http://hdl.handle.net/10366/134243 Fri, 24 Apr 2026 13:18:12 GMT 2026-04-24T13:18:12Z http://hdl.handle.net/10366/171053 [EN]Current Network Intrusion Detection Systems (NIDS) often fail to detect adversarial evasion attacks, creating critical security blind spots. To address this, we propose a standardized adversarial evaluation protocol that quantifies performance degradation against Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and AutoAttack ensemble attacks, establishing empirically observed performance bounds. We implemented a high-throughput hybrid architecture combining 1D-CNN, Bidirectional LSTM, and Transformer mechanisms, designed specifically to balance varying traffic dynamics and robustness. Unlike prior studies that report only clean-data accuracy, our evaluation of UNSW-NB15, CICIDS2017, and CICIoT2023 demonstrates competitive performance (e.g., strong multi-class F1 scores) while revealing robustness profiles up to an operational limit of e=0.05. Crucially, we validated our results under a temporal split using the official UNSW-NB15 train/test partition, confirming that binary detection (94.20% accuracy, 95.69% F1) generalizes under distribution shift. We further compared the proposed method with PGD-based adversarial training (PGD-AT) to quantify the robustness–accuracy trade-off. Our results advocate the use of security curves as a standard metric for NIDS validation in hostile environments. Wed, 01 Jul 2026 00:00:00 GMT http://hdl.handle.net/10366/171053 2026-07-01T00:00:00Z http://hdl.handle.net/10366/170727 [EN]Accurate segmentation of meningiomas in magnetic resonance imaging scans is essential for clinical planning, yet remains challenging due to their irregular shapes and subtle boundaries. In this study, we refine skip connections in convolutional encoder–decoder networks (widely known through the U-Net architecture) by selectively integrating shifted window transformer blocks. Unlike prior transformer-based architectures, which primarily enhance encoder or decoder stages, our approach targets shallow skip connections to improve the fusion of local detail and global context. An ablation study on the BraTS Meningioma 2023 dataset demonstrates that applying transformer blocks to the first two skip levels yields an optimal balance between accuracy and efficiency. The proposed model achieves a Dice similarity coefficient of 0.9119, outperforming conventional encoder–decoder baselines such as U-Net, Attention U-Net, and a widened U-Net variant, while delivering more precise boundary delineation with competitive recall. Mon, 15 Jun 2026 00:00:00 GMT http://hdl.handle.net/10366/170727 2026-06-15T00:00:00Z http://hdl.handle.net/10366/170401 [EN]This study analyzes volatility dynamics and regional financial integration in European and Latin American equity markets under heightened global uncertainty and the growing relevance of sustainable finance. It aims to assess volatility persistence, asymmetric responses to negative information, and the role of intraregional integration in shock transmission and financial stability. Design/methodology/approach – Daily equity index returns from representative European and Latin American markets over 2010–2025 are analyzed using asymmetric GARCH-type models (EGARCH and GJRGARCH) with skewed innovations. Volatility persistence is measured through model parameters and half-life indicators, while financial integration is examined using Dynamic Conditional Correlation (DCC-GARCH) models. Robustness is evaluated through structural stability tests and pre- and post-COVID-19 comparisons. Findings – European markets exhibit high volatility persistence but short half-lives (approximately 4–6 days), indicating faster shock absorption. Latin American markets display longer half-lives (around 8–12 days), reflecting more persistent volatility. Asymmetric effects are stronger and more systematic in Europe, while Latin America shows weaker and more heterogeneous responses. Intraregional correlations are extremely high in Europe, limiting diversification, whereas Latin America remains moderately and unevenly integrated. No evidence of structural breaks is found. Originality/value – The study offers a unified long-horizon comparative framework combining asymmetric GARCH models, half-life measures, dynamic correlations, and stability diagnostics. It provides robust evidence on structural differences between developed and emerging markets, with implications for investors and policymakers in financial stability and sustainable finance. Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/10366/170401 2026-01-01T00:00:00Z http://hdl.handle.net/10366/170400 [EN]New technological advances have made it possible to improve precision and efficiency in the consumption of natural resources. This article presents a series of different use cases in which technology has benefited peripheral and crossborder areas and continues to do so. Real-scenario implementations of cuttingedge Internet of Things (IoT) technologies have been conducted in Portugal Norte Region and Castilla y León. The findings demonstrate the direct impact of technological applications on the regions and the production efficiency. Wed, 01 Jan 2020 00:00:00 GMT http://hdl.handle.net/10366/170400 2020-01-01T00:00:00Z http://hdl.handle.net/10366/170398 [EN]This article aims at presenting Blockchain and Distributed Ledger Technologies from business perspective (although providing adequate technology context) and, especially, highlighting concrete implementations in Agri-Food Supply Chain, bringing security, transparency and robustness to solutions, and enabling the creation of added value through the provisioning of information to consumers which allow them to understand the origin, the transformation and the transportation of agri-food goods. It also brings some examples of European Programmes and Projects that are supporting innovative solutions to reach the market. Wed, 01 Jan 2020 00:00:00 GMT http://hdl.handle.net/10366/170398 2020-01-01T00:00:00Z http://hdl.handle.net/10366/170397 [EN]Industry 4.0 is reshaping the way all the economic sectors are working. The complete adoption and understanding by the companies, large or small, of the digital transformation opportunities and benefits, requires the existence of effective instruments. Digital Innovation Hubs (DIHs) are an important instrument, strongly promoted by the European Commission, to help companies to take advantage of digital opportunities. Aiming to boost and create synergies between several DIHs and research centers located in the northern region of Portugal and Spain, and considering the disruptive ICT technologies, the establishment of an inter-regional DIH that results from the cooperation between these entities assumes a crucial importance to transform this region into an innovative pole of reference. This paper aims to describe the strategy for the management and improvement of the quality of the innovation being developed by this inter-regional DIH under the scope of the DISRUPTIVE project. Besides considering the individual strategies of the associated members, it includes cooperative aspects, regarding the sharing of knowledge, technology, and skills, aiming to improve the quality of innovation, as well as the adoption of digitization by the companies in this region. Wed, 01 Jan 2020 00:00:00 GMT http://hdl.handle.net/10366/170397 2020-01-01T00:00:00Z http://hdl.handle.net/10366/170396 [EN]This article introduces the concern that exists in the wider economic world concerning the developments carried out in Smart Cities. The various studies that have been developed capture the economic approach by focusing on specific economic development theories. This article initially provides a theoretical response to the need for a joint approach to the different economic theories relating to Smart Cities, placing the bases of their development in the circular economy. Subsequently, the paper presents a device-based proposal to validate the sustainability principles indicated in the Smart Economy, focusing exclusively on the areas of health and mobility. As a whole, the work concludes with the need to incorporate sustainability criteria into economic ambition so that technological developments have a place in future Smart Cities. Fri, 01 Jan 2021 00:00:00 GMT http://hdl.handle.net/10366/170396 2021-01-01T00:00:00Z http://hdl.handle.net/10366/170395 [EN]Machine Learning (ML) is a disruptive concept that has given rise to and generated interest in different applications in many fields of study. The purpose of Machine Learning is to solve real-life problems by automatically learning and improving from experience without being explicitly programmed for a specific problem, but for a generic type of problem. This article approaches the different applications of ML in a series of econometric methods. Objective: The objective of this research is to identify the latest applications and do a comparative study of the performance of econometric and ML models. The study aimed to find empirical evidence for the performance of ML algorithms being superior to traditional econometric models. The Methodology of systematic mapping of literature has been followed to carry out this research, according to the guidelines established by [39], and [58] that facilitate the identification of studies published about this subject. Results: The results show, that in most cases ML outperforms econometric models, while in other cases the best performance has been achieved by combining traditional methods and ML applications. Conclusion: inclusion and exclusions criteria have been applied and 52 articles closely related articles have been reviewed. The conclusion drawn from this research is that it is a field that is growing, which is something that is well known nowadays and that there is no certainty as to the performance of ML being always superior to that of econometric models. Fri, 01 Jan 2021 00:00:00 GMT http://hdl.handle.net/10366/170395 2021-01-01T00:00:00Z http://hdl.handle.net/10366/170394 This article describes the development of a recommender system to obtain buy/sell signals from the results of technical analyses and of forecasts performed for companies operating in the Spanish continuous market. It has a modular design to facilitate the scalability of the model and the improvement of functionalities. The modules are: analysis and data mining, the forecasting system, the technical analysis module, the recommender system, and the visualization