Examinando por Autor "Sanz Urquijo, Borja"
Mostrando 1 - 6 de 6
Resultados por página
Opciones de ordenación
Ítem Classification of SARS-CoV-2 sequences as recombinants via a pre-trained CNN and identification of a mathematical signature relative to recombinant feature at Spike, via interpretability(Public Library of Science, 2024-08) Guerrero Tamayo, Ana; Sanz Urquijo, Borja; Olivares, Isabel; Moragues Tosantos, María Dolores; Casado, Concepción; Pastor López, IkerThe global impact of the SARS-CoV-2 pandemic has underscored the need for a deeper understanding of viral evolution to anticipate new viruses or variants. Genetic recombination is a fundamental mechanism in viral evolution, yet it remains poorly understood. In this study, we conducted a comprehensive research on the genetic regions associated with genetic recombination features in SARS-CoV-2. With this aim, we implemented a two-phase transfer learning approach using genomic spectrograms of complete SARS-CoV-2 sequences. In the first phase, we utilized a pre-trained VGG-16 model with genomic spectrograms of HIV-1, and in the second phase, we applied HIV-1 VGG-16 model to SARS-CoV-2 spectrograms. The identification of key recombination hot zones was achieved using the Grad-CAM interpretability tool, and the results were analyzed by mathematical and image processing techniques. Our findings unequivocally identify the SARS-CoV-2 Spike protein (S protein) as the pivotal region in the genetic recombination feature. For non-recombinant sequences, the relevant frequencies clustered around 1/6 and 1/12. In recombinant sequences, the sharp prominence of the main hot zone in the Spike protein prominently indicated a frequency of 1/ 6. These findings suggest that in the arithmetic series, every 6 nucleotides (two triplets) in S may encode crucial information, potentially concealing essential details about viral characteristics, in this case, recombinant feature of a SARS-CoV-2 genetic sequence. This insight further underscores the potential presence of multifaceted information within the genome, including mathematical signatures that define an organism’s unique attributes.Ítem The contribution of data to feminist transformation of women’s rights to health(Universidad de Alicante / Universitat d'Alacant, Instituto de Investigación de Estudios de Género, 2023-07-10) Sanz Urquijo, Borja ; López Belloso, MaríaDigital technologies and data science have evolved rapidly. But how does the digital evolution affect women’s rights? Bunch argued that, to implement women’s rights, it was first necessary to observe how they are violated (Bunch, 1990). This article examines how femtec’s apps work, delivering reproductive and sexual health services to millions of women. Specifically, it analyzes the data collection permissions of 45 femtech apps to assess what the platform intends to do with the personal data collected and its objectives. To understand how these apps use data, we explored the goals of these apps in data collection and whether data could be collected and used to transform women’s health. Thus, this work is structured in four sections. First, a theoretical review of Bunch’s proposal and its contribution to data feminism is raised. Second, the potential for feminist transformation of human rights using digital technologies is discussed, particularly in women’s health. The third section details the current use of health data captured by health apps. This article ends by drawing the main conclusions of the analysis and providing recommendations for a feminist transformation of data activism from a human rights perspective.Ítem Empowering change: unveiling the synergy of feminist perspectives and AI tools in addressing domestic violence(Universitat de Girona = Universidad de Gerona, 2024) Izaguirre Choperena, Ainhoa; López Belloso, María; Sanz Urquijo, BorjaGender-based violence remains a widespread issue in our societies. Women who are victims-survivors often encounter significant barriers when seeking support services, and frontline responders frequently lack the necessary skills and capacities to provide an adequate response. In this context, artificial intelligence, particularly through the use and development of chatbots, has emerged as a potential solution to enhance and simplify access to these services for women. This is where the European project IMPROVE (Improving Access to Services for Victims of Domestic Violence by Accelerating Change in Frontline Responder Organisations) comes into play. Using a qualitative methodology, this study captures the voices of victim-survivors, exploring their views on the use of AI tools in the context of domestic violence, while also comparing these perspectives with the general societal perception of chatbots as reflected in media coverageÍtem Enhancing real-time processing in Industry 4.0 through the paradigm of edge computing(Multidisciplinary Digital Publishing Institute (MDPI), 2025-01) Gomez Larrakoetxea, Nerea; Sanz Urquijo, Borja; Pastor López, Iker; García Barruetabeña, Jon; García Bringas, PabloThe industrial sector has undergone significant digital transformation, driven by advancements in technology and the Internet of Things (IoT). These developments have facilitated the collection of vast quantities of data, which, in turn, pose significant challenges for real-time data processing. This study seeks to validate the efficacy and accuracy of edge computing models designed to represent subprocesses within industrial environments and to compare their performance with that of