Repositorio da Universidade da Coruña
Not a member yet
35055 research outputs found
Sort by
De abajo a arriba. El espacio del conocimiento local en la gobernanza de los incendios forestales
Esta publicación es parte del proyecto de I+d+I PID2019-107443RA-I00, financiado por MCIN/AEI/10.13039/50110001103
Fully-automatic end-to-end approaches for 3D drusen segmentation in Optical Coherence Tomography images
Presented at: 28th International Conference on Knowledge Based and Intelligent information and Engineering Systems (KES 2024)[Abstract]: Drusen, small lipid deposits located below the retina, are early biomarkers of age-related macular degeneration (AMD), a condition that leads to visual impairment worldwide, especially among the elderly. The presence of AMD is linked with Alzheimer’s Disease (AD) and dense deposit disease (DDD), emphasizing the critical need for early and accurate detection of drusen in retinal tissues. Optical Coherence Tomography (OCT), with its non-invasive and high-resolution imaging capabilities, stands as a pivotal tool for early AMD diagnosis through the identification of drusen. However, the reliance on manual segmentation of drusen in 3D OCT images introduces significant challenges: it is not only time-consuming but also subject to inter-observer variability, severely constraining its efficacy for widespread screening applications. These limitations underscore the critical need for an automated solution that can improve diagnostic workflows, ensure consistency across interpretations, and facilitate the processing of large datasets with improved accuracy and efficiency. In response, we propose a new deep learning-based, fully-automatic end-to-end approach for the segmentation of drusen in 3D OCT volumes.
Complementary, a pivotal aspect of our research involves the first detailed comparative analysis between 2D and 3D end-to-end approaches. This comparison is crucial for understanding the impact of dimensional spatial information on the accuracy of drusen segmentation within OCT scans. The findings demonstrate that the 3D approach, by leveraging the depth and complexity of spatial data available in 3D OCT volumes, markedly surpasses the 2D approach. This superior performance underlines the importance of 3D spatial information in enhancing diagnostic precision. Through automating the segmentation process, our proposal not only makes AMD screening more efficient and precise but also significantly advances the diagnosis of retinal diseases, potentially enriching our understanding of systemic conditions connected through retinal biomarkers.This work was supported by Ministerio de Ciencia e Innovacion, Government of Spain through the research project with [grant numbers PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educacion, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24] and predoctoral grant [grant number ED481A-2023-152]. Furthermore, this work was supported by the Instituto de Salud Carlos III (ISCIII) under the grant [FORT23/00010] as part of the Programa FORTALECE del Ministerio de Ciencia e Innovacion.Xunta de Galicia; ED431C 2020/24Xunta de Galicia; ED481A-2023-15
Deep Learning-Based Approaches for Ciliary Muscle Segmentation and Biomarker Extraction
Presentado en: XX Conferencia de la Asociación Española para la Inteligencia Artificial, A Coruña, 19 - 21 de Junio de 2024 (CAEPIA 2024)[Abstract]: This paper highlights our recently published work that involves the application of deep learning techniques to perform the segmentation of the ciliary muscle in Anterior Segment Optical Coherence Tomography (AS-OCT) images. The ciliary muscle is vital for various anterior segment of the eye functions, including intraocular pressure regulation and lens shape maintenance. To advance research, we propose a fully automatic method for segmenting and measuring ciliary muscle biomarkers in 6 mm and 16 mm scan depths, commonly used in clinical analysis. Our approach ensures repeatable and immediate results through thorough exploration of artificial intelligence approaches combining different network