Doctoral School

Reading date: 18/02/2026

• BORJA ROBALINO, RICARDO STALIN: Optimización bayesiana en técnicas machine Learning clásicas: redes neuronales y XGBoost y su aplicación como modelos predictores de diabetes en pacientes ecuatorianos
  
  Author: BORJA ROBALINO, RICARDO STALIN
  Thesis file: (contact the Doctoral School to confirm you have a valid doctoral degree and to get the link to the thesis)
  Programme: DOCTORAL DEGREE IN STATISTICS AND OPERATIONS RESEARCH
  Department: Department of Statistics and Operations Research (EIO)
  Mode: Normal
  Deposit date: 22/01/2026
  Reading date: pending
  Reading time: pending
  Reading place: pending
  Thesis director: MONLEON GETINO, ANTONIO | GIBERT OLIVERAS, CARINA
  Thesis abstract: Machine learning (ML) is a branch of artificial intelligence that allows human capabilities to be imitated through various algorithms and techniques that learn from data using learning processes (supervised, unsupervised, or reinforcement) for decision-making with minimal human intervention. Classic ML models have generated great results in the automation of classification and regression processes in various areas. Within classification, artificial neural networks (ANN) have gained relevance due to their ability to learn and model complex nonlinear relationships. Similarly, the XGBoost model based on decision trees has demonstrated great efficiency, speed, scalability, and performance, winning several competitions. On the other hand, Bayesian inference has provided a probabilistic and revolutionary framework for optimizing machine learning models, with the implementation of uncertainty in the estimation process, combining evidence with prior beliefs, in order to reduce overfitting and improve predictions by adjusting parameters and hyperparameters.This research aims to optimize two classic machine learning techniques (artificial neural networks and XGBoost) for classification using Bayesian inference and to build a diabetes prevention model for the Ecuadorian population. The study begins with a theoretical and mathematical conceptualization of each algorithm, followed by an analysis of the various points of intervention, programming, and implementation of Bayesian models using Markov chain Monte Carlo (MCMC) estimation techniques and variational inference (VI), validation using public databases, implementation of a client-server system with multiple specialized backends, and, finally, the development of a real application as predictors of type 1, type 2, and gestational diabetes.As a result, a Bayesian model was implemented in artificial neural networks (ANN) at two inference points. The first adjusted the parameters at each backpropagation step; however, it presented itself as an option with a prohibitive computational overhead. As a second intervention, an adjustment was made to the activation function in the final layer, obtaining positive and computationally viable results. In the case of XGBoost, the predictions were adjusted at each boosting step before vectorization, demonstrating high predictive power in both the use of the MCMC technique and IV. Validation with the Pima Indians Diabetes database and the use of various distribution functions demonstrated the robustness and sensitivity of the implemented models, while generalization and consistency were verified through application to various databases. In all cases, results superior to or equal to those obtained using the traditional model were obtained, depending on the characteristics of the data.In addition, a web application (client-server) was implemented with Bayesian proposals, allowing users to interact with the models in an easy and intuitive way, with options for data loading, parameter configuration and probability distributions, estimation techniques (MCMC or IV), training-validation process or use of cross-validation, real-time results, and model download options. The application of the Bayesian proposal to a real case, such as the prediction of type 1, type 2, and gestational diabetes, with data from Ecuadorian patients, presented encouraging results (accuracy = 99.47%), becoming the first predictive model for the three types of diabetes at the regional and national level, confirming that the use of this approach is an excellent alternative for the optimization of machine learning models.
  

