https://hdl.handle.net/10259/5378 2026-10-12T01:24:31Z https://hdl.handle.net/10259/12057 Dilated residual U-Net with spatial–channel attention for building footprint extraction from UAV imagery in diverse landscapes Pham, Dung T.; Tran, Duy X.; Tran, Thuong V.; Latorre Carmona, Pedro; Bruce, David; Zhu, Xuan Accurate extraction of building footprints from unmanned aerial vehicle (UAV) imagery is essential for urban planning, infrastructure monitoring, and disaster risk management. However, segmentation performance remains challenged by scale variability, spectral ambiguity, and partial occlusion in heterogeneous environments. Here, we examine the integration of dilated convolution, residual learning, and spatial–channel attention within a unified U-Net framework for building footprint extraction. Rather than introducing new architectural components, the proposed approach investigates how these established mechanisms influence segmentation behaviour across diverse landscape conditions. Multi-rate dilated convolution is incorporated in the bottleneck stage; residual connections support stable feature propagation, and attention modules enhance feature discrimination. The model was evaluated on the WHU Building Dataset and a newly developed UAV dataset (HUMG) representing diverse environmental conditions in Vietnam. Results showed improved segmentation performance relative to U-Net, Feature Pyramid Network, and SegFormer, particularly in dense urban, rural, and vegetation-occluded environments. Although the proposed model incurs higher computational costs, the additional complexity reflects both increased model capacity and integrated architectural design. The findings demonstrate that systematic adaptation of established mechanisms can enhance building segmentation robustness in high-resolution UAV imagery for offline geospatial applications. 2026-08-01T00:00:00Z 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. 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 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. 2026-02-01T00:00:00Z