architectures, encoders, data augmentation and transfer learning strategies. Additionally, we extract relevant biomarkers, aiding in diagnoses and monitoring of ocular diseases such as glaucoma, myopia, and presbyopia, and facilitating the development of new therapeutic strategies. With high accuracy values (0.9665 ± 0.1280 and 0.9772 ± 0.0873 for the best 6 mm and 16 mm combinations, respectively), our system provides clinicians and researchers with a valuable, automatic tool for ciliary muscle segmentation and analysis in AS-OCT images.This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers RTI2018-095894-B-I00,
PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educacioó, Universidade, e Formación Profesional, Xunta de Galicia,
Grupos de Referencia Competitiva, [grant number ED431C 2020/24], predoctoral grant [grant number ED481A-2023-152].Xunta de Galicia; ED431C 2020/24Xunta de Galicia; ED481A-2023-15
From liquid migrations to rootedness: Plans to make the move permanent among recent Spanish emigrants to other European countries
Este artículo forma parte de los resultados del proyecto de investigación PID2019-105041RA-I00 financiado por MCIN/AEI/10.13039/501100011033[Resumen]: La emigración española hacia Europa, surgida tras la crisis económica de 2008, se describió como una migración fluida y transitoria, conocida como migración líquida. En efecto, el punto de partida de esta movilidad para muchos jóvenes españoles venía marcado por procesos como la emancipación familiar, la ampliación de estudios o la incorporación al mercado laboral. Ha pasado ya más de una década desde que algunos de estos jóvenes se marcharon y protagonizaron una transición entre la juventud y la madurez. Este artículo analiza qué motivos han provocado la transición vital desde un proyecto migratorio temporal hacia una migración permanente, una cuestión que ha recibido menor atención en la literatura académica. Los motivos de anclaje pueden resumirse en tres tipos: estar motivados por la consolidación laboral y económica, estar motivados por cuestiones vinculadas al ciclo de vida familiar (tener pareja e hijos en destino) y también a motivos involuntarios que hacen imposible el regreso a España. La metodología utilizada es de carácter cualitativo y analizará 38 entrevistas en profundidad a emigrantes españoles residentes en el Reino Unido y Francia con un proyecto migratorio de permanencia.[Abstract]: Spanish emigration to the rest of Europe following the economic crisis of 2008 has been described as a fluid and transitory migration, known as liquid migration. Indeed, the start-ing point for this mobility for many young Spaniards was marked by processes such as independence from the family, higher education, or joining the labour market. More than a decade has passed since some of these young people left and made the transition from youth to maturity. This article analyses the reasons that have triggered the essential transi-tion from temporary to permanent migration, an issue that has received less attention in the academic literature. The reasons for permanent migration can be summarised in three categories: employment and economic security; family reasons (having a partner and chil-dren at the destination); and non-voluntary reasons that make it impossible to return to Spain. The methodology used is qualitative, analysing 38 in-depth interviews with Spanish emigrants living in the United Kingdom and France who intend to stay there permanently
Networks of sexual exploitation: the use of new technologies to weave trafficking networks
[Resumen] La trata de seres humanos, especialmente con fines de explotación sexual, ha
encontrado en las redes sociales un nuevo aliado. Plataformas como Facebook,
Instagram y X se han convertido en herramientas clave para que las redes de trata capten
a sus víctimas, la mayoría mujeres y niñas. El auge de las tecnologías y el uso masivo de
redes sociales han facilitado a los delincuentes acceder a personas vulnerables, utilizando
el engaño, la manipulación y el chantaje. Desde la pandemia, este fenómeno ha crecido
