https://hdl.handle.net/10259/5378 Mon, 17 Aug 2026 10:28:39 GMT 2026-08-17T10:28:39Z https://hdl.handle.net/10259/11961 Activity and Dropout Tracking in Moodle Using UBUMonitor Application Ji, Yi Peng; Marticorena Sánchez, Raúl; Pardo Aguilar, Carlos; López Nozal, Carlos; Juez Gil, Mario Teaching with online learning platforms should simplify the monitoring of students’ activity, particularly when evaluating student dropout. Popular learning environments such as Moodle should implement visual analytic tools that facilitate such tasks, nevertheless, institutions are usually reluctant to incorporate them. This paper presents UBUMonitor, a desktop application that allows the visualization of student’s activity data, extended as a proof of concept with a module for dropout tracking. Therefore, by using UBUMonitor, teachers will be able to easily visualize their students’ engagement with their subject, which can facilitate early action to prevent students from dropping out more effectively. Mon, 01 Aug 2022 00:00:00 GMT https://hdl.handle.net/10259/11961 2022-08-01T00:00:00Z 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/10259/11861 Bioengineering approaches to dynamic impact analysis for cranial fracture interpretation in arcaheology Rodríguez Iglesias, Daniel; Pantoja Pérez, Ana; De la Rosa, Ángel; Latorre Carmona, Pedro; Sala, Nohemi Cranial fractures are widely documented in archaeological contexts, yet the application of fracture mechanics to differentiate traumatic events remains limited. This study analyses a dataset of 234 human cadavers subjected to 329 experimentally controlled blunt-impact tests, examining mechanical variables and fracture patterns that could be relevant to archaeological interpretation. The results show substantial methodological variability across the analysed studies. Analysis of these studies indicates that impact energy is the most reliable parameter for assessing fracture severity, suggesting a preliminary fracture threshold of around 2000 N, and that bone thickness is a major determinant of cranial resistance. Clear differences in fracture morphology according to impact surface were also observed: focal surfaces frequently produce depressed and comminuted fractures, whereas broad surfaces predominantly generate linear fractures. These data provide a framework for archaeological analysis: bone thickness, fracture morphology, and the presence and distribution of secondary fractures offer indirect but informative proxies for impact energy and surface characteristics, which could help to distinguish violent from non-violent events. This study emphasizes the need for dynamic fracture-mechanics approaches and targeted experimental work to better characterise archaeological impacts. Sun, 01 Feb 2026 00:00:00 GMT https://hdl.handle.net/10259/11861 2026-02-01T00:00:00Z https://hdl.handle.net/10259/11430 Semi-supervised prediction of protein fitness for data-driven protein engineering Olivares Gil, Alicia; Barbero Aparicio, José Antonio; Rodríguez Diez, Juan José; Diez Pastor, José Francisco; García Osorio, César; Davari, Mehdi D. Protein fitness prediction plays a crucial role in the advancement of protein engineering endeavours. However, the combinatorial complexity of the protein sequence space and the limited availability of assay-labelled data hinder the efficient optimization of protein properties. Data-driven strategies utilizing machine learning methods have emerged as a promising solution, yet their dependence on labelled training datasets poses a significant obstacle. To overcome this challenge, in this work, we explore various ways of introducing the latent information present in evolutionarily related sequences (homologous sequences) into the training process. To do so, we establish several strategies based on semi-supervised learning (unsupervised pre-processing and wrapper methods) and perform a comprehensive comparison using 19 datasets containing protein-fitness pairs. Our findings reveal that using the information present in the homologous sequences can improve the performance of the models, especially when the number of available labelled sequences is considerably low. Specifically, the combination of a sequence encoding method based on Direct Coupling Analysis (DCA), with MERGE (a hybrid regression framework that combines evolutionary information with supervised learning) and an SVM regressor, outperforms other encodings (PAM250, UniRep, eUniRep) and other semi-supervised wrapper methods (Tri-Training Regressor, Co-Training Regressor). In summary, the demonstrated performance gains of this strategy mark a substantial leap towards more robust and reliable predictive models for protein engineering tasks. This advancement holds the potential to streamline the design and optimisation of proteins for diverse applications in biotechnology and therapeutics. Mon, 01 Dec 2025 00:00:00 GMT https://hdl.handle.net/10259/11430 2025-12-01T00:00:00Z