Search

Tesis doctoral en período de exposición pública, Para la consulta de la tesis acudir a la Escuela de Doctorado, Ingeniería y Tecnologías Industrial, Informática y Civil

Las Jornadas en Enseñanza Universitaria en Informática (JENUI) se han venido desarrollando a lo largo de tres décadas, desde el año 1994 a la actualidad. En dicho periodo, la temática abordada ha evolucionado, cambiando el ámbito y tema de los trabajos, en función del progreso de la informática y su enseñanza en el ámbito universitario. La técnica de aprendizaje no supervisado sobre texto, denominada modelo de temas (topic model), mejora la comprensión de grandes cantidades de datos textuales agrupando los documentos en temas. El presente trabajo aplica esta técnica procesando las actas completas de JENUI con sus 1745 documentos. Partiendo de la extracción del texto de títulos y resúmenes, se aplica el algoritmo de Latent Dirichlet Allocation (LDA), estimando el número óptimo de temas. El trabajo construye un clasificador temático con los artículos de JENUI. Además, analiza la distribución de temas y las probabilidades de los términos de cada tema junto con la evolución temática de los trabajos a largo del tiempo. Desde una perspectiva más objetiva y científica, se concluye que existe una evolución temática, a lo largo de las 27 ediciones con actas de JENUI., The JENUI (Jornadas en Enseñanza Universitaria en Informática) have been held for three decades, from 1994 to the present day. During this period, the subject matter has evolved, changing the scope and topic of the papers, depending on the progress of computer science and its teaching at university level. The unsupervised text-based learning technique, known as the topic model, improves the understanding of large amounts of textual data by grouping documents into topics. This paper applies this technique by processing the complete proceedings of JENUI with its 1745 documents. Starting from the extraction of text from titles and abstracts, the Latent Dirichlet Allocation (LDA) algorithm is applied, estimating the optimal number of topics. The work constructs a topic classifier with the JENUI articles. In addition, it analyses the distribution of topics and the probabilities of the terms of each topic together with the topic evolution of the papers over time. From a more objective and scientific perspective, it is concluded that there is a thematic evolution over the 27 editions with JENUI proceedings.

En este artículo se presenta la herramienta docente VASS, una aplicación web diseñada para facilitar la enseñanza de algoritmos de aprendizaje semisupervisado. El aprendizaje semisupervisado es una técnica, relativamente novedosa dentro del aprendizaje automático, que, además de los datos etiquetados, utiliza datos no etiquetados para mejorar el rendimiento de los modelos de aprendizaje automático. Esto es especialmente necesario en los contextos en los que la adquisición de datos etiquetados es laboriosa o muy costosa. VASS (visualizador de algoritmos semisupervisados) tiene una interfaz intuitiva que permite a los usuarios entrenar y visualizar el funcionamiento interno de cuatro algoritmos semisupervisados clave: Self-Training, Co-Training, Tri-Training y Democratic Co-Learning. La aplicación se ha desarrollado pensando en su utilidad en entornos educativos, proporcionando a estudiantes y profesores una herramienta valiosa para explorar y comprender estos conceptos fundamentales. VASS no solo busca mejorar la accesibilidad a los algoritmos semisupervisados, sino también fomentar una comprensión más profunda de su funcionalidad., This article presents the VASS teaching tool, a web application designed to facilitate the teaching of semisupervised learning algorithms, a relatively new technique in machine learning that, in addition to labeled data, uses unlabeled data to improve the performance of machine learning models. This is especially necessary in those contexts where the acquisition of labeled data is laborious or very expensive. VASS (Visualizer of semisupervised Algorithms) has an intuitive interface that allows users to train and visualize the inner workings of four key semisupervised algorithms: Self-Training, Co-Training, Tri-Training and Democratic Co-Learning. The application has been developed with its usefulness in educational environments in mind, providing students and teachers with a valuable tool to explore and understand these fundamental concepts. VASS not only seeks to improve the accessibility of semisupervised algorithms, but also to foster a deeper understanding of their functionality.