notablemente, con un aumento del consumo de pornografía violenta y la creación de
espacios en la "deep web" donde se perpetúan estas explotaciones. Incluso en
plataformas como Onlyfans, muchas jóvenes, motivadas por el deseo de ganar dinero, se
exponen a los riesgos de ser captadas por estas redes. Pese a la existencia de
normativas internacionales, no se cuenta aún con una legislación integral que regule el
uso de internet para combatir este tipo de explotación.[Resumo] A trata de seres humanos, especialmente con fins de explotación sexual, atopou
nas redes sociais un novo aliado. Plataformas como Facebook, Instagram e X
convertéronse en ferramentas clave para que as redes de trata capten ás súas vítimas,
maioritariamente mulleres e nenas. O auxe das tecnoloxías e o uso masivo de redes
sociais facilitou que os delincuentes accedan a persoas vulnerables, empregando o
engano, a manipulación e o chantaxe. Dende a pandemia, este fenómeno creceu
notablemente, cun aumento do consumo de pornografía violenta e a creación de espazos
na "deep web" onde se perpetúan estas explotacións. Mesmo en plataformas como
Onlyfans, moitas mozas, motivadas polo desexo de gañar cartos, expóñense aos riscos
de seren captadas por estas redes. A pesar da existencia de normativas internacionais,
aínda non se conta cunha lexislación integral que regule o uso de internet para combater
este tipo de explotación.[Abstract] Human trafficking, especially for the purpose of sexual exploitation, has found a
new ally in social media. Platforms such as Facebook, Instagram and X have become key
tools for trafficking networks to target their victims, mostly women and girls. The rise of
technology and the massive use of social media have made it easier for criminals to gain
access to vulnerable individuals, using deception, manipulation, and blackmail. Since the
pandemic, this phenomenon has grown significantly, with an increase in the consumption
of violent pornography and the creation of spaces on the ‘deep web’ where these forms of
exploitation are perpetuated. Even on platforms such as Onlyfans, many young women,
motivated by the desire to earn money, expose themselves to the risks of being targeted
by these networks. Despite the existence of international regulations, there is still no
comprehensive legislation that regulates the use of the internet to combat this type of
exploitation.Traballo fin de mestrado (UDC.SOC). Políticas sociais e intervención sociocomunitaria. Curso 2023/202
Longitudinal stability of molecular endotypes of knee osteoarthritis patients
[Abstract]
Objective: To assess the longitudinal stability of biomarker-based molecular endotypes of knee osteoarthritis (KOA) participants from APPROACH and to evaluate the consistency of findings in an independent KOA population.
Methods: Nineteen biomarkers were measured longitudinally in 295 KOA participants from the APPROACH cohort. K-means clustering was used to identify the structural damage, inflammation, and low tissue turnover endotypes at the six-, 12-, and 24-month follow-ups. Endotype stability was defined as having the same independent endotype assignment longitudinally for patients with complete data (n = 226). Clinical and biochemical characteristics were compared between participants with longitudinally stable and unstable endotypes. The presence and longitudinal stability of the endotypes were evaluated in a different KOA population from the placebo arm of the oral salmon calcitonin trials.
Results: An average overall longitudinal endotype stability of 55% (Fleiss' Kappa of 0.53; 95% confidence interval [CI]: 0.46, 0.60) was demonstrated. An average stability of 59% (range: 54-59%) was observed for the structural damage endotype (Fleiss' Kappa 0.52; 95% CI: 0.45, 0.60), 54% (52-56%) for the inflammatory (Fleiss' Kappa 0.61; 95% CI: 0.53, 0.68), and 50% (49-52%) for the low tissue turnover endotype (Fleiss' Kappa 0.46; 95% CI: 0.39, 0.54). Participants with longitudinally unstable endotypes exhibited molecular properties of more than one endotype, which were detectable already at the first visit.
