https://hdl.handle.net/10259/4219 Sat, 11 Jul 2026 18:46:12 GMT 2026-07-11T18:46:12Z https://hdl.handle.net/10259/11886 The role of awareness and gamification on technical debt management Crespo, Yania; López Nozal, Carlos; Marticorena Sánchez, Raúl; Gonzalo Tasis, Margarita; Piattini, Mario Managing technical debt and developing easy-tomaintain software are very important aspects for technological companies. Integrated development environments (IDEs) and static measurement and analysis tools are used for this purpose. Meanwhile, gamification also is gaining popularity in professional settings, particularly in software development. Objective. This paper aims to analyse the improvement in technical debt indicators due to the use of techniques to raise developers’ awareness of technical debt and the introduction of gamification into technical debt management. Method. A quasi-experiment that manipulates a training environment with three different treatments was conducted. The first treatment was based on training in the concept of technical debt, bad smells and refactoring, while using multiple plugins in IDEs to obtain reports on quality indicators of both the code and the tests. The second treatment was based on enriching previous training with the use of SonarQube to continuously raise awareness of technical debt. The third was based on adding a gamification component to technical debt management based on a contest with a top ten ranking. The results of the first treatment are compared with the use of SonarQube for continuously raising developers’ awareness of technical debt; while the possible effect of gamification is compared with the results of the previous treatment. Results. It was observed that continuously raising awareness using a technical debt management tool, such as SonarQube, significantly improves the technical debt indicators of the code developed by the participants versus using multiple code and test quality checking tools. On the other hand, incorporating some kind of competition between developers by defining a contest and creating a ranking does not bring about any significant differences in the technical debt indicators. Conclusions. Investment in staff training through tools to raise developers’ awareness of technical debt and incorporating it into continuous integration pipelines does bring improvements in technical debt management. Sat, 01 Oct 2022 00:00:00 GMT https://hdl.handle.net/10259/11886 2022-10-01T00:00:00Z https://hdl.handle.net/10259/11884 Processing and analysis of portable EEG data for cognitive load assessment in neurotypical university students Sáiz Manzanares, María Consuelo; Ortega Renuncio, Raúl; Marticorena Sánchez, Raúl The use of electroencephalogram (EEG) to gain insight into cognitive and metacognitive processing during task execution is being pioneered in natural learning contexts; an opportunity not without its challenges. Accordingly, a pilot study was conducted to explore the feasibility of this approach. The aims of this study were: (1) to demonstrate how raw data extracted from an EEG device may be processed; (2) to determine whether there were differences in pre-task cognitive load between senior university students (Group 1), novice university teachers (Group 2) and experienced university teachers (Group 3); (3) To determine whether the peak power (μV2) per brain band (Delta, Theta, Alpha, Beta and Gamma) recorded during task performance was different depending on the type of participant; (4) To determine whether there were un-labelled groupings (clusters), and whether they corresponded to the type of participant. The raw data were processed using the MNE-Python toolkit. No significant differences were found in the perception of cognitive load or in peak power with respect to participant type. However, different frequencies of maximum activation of brain channels in the Delta wave were found by participant type. The largest overlaps were found between Group 1 and Group 2. Future studies will address the influence of other variables such as age, gender, type of studies and cranial tomography. In addition, 3D analyses with integration of brain surfaces and sensors will be applied. Sun, 01 Mar 2026 00:00:00 GMT https://hdl.handle.net/10259/11884 2026-03-01T00:00:00Z https://hdl.handle.net/10259/11881 Remote sensing colour image semantic segmentation of large herbivorous mammal trails Diez Pastor, José Francisco; González Moya, Francisco Javier; Latorre Carmona, Pedro; Pérez-Barbería, Francisco Javier; Kuncheva, Ludmila I. .; Canepa Oneto, Antonio Jesús; Arnaiz González, Álvar; García Osorio, César Detection of spatial areas where biodiversity is at risk is of paramount importance for the conservation and monitoring of ecosystems. Large terrestrial mammalian herbivores are keystone species as their activity not only has deep effects on soils, plants, and animals but also shapes landscapes, as large herbivores act as allogenic ecosystem engineers. One key landscape feature that indicates intense herbivore activity and potentially impacts biodiversity is the formation of grazing trails. Grazing trails are formed by the continuous trampling activity of large herbivores that can produce complex networks of tracks of bare soil. Here, we evaluated different algorithms based on machine learning techniques to identify grazing trails. Our goal is to automatically detect potential areas with intense herbivory activity, which might be beneficial for conservation and management plans. We have applied five semantic segmentation methods combined with fourteen encoders aimed at mapping grazing trails on aerial images. Our results indicate that in most cases the chosen methodology successfully mapped the trails, although there were a few instances where the actual trail structure was underestimated. The UNet architecture with the MambaOut encoder was the best architecture for mapping trails. The proposed approach could be applied to develop tools for mapping and monitoring temporal changes in these landscape structures to support habitat conservation and land management programmes. This is the first time, to the best of our knowledge, that competitive image segmentation results are obtained for the detection and delineation of trails of large herbivorous mammals.Footnote Sun, 01 Feb 2026 00:00:00 GMT https://hdl.handle.net/10259/11881 2026-02-01T00:00:00Z https://hdl.handle.net/10259/11804 Análisis de registros multicanal en el comportamiento humano Sáiz Manzanares, María Consuelo; Marticorena Sánchez, Raúl; García García, David Este manual especializado, enmarcado en el Máster de Ingeniería Biomédica de la Universidad de Burgos, ofrece una guía rigurosa para el estudio del comportamiento humano mediante registros multicanal. A través de un enfoque interdisciplinar, la obra fusiona la ingeniería con las ciencias de la salud para dotar al lector de las herramientas metodológicas necesarias en la captura y análisis de señales fisiológicas complejas. El lector encontrará un análisis profundo de tecnologías de vanguardia como el eye tracking, la electroencefalografía (EEG) y la respuesta psicogalvánica (GSR). Además, el texto aborda el procesamiento avanzado con MNE-Python y el uso de Machine Learning para la interpretación de datos. Con un enfoque práctico basado en proyectos y una reflexión necesaria sobre la ética en la IA generativa, esta obra es la referencia definitiva para profesionales e investigadores que buscan liderar la innovación tecnológica en entornos clínicos e industriales. Mon, 01 Jun 2026 00:00:00 GMT https://hdl.handle.net/10259/11804 2026-06-01T00:00:00Z