platform. The specification of each module is presented, as well as the dependencies and communication between them. Moreover, the proposal includes a visualization platform for high-level interaction between the user and the recommender system. This platform presents the conclusions that were abstracted from the resulting values. Fri, 01 Jan 2021 00:00:00 GMT http://hdl.handle.net/10366/170394 2021-01-01T00:00:00Z http://hdl.handle.net/10366/170393 [EN]The 2030 Agenda is a clear development milestone for humanity in its ambition to care for our future generations. Smart Cities play an essential role in this development, the development direction of which is based, among others factors, on the fulfilment of the criteria set by the various Sustainable Development Goals (SDGs). The purpose of the current research is to verify the current state of science concerning the development of the SDGs in Smart Cities to establish a theoretical framework for the development and integration of data specific to a Smart City to participate in homogeneous monitoring of these indicators and to compare with other Smart Cities. Once a robust bibliographic study has been carried out, we proceed to establish a theoretical study, the application methodology of which follows a process developed in various phases to obtain an integrated system for monitoring and linking of the development of Smart Cities according to the criteria set out in the applicable SDGs. The clear implication is establishing an objective and efficient process that covers collection to integrate and compare the obtained data. One of the limitations of this process is overcoming the technological barrier in specific less developed environments that may not have sufficient funding. With respect to future lines of research, the current study opens the door to studying the implications of this type of process on the management and elaboration of specific public policies, for example, concerning the time taken to establish and resolve them. Sat, 01 Jan 2022 00:00:00 GMT http://hdl.handle.net/10366/170393 2022-01-01T00:00:00Z http://hdl.handle.net/10366/170389 [EN]Currently, the concern for achieving and fulfilling the Sustainable Development Goals (SDGs) is a constant in advanced societies. The scientific community and various organisations are working on obtaining an information system that will make it possible to offer the necessary value to this type of sustainability information. The article aims to incorporate criteria on the technology used in the reporting system, specifically in collecting the different types of data and generating other interfaces. The methods described here are carried out on a specific case study, a Smart City, showing the different types of data that exist and the possible interfaces that allow objective monitoring of the achievement of the SDGs. It is, therefore, a descriptive study of a process whose results are the establishment of criteria concerning the different data sources as well as the generation of a set of interfaces that motivate the monitoring that can be carried out in a specific city to observe its compliance and deviations from critical values, for example, environmental. The main conclusions of this research establish the importance of incorporating and sizing the technology needed to develop the criteria for monitoring the SDGs. There is a need for convergence between the correct, objective and universal provision of this type of sustainability information and the technology used for the collection and presentation of the data. Sat, 01 Jan 2022 00:00:00 GMT http://hdl.handle.net/10366/170389 2022-01-01T00:00:00Z http://hdl.handle.net/10366/170387 [EN]Sustainable development and its significant challenges motivate various international organisations in a way that has never been seen before. With Europe at the forefront, countries such as the United States want to be included in the progress and what a clear and determined commitment to sustainability means for future generations. Our study aimed to go deeper into the follow-up and monitoring of the development of reliable indicators that make the continuous improvement process in sustainability robust. To this end, and using the fuzzy logic methodology, we applied it to one of the indices that have been developed to date, the “Sustainable Development Report” (in its 2022 edition), working on the specific application of SDG 11. Our results show favourable positions for countries such as Brunei Darussalam, Tonga, Tuvalu, Andorra, and the Netherlands and provide robustness when there is a lack of data quality and improvements in the implementation of the process when experts intervene. Sun, 01 Jan 2023 00:00:00 GMT http://hdl.handle.net/10366/170387 2023-01-01T00:00:00Z http://hdl.handle.net/10366/170385 [EN]The strategic importance of sustainability is evident when it comes, for example, to health. Public policies aimed at mitigating the effects of harmful substances, such as fine particulate matter (PM 2.5), are justified by the direct link between fine particulate matter and the health of citizens, in this case, premature deaths. An advanced statistical and exhaustive analysis of different areas and countries shows a strong link between exposure to 