Repositorio Institucional
El Repositorio Institucional recoge la producción científica y académica de la Universidad de Deusto en acceso abierto, a fin de mejorar su preservación, accesibilidad y visibilidad.
Comunidades en DSpace
Selecciona una comunidad para explorar sus colecciones.
Envíos recientes
Modelling of biomedical data using Quantum Computing approach
(Universidad de Deusto, 2023-03-13) Maheshwari, Danyal; García-Zapirain, Begoña; Sierra Sosa, Daniel Esteban; Facultad de Ingeniería, Programa de Doctorado en Ingeniería para la Sociedad de la Información y Desarrollo Sostenible por la Universidad de Deusto
Quantum technologies have become powerful tools for a wide range of application disciplines, which tend to range from chemistry to agriculture, natural language processing, and healthcare due to exponentially growing computational power and advancement in machine learning algorithms. Furthermore, the processing of classical data and machine learning algorithms in the quantum domain has given rise to an emerging field like quantum machine learning. As a result, quantum machine learning has become a common and effective technique for data processing and classification across a wide range of domains. Consequently, quantum machine learning is the most commonly used application of quantum computing. The main objective of this work is to present a brief overview of current state-of-the-art published articles between 2013 and 2021 to identify, analyze, and classify the different QML algorithms and applications in the biomedical field. Furthermore, the approach adheres to the requirements for conducting systematic literature review techniques such as research questions and quality metrics of the articles. Initially, we discovered 3149 articles, excluded the 2847 papers, and read the 121 full papers. Therefore, this research compiled 30 articles that comply with the quantum machine learning models, and quantum circuits are using biomedical data.
In the first case study of the diabetes dataset, we used two different approaches. In the first approach, we presented a Quantum versus classical implementation of Machine learning (ML) algorithm applied to a diabetes dataset. Diabetes is a Sixth deadliest disease in the world and approximately 10 million new cases are registered every year worldwide. The proposed system tackles a binary classification problem of patients with diabetes into two different classes: diabetes patients with acute diseases and diabetes patients without acute diseases. Our study compares classical and quantum algorithms, namely Decision Tree, Random Forest, Extreme Boosting Gradient and Adaboost, Qboost, Voting Model 1, Voting Model 2, Qboost Plus, New model 1 and New Model 2 along with an ensemble method which creates a strong classifier from a committee of weak classifiers. The results we achieved using the validation metrics of the New Model 1 showed an overall precision of 69%, a recall of 69%, an F1-Score of 69%, a specificity of 69% and an accuracy of 69% on our diabetes dataset, with an increase of the computation speed by 55 times in comparison of the classical system.
In the second approach, we presented the application of a Variational Quantum Classifier (VQC) for binary classification of the diabetes disease. To deal with the limitation of noisy intermediate-scale quantum systems (NISQ), we used a pre-processing method to enhance the prediction rate when applying the VQC method. The process includes feature selection and state preparation. Quantum state preparation is critical for obtaining a functioning pipeline in a quantum machine learning (QML) model. Amplitude encoding is a state preparation approach that enhances the performance of data encoding and the learning of quantum models. As a result, our proposed methods achieved accuracies of 75%, 71.4%, and 68.73% by using VQC model and in contrast, the amplitude encoding-based VQC achieved 98.40%, 67.3%, and 74.50% accuracies on the synthetic, sonar, and diabetes dataset, respectively.
In the second case study, we presented cardiovascular diseases (CVD) as conditions affecting the heart and blood vessels. Most approaches for the prediction of ischemic heart disease (IHD) have centered on pain symptoms, age, and gender. However, numerous variables have been identified as determining risk factors for developing IHD. This case study presents a collection of computationally efficient QML algorithms for cardiovascular illness classification, including Optimized Quantum Support Vector Machine (OQSVM) and Hybrid Quantum Multi-Layer Perceptron (HQMLP). Effective pre-processing and feature selection techniques, such as wrapper and filter, enhance prediction rate and ensure the robustness of the proposed frameworks. The proposed model performance metrics are compared to those of recently published and conventional models with complex architectures. The greatest accuracy of the proposed Support Vector Machine (SVM), OQSVM, Multilayer Perceptron (MLP), and HQMLP models are 96%, 94%, 94%, and 93%, respectively, when 10 features of the cardiovascular dataset are taken into consideration.
Furthermore, the our proposed studies are computationally efficient and have the potential to be beneficial in real-time healthcare applications. This Ph.D. dissertation presents one conference and 2 journals published articles in the Q1 journals.
Teachers’ learning and pedagogical beliefs change through Lesson Study
(Universidad de Deusto, 2022-10-14) Khokhotva, Olga; Elexpuru Albizuri, Iciar; Facultad de Educación y Deporte, Programa de Doctorado en Educación por la Universidad de Deusto
This thesis is about passion for teaching, learning and intellectual and emotional growth for the betterment of society. On the central stage are the teachers, whose values, moral purpose, passion, commitment and collaborative agency kindles endless aspiration for improving teaching and learning to ensure the well-being and happiness of students.
This thesis is about enthusiastic and passionate educators open to innovation and experimenting with new approaches to professional learning and development in the context of Kazakhstan and the Basque Autonomous Community, Spain. It is about eight English as Foreign Language teachers who, along with the author of this thesis, set out on a journey of exploring their teaching practice with Lesson Study, and the outcomes of such an endeavour.
