Noemí DeCastro-García
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Noemí DeCastro-García has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- David Escudero García
Universidad de León
12 shared publications - Miguel V. Carriegos
Universidad de León
11 shared publications - Ángel Luis Muñoz Castañeda
Departamento de Matemáticas, Universidad de León, León, Spain
9 shared publications Ángel Manuel Guerrero-Higueras
Dept. Mech, Computer and Aerospace Eng. , Universidad de León , León , Spain
4 shared publicationsMiguel V. Carriegos
3 shared publications- Vicente Matellán
University of Leon
3 shared publications
Latest Publications
- 31 May 2026
- Published by Springer Nature
- p. 55-71
Output Feedback Transformations for Preserving Observability and Structural Decodability in Convolutional Codes
- 31 May 2026
- Published by Springer Nature
- p. 55-71
Output Feedback Transformations for Preserving Observability and Structural Decodability in Convolutional Codes
- Open Access
- 29 January 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 123 (1) , 2
Reinforcement Learning for the Optimization of Adaptive Intrusion Detection Systems
Network intrusion detection is an activity of increasing importance due to the annual rise in attacks. In the literature, the use of machine learning solutions is one of the most common mechanisms for improving the performance of detection systems. One of the main problems with these approaches is data imbalance: the volume of malicious traffic is much lower than normal traffic, making it difficult to create an effective model. The use of ensemble models, which combine several individual models, can increase robustness against data imbalance. To try to improve the effectiveness of ensemble models against imbalance, in this work, we apply reinforcement learning to combine the individual predictions of the ensemble models, with the objective of improving predictions compared to classic weighted voting algorithms.
- 29 January 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 123 (1) , 2
Open AccessReinforcement Learning for the Optimization of Adaptive Intrusion Detection Systems
Network intrusion detection is an activity of increasing importance due to the annual rise in attacks. In the literature, the use of machine learning solutions is one of the most common mechanisms for improving the performance of detection systems. One of the main problems with these approaches is data imbalance: the volume of malicious traffic is much lower than normal traffic, making it difficult to create an effective model. The use of ensemble models, which combine several individual models, can increase robustness against data imbalance. To try to improve the effectiveness of ensemble models against imbalance, in this work, we apply reinforcement learning to combine the individual predictions of the ensemble models, with the objective of improving predictions compared to classic weighted voting algorithms.
- Open Access
- 1 January 2026
- Published by Wiley in Computational and Mathematical Methods
- Vol. 2026 (1)
Modified Fast Inertial‐Type Krasnosel’skii‐Mann Iterative Scheme Involving Asymptotically Nonexpansive Mapping
It is our aim to propose a new iterative algorithm with an inertial term involving asymptotically nonexpansive mapping in the framework of Hilbert spaces. Let T : H ⟶ H be asymptotically nonexpansive mapping with F ( T ) ≠ ∅ ∅ and let be defined by x n +1 = σ n z n + b n ( T n σ n z n − σ n z n ) + ε n , ∀ n ≥ 1. T satisfies an additional mild condition, then the sequence converges strongly to . Our main contribution lies in establishing a strong convergence theorem for this method, without relying on the assumption that . Our strong convergence theorems extend the corresponding convergence theorems in literature for nonexpansive maps to a more general class of asymptotically nonexpansive maps. Furthermore, our proposed algorithm is implemented by finding the fixed point of common solutions to a variational inequality problem and η −inverse‐strongly monotone mapping in Hilbert space. Numerical illustrations showed some improvements over existing results in literature.
- 1 January 2026
- Published by Wiley in Computational and Mathematical Methods
- Vol. 2026 (1)
Open AccessModified Fast Inertial‐Type Krasnosel’skii‐Mann Iterative Scheme Involving Asymptotically Nonexpansive Mapping
It is our aim to propose a new iterative algorithm with an inertial term involving asymptotically nonexpansive mapping in the framework of Hilbert spaces. Let T : H ⟶ H be asymptotically nonexpansive mapping with F ( T ) ≠ ∅ ∅ and let be defined by x n +1 = σ n z n + b n ( T n σ n z n − σ n z n ) + ε n , ∀ n ≥ 1. T satisfies an additional mild condition, then the sequence converges strongly to . Our main contribution lies in establishing a strong convergence theorem for this method, without relying on the assumption that . Our strong convergence theorems extend the corresponding convergence theorems in literature for nonexpansive maps to a more general class of asymptotically nonexpansive maps. Furthermore, our proposed algorithm is implemented by finding the fixed point of common solutions to a variational inequality problem and η −inverse‐strongly monotone mapping in Hilbert space. Numerical illustrations showed some improvements over existing results in literature.
- Open Access
- 13 June 2025
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 93
Conformal prediction for labelling and updating online models in the presence of concept drift in cybersecurity
- 13 June 2025
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 93
Open AccessConformal prediction for labelling and updating online models in the presence of concept drift in cybersecurity
- Open Access
- 8 April 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (8) , 4090
Generative Artificial Intelligence and Machine Translators in Spanish Translation of Early Vulnerability Cybersecurity Alerts
The increasing reliance on artificial intelligence in cybersecurity has broadened the role of generative artificial intelligence in tasks such as text generation and translation. This study assesses the effectiveness of generative artificial intelligence and conventional translation tools in translating early vulnerability alerts from English to Spanish—a critical process for ensuring the timely dissemination of cybersecurity information. Utilizing a dataset provided by the Spanish National Cybersecurity Institute, translations were generated using various systems and evaluated through linguistic assessment metrics, including methods measuring lexical similarity and others capturing semantic meaning beyond direct word matching. Additionally, word embeddings were employed to enhance the accuracy of semantic similarity analysis. The results indicate that conventional translation tools generally exhibit greater accuracy and structural fidelity, whereas generative artificial intelligence produces more natural-sounding translations. However, this flexibility results in greater variability in translation quality. The findings suggest that while generative artificial intelligence may serve as a valuable complement to traditional tools, its inconsistencies may limit its suitability for highly technical content that demands precision. This study underscores the importance of integrating both approaches to improve the accuracy and accessibility of cybersecurity alerts across different languages.