• CASTRO CARRASCO, REBECA IGNACIA: Characterization of sulfate-reducing biofilms using an amperometric printed H₂S sensor
  
  Author: CASTRO CARRASCO, REBECA IGNACIA
  Thesis file: (contact the Doctoral School to confirm you have a valid doctoral degree and to get the link to the thesis)
  Programme: DOCTORAL DEGREE IN NATURAL RESOURCES AND THE ENVIRONMENT
  Department: Department of Mining, Industrial and ICT Engineering (EMIT)
  Mode: Normal
  Deposit date: 22/01/2026
  Reading date: pending
  Reading time: pending
  Reading place: pending
  Thesis director: GABRIEL BUGUÑA, GEMMA | GUIMERÀ VILLALBA, XAVIER
  Thesis abstract: A comprehensive understanding of sulfidogenic processes in bioreactors remains incomplete by the limited availability of tools suitable for the sulfate-reducing activity characterization of immobilized biomass. To address this limitation, the present work is based on developing suitable alternatives for sulfate reducing biomass characterization using electrochemical microsensors. In this sense, a flow-cell bioreactor was developed for real-time monitorization using artificially immobilized biomass to substitute the natural immobilization derived from extracellular polymeric compounds. Physical and functional evaluations enabled the identification of a polymer–biomass matrix capable of preserving sulfate-reducing performance while ensuring adequate microbial retention and structural integrity, as well as a range of operational conditions was assessed to generate detailed H₂S production profiles within the flow-cell bioreactor. In parallel, an inkjet-printed H₂S microsensor was fabricated on polyethylene terephthalate substrates using silver and gold inks and modified with Single-walled carbon nanotubes reinforced with Polyvinyl alcohol and Polydiallyldimethylammonium chloride, which improved ink dispersion, adhesion, and mechanical stability. The optimized formulation yielded long-term operational stability, linear responses across different media, and performance comparable to commercial microsensors despite an initial decrease in sensitivity. Furthermore, the study evaluated the operational behavior of artificial sulfate-reducing granules in column and continuous stirred tank reactors, demonstrating high sulfate removal efficiencies at moderate loading rates, superior stability in column configurations, accumulation of volatile fatty acids associated with incomplete glycerol oxidation, and the effectiveness of a bioaugmentation strategy based on acetate-oxidizing sulfate reducing bacteria immobilized in artificial granules. Lastly, the integrated platform was validated for the analysis of H₂S production in immobilized sulfate-reducing biofilms, combining the flow-cell bioreactor with direct ink writing printed microsensors for simultaneous, in situ monitoring of H₂S and pH. Three-dimensional mapping revealed pronounced H₂S gradients driven by mass-transfer limitations and hydrodynamic dispersion, while printed electrodes exhibited linear amperometric responses and stable performance over extended operation, thereby confirming the suitability of the proposed platform for high-resolution, real-time characterization of sulfidogenic biofilms and immobilized sulfate-reducing biomass.
  

• FERNANDEZ GONZALEZ, POL: Structural and functional characterization of rhodopsin mutants associated with retinitis pigmentosa and their modulation by small molecules
  