Conclusions: Our study showed for the first time that more than half of KOA participants exhibited a longitudinally stable endotype, highlighting the applicability of biomarker-based endotyping in a clinical trial setting
Web abierta para el análisis de la blockchain de Solana
[Resumen]: Actualmente, la comunidad de Solana y el uso de su blockchain están en continua expansión, con un número creciente de desarrolladores y proyectos que pretenden contribuir a crear un ecosistema que va más allá de movimientos especulativos tan habituales en el mundo crypto. A pesar de ello, la blockchain de Solana se ve afectada por proyectos que fracasan y proyectos con tokens fraudulentos, llevando consigo el capital de sus inversores. Por esta razón, surge la idea de comprender y analizar lo que sucede en la red para distinguir los proyectos o tokens con buena salud de los que pudiesen presentar problemas, a través del análisis On-Chain. Este análisis se basa en los datos obtenidos acerca de lo que sucede en la cadena de bloques, el volumen de transacciones, la distribución e intercambios de tokens y la actividad de ciertas cuentas. El análisis de estos datos proporciona una visión más profunda acerca del origen de los
movimientos de capital en la red, en contraste con el análisis técnico tradicional, que se basa en el estudio de patrones históricos de precios y volúmenes de capital de forma general, y que puede ser incapaz de captar movimientos repentinos en proyectos o tokens específicos. Este enfoque podría resultar útil en entornos volátiles como el de la blockchain de Solana.[Abstract]: Currently, the Solana community and the use of its blockchain are continuously expanding, with a growing number of developers and projects aiming to contribute to creating an ecosystem that goes beyond the speculative movements so common in the crypto world. Despite this, the Solana blockchain is affected by failed projects or projects with fraudulent tokens, taking investors’ capital with them. For this reason, the idea arises to understand and analyze what is happening on the network to distinguish between healthy projects or tokens and those that may present problems, through On-Chain analysis. This analysis is based
on data obtained about what happens on the blockchain, such as transaction volume, token distribution and exchanges, and the activity of certain accounts. The analysis of these data provides deeper insight into the origin of capital movements on the network, in contrast to traditional technical analysis, which is based on the study of historical price patterns and capital volumes in a general way, and may fail to capture sudden movements in specific projects or tokens. This approach could be useful in volatile environments such as the Solana blockchain.Traballo fin de grao (UDC.FIC). Enxeñaría Informática. Curso 2023/202
Towards the Industrial Metaverse: A Game-Based VR Application for Fire Drill and Evacuation Training for Ships and Shipbuilding
Presented at: Web3D '24: Proceedings of the 29th International ACM Conference on 3D Web Technology Article, September 25–27, 2024, Guimarães, PortugalThis is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in https://doi.org/10.1145/3665318.3678229.[Abstract]: This paper details the creation of a novel Virtual Reality-based application for the Industrial Metaverse aimed at shipboard fire emergency training for fire drill and evacuation, aligned with the Safety of Life at Sea (SOLAS) convention requirements. Specifically, the application includes gamified scenarios with different levels (e.g., varying fire intensities in engine rooms and galleys). The paper details comprehensively the VR development while providing a holistic overview and practical guidelines. Thus, it can guide practitioners, developers and future researchers to shape the next generation of Industrial Metaverse applications for the shipbuilding industry. Moreover, the paper includes the results of a preliminary user evaluation aimed at quantifying user decision-making and risk assessment skills. The presented results of the experiments provide insights into user performance and allow for pointing out at different future challenges.This work has been funded by grants TED2021-129433A-C22 (HELENE) and PID2020-118857RA-100 (ORBALLO) funded by MCIN/AEI/10.13039/501100011033 and the European
Union NextGenerationEU/PRTR, and by contract "Colaboración en proyecto ARGOS" (F22/11, CITIC)
Modificaciones en el estado de ánimo de la población escolar por aislamiento social relacionado con la práctica de actividad física
[Resumen] La irrupción del SARS-CoV-2 o COVID-19, supuso un cambio importante en la población mundial. En España, las medidas de contención y erradicación del virus interpuestas por el Gobierno, contemplaron largos periodos de confinamiento domiciliario que tuvieron importantes consecuencias para la salud y en los hábitos de la población infanto-juvenil. Estas medidas, que se prolongaron entre marzo y junio de 2020, provocaron modificaciones en los hábitos alimentarios, el descenso de la práctica deportiva y actividades físicas recreacionales así como un incremento de actividades sedentarias. Sin embargo, años después del fin de esta pandemia, todavía existen importante secuelas en la población directamente relacionadas con la salud mental, el bienestar emocional y los estados de ánimo. El objetivo de este estudio fue determinar el impacto en el estado de ánimo de una muestra de niños y niñas a causa del confinamiento domiciliario relacionado con la práctica de actividad física. Método: Participaron 50 niños de la Comunidad de Cantabria (España) entre 11-12 años (n = 50; M = 11,40; SD = 0,50), 33 (66%) niños y 17 (34%) niñas. Se ha utilizado el cuestionario Profile of Mood States (POMS) y un cuestionario ad hoc para datos sociodemográficos y otra información relevante. Resultados: El análisis comparativo de los estados de ánimo preconfinamiento y durante el confinamiento, evidenció un descenso en sus valores en todos los estados de ánimo evaluados por el POMS: tensión, depresión, ira, confusión, fatiga y vigor. No existieron diferencias estadísticamente significativas entre niños y niñas. Conclusiones: El estudio evidencia que el confinamiento domiciliario provocó cambios en los estados de ánimo en niños y niñas entre 11 y 12 años en relación con la práctica de actividad física.[Abstract] The irruption of SARS-CoV-2 or COVID-19, meant an important change in the world population. In Spain, the containment
and eradication measures imposed by the Government contemplated long periods of home confinement that had important consequences for the health and habits of the infant-juvenile population. These measures, which lasted from March to June 2020, led to
changes in eating habits, a decrease in the practice of sports and recreational physical activities and an increase in sedentary activities.
