DeustoTeka Examinando por Autor "Sanz Urquijo, Borja"

Examinando por Autor "Sanz Urquijo, Borja"

Mostrando 1 - 9 de 9

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, Iker
The 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.
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, María
Digital 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.
Discovering mathematical patterns behind HIV-1 genetic recombination: a new methodology to identify viral features
(Institute of Electrical and Electronics Engineers Inc., 2023-09-04) Guerrero Tamayo, Ana ; Sanz Urquijo, Borja ; Casado, Concepción ; Moragues Tosantos, María Dolores ; Olivares, Isabel ; Pastor López, Iker
In this article, we introduce a novel methodology for characterizing viral genetic features: the Unified Methodology of recombinant virus Identification (UMI). Our methodology converts genomic sequences into spectrograms, applies transfer learning using a pre-trained Convolutional Neural Network (CNN), and employs interpretability tools to identify the genomic regions relevant for characterizing a viral sequence as recombinant. The UMI methodology does not necessitate multiple sequence alignment or manual adjustments. As a result, it operates much faster, has low computational demands, and is capable of handling substantial amounts of data. To validate this, we applied UMI to one extensively studied and documented case: HIV-1 genetic recombination. We worked with all identified HIV-1 complete sequences (13554 sequences up to 2020), searching for mathematical patterns, signatures, that characterize an HIV-1 sequence as recombinant. CNN's hit rate (test accuracy) is 94%, with consistent and differentiated decision areas in each category. Using interpretability tools, we verified that the hot zones were similar for sequences of the same subtype and phylogenetic proximity. The leading areas for classifying a sequence as recombinant or non-recombinant are coincident with genomic regions that play a key role in genetic recombination processes. By applying UMI methodology we found that there is indeed a genome mathematical pattern that assesses an HIV-1 sequence as recombinant. In addition, we located its position. Considering expert knowledge, our results showed a substantial, robust and biologically-consistent hit rate. This type of solution can successfully guide the location and subsequent characterization of relevant areas, avoiding the heavy analysis of multiple sequence alignment and manual adjustments.
Efficient machine learning on edge computing through data compression techniques
(Institute of Electrical and Electronics Engineers Inc., 2023-03-29) Gomez Larrakoetxea, Nerea; Eskubi Astobiza, Joseba; Pastor López, Iker ; Sanz Urquijo, Borja; García Barruetabeña, Jon; Zubillaga Rego, Agustín José
This paper discusses the increasing amount of data handled by companies and the need to use Big Data and Data Analytics to extract value from this data. However, due to the large amount of data collected, challenges related to the computational capacity of machines often arise when performing this analysis to acquire relevant information for the organization, especially when we are using edge computing. The paper aims to train machine learning models using compressed data, with two compression techniques applied to the original data. The results show that models trained with compressed data achieved similar accuracy to those trained with uncompressed data, and different compression techniques were compared. The research extended a previous study by analyzing the use of autoencoders for compression and reducing both instances and dimensionality of the dataset. The accuracy rate of the models when trained with compressed data instead of original data was maintained.
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, Borja
Gender-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 coverage
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, Pablo
The 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.
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, Pablo
Content-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.
Let's do it right the first time: survey on security concerns in the way to quantum software engineering
(Elsevier B.V., 2023-06-14) Arias Alamo, Danel; García Rodríguez de Guzmán, Ignacio ; Rodríguez, Moises; Terres Escudero, Erik B.; Sanz Urquijo, Borja ; Gaviria de la Puerta, José ; Pastor López, Iker ; Zubillaga Rego, Agustín José ; García Bringas, Pablo
Quantum computing is no longer a promise of the future but a rapidly evolving reality. Advances in quantum hardware are making it possible to make tangible a computational reality that until now was only theoretical. The proof of this is that development languages and platforms are appearing that bring physical principles closer to developers, making it feasible to begin to propose, in different areas of society, solutions to problems that until now were unsolvable. However, security vulnerabilities are also emerging that could hinder the progress of quantum computing, as well as its transition and development in industry. For this reason, this article proposes a review of some of the first artefacts that are emerging in the field of quantum computing. From this analysis, we begin to identify possible security issues that could become potential vulnerabilities in the quantum software of tomorrow. Likewise, and following the experience in classical software development, the testing technique is analysed as a possible candidate for improving security in quantum software development. Following the principles of Quantum Software Engineering, we are aware of the lack of tools, techniques and knowledge necessary to guarantee the development of quantum software in the immediate future. Therefore, this article aims to offer some first clues on what would be a roadmap to guarantee secure quantum software development.
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 INFORMACION
El 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.

Examinando por Autor "Sanz Urquijo, Borja"

Resultados por página

Opciones de ordenación