  Author: FERNANDEZ GONZALEZ, POL
  Thesis file: (contact the Doctoral School to confirm you have a valid doctoral degree and to get the link to the thesis)
  Programme: DOCTORAL DEGREE IN AGRI-FOOD TECHNOLOGY AND BIOTECHNOLOGY
  Department: Department of Agri-Food Engineering and Biotechnology (DEAB)
  Mode: Normal
  Deposit date: 09/01/2026
  Reading date: 18/02/2026
  Reading time: 15:00
  Reading place: Sala de conferències de l'edifici TR5 de l'ESEIAAT. Carrer de Colom, 1, 08222 Terrassa, Barcelona
  Thesis director: GARRIGA SOLE, PERE
  Thesis abstract: G protein-coupled receptors constitute the largest superfamily of membrane proteins in mammals and play essential roles in signal transduction. Among them, rhodopsin serves as the primary photoreceptor in rod cells, mediating vision under dim light conditions. Mutations in the rhodopsin gene are the leading cause of retinitis pigmentosa, an inherited retinal degenerative disease characterized by progressive photoreceptor death and eventual blindness. Despite the severity of this condition, therapeutic options remain limited, making the development of novel stabilization strategies crucial. This thesis presents a comprehensive investigation of retinitis pigmentosa-associated rhodopsin mutations and evaluates the therapeutic potential of small molecule stabilizers as pharmacological chaperones. Through systematic biochemical, biophysical, and structural analyses, we characterized three pathogenic mutations located in transmembrane helix 3 (T108P and G121R) and the N-terminal region (M39R), revealing distinct molecular mechanisms underlying photoreceptor dysfunction. The T108P mutation preserved protein trafficking and chromophore binding but exhibited reduced thermal stability and severely impaired G protein activation due to conformational rigidity of the ERY motif. In contrast, G121R displayed features of a misfolding phenotype with complete loss of chromophore binding and partial intracellular retention, likely triggering endoplasmic reticulum stress-mediated apoptosis. The M39R variant, associated with sector retinitis pigmentosa, showed slightly reduced folding efficiency but partial significant preservation of native-like structure.Analysis of the G90V mutation, in transmembrane helix II, in a conformationally stabilized background (with the engineered N2C/D282C disulfide bond) demonstrated that while structural stabilization enhanced thermal and chemical resistance, it could not rescue the fundamental photoactivation defects. Solid-state nuclear magnetic resonance spectroscopy revealed subtle perturbations in retinal configuration and reduced conformational flexibility in key structural elements.Finally, evaluation of geraniol as a potential pharmacological chaperone showed promising results, enhancing M39R rhodopsin thermal stability without affecting chromophore regeneration, photobleaching, or activation dynamics. Its hydrophobic nature suggests interaction with the opsin membrane environment, establishing it as a candidate for further therapeutic development.Molecular dynamics simulations provided atomic-level insights into mutation-induced conformational changes, supporting experimental findings and revealing how subtle structural alterations lead to distinct pathogenic outcomes. Additionally, we successfully developed and optimized protocols for rhodopsin expression, purification, and solid-state nuclear magnetic resonance analysis, establishing a promising methodological framework applicable to other G protein-coupled receptors.These findings advance our understanding of rhodopsin-associated retinal degeneration mechanisms and demonstrate the feasibility of small molecule stabilization as a therapeutic strategy. The work provides a foundation for developing targeted interventions for retinitis pigmentosa and potentially other G protein-coupled receptors-related disorders, while highlighting the importance of mutation-specific therapeutic approaches.
  

• MUÑOZ GALAN, HELENA: Sensor design and development for autonomous devices for disease diagnosis and therapy
  
  Author: MUÑOZ GALAN, HELENA
  Thesis file: (contact the Doctoral School to confirm you have a valid doctoral degree and to get the link to the thesis)
  Programme: DOCTORAL DEGREE IN POLYMERS AND BIOPOLYMERS
  Department: Department of Chemical Engineering (EQ)
  Mode: Normal
  Deposit date: 22/01/2026
  Reading date: pending
  Reading time: pending
  Reading place: pending
  Thesis director: ALEMAN LLANSO, CARLOS ENRIQUE | PÉREZ MADRIGAL, MARIA DEL MAR
  Thesis abstract: This doctoral research addresses key challenges in diabetes management by integrating sustainable materials, non-invasive sensing, and advanced insulin delivery technologies into a unified framework. Diabetes mellitus is a chronic metabolic disorder that requires continuous glucose monitoring and precise insulin administration to maintain glycemic control and reduce complications. Responding to these needs, the thesis is structured around three major contributions.First, the work advances the development of a previously created non-invasive glucose-monitoring device by incorporating recycled low-density polyethylene (LDPE) into the sensor design. The use of recycled LDPE improves sustainability, cost-efficiency, and environmental compatibility while maintaining reliable sensing performance. This demonstrates the feasibility of repurposing plastic waste in biomedical technologies without compromising functionality.Second, the research explores new strategies for controlled insulin delivery through stimuli-responsive hydrogels. Hydrogels based on poly(γ-glutamic acid) and multi-armed polyethylene glycol (PEG) were engineered to achieve sustained and tunable insulin release. The incorporation of poly(3,4-ethylenedioxythiophene) (PEDOT), a biocompatible conducting polymer, enables electrically triggered and on-demand insulin delivery. This approach offers a minimally invasive alternative to conventional injection-based therapies and highlights the potential of electro-responsive materials in smart drug-delivery systems.Finally, the thesis investigates the nanomechanical properties of multi-armed PEG hydrogels using a microcantilever-based optomechanical sensor. This analysis provides essential insights into the structural behavior, stability, and long-term performance of the hydrogels, contributing to the optimization of their mechanical robustness and responsiveness.Together, these contributions form a comprehensive strategy for improving diabetes care. By integrating non-invasive monitoring, environmentally conscious materials, and intelligent delivery platforms, the research promotes more sustainable biomedical solutions while advancing patient-centered therapeutic tools.
  