- 8 April 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (8) , 4090
Open AccessGenerative Artificial Intelligence and Machine Translators in Spanish Translation of Early Vulnerability Cybersecurity Alerts
The increasing reliance on artificial intelligence in cybersecurity has broadened the role of generative artificial intelligence in tasks such as text generation and translation. This study assesses the effectiveness of generative artificial intelligence and conventional translation tools in translating early vulnerability alerts from English to Spanish—a critical process for ensuring the timely dissemination of cybersecurity information. Utilizing a dataset provided by the Spanish National Cybersecurity Institute, translations were generated using various systems and evaluated through linguistic assessment metrics, including methods measuring lexical similarity and others capturing semantic meaning beyond direct word matching. Additionally, word embeddings were employed to enhance the accuracy of semantic similarity analysis. The results indicate that conventional translation tools generally exhibit greater accuracy and structural fidelity, whereas generative artificial intelligence produces more natural-sounding translations. However, this flexibility results in greater variability in translation quality. The findings suggest that while generative artificial intelligence may serve as a valuable complement to traditional tools, its inconsistencies may limit its suitability for highly technical content that demands precision. This study underscores the importance of integrating both approaches to improve the accuracy and accessibility of cybersecurity alerts across different languages.
- Open Access
- 1 January 2025
- Published by American Institute of Mathematical Sciences (AIMS) in AIMS Mathematics
- Vol. 10 (7) , 16762-16795
Meta-feature-based data preprocessing for machine learning through correlation structures and cost-aware benchmarking: A case study in cybersecurity
One of the current challenges in applying machine learning is optimizing the constructed models to achieve the best possible performance. This article proposes a novel approach to determine which data preprocessing strategy may be most beneficial for enhancing the evaluation fit metrics, based on studying the correlation between the dataset's meta-features and the performance response variables. Additionally, the meta-features were categorized in terms of modification cost and control over the model's fit to determine which strategies appeared to be the most optimal. Also, we studied if these transformation can improve the results obtained by several training and testing proportions. The study was conducted with 42 different configuration datasets derived from the multiclass classification problem of IP address maliciousness. Three machine learning algorithms and tools were evaluated: Autosklearn, Gaussian Mixture Models, and Extreme Gradient Boosting; all of them have been studied on the same problem in previous works. Also, we applied five different types of data transformations, such as scaling, dimensionality reduction techniques, and quantile transformation. The results show that meta-feature correlation analysis significantly improves machine learning performance by guiding data preprocessing and transformation strategies, sometimes even surpassing the best original performance.
- 1 January 2025
- Published by American Institute of Mathematical Sciences (AIMS) in AIMS Mathematics
- Vol. 10 (7) , 16762-16795
Open AccessMeta-feature-based data preprocessing for machine learning through correlation structures and cost-aware benchmarking: A case study in cybersecurity
One of the current challenges in applying machine learning is optimizing the constructed models to achieve the best possible performance. This article proposes a novel approach to determine which data preprocessing strategy may be most beneficial for enhancing the evaluation fit metrics, based on studying the correlation between the dataset's meta-features and the performance response variables. Additionally, the meta-features were categorized in terms of modification cost and control over the model's fit to determine which strategies appeared to be the most optimal. Also, we studied if these transformation can improve the results obtained by several training and testing proportions. The study was conducted with 42 different configuration datasets derived from the multiclass classification problem of IP address maliciousness. Three machine learning algorithms and tools were evaluated: Autosklearn, Gaussian Mixture Models, and Extreme Gradient Boosting; all of them have been studied on the same problem in previous works. Also, we applied five different types of data transformations, such as scaling, dimensionality reduction techniques, and quantile transformation. The results show that meta-feature correlation analysis significantly improves machine learning performance by guiding data preprocessing and transformation strategies, sometimes even surpassing the best original performance.
- Open Access
Construction of observable and MDP convolutional codes with good decodable properties for erasure channels by I/S/O representations
This paper addresses the construction of observable convolutional codes that exhibit good performance with the available decoding algorithms for erasure channels. Our construction is based on the use of input/state/output (I/S/O) representations and the invariance of certain properties of linear systems under various group actions.
Open AccessConstruction of observable and MDP convolutional codes with good decodable properties for erasure channels by I/S/O representations
This paper addresses the construction of observable convolutional codes that exhibit good performance with the available decoding algorithms for erasure channels. Our construction is based on the use of input/state/output (I/S/O) representations and the invariance of certain properties of linear systems under various group actions.
- 9 October 2024
- Published by Springer Nature
- p. 177-189
Application of Transfer Learning to Online Models in Malware Detection
- 9 October 2024
- Published by Springer Nature
- p. 177-189
Application of Transfer Learning to Online Models in Malware Detection
- 28 January 2024
- Published by Springer Nature in Wireless Networks
- Vol. 30 (9) , 7423-7444
Transfer and online learning for IP maliciousness prediction in a concept drift scenario
- 28 January 2024
- Published by Springer Nature in Wireless Networks
- Vol. 30 (9) , 7423-7444
Transfer and online learning for IP maliciousness prediction in a concept drift scenario
- 29 August 2023
- Published by Springer Nature
- p. 15-26
Application of Anomaly Detection Models to Malware Detection in the Presence of Concept Drift
- 29 August 2023
- Published by Springer Nature
- p. 15-26
Application of Anomaly Detection Models to Malware Detection in the Presence of Concept Drift