Specifically, the outcomes have been presented through a compendium of four consecutive publications bound by the logic of an action research project where each research question is shaped by the preceding research loop. Sculpted by four research questions, the exploration of teachers' learning and pedagogical beliefs change through Lesson Study commences in the context of educational Reform at Scale in Kazakhstan and finalises in the context of a school in the Basque Country, Spain. Each publication showcases a separate case study for which a unique literature review was compiled and specific and original theoretical and analytical frameworks were built.
La calidad de vida y su medida. Sistema de indicadores sociales para el País Vasco
(Universidad de Deusto, 1990-02-21) Setién Santamaría, María Luisa; Jiménez Blanco, José; Facultad de Ciencias Políticas y Sociología
La tesis tiene como objetivo fundamental, la elaboración de un sistema de indicadores sociales para medir la calidad de vida, basado en un marco conceptual y teórico. El sistema de indicadores de calidad de vida está orientado para su aplicación al País Vasco.
Passenger vehicles comfort simulation strategy on a stewart platform considering damper dynamic models
(Universidad de Deusto, 2022-05-06) Santos Arconada, Verónica; García Barruetabeña, Jon; Facultad de Ingeniería, Programa de Doctorado en Ingeniería para la Sociedad de la Información y Desarrollo Sostenible por la Universidad de Deusto
The investigation developed in the Doctoral Thesis ‘Passenger vehicles comfort simulation strategy on an electric Stewart Platform considering damper dynamic models’ is focused on investigating the comfort simulation methodology for passenger vehicles on a Stewart Platform through dynamic modelling of the suspension system. The acquired knowledge is used to improve the driving comfort simulation strategy of an electric Stewart Platform in the 1-10 Hz frequency range.
Aimed at exploring how whole-body vibration transmission influences comfort, performance, and long-term health of the driver, this research is an objective evaluation of passenger vehicles comfort characteristics on a Stewart Platform based on standard mathematical formulae and frequency analyses. Then, vehicle simulators present a multitude of advantages as a tool for ride and comfort analysis in the preliminary stages of the dynamic development of a car. To carry out this analysis, it is necessary to follow the following methodology: first, to develop accurate and computationally efficient vehicle component models. Second, to implement a control strategy on the hexapod that guarantees a fidelity performance in the 1-10 Hz range. Third, to establish a simulation methodology that guarantees equivalent levels of comfort between a simulator and a passenger car.
Concerning the influence of component models on the comfort of passenger vehicles, a simplified nonlinear dynamic model of a twin-tube passive hydraulic damper is proposed. This simplified model is able to simulate the damper behaviour from performance on force-movement tests on a dynamometer based on geometry, flow, and pressure models considering some simplifications regarding temperature, cavitation, and compressibility.
Regarding driving simulators, the advantages of electric servo drive systems in low-cost and high-efficiency, make the be the best choice in many motion simulation applications, However, it is essential to guarantee the accuracy of the platform movement to reach the high standards required by the automotive industry in terms of ride comfort. Therefore, this research proposes a motion control strategy based on the experimental dynamic model of an electric Stewart Platform and on commanded signal modulation through its frequency components identification by means of the autorregressive method that allows to optimize its performance throughout its operating range under real road signals in the 6 degrees-of-freedom (DOF).
In terms of comfort simulation methods, when the motion of a vehicle includes shocks or impulsive speed changes, the Vibration Dose Value (VDV) is considered the most suitable variable for vibration assessment. It provides a measure of the total vibration exposure, taking into account the magnitude, frequency and duration of exposure. Therefore, a comfort simulation methodology has been implemented in an electric Stewart Platform and has been validated by means of the measured VDV at the contact point of the driver and the seat for different driving manoeuvres.
Regarding the results reported in this study, first, the developed dynamic model of damper presents an accuracy greater than 84 % in the rebound cycle and greater that 80 % in the compression cycle compared to the experimental results for all the testing velocities. Second, the experimental control strategy presented for an electric Stewart Platform allows improving the accuracy of the simulator response by more than 50 %. Third, it is verified that the driving simulator allows recreating the vibroacoustic behaviour of a passenger vehicle in the same manoeuvres carried out on the road, reaching deviations of the VDV calculated in the seat of less than 15 % in the three linear axis for all the evaluated manoeuvres.
Las ideas lingüísticas vascas en el siglo XVI (Zaldibia, Garibay, Poza)
(Universidad de Deusto, 1990-02-02) Zubiaur Bilbao, José Ramón; Altuna, Patxi; Facultad de Filosofía y Letras
Nuestro trabajo aspira a ser una aportación a la historia de la Lingüística Vasca, estudiando el que podría ser considerado como su periodo inicial: el siglo XVI, en los tres autores siguientes:
-el Bachiller Martínez de Zaldibia (cap. 2.)
-Esteban de Garibay (cap. 3.)
-el Licenciado Andrés de Poza (cap. 4.)
Estos forman, en nuestra opinión , la primera generación- si se me permite este polémico término -de vascólogos o lingüistas vascos.
Sus obras fueron escritas todas ellas en la segunda mitad del siglo XVI, de 1564, fecha probable de la "Suma de cosas Cantábricas y Guipuzcoanas" del bachiller Zaldibia, a los años 1590-96, los de los últimos escritos del Ldo. Poza o del cronista Garibay.