https://hdl.handle.net/10481/13705 2026-04-20T07:35:29Z https://hdl.handle.net/10481/112873 StreakMind: AI detection and analysis of satellite streaks in astronomical images with automated database integration Carrillo Sánchez, Richard Rafael; Duffard, René Damian; García Martín, Pablo; Romero, Javier; Morales, Nicolás; Gonçalves, Luis Context. Artificial satellites and space debris are increasingly contaminating astronomical images, affecting scientific surveys and producing large volumes of streaked exposures. Manual inspection is no longer feasible at scale, and reliable identification and characterisation of streaks has become essential for both the quality control of data and the monitoring of objects in Earth orbit. Aims. We present StreakMind, an automated pipeline designed to detect near-Earth objects (NEOs) and satellite streaks in astronomical images, characterise their geometry, and cross-identify them with known orbital objects. The system integrates all inference results into a structured database suitable for large surveys. Methods. A YOLO-OBB model was trained on a hybrid manual-synthetic dataset of 2335 images and used to detect streaks in processed FITS frames. Geometric refinement, inter-frame association, satellite cross-identification, and Gaussian-based confidence scoring were then applied to produce final identifications, which were stored in a normalised relational database. In this work, images acquired at La Sagra Observatory (L98) with a Celestron C14+Fastar telescope were used to develop and test automated streak detection and characterisation methods. Results. On the test set, the model achieved a precision of 94% and a recall of 97%. It reliably detected faint streaks, delivered consistent geometric reconstructions across the dataset, and performed robust satellite cross-identification. The Gaussian-based confidence scoring provided stable identification probabilities across consecutive frames. Conclusions. StreakMind demonstrates strong potential for large-scale automated analyses of linear streaks produced by both NEOs and artificial satellites in ground-based astronomical images. The pipeline offers high detection reliability, robust geometric reconstruction, and reproducible satellite cross-identification within a fully integrated end-to-end framework. https://hdl.handle.net/10481/112867 Analyzing Late Antiquity Shifts of Trade Regime in the Iberian Peninsula and Their Causes via Change Point Detection Methods Merelo Guervos, Juan Julián History attempts to make sense of disparate information by trying to create discourse that lays a series of events with crisp cause–effect relationships in a sequence. Epochal shifts, such as the change from Antiquity to the Middle Ages, are especially complex since they involve a large number of economic, political and even religious factors which occur over long periods and that might overlap and interact through reciprocal feedback mechanisms, making this cause–effects sequence difficult to establish. In this research we adopt a data-driven and well-established methodology to identify, with quantifiable statistical precision, the moment when this shift happened, and from there arrive at its possible causes. We will use historical coin hoard data to find out whether such a shift is detected in a peripheral part of the Roman Empire, the Iberian Peninsula. To do so, we will apply different changepoint analysis methods to a time series of trade links created from that data, and conduct a retrospective analysis based on that result, analyzing the structure of the trade networks before and after the link. Thus, we progress from identifying when the shift happened to identifying where it took place, which in turn allows us to get to investigate why it happened, namely, historical events that could have caused it. This methodology can be used to analyze epochal changes in several steps using time-stamped network data, possibly finding disregarded causes or cause–effect links that could have been overlooked by qualitative methods; in this case, we have applied it to a dataset of coin hoards either found in the Iberian Peninsula or including coins minted there, finding a changepoint in the early 5th century, which, through network analysis, has been linked to a loss of trade with the area of Britannia https://hdl.handle.net/10481/112339 Remote handling operation for IFMIF-DONES supported by time-sensitive networking Vázquez Rodríguez, Víctor; Valenzuela Segura, Elio; Shepstone, Ricardo; Megías Núñez, Carlos; Miccichè, Gioacchino; Ros Vidal, Eduardo; Barranco Expósito, Francisco Experimental fusion research facilities, such as the International Fusion Materials Irradiation Facility-DEMO Oriented Neutron Source (IFMIF-DONES), require advanced remote handling (RH) systems to perform maintenance and inspection tasks in a safe and reliable manner, due to their intrinsic high-radiation nature. The mixed-criticality requirements of the data streams used in these systems force the deployment of separate networks