Examinando por Autor "Alfaro, Cesar"

Mostrando 1 - 11 de 11

Adapting support vector optimisation algorithms to textual gender classification
(Springer, 2024-04-13) Gómez, Javier; Alfaro, Cesar; Ortega, Felipe; Moguerza, Javier M.; Algar, Maria Jesus; Moreno, Raul
In this paper, we focus on the problem of determining the gender of the person described in a biographical text. Since support vector machine classifiers are well suited for text classification tasks, we present a new stopping criterion for support vector optimisation algorithms tailored to this problem. This new approach exploits the geometric properties of the vector representation of such content. An experiment on a set of English and Spanish biographical articles retrieved from Wikipedia illustrates this approach and compares it to other machine learning classification algorithms. The proposed method allows real-time classification algorithm training. Moreover, these results confirm the advantage of leveraging additional gender information in strongly inflected languages, like Spanish, for this task
Advanced System for Enhancing Location Identification through Human Pose and Object Detection
(MDPI, 2023-08-18) Medrano, Kevin; Crespo, Jonathan; Gomez, Javier; Alfaro, Cesar
Location identification is a fundamental aspect of advanced mobile robot navigation systems, as it enables establishing meaningful connections between objects, spaces, and actions. Understanding human actions and accurately recognizing their corresponding poses play pivotal roles in this context. In this paper, we present an observation-based approach that seamlessly integrates object detection algorithms, human pose detection, and machine learning techniques to effectively learn and recognize human actions in household settings. Our method entails training machine learning models to identify the common actions, utilizing a dataset derived from the interaction between human pose and object detection. To validate our approach, we assess its effectiveness using a diverse dataset encompassing typical household actions. The results demonstrate a significant improvement over existing techniques, with our method achieving an accuracy of over 95% in classifying eight different actions within household environments.. Furthermore, we ascertain the robustness of our approach through rigorous testing in real-world environments, demonstrating its ability to perform well despite the various challenges of data collection in such settings. The implications of our method for robotic applications are significant, as a comprehensive understanding of human actions is essential for tasks such as semantic navigation. Moreover, our findings unveil promising opportunities for future research, as our approach can be extended to learn and recognize a wide range of other human actions. This perspective, which highlights the potential leverage of these techniques, provides an encouraging path for future investigations in this field.
ESPRES: A web application for interactive analysis of multiple pressures in aquatic ecosystems
(Elsevier, 2020-11-20) Udias, Angel; Pistocchi, Alberto; Vigiak, Olga; Grizzetti, Bruna; Bouraoui, Faycal; Alfaro, Cesar
ESPRES (Efficient Strategies for anthropogenic Pressure Reduction in European waterSheds) is a web-based Decision Support System (DSS) designed to explore management options for achieving environmental targets in European freshwaters. The tool integrates multi-objective optimization (MOO) algorithms for selecting the best management options in a river basin and models assessing the consequent changes in the water quantity (water flow) and quality (nutrient concentration). The MOO engine identifies Pareto front strategies that are trade-offs between environmental objectives for water bodies and the effort required for reducing the pressures. The web interface provides tools to set the effort perceived by different river basin stakeholders considering technical feasibility, political difficulty, and social acceptability of the alternative options. The environmental impact of management options (scenarios) is assessed with models developed at the European scale. ESPRES enables comparison of management solutions and allows quantifying environmental and socio-economic trade-offs inherent to the decision making process.
ESPRES: A web application for interactive analysis of multiple pressures in aquatic ecosystems
(Elsevier, 2020-07-11) Udias, Angel; Pistocchi, Alberto; Vigiak, Olga; Grizzetti, Bruna; Bouraoui, Faycal; Alfaro, Cesar
ESPRES (Efficient Strategies for anthropogenic Pressure Reduction in European waterSheds) is a web-based Decision Support System (DSS) designed to explore management options for achieving environmental targets in European freshwaters. The tool integrates multi-objective optimization (MOO) algorithms for selecting the best management options in a river basin and models assessing the consequent changes in the water quantity (water flow) and quality (nutrient concentration). The MOO engine identifies Pareto front strategies that are trade-offs between environmental objectives for water bodies and the effort required for reducing the pressures. The web interface provides tools to set the effort perceived by different river basin stakeholders considering technical feasibility, political difficulty, and social acceptability of the alternative options. The environmental impact of management options (scenarios) is assessed with models developed at the European scale. ESPRES enables comparison of management solutions and allows quantifying environmental and socio-economic trade-offs inherent to the decision making process.
Forecasting and assessing consequences of aviation safety occurrences
(Elsevier, 2019-01) Rios Insua, David; Alfaro, Cesar; Gomez, Javier; Hernandez-Coronado, Pablo; Bernal, Francisco
Aviation safety is essential for the healthy growth and sustainability of the global economy. The implementation of Safety Management Systems to support safe service delivery has become one of the most important goals within the airline industry over the last years. However, in most cases the involved organisations use unsophisticated methods based on risk matrices for the development of such systems. In this paper, we present models to forecast and assess the consequences of aviation safety occurrences as part of a framework for aviation safety risk management at state level.
Forecasting aviation safety occurrences
(John Wiley & Sons Ltd., 2022-06-17) Flores, Bruno; Rios Insua, David; Alfaro, Cesar; Gomez, Javier
We present a general framework for aviation safety occurrence forecasting. This is a major component of a methodology for aviation safety risk management at national level. It covers novel models as well as novel combinations of earlier models. Having good quality occurrence and severity forecasting models is paramount to properly manage risks, maintain the confidence of its users and preserve the status of aviation as a safe transportation mode. The problem is involved due to the presence of complex effects like seasonality, trends, or stress that impact the rates of various occurrences and the uncertainty about future number of operations.