Reading date: 19/02/2026

• MEDRANO DÍAZ, MANUEL ALEJANDRO: Estimación de series de tiempo de imágenes mediante técnicas de aprendizaje profundo
  
  Author: MEDRANO DÍAZ, MANUEL ALEJANDRO
  Thesis file: (contact the Doctoral School to confirm you have a valid doctoral degree and to get the link to the thesis)
  Programme: DOCTORAL DEGREE IN AUTOMATIC CONTROL, ROBOTICS AND VISION
  Department: Department of Automatic Control (ESAII)
  Mode: Change of supervisor
  Deposit date: 20/01/2026
  Reading date: 19/02/2026
  Reading time: 16:00
  Reading place: Aula Maestría de Ciencias de la Computación, Instituto Tecnológico de Culiacán, MéxicoEnlace Videoconferencia: https://meet.google.com/cya-jyje-zeq
  Thesis director: PUIG CAYUELA, VICENÇ | RODRÍGUEZ RANGEL, HÉCTOR
  Thesis abstract: An image time series (ITS) is a chronologically ordered sequence of images showing the spatial change of its elements over time. Satellite images of meteorological events can be treated as ITS by displaying their values through pixel color intensity.Estimating from a ITS with a deep learning model is a complex problem that requires analyzing various configurations that determine how images are processed. It is a computationally intensive problem, which, due to its non-deterministic characteristics, requires combining different parameter configurations to extract spatio-temporal relationships. Thus, the complexity of the problem increases as the dimensions to be evaluated increase.To solve this problem, a robust and scalable conceptual model for ITS estimation is proposed that extracts the spatiotemporal relationships between pixels and their neighborhoods. Based on the specifications of the proposed model, a methodological proposal is developed that allows the estimation of meteorological maps using deep learning models. The proposed methodology is implemented through the design of a software architecture that translates abstract elements into software components, allowing the methodology to be evaluated through the use of deep learning models in different case studies.In the case study of the United States (US) drought monitor, experimentation with deep learning models based on ConvLSTM and Multi-CNN mostly yielded an F1-score of over 0.90 for the estimation of step t+1, with the best model obtaining an F1-score of 0.9953. Due to the high memory demand of the data dimensions, together with the physical limitations of the hardware equipment, dimension reduction techniques were applied to the images. Using the fragmentation technique with the ConvLSTM architecture, an F1-score of 0.9684 was obtained by reducing the dimension of the samples by 48%. By applying recursive and direct multi-step estimation strategies, medium-term estimates could be made. However, due to the complexity of the spatiotemporal analysis, there is an accumulated error that affects the quality of the medium-term estimate.In a second case study on US standardized precipitation index (SPI) maps, a ConvLSTM architecture is used to estimate step t+1. The results show that the best learning model obtains an F1-score of 0.5268, while the Naïve model obtains an F1-score of 0.3408. The results demonstrate the capabilities of deep learning models to extract spatiotemporal relationships from a sequence of images, laying the foundation for a branch of research focused on image estimation.