and communication technologies. Commonly, it includes fieldbuses for traffic control, standard Ethernet for video and general-purpose traffic, and dedicated networks for the most critical safety-related signals. This fragmentation leads to complex and costly deployments and also prevents the application of models for predictive maintenance or advanced monitoring. The time-sensitive networking (TSN) technology stack aims to provide deterministic behaviour for data transmission over standard Ethernet, allowing for convergence on a single network and ensuring bounded latencies for critical traffic. In this work, we propose a design and validate the TSN-based communication architecture for the RH system of IFMIF-DONES. The design ensures bounded delivery times for safety-critical interlock signals, achieving a worst-case delay under 30 us even under high network load. The proposed network is also validated in a real robotic teleoperation task, where artificial intelligence is applied for object detection and tracking, using mixed-criticality video streams. Our results show that TSN traffic shapers are essential in providing the necessary latency and bandwidth guarantees for such teleoperation tasks, enabling network convergence in this kind of deployments. https://hdl.handle.net/10481/112114 Assessing Bias in the Evaluation of Blood Glucose Prediction Models Rodríguez León, Ciro; Avilés-Pérez, María Dolores; Baños Legrán, Oresti; Lopez-Ibarra Lozano, Pablo J.; Muñoz Torres, Manuel Eduardo; Quesada Charneco, Miguel; Villalonga Palliser, Claudia Diabetes mellitus (DM) poses a critical global health challenge, with type 1 diabetes (T1D) patients presenting unique difficulties in maintaining a safe blood glucose level (BGL). This work demonstrates that evaluating BGL prediction models without considering different BGL ranges, hypoglycemia, hyperglycemia, and normoglycemia, introduces bias in assessing the prediction results. Data are obtained from the T1DiabetesGranada dataset, comprising over 22.5 million measured BGL values recorded at 15-min intervals, and are preprocessed into a uniform format for supervised learning. Time series are segmented into windows with a 2-h history length and prediction horizons of 30 and 60 min. An LSTM architecture is used to predict BGL values due to its ability to capture temporal dependencies. The evaluation combines traditional non-clinical metrics (RMSE, MAE, MAPE) with clinical metrics derived from the Clarke Error Grid. The newly proposed evaluation strategy assesses BGL prediction models performance not only across the entire BGL range but also within different BGL ranges. Results indicate that evaluation metrics computed using the entire BGL range may suggest satisfactory BGL prediction model performance. However, significant deficiencies emerge in hypoglycemic ranges, implying that conventional evaluation strategies may overestimate BGL prediction models capabilities. These findings highlight the need for a comprehensive evaluation strategy in different BGL ranges to avoid bias, especially while evaluating clinically critical regions. https://hdl.handle.net/10481/112037 Clustering type 1 diabetes patients based on blood glucose level measurements; Clustering type 1 diabetes patients based on blood glucose level measurements Rodríguez León, Ciro; Avilés-Pérez, M. D.; Baños, Oresti; Lopez-Ibarra Lozano, Pablo J.; Muñoz Torres, Manuel Eduardo; Quesada Charneco, Miguel; Villalonga Palliser, Claudia Improving diabetes mellitus management requires accurate blood glucose predictions to prevent dangerous glycemic extreme events; however, traditional models often struggle with the inherent fluctuations in blood glucose levels. In this work, the identification of distinct patient groups exhibiting common characteristics based on longitudinal continuous glucose monitoring (CGM) data is explored. This clustering approach aims to offer valuable insights for both enhancing predictive modeling accuracy and informing clinical relevance. Raw CGM data was transformed into structured feature sets using statistical descriptors calculated across clinically meaningful time intervals. Following outlier removal, multiple clustering algorithms were evaluated, with the optimal solution selected based on internal metrics and validation by clinical experts. The analysis revealed six distinct patient groups, each characterized by unique glycemic behaviors, including well-controlled, prone to hyperglycemia, and prone to hypoglycemia profiles. It is proposed that these identified clusters can improve glucose prediction by strategically balancing personalized and generalized approaches. Furthermore, valuable insights into individual metabolic variability can be obtained, potentially supporting the development of tailored treatment strategies. While acknowledging limitations inherent in data transformation and expert-driven evaluation, this clustering methodology represents a significant step towards more precise and data-driven diabetes mellitus management.