𝑃𝑀2.5, premature deaths in other countries, and significant differences in 𝑃𝑀2.5 levels between urban and rural areas. Although 𝑃𝑀2.5 concentration has decreased in most countries studied, this effort must be continued and aligned with the Sustainable Development Goals of the 2030 Agenda, underlining the need to implement effective air pollution control policies to reduce the health risks associated with 𝑃𝑀2.5 exposure. To this end, identifying temporal trends and geographical patterns can guide the development of specific interventions tailored to the needs of each region. Mon, 01 Jan 2024 00:00:00 GMT http://hdl.handle.net/10366/170385 2024-01-01T00:00:00Z http://hdl.handle.net/10366/170384 [EN]This work aims to examine the bidirectional relationship between mental health and personal finance, synthesizing empirical evidence to identify trends, characteristics and future directions for research. Design/methodology/approach – Using PRISMA Framework guidelines, 32 articles published between 2002 and 2024 from Web of Science were analyzed. Bibliometric tools (Microsoft Excel and R Studio) mapped research evolution, country collaborations and keyword co-occurrence. Thematic analysis clustered findings intomental health, financial capability and financial literacy perspectives. Findings – The interplay between mental health and personal finance creates a self-perpetuating cycle, wherein structural elements like debt and income instability disproportionately impact marginalized populations, including women, autistic individuals and low-income families. Financial literacy, while important, cannot stand alone; it necessitates accompanying structural support such as debt relief and cash transfers. Central facilitators encompass fiscal assurance and personal efficacy. Advancements like artificial intelligence and longitudinal designs are propelling development in this domain; however, discrepancies in measurement continue to exist. Originality/value – This review synthesizes a diverse array of literature, underscoring the imperative for integrated mental and financial health interventions. It offers a critical examination of the excessive dependence on solutions focused solely on the individual, advocating for comprehensive policies that tackle financial instability as a matter of public health significance. Future inquiries should aim to establish uniform metrics, investigate the ramifications of digital finance and emphasize the importance of crosscultural causal analyses. Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/10366/170384 2025-01-01T00:00:00Z http://hdl.handle.net/10366/170383 [EN]Energy efficiency in industrial environments is subject to regulatory and economic constraints. Automated intralogistics systems, such as High Rack Storage Systems (HRSS), exhibit complex and dynamic energy patterns. This paper proposes an unsupervised learning approach that uses Self-Organizing Maps (SOMs) to characterize operational energy states from HRSS measurements (power, voltage, and position). After preprocessing, we train an SOM and apply Watershed segmentation to obtain a topological map of states, and we analyze state transitions with a Markov model to study persistence and switching behavior. The approach yields an interpretable taxonomy of energy use and highlights operating conditions associated with different efficiency levels, as well as central states that influence system behavior. While the study focuses on a single demonstrator, the results suggest that SOM can support explainable monitoring and analysis of industrial energy behavior and may help guide proactive energy-management decisions in Industry 4.0 settings. Sat, 01 Nov 2025 00:00:00 GMT http://hdl.handle.net/10366/170383 2025-11-01T00:00:00Z http://hdl.handle.net/10366/170379 [EN]In the current context, where the productivity paradox coexists with growing concerns about inequality, quantum economics and quantum game theory are emerging as novel frameworks to address inherent uncertainty and complex strategic interactions. Quantum game theory applies the principles of quantum mechanics to model strategic interactions, providing new insights into decision-making, optimization and conflict resolution. In this article, we conduct a systematic review following the PRISMA methodology and a bibliometric analysis of the literature on quantum game theory to assess its development, methodologies and applications. We examine the growing interest in quantum technologies such as quantum computing, quantum communication and quantum simulation, which have had a significant impact on both theoretical models and practical economic and social systems. By mapping trends in the quantum game theory research landscape, this article aims to identify key advances, highlight important milestones and propose future directions for research in this emerging field. This comprehensive mapping not only elucidates the dynamic evolution and interdisciplinary convergence of quantum and evolutionary game theory, but also establishes a foundation for future research, fostering innovative approaches to complex decisionmaking in increasingly uncertain and interconnected environments. Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/10366/170379 2025-01-01T00:00:00Z