GREENeR: An R Package to Estimate and Visualize Nutrients Pressures on Surface Waters
(The R Foundation, 2023-09) Udías , Angel; Grizzetti, Bruna; Vigiak, Olga; Aloe, Alberto; Alfaro, Cesar; Gomez, Javier
Nutrient pollution affects fresh and coastal waters around the globe. Planning mitigating actions requires tools to assess fluxes of nutrient emissions to waters and expected restoration impacts. Conceptual river basin models take advantage of data on nutrient emissions and concentrations at monitoring stations, providing a physical interpretation of monitored conditions, and enabling scenario analysis. The GREENeR package streamlines water quality model in a region of interest, considering nutrient pathways and the hydrological structure of the river network. The package merges data sources, analyzes local conditions, calibrate the model, and assesses yearly nutrient levels along the river network, determining contributions of load in freshwaters from diffuse and point sources. The package is enriched with functions to perform thorough parameter sensitivity analysis and for mapping nutrient sources and fluxes. The functionalities of the package are demonstrated using datasets from the Vistula river basin.
Out of the Niche: Using Direct Search Methods to Find Multiple Global Optima
(MDPI, 2022-04-30) Cano, Javier; Alfaro, Cesar; Gomez, Javier; Duarte, Abraham
Multimodal optimization deals with problems where multiple feasible global solutions coexist. Despite sharing a common objective function value, some global optima may be preferred to others for various reasons. In such cases, it is paramount to devise methods that are able to find as many global optima as possible within an affordable computational budget. Niching strategies have received an overwhelming attention in recent years as the most suitable technique to tackle these kinds of problems. In this paper we explore a different approach, based on a systematic yet versatile use of traditional direct search methods. When tested over reference benchmark functions, our proposal, despite its apparent simplicity, noticeably resists the comparison with state-of-the-art niching methods in most cases, both in the number of global optima found and in the number of function evaluations required. However, rather than trying to outperform niching methods—far more elaborated—our aim is to enrich them with the knowledge gained from exploiting the distinctive features of direct search methods. To that end, we propose two new performance measures that can be used to evaluate, compare and monitor the progress of optimization algorithms of (possibly) very different nature in their effort to find as many global optima of a given multimodal objective function as possible. We believe that adopting these metrics as reference criteria could lead to more sophisticated and computationally-efficient algorithms, which could benefit from the brute force of derivative-free local search methods.
Safer skies over Spain
(Institute for Operations Research and Management Sciences, 2020-01-24) Elvira, Veronica; Bernal, Francisco; Hernandez-Coronado, Pablo; Herraiz, Esperanza; Alfaro, Cesar; Gomez, Javier; Rios Insua, David
Agencia Estatal de Seguridad Aerea, the Spanish aviation safety and security agency, applied an innovative risk-analysis methodology and decision support system, developed in partnership with the Spanish Royal Academy of Sciences, to improve Spain’s national aviation safety. The agency uses several analytics methods to forecast the likelihood and impact of various types of safety occurrences. This enables management to focus attention and resources where they will be most effective. For example, a nonlinear optimization model allocates inspection resources. The result has been a major improvement in aviation safety, which led to reductions in aircraft repairs, maintenance, delays, and expenses. The agency estimated annual savings to be about 800 million euros in equivalent safety costs.
Toward Accelerated Training of Parallel Support Vector Machines Based on Voronoi Diagrams
(MDPI, 2021-11-29) Alfaro, Cesar; Gomez, Javier; M. Moguerza, Javier; Castillo, Javier; Martinez, Jose I.
Typical applications of wireless sensor networks (WSN), such as in Industry 4.0 and smart cities, involves acquiring and processing large amounts of data in federated systems. Important challenges arise for machine learning algorithms in this scenario, such as reducing energy consumption and minimizing data exchange between devices in different zones. This paper introduces a novel method for accelerated training of parallel Support Vector Machines (pSVMs), based on ensembles, tailored to these kinds of problems. To achieve this, the training set is split into several Voronoi regions. These regions are small enough to permit faster parallel training of SVMs, reducing computational payload. Results from experiments comparing the proposed method with a single SVM and a standard ensemble of SVMs demonstrate that this approach can provide comparable performance while limiting the number of regions required to solve classification tasks. These advantages facilitate the development of energy-efficient policies in WSN.
Uncertainty in functional network representations of brain activity of alcoholic patients
(Springer, 2020-10-12) Zanin, Massimiliano; Belkoura, Sedik; Gomez, Javier; Alfaro, Cesar; Cano, Javier
In spite of the large attention received by brain activity analyses through functional networks, the effects of uncertainty on such representations have mostly been neglected. We here elaborate the hypothesis that such uncertainty is not just a nuisance, but that on the contrary is condition-dependent. We test this hypothesis by analysing a large set of EEG brain recordings corresponding to control subjects and patients suffering from alcoholism, through the reconstruction of the corresponding Maximum Spanning Trees (MSTs), the assessment of their topological differences, and the comparison of two frequentist and Bayesian reconstruction approaches. A machine learning model demonstrates that the Bayesian reconstruction encodes more information than the frequentist one, and that such additional information is related to the uncertainty of the topological structures. We finally show how the Bayesian approach is more effective in the validation of generative models, over and above the frequentist one, by proposing and disproving two models based on additive noise.