FBFernando Boto

Fernando Boto

*This is an algorithmically generated author record based on publicly available information.

Fernando Boto has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Evaluating Graph RAG vs. Vector RAG under Network Scaling, Topological Noise, and Financial Cost Constraints in Cross-Border Electrical Grid Cybersecurity

    by Alberto Tellaeche Iglesias, José Gaviria De la Puerta, Fernando Boto Sanchez

    The ongoing digital transformation of critical energy infrastructures and theoperational interconnections of cross-border Smart Grids demand advancedautomated situational awareness and resilient threat intelligence frameworks.While Retrieval-Augmented Generation (RAG) architectures are increasinglydeployed in Security Operations Centers (SOCs) for threat hunting andvulnerability management, standard dense vector retrieval (Vector RAG)struggles to capture multi-hop topological dependencies and complex attackpaths across interconnected IT/OT control systems. Conversely, KnowledgeGraph-structured retrieval (Graph RAG) preserves structural relationshipsbut introduces substantial computational, memory, and financial overheads.In this paper, we present an exhaustive quantitative benchmark comparingGraph RAG against Vector RAG across four network scaling tiers (Baseline,Medium, Large, and Mega), varying topological noise rates, and financialcost constraints within a cross-border electrical power grid spanning two nations. Our experimental findings demonstrate that Graph RAG substan-tially improves Context Recall over Vector RAG, maintaining 86.3%–100.0%across network scales compared to dropping below 3.8% for Vector RAG atMega scale. Furthermore, Graph RAG exhibits remarkable latency stability(0.86s–0.92s across all scale tiers) and robust resilience against topologicalnoise insertion. However, this analytical superiority introduces substantialoperational trade-offs: Graph RAG token consumption scales exponentiallyup to 2.70M tokens per query (an estimated cloud-equivalent cost of $6.75USD) at the Mega scale, whereas Vector RAG maintains a near-constant con-sumption of 262 tokens ($0.0007 USD). Finally, we synthesize these trade-offsand propose actionable architectural guidelines for deploying cost-effective,high-recall LLM solutions in critical infrastructure cybersecurity.

  • Metal Forming Process Efficiency Improvement Based on AI Services

    by Fernando Boto, Daniel Cabello, Juan Antonio Ortega, Blanca Puigjaner, Asier Alonso


  • Open Access

    Exploring Data Augmentation and Active Learning Benefits in Imbalanced Datasets

    by Luis Moles, Alain Andres, Goretti Echegaray, Fernando Boto

    Despite the increasing availability of vast amounts of data, the challenge of acquiring labeled data persists. This issue is particularly serious in supervised learning scenarios, where labeled data are essential for model training. In addition, the rapid growth in data required by cutting-edge technologies such as deep learning makes the task of labeling large datasets impractical. Active learning methods offer a powerful solution by iteratively selecting the most informative unlabeled instances, thereby reducing the amount of labeled data required. However, active learning faces some limitations with imbalanced datasets, where majority class over-representation can bias sample selection. To address this, combining active learning with data augmentation techniques emerges as a promising strategy. Nonetheless, the best way to combine these techniques is not yet clear. Our research addresses this question by analyzing the effectiveness of combining both active learning and data augmentation techniques under different scenarios. Moreover, we focus on improving the generalization capabilities for minority classes, which tend to be overshadowed by the improvement seen in majority classes. For this purpose, we generate synthetic data using multiple data augmentation methods and evaluate the results considering two active learning strategies across three imbalanced datasets. Our study shows that data augmentation enhances prediction accuracy for minority classes, with approaches based on CTGANs obtaining improvements of nearly 50% in some cases. Moreover, we show that combining data augmentation techniques with active learning can reduce the amount of real data required.


  • Combining physics-based and data-driven methods in metal stamping

    by Amaia Abanda, Amaia Arroyo, Fernando Boto, Miguel Esteras


  • Convolutional Neural Networks for Structured Industrial Data

    by Luis Moles, Fernando Boto, Goretti Echegaray, Iván G. Torre


  • Open Access

    Data Driven Performance Prediction in Steel Making

    by Fernando Boto, Maialen Murua, Teresa Gutierrez, Sara Casado, Ana Carrillo, Asier Arteaga

    This work presents three data-driven models based on process data, to estimate different indicators related to process performance in a steel production process. The generated models allow the optimization of the process parameters to achieve optimal performance and quality levels. A new approach based on ensembles has been developed with feature selection methods and four state-of-the-art regression approximations (random forest, gradient boosting, xgboost and neural networks). The results show that the proposed approach makes the prediction more stable reducing the variance for all cases, even in one case, slightly reducing the bias. Furthermore, from the four machine learning paradigms presented, random forest is the one with the best results in a quantitative way, obtaining a coefficient of determination of 0.98 as a maximum, depending on the target sub-process.


  • Open Access

    Metamodels’ Development for High Pressure Die Casting of Aluminum Alloy

    by Eva Anglada, Fernando Boto, Maider García de Cortazar, Iñaki Garmendia

    Simulation is a very useful tool in the design of the part and process conditions of high-pressure die casting (HPDC), due to the intrinsic complexity of this manufacturing process. Usually, physics-based models solved by finite element or finite volume methods are used, but their main drawback is the long calculation time. In order to apply optimization strategies in the design process or to implement online predictive systems, faster models are required. One solution is the use of surrogate models, also called metamodels or grey-box models. The novelty of the work presented here lies in the development of several metamodels for the HPDC process. These metamodels are based on a gradient boosting regressor technique and derived from a physics-based finite element model. The results show that the developed metamodels are able to predict with high accuracy the secondary dendrite arm spacing (SDAS) of the cast parts and, with good accuracy, the misrun risk and the shrinkage level. Results obtained in the predictions of microporosity and macroporosity, eutectic percentage, and grain density were less accurate. The metamodels were very fast (less than 1 s); therefore, they can be used for optimization activities or be integrated into online prediction systems for the HPDC industry. The case study corresponds to several parts of aluminum cast alloys, used in the automotive industry, manufactured by high-pressure die casting in a multicavity mold.


  • Open Access

    A slag prediction model in an electric arc furnace process for special steel production

    by Maialen Murua, Fernando Boto, Eva Anglada, Jose Mari Cabero, Leixuri Fernandez


  • Open Access

    Predictive Maintenance on the Machining Process and Machine Tool

    by Alberto Jimenez-Cortadi, Itziar Irigoien, Fernando Boto, Basilio Sierra, German Rodriguez

    This paper presents the process required to implement a data driven Predictive Maintenance (PdM) not only in the machine decision making, but also in data acquisition and processing. A short review of the different approaches and techniques in maintenance is given. The main contribution of this paper is a solution for the predictive maintenance problem in a real machining process. Several steps are needed to reach the solution, which are carefully explained. The obtained results show that the Preventive Maintenance (PM), which was carried out in a real machining process, could be changed into a PdM approach. A decision making application was developed to provide a visual analysis of the Remaining Useful Life (RUL) of the machining tool. This work is a proof of concept of the methodology presented in one process, but replicable for most of the process for serial productions of pieces.