Zerrendatu Konputazio Ingeniaritza eta Sistema Adimentsuak Unibertsitate Masterra honen arabera: argitalpen data
82-tik 61-80 emaitza erakusten
-
-
Mitigación autónoma de intrusiones en redes SDN utilizando agentes inteligentes basados en MuZero
(2022-12-23)El paradigma de las redes definidas por software (SDN) permite desarrollar sistemas que monitorizan y controlan el tráfico de una red de forma centralizada, facilitando la implementación de sistemas basados en el aprendizaje ... -
Trenen trakzio profilen optimizazioa energia kontsumoa minimizatuz
(2022-12-23)[EU] Proiektu hau CAF-Signalling enpresak dituen beharrei erantzun bat emateko burutu da. Gaur egun energia kontsumoaren minimizazioa enpresa guztiek mahai gainean jarri behar duten gai bat da, eta bide horretan, tren ... -
A tableau method for the realizability and synthesis of reactive safety specifications
(2022-12-23)Reactive systems are systems that continuously interact with the environment. In general, as they are critical systems, a failure or malfunction can result in serious consequences, such as loss of human lives or large ... -
-
Comparación entre modelos Shallow y Deep para la detección de anomalías
(2022-12-23)Este documento recoge el proceso seguido para la realización del Trabajo de Fin de Máster, el cual consiste en aprender diferentes modelos de One Class Classification para la clasificación de fallos del eje de una grúa. ... -
Evaluation and development of deep neural networks for super-resolution of microscopy and astrophysics images
(2022-12-23)Due to physical constrains of an Electron Microscope, capturing high-resolution scans of a subject takes a very long time. On the other hand, running a Gravitational N-body simulation of hundreds of millions of particles, ... -
Understanding the elementary landscape decomposition of the QAP and its effects on local search based algorithms
(2022-12-23)Elementary landscapes are a special type of combinatorial landscapes that have some properties that make them particularly suitable for working with meta-heuristic algorithms, specially local search based methods. In most ... -
Lithium-ion battery remaining useful life prediction
(2022-12-23)Lithium-Ion Battery Remaining Useful Life Prediction work consists of an initial approach to battery life prediction using Severson dataset and data-driven LSTM-based RUL predictive methods. Although the memory is ... -
An analysis of the relevance of temporal information in time series classification
(2022-12-23)In recent years, the interest in time series has increased considerably due to the vast amount of such data collected in a variety of fields. Time series are a particular type of data: they are sets of ordered observations. ... -
Selection of critical nodes in drone airways graphs via graph neural networks
(2022-12-23)This Master Thesis has two distinct parts. The first one mod- els an application of Graph Neural Networks (GNN) for the identifica- tion of critical nodes in graphs that correspond to traffic networks. We call critical ... -
Diskurtsoko koherentzia erlazioen iragarpenak euskararako BERT sare neuronal aurreentrenatua erabiliz
(2022-12-23)Rhetorical Structure Theory (RST) teoriak testuak deskribatzeaz arduratzen da, koherentzia azalduz. Deskribapena zuhaitz eran antolatuta adierazten da, testua segmentuetan banatuta egonik. Segmentuak erlazioen bidez lotzen ... -
GowFed: a novel federated intrusion detection system for IoT devices
(2022-12-23)[EN] Intrusion detection systems are evolving into intelligent systems that perform data analysis while searching for anomalies in their environment. The development of deep learning techinques paved the way to build more ... -
Transformer-based architecture for 2D semantic segmentation of mitochondria
(2022-12-23)In this project, we have studied the state-of-the-art of semantic segmentation of biomedical images and compared the performance of a new Transformer-based architecture with the most used convolutional architecture for ... -
Information extraction from verbal autopsies
(2022-12-23)Civil registration and vital statistics registers births and deaths and compiles statistics. These statistics are a key factor to promote public health policies, register longevity and the health of the population. Death ... -
Building hybrid classical-quantum classifiers to deal with unbalanced datasets
(2022-12-23)Quantum circuits offer a different approach to process data through quantum operations and measurements of quantum states. At the same time, the increasing number of advances in technology has opened a path to turning these ... -
The “Extended Reach” method: exploring the neighbors of the neighbors to escape from local optima
(2022-12-23)[EN] Local search is a widely used meta-heuristic due to its simple yet effective approach for solving computationally hard optimization problems. Despite their popularity, hill-climbing algorithms get stuck in local optima, ... -
Mejora de la efectividad de la clasificación en la plataforma WEKA en base al uso de métodos de remuestreo sobre la distribución de clases óptima
(2022-12-23)Los problemas de clasificación de bases de datos desbalanceadas constituyen un paradigma específico dentro del Machine Learning que ha sido ampliamente estudiado en los últimos años y que puede ser abordado desde distintos ... -
Evolutionary computation in hierarchical model discovery
(2022-12-23)Despite its continuous growth, probabilistic programming is still a great unknown among scientists, specially those whose research areas involve sampling dis- tributions, statistical modeling or statistical inference. ... -
Preprocesado y clasificación de imágenes médicas para el tratamiento SBRT
(2022-12-23)En este proyecto de fin de máster se han desarrollado y estudiado herramientas para el preprocesado y clasificación de imágenes médicas para el tratamiento de Radiocirugía Estereotáctica (SBRT). La prevención y terapia ...