Nebot Castells, Maria Angela
Total activity: 186
Research group
SOCO - Soft Computing
Department
Department of Computer Science
School
Barcelona School of Informatics (FIB)
E-mail
angelacs.upc.edu
Contact details
UPC directory Open in new window

Graphic summary
  • Show / hide key
  • Information


Scientific and technological production
  •  

1 to 50 of 186 results
  • PEM fuel cell fault diagnosis via a hybrid methodology based on fuzzy and pattern recognition techniques

     Escobet Canal, Antoni; Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    Engineering applications of artificial intelligence
    Vol. 36, p. 40-53
    DOI: 10.1016/j.engappai.2014.07.008
    Date of publication: 2014-08
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    In this work, a fault diagnosis methodology termed VisualBlock-Fuzzy Inductive Reasoning, i.e. VisualBlock-FIR, based on fuzzy and pattern recognition approaches is presented and applied to PEM fuel cell power systems. The innovation of this methodology is based on the hybridization of an artificial intelligence methodology that combines fuzzy approaches with well known pattern recognition techniques. To illustrate the potentiality of VisualBlock-FIR, a non-linear fuel cell simulator that has been proposed in the literature is employed. This simulator includes a set of five fault scenarios with some of the most frequent faults in fuel cell systems. The fault detection and identification results obtained for these scenarios are presented in this paper. It is remarkable that the proposed methodology compares favorably to the model-based methodology based on computing residuals while detecting and identifying all the proposed faults much more rapidly. Moreover, the robustness of the hybrid fault diagnosis methodology is also studied, showing good behavior even with a level of noise of 20 dB.

    In this work, a fault diagnosis methodology termed VisualBlock-Fuzzy Inductive Reasoning, i.e. VisualBlock-FIR, based on fuzzy and pattern recognition approaches is presented and applied to PEM fuel cell power systems. The innovation of this methodology is based on the hybridization of an artificial intelligence methodology that combines fuzzy approaches with well known pattern recognition techniques. To illustrate the potentiality of VisualBlock-FIR, a non-linear fuel cell simulator that has been proposed in the literature is employed. This simulator includes a set of five fault scenarios with some of the most frequent faults in fuel cell systems. The fault detection and identification results obtained for these scenarios are presented in this paper. It is remarkable that the proposed methodology compares favorably to the model-based methodology based on computing residuals while detecting and identifying all the proposed faults much more rapidly. Moreover, the robustness of the hybrid fault diagnosis methodology is also studied, showing good behavior even with a level of noise of 20 dB.

    © IFAC 2014. This work is posted here by permission of IFAC for your personal use. Not for distribution. The original version was published in ifac-papersonline.net

  • Exploration of Customer Churn Routes Using Machine Learning Probabilistic Models  Open access

     García Gómez, David
    Department of Computer Science, Universitat Politècnica de Catalunya
    Theses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Los procesos actuales de globalización y desregulación están cambiando el marco competitivo en la mayoría de sectores económicos. La aparición de nuevos competidores y tecnologías conlleva un fuerte aumento de la competencia y una