Programa de Doctorat en Informàtica: Enviaments recents
Ara mostrant els elements 1-20 de 97
Human Activity Recognition with Consumer Devices and Real-Life Perspectives
During the last decade, research on human activity recognition has grown due to its applications in diverse fields such as video surveillance, exercise monitoring or health monitoring systems. In the latter case, researchers ...
Nuevas Técnicas para la Mejora Espacial de Imágenes Inter-Sensor en Datos de Teledetección
La presente tesis doctoral presenta innovaciones en teledetección, centrándose en el realce de imágenes y la integración de datos de diferentes plataformas y sensores, especialmente de los satélites Sentinel-2 y Sentinel-3 ...
Deep learning models for multimodal and multispectral remote sensing image processing.
Remote sensing (RS) images have become fundamental in many important application fields, including land-cover and mapping, urban planning, forest monitoring, agricultural land management, or weather forecasting, among ...
Análisis y modelización de los procesos de aprendizaje profundo
El objetivo de esta tesis es el diseño, implementación y validación experimental de soluciones software paralelas para el aprendizaje automático mediante redes neuronales profundas (RNPs). Estos estudios abordan tres ...
Definition and analysis of strategic predictive indicators for social networks
This thesis delves into a novel research area in Social Business Intelligence (SBI) focusing on social indicators. It proposes advanced methodologies for discovering and describing social indicators, using social network ...
"Horizon: Resilience": A Smartphone-based Serious Game Intervention for Depressive Symptoms
Depression is the most prevalent mental disorder in our society, leading to disability and suicide deaths. Although effective evidence-based psychological treatments exist, they reach only a fraction of those in need. ...
Mixed Reality Human-Robot Interface for Robotic Operations in Hazardous Environments
This thesis addresses the need for reliable and immersive human-robot interfaces in hazardous environments. Three key goals were achieved. Firstly, techniques were developed to provide immersive interactions while ensuring ...
Applying Mobile and Geospatial Technologies to Ecological Momentary Interventions
Today a large percentage of the population suffers from anxiety-related problems. This anxiety can appear in day-to-day situations. An effective therapy for these problems is exposure. In it, the person is gradually exposed ...
Sistema interactivo de realidad aumentada y gamificación para la rehabilitación y mejora física asistida en entornos no supervisados basado en cámaras RGB-D
KineActiv es un sistema que permite la rehabilitación de miembros superiores e inferiores de manera autónoma, no supervisada por un fisioterapeuta. Se ha desarrollado un entorno de realidad aumentada, usado cámaras RGB-D, ...
Study and Prediction of Air Quality in Smart Cities through Machine Learning Techniques Considering Spatiotemporal Components
Air quality is considered one of the top concerns. Information and knowledge about air quality can assist in effectively monitoring and controlling concentrations, reducing or preventing its harmful impacts and consequences. ...
Beyond saccadic movements for interactive perception in robotics
This thesis takes inspiration from biology to replicate in robots the oculomotor strategies humans and other species use to acquire visual information. Firstly, it establishes the foundations of the work by reviewing current ...
Game Development Based on Multi-agent Systems
Video game development is a multidisciplinary process that requires both technical and artistic knowledge. Even though there are tools to ease the creation of video games, they are still complex applications that require ...
Design and evaluation of variable-stiffness robotic grippers
In store warehouses, objects differ in terms of shape. During the automation process, reliable grasping is required, due to the variability of object shapes and positions. The main objective is to create and validate a ...
Towards a predictive interface for the specification of intervention tasks in underwater robotics
Robots play a critical role in our everyday lives, performing tasks as diverse as maintenance, surveillance, exploration in harsh environments, or search and rescue operations. Concerning the different environments where ...
Making Biosignals Available
This thesis is an invitation to rethink how simplistic approaches to biosignal processing enrich the potential of personal sensing in line with the fast development of what have come to be undeniably ubiquitous technologies. ...
An Analytics Platform for Integrating and Computing Spatio-Temporal Metrics in Location-aware Games
This thesis presents an analytics platform for calculating spatio-temporal metrics in the context of geogames and context-based applications. It is based on an underlying conceptual model for spatio-temporal metrics, which ...
Analysis of Parallelization Strategies in the context of Hierarchical Matrix Factorizations
H-matrices offer log-linear storage and computations costs, thanks to a controlled accuracy loss. This is the reason why they are specially suitable for Boundary Element Methods (BEM). Task-parallelism strategies are applied ...
Avances en Telerobótica Inalámbrica Submarina
Los estándares de comunicación sin umbilicales utilizados a través del aire son inútiles bajo el agua debido a la elevada atenuación de las ondas de radiofrecuencia. Esto obliga al uso de otras tecnologías con capacidades ...
Nuevos Algoritmos Basados en Grafos y Clustering para el Tratamiento de Complejidades de los Datos
La distribución no balanceada de los datos entre las clases, así como la presencia de ruido y el traslape de clases, son complejidades de los datos que a menudo interfieren en el rendimiento de clasificadores. Para afrontar ...
Procedural Generation of Natural Environments
The video games, simulators and virtual reality industry increasingly demands more complex and realistic natural environments, which makes manual generation difficult. To solve it, procedural techniques have been developed, ...