The consolidation of telerehabilitation for the treatment of many diseases over the last decades is a consequence of its cost-effective results and its ability to offer access to rehabilitation in remote areas. Telerehabilitation operates over a distance, so vulnerable patients are never exposed to unnecessary risks. Despite its low cost, the need for a professional to assess therapeutic exercises and proper corporal movements online should also be mentioned. The focus of this paper is on a telerehabilitation system for patients suffering from Parkinson’s disease in remote villages and other less accessible locations. A full-stack is presented using big data frameworks that facilitate communication between the patient and the occupational therapist, the recording of each session, and real-time skeleton identification using artificial intelligence techniques. Big data technologies are used to process the numerous videos that are generated during the course of treating simultaneous patients. Moreover, the skeleton of each patient can be estimated using deep neural networks for automated evaluation of corporal exercises, which is of immense help to the therapists in charge of the treatment programs., This work was supported by project PI19/00670 of the Ministerio de Ciencia, Innovación y Universidades, Instituto de Salud Carlos III, Spain. The authors gratefully acknowledge the support of the NVIDIA Corporation and its donation of the TITAN Xp GPU used in this research. In addition, this work was partially supported by the European Social Fund, as the authors José Miguel Ramírez-Sanz, José Luis Garrido-Labrador, and Alicia Olivares-Gil are the recipients of a pre-doctoral grant (EDU/875/2021) from the Conserjería de Educación de la Junta de Castilla y León.

Artículo de revisión, Gait abnormalities are a hallmark of Parkinson’s disease and contribute to falling risk. As disease symptoms progress, assistive devices are often prescribed. However, there are no guidelines for choosing appropriate ambulatory devices for gait impairment., This work was supported by the project PI19/00670 of the Ministerio de Ciencia, Innovación y Universidades, Instituto de Salud Carlos III, Spain. The authors declare that there are no additional disclosures to report relevant to this work.

[EN] Understanding the scientific and social structure of a discipline is a fundamental aspect for scientific evaluation processes, identifying trends and niches, and balancing the trade-off between exploitation and exploration in research. In the present contribution, the production of doctoral theses is used as a proxy to analyze the scientific structure of the knowledge area of business organization in Spain. To that end, a complex networks approach is selected, and two different networks are built: (i) the social network of co-participation in thesis examining committees and thesis supervision, and (ii) a bipartite network of theses and thesis descriptors. The former has a modular structure that is partially explained by thematic specialization in different subdisciplines. The latter serves to assess the interdisciplinary structure of the discipline, as it enables the characterization of affinity levels between fields, research poles and thematic clusters. Our results have implications for the scientific evaluation and formal definition of related fields.

Understanding the scientific and social structure of a discipline is a fundamental aspect for scientific evaluation processes, identifying trends and niches, and balancing the trade-off between exploitation and exploration in research. In the present contribution, the production of doctoral theses is used as a proxy to analyze the scientific structure of the knowledge area of business organization in Spain. To that end, a complex networks approach is selected, and two different networks are built: (i) the social network of co-participation in thesis examining committees and thesis supervision, and (ii) a bipartite network of theses and thesis descriptors. The former has a modular structure that is partially explained by thematic specialization in different subdisciplines. The latter serves to assess the interdisciplinary structure of the discipline, as it enables the characterization of affinity levels between fields, research poles and thematic clusters. Our results have implications for the scientific evaluation and formal definition of related fields., Spanish Ministry of Science, Innovation and Universities (RED2018-102518-T), the Spanish State Research Agency (PID2020-118906GB-I00 and PID2020-119894GB-I00 via AEI/10.13039/501100011033), the Junta de Castilla y León – Consejería de Educación (BU055P20), Fundación La Caixa (2020/00062/001) and from NVIDIA Corporation and its donation of the TITAN Xp GPUs that facilitated this research. This work was partially supported by the European Social Fund, as the authors José Miguel Ramírez-Sanz, José Luis Garrido-Labrador and Alicia Olivares-Gil are the recipient of a predoctoral grant from the Department of Education of Junta de Castilla y León (VA) (ORDEN EDU/875/2021). In addition, this work was also partially supported by the Generalitat Valenciana via its Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital, as Adrián Arnaiz is recipicient of a predoctoral grant.