https://hdl.handle.net/20.500.11984/1143 Sat, 04 Apr 2026 09:30:28 GMT 2026-04-04T09:30:28Z https://hdl.handle.net/20.500.11984/14078 Enhancing the Efficiency of Open-Cathode PEM Fuel Cells: An Experimental Study Aranguren Deriozpide, Jon; Mediavilla Guisasola, Miguel; Oca, Laura; Goikoetxea, Ander; Canales, Jose Maria Open-cathode Proton Exchange Membrane (PEM) fuel cells are a promising solution for small-scale (less than 10kW) portable applications [1]. These compact and cost-effective devices feature a structurally simple design where axial fans simultaneously supply oxygen and regulate stack temperature through forced convection [2]. However, direct exposure of the cathode to ambient conditions creates significant challenges, as fluctuations in air temperature and humidity directly impact system performance and efficiency [3-4]. Thu, 01 Jan 2026 00:00:00 GMT https://hdl.handle.net/20.500.11984/14078 2026-01-01T00:00:00Z https://hdl.handle.net/20.500.11984/14071 CFD investigation of solid content influence on thermal sterilization of canned products Alonso de Mezquia, David; Lapeira, Estela; Bou-Ali, M. Mounir The objective of this study is to analyze the impact of solid particle size on the thermal sterilization process of canned food using Computational Fluid Dynamics (CFD). The study investigates how different particle sizes influence heat transfer efficiency, heating rate, and overall process lethality. A CFD-based model, validated against experimental data, is employed to assess temperature distribution and determine the slowest heating zone (SHZ) for various particle configurations. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/20.500.11984/14071 2025-01-01T00:00:00Z https://hdl.handle.net/20.500.11984/14070 Deep Learning-based age prediction models from retinal Optical Coherence Tomography images Zuazo Atutxa, Garazi; Ayala, Unai; Gabilondo, Iñigo; Barrenechea, Maitane This study evaluates the potential of Optical Coherence Tomog raphy (OCT) as a non-invasive tool for retinal age prediction in healthy individuals. A dataset comprising 1,180 eyes from 517 con trol subjects was used to compare deep learning models trained on different OCT scan types: peripapillary B-scans, individual macula raster B-Scans, and full macular volumes. Images underwent stan dardized preprocessing, and models based on 2D and 3D ResNet architectures were trained and optimized using Transfer Learning. Results show that volumetric macular scans applied in a ResNet 3D model achieved the lowest Mean Absolute Error (3.07 years), outperforming both previous literature and all tested 2D configura tions. Overall, findings highlight that integrating depth and spatial features in OCT data significantly enhances retinal age estimation. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/20.500.11984/14070 2025-01-01T00:00:00Z https://hdl.handle.net/20.500.11984/14061 Predictive modeling of cardiovascular risk factors using OCT and Fundus Images with deep learning techniques Arenzana, Irati; Ruiz, Susana; Díaz, Pablo; Franquesa, Francesc; Muñoz, Rafael; Gómez, Sandra; Sánchez Fortún, Adrian; Popuplana, Àngels; Sabala, Antoni; Mugica, Xabier; Besada, Idoia; Ayala, Unai; Barrenechea, Maitane PURPOSE: The study aims to develop and test predictive models using fundus and Optical Coherence Tomography (OCT) images to detect retinal structural patterns linked to cardiovascular risk factor and events, specifically arterial hypertension (AHT), type II diabetes mellitus (T2D) and dyslipidemia. METHODS: The study included patients over 18 years old registered in the hospital information system, regardless of cardiovascular disease history. Imaging data comprised macula-centered and optic nerve-centered OCT images, as well as 45º or greater fundus images, collected between January 2016 and May 2024. A total of 30,773 OCT images were extracted, including 3,837 OCTs from health subjects, which were used as control group across three predictive models. Cohorts included 6,321 OCTs from patients with AHT, 3,479 from those with T2D and 6,824 from patients with dyslipidemia, with some images overlapping across cohorts due to comorbidities. Three predictive models were developed, each targeting one cardiovascular risk factor. For each cohort, two reference architectures, SwinTransformerV2 and RETFound, were trained and tested to compare their ability to capture structural retinal patterns associated with the studied risk factors. Predictive performance of the models was assessed using the area under the receiver operating characteristic curve (AUC). Thu, 01 Jan 2026 00:00:00 GMT https://hdl.handle.net/20.500.11984/14061 2026-01-01T00:00:00Z