Examinar por departamento (eus.) "Konputagailuen Arkitektura eta Teknologia"
Now showing items 21-40 of 81
-
Benchmarking Object Detection Deep Learning Models in Embedded Devices
(MDPI, 2022)Object detection is an essential capability for performing complex tasks in robotic applications. Today, deep learning (DL) approaches are the basis of state-of-the-art solutions in computer vision, where they provide very ... -
Blood Cell Revolution: Unveiling 11 Distinct Types with ‘Naturalize’ Augmentation
(MDPI, 2023-12-10)Artificial intelligence (AI) has emerged as a cutting-edge tool, simultaneously accelerating, securing, and enhancing the diagnosis and treatment of patients. An exemplification of this capability is evident in the analysis ... -
Changes in Day/Night Activity in the 6-OHDA-Induced Experimental Model of Parkinson’s Disease: Exploring Prodromal Biomarkers
(Frontiers Media, 2020-10-14)The search for experimental models mimicking an early stage of Parkinson's disease (PD) before motor manifestations is fundamental in order to explore early signs and get a better prognosis. Interestingly, our previous ... -
Characterization of e-Government adoption in Europe
(Plos One, 2020-04-17)The digital divide in Europe has not yet been bridged and thus more contributions towards understanding the factors affecting the different dimensions involved are required. This research offers some insights into the topic ... -
Classifier Subset Selection for the Stacked Generalization Method Applied to Emotion Recognition in Speech
(MDPI, 2016-01)In this paper, a new supervised classification paradigm, called classifier subset selection for stacked generalization (CSS stacking), is presented to deal with speech emotion recognition. The new approach consists of an ... -
Combination of web usage, content and structure information for diverse web mining applications in the tourism context and the context of users with disabilities
(2015-07-27)This PhD focuses on the application of machine learning techniques for behaviourmodelling in different types of websites. Using data mining techniques two aspects whichare problematic and difficult to solve have been ... -
Context- and Template-Based Compression for Efficient Management of Data Models in Resource-Constrained Systems
(MDPI, 2017-08)The Cyber Physical Systems (CPS) paradigm is based on the deployment of interconnected heterogeneous devices and systems, so interoperability is at the heart of any CPS architecture design. In this sense, the adoption of ... -
Contributions on agreement in dynamic distributed systems
(2015-06-25)This Ph.D. thesis studies the agreement problem in dynamic distributed systems by integrating both the classical fault-tolerance perspective and the more recent formalism based on evolving graphs. First, we developed a ... -
Contributions to automatic learning of kernel functions
(2020-07-03)Muchos algoritmos de aprendizaje automático se basan en funciones de kernel para resolverlas tareas propuestas. Entre estos algoritmos podemos encontrar métodos de kernel, como lasMáquinas de vectores de soporte (SVMs), o ... -
Contributions to comprehensible classification
(2020-07-16)La tesis doctoral descrita en esta memoria ha contribuido a la mejora de dos tipos de algoritmos declasificación comprensibles: algoritmos de \'arboles de decisión consolidados y algoritmos de inducciónde reglas tipo PART.En ... -
Contributions to High-Throughput Computing Based on the Peer-to-Peer Paradigm
(2015-06-18)This dissertation focuses on High Throughput Computing (HTC) systems and how to build a working HTC system using Peer-to-Peer (P2P) technologies. The traditional HTC systems, designed to process the largest possible number ... -
Contributions to the efficient use of general purpose coprocessors: kernel density estimation as case study
(2015-06-19)The high performance computing landscape is shifting from assemblies of homogeneous nodes towards heterogeneous systems, in which nodes consist of a combination of traditional out-of-order execution cores and accelerator ... -
Contributions to Web Accessibility: Device-tailored Evaluation, User-tailored Interface Generation and the Interplay with User Experience
(2017-04-25)AbstractThe Web has an incredible importance in our modern society and for many people it has become a fundamental part of their lives. It enables us to Access a huge amount of information, and use a wide range of services ... -
Design and development of a gait training system for Parkinson’s disease
(Public Library Science, 2018-11-12)Background Rhythmic Auditory Stimulation (RAS) is an effective technique to improve gait and reduce freezing episodes for Persons with Parkinson's Disease (PwPD). The BeatHealth system, which comprises a mobile application, ... -
Development and Implementation of a Community-Based Research Network
(Cambridge University Press, 2020-05-18)Introduction: People aging with long-term physical disabilities (PAwLTPD), meaning individuals with onset of disability from birth through midlife, often require long-term support services (LTSS) to remain independence. ... -
Diagnostic classification of Parkinson’s disease based on non-motor manifestations and machine learning strategies
(Springer, 2023-03)Non-motor manifestations of Parkinson’s disease (PD) appear early and have a significant impact on the quality of life of patients, but few studies have evaluated their predictive potential with machine learning algorithms. ... -
Distância diacrónica automática entre variantes diatópicas do português e do espanhol
(Universidade do Minho, 2020-06-29)[POR] O objetivo deste trabalho é aplicar uma metodologia baseada na perplexidade, para calcular automaticamente a distância interlinguística entre diferentes períodos históricos de variantes diatópicas de idiomas. Esta ... -
Distributed eventual leader election in the crash-recovery and general omission failure models.
(2020-01-24)Distributed applications are present in many aspects of everyday life. Banking, healthcare or transportation are examples of such applications. These applications are built on top of distributed systems. Roughly speaking, ... -
Dynamic selection of the best base classifier in one versus one
(Elsevier, 2015-05-19)Class binarization strategies decompose the original multi-class problem into several binary sub-problems. One versus One (OVO) is one of the most popular class binarization techniques, which considers every pair of classes ... -
Evaluation of two virtual cursors for assisting web access to people with motor impairments
(Elsevier, 2019-08-02)People with motor impairments (MI) may face accessibility barriers when using computers due to their health conditions and therefore need to use alternative devices to a standard mouse for pointing and clicking in graphical ...