, several challenges have appeared, but, at the same time, many ...

    Image similarity for registration and manifold learning: application to brain analysis 

    Zimmer, Veronika Anne (Date of defense: 2017-02-13)

    The aim of this thesis is to explore and develop measures for image comparison in two main areas of medical image analysis: image registration and manifold learning for population analysis. In particular, the main contributions ...

    Improvements to incentives in incentive-driven blockchain technologies 

    McMenamin, Conor (Date of defense: 2023-03-17)

    In this thesis, we present a set of protocols in areas at the core of current blockchain technology literature; consensus, decentralized finance and distributed computing. These areas are bound by a critical dependency ...

    Improving sound retrieval in large collaborative collections 

    Favory, Xavier (Date of defense: 2021-03-04)

    Capturing sounds on a recording medium to enable their preservation and reproduction started to be possible during the industrial revolution of the 19th century, originally achieved through mechanic and acoustic devices, ...

    In-depth exploration of the syntactic capabilities of autoencoding language models for downstream applications 

    Pérez-Mayos, Laura (Date of defense: 2022-06-15)

    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 ...

    Incorporating prosody into neural speech processing pipelines: applications on automatic speech transcription and spoken language machine translation 

    Öktem, Alp (Date of defense: 2019-02-25)

    In this dissertation, I study the inclusion of prosody into two applications that involve speech understanding:~automatic speech transcription and spoken language translation. In the former case, I propose a method that ...

    Individual traits versus invariances of cognitive functions: a model-based study of brain connectivity 

    Pallarés Picazo, Vicente (Date of defense: 2019-04-12)

    Es conocido en la literatura de neuroimagen que las redes cerebrales funcionales reflejan rasgos personales. Estas características individuales, podrían interferir al caracterizar la cognición entendida como la manera en ...

    Information fusion and learning from diverse clinical cohorts and heterogeneus data 

    Martí Castellote, Pablo-Miki (Date of defense: 2023-09-27)

    This PhD thesis explores how data science can be leveraged to learn from diverse cohorts and fuse information from heterogeneous data, aiming to advance understanding and improve prediction in healthcare settings. It covers ...

    Information processing in the cortex: the relevance of coherent oscillations for neuronal communication 

    Buehlmann, Andrés (Date of defense: 2010-07-20)

    Les oscil·lacions d'activitat neuronal són un fenomen omnipresent a l'escorça cerebral. La funció d'aquestes oscil·lacions, però, no està clara. ¿Són només un epifenomen de les elevades taxes de descàrrega de potencials ...

    Information propagation in the cortex across the sleep-wake cycle: a computational study 

    Razi, Farhad (Date of defense: 2023-07-21)

    During the deep phases of sleep we do not normally wake up by a thunder, but we nevertheless notice it when awake. The exact same sound gets to our ears and cortex through the thalamus and still, it triggers two very ...

    Information representation and processing in neuronal networks: from biological to artificial systems and from first to second-order statistics 

    Lawrie, Sofía (Date of defense: 2022-03-28)

    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 ...

    Interaction and participation in collaborative storytelling systems 

    Colás Álvarez, Joaquim (Date of defense: 2017-09-20)

    Storytelling is one of the oldest models of cultural expression in human history. Thanks to the evolution of information technologies, the Web 2.0 paradigm has impacted in this field: some modern audiences actively participate ...

    Internal logistics optimization in the automotive industry 

    Fabri Lima, Marcelus (Date of defense: 2020-01-27)

    This thesis focus on internal logistics flows (ILF), which is defined as the flows of materials inside the same business or the same plant. Precisely, this work approaches the ILF of SEAT, a company in the Volkswagen ...

    Interoperabilidad de metadatos en sistemas distribuidos 

    Peig Olivé, Enric (Date of defense: 2004-02-09)

    Usar metadatos para referenciar, etiquetar y describir recursos es cada vez más usual. Esto permite establecer mejores mecanismos para descubrir y localizar material publicado en repositorios públicos accesibles por la ...

    Interpretable deep-learning models for sound event detection and classification 

    Zinemanas Frieti, Pablo (Date of defense: 2023-10-20)

    Deep-learning models have revolutionized state-of-the-art technologies in many research areas, but their black-box structure makes it difficult to understand their inner workings and the rationale behind their predictions. ...

    Interpretable machine learning through radiomics and attribute-regularized neural networks for cardiology 

    Cetin, Irem (Date of defense: 2022-05-23)

    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 ...

    Irregularly sampled image resortation and interpolation 

    Facciolo Furlan, Gabriele (Date of defense: 2011-03-03)

    The generation of urban digital elevation models from satellite images using stereo reconstruction techniques poses several challenges due to its precision requirements. In this thesis we study three problems related ...