traditional cloud computing models. By processing data locally at the point of collection, edge computing models provide substantial benefits in minimizing latency and enhancing processing efficiency, which are crucial for real-time decision-making in industrial operations. This research demonstrates that models derived from distinct subprocesses yield superior accuracy compared to comprehensive models encompassing multiple subprocesses. The findings indicate that an increase in data volume does not necessarily translate to improved model performance, particularly in datasets that capture data from production processes, as combining independent process data can introduce extraneous ‘noise’. By subdividing datasets into smaller, specialized edge models, this study offers a viable approach to mitigating the latency challenges inherent in cloud computing, thereby enhancing real-time data processing capabilities, scalability, and adaptability for modern industrial applications.Ítem An innovative framework for supporting content-based authorship identification and analysis in social media networks(Oxford University Press, 2024-08) Gaviria de la Puerta, José; Pastor López, Iker; Tellaeche Iglesias, Alberto; Sanz Urquijo, Borja; Sanjurjo González, Hugo; Cuzzocrea, Alfredo; Bringas García, PabloContent-based authorship identification is an emerging research problem in online social media networks, due to a wide collection of issues ranging from security to privacy preservation, from radicalization to defamation detection, and so forth. Indeed, this research has attracted a relevant amount of attention from the research community during the past years. The general problem becomes harder when we consider the additional constraint of identifying the same false profile over different social media networks, under obvious considerations. Inspired by this emerging research challenge, in this paper we propose and experimentally assess an innovative framework for supporting content-based authorship identification and analysis in social media networks.Ítem Rubicón: un nuevo enfoque para la seguridad en las aplicaciones de smartphones(Universidad de Deusto, 2012-12-11) Sanz Urquijo, Borja; García Bringas, Pablo; Facultad de Ingeniería; SISTEMAS DE INFORMACIONEl crecimiento del número de teléfonos móviles inteligentes o smarphones ha sido exponencial. Estos equipos, dotados de gran movilidad y hardware dedicado (p.ej., GPS o giroscopio) son gobernados por sistemas operativos cada vez más complejos .Además, la proliferación de las «tiendas de aplicaciones» ha creado una forma sencilla para el usuario de instalar aplicaciones en el terminal. Desafortunadamente, la gestión de la seguridad de estos dispositivos dista mucho de ser óptima. La proliferación del aplicaciones maliciosas (malware) en este tipo de plataformas, el acceso por parte de las aplicaciones a datos sensibles y su gestión a espaldas de los usuarios ha creado un escenario en el que los dispositivos almacenan una gran cantidad de información sensible y privada (p.ej., la agenda, los mensajes, los correos electrónicos, etc.) y cuya seguridad no está tan madura como en entornos más asentados, como pueden ser los equipos de escritorio. La comunidad científica se ha lanzado a buscar soluciones para mitigar esta problemática. Para ello, se han intentado migrar modelos que funcionaban en entornos de escritorio a este tipo de dispositivos con suerte dispar: se han desarrollado representaciones de las aplicaciones de smartphones, para posteriormente utilizar técnicas de aprendizaje automático para clasificar las aplicaciones, aunque el resultado obtenido no es tan óptimo como en otros entornos. Con este telón de fondo, el objetivo es determinar qué amenazas son las más peligrosas para estos dispositivos y mitigar las amenazas de seguridad y privacidad a las que está expuesto el terminal, sin que sea necesaria la intervención del usuario. Por ello, se formula la siguiente hipótesis: «Es posible, mediante el uso de algoritmos supervisados de inteligencia artificial y minería de datos, hacer una gestión inteligente, automática, y efectiva de la seguridad en las aplicaciones de los teléfonos smartphones tal que libere al usuario de parte de la responsabilidad de la gestión de la seguridad del mismo.». Para validar esta hipótesis, se realiza en primer lugar una evaluación exhaustiva de las soluciones existentes. A continuación, se desarrolla un nuevo modelado de las amenazas existentes en este tipo de dispositivos. A fin de validar este nuevo modelado, se realiza un banco de ataques que define los mayores activos, amenazas, ataques y vulnerabilidades que se dan en estos dispositivos. Tras evaluar el resultado obtenido, se determina que la mayor amenaza se centra en el software malicioso o malware. Posteriormente se fijarán los criterios sobre los que se evaluará la solución propuesta para la detección de este tipo de software. A continuación se diseñará y desarrollará una solución que mejore esta situación, específicamente sobre la plataforma Android, para, finalmente, evaluarla mediante el uso de métricas aplicadas en el área de la inteligencia artificial y contrastarla en base a los criterios anteriormente seleccionados. Los smartphones se han convertido en una herramienta importante en el día a día que almacena una gran cantidad de información sensible. Mediante esta investigación se busca avanzar en el estado del arte en la detección del malware en smartphones, avanzando en la creación de un entorno seguro para el uso de este tipo de sistemas.