However, years after the end of this pandemic, there are still important sequelae in the population directly related to mental health,
emotional well-being and moods. The objective of this study was to determine the impact on the mood of a sample of children due to
home confinement related to the practice of physical activity. Methods: 50 children from the Community of Cantabria (Spain) aged
11-12 years (n = 50; M = 11.40; SD = 0.50) participated, 33 (66%) boys and 17 (34%) girls. The Profile of Mood States (POMS)
questionnaire and an ad hoc questionnaire were used for sociodemographic data and other relevant information. Results: Comparative
analysis of mood states preconfinement and during confinement showed a decrease in values for all mood states assessed by the POMS:
tension, depression, anger, confusion, fatigue and vigor. There were no statistically significant differences between boys and girls.
Conclusions: The study evidences that home confinement caused changes in mood states in boys and girls between 11 and 12 years of
age in relation to the practice of physical activity
A New Methodology for Experimental Analysis of Single-Cavity Bubble’s Nucleation, Growth and Detachment in Saturated HFE-7100
[Abstract] The study of single bubble nucleation, growth and detachment processes has being carried out with remarkable relevance in the last fifty years. The complexity of the associated phenomena are still a challenge for the researchers in the field, yielding a lot of works trying to explain the enrolled mechanisms. These studies include experimental, numerical and even theoretical approaches. In particular but not exclusively for numerical approaches, it is of essential importance having a solid and detailed experimental description of the full event. It is in this context that this work emerges, proposing a methodology for characterizing the single bubble nucleation, growth and detachment process. This methodology is based in the determination of a “typical bubble” that represents the whole phenomena, providing the reconstruction of a main bubble life-cycle with its uncertainty (both in space and time). This reconstruction allows the determination of several important characteristics, such as bubble volume, apparent contact angle, dry radius, and the forces acting on the bubble. This work analyzes a set of bubbles growing from a cavity of
diameter, under saturated conditions at 0,583 bar and superheating of 25,8 °C. All the outputs were obtained considering a carefully uncertainty determination and propagation from both systematic and random sources, which are not negligible as it is demonstrated in this work. The importance of considering a sufficient number of bubbles to characterize the phenomenon was also addressed, considering an analysis of uncertainties for different set of bubbles. The methodology was also confronted to previous approaches reported elsewhere, that ensured its performance, robustness, and validation.Brasil. São Paulo Research Foundation; 2016/09509-1Brasil. São Paulo Research Foundation; 2019/21022-9Brasil. São Paulo Research Foundation; 2021/14338-0Brasil. São Paulo Research Foundation; 2023/02383-6The authors acknowledge the support received from FAPESP, Brazil (São Paulo Research Foundation, grants 2016/09509-1, 2019/21022-9, 2021/14338-0 and 2023/02383-6) and CNPq, Brazil (National Council for Scientific and Technological Development, process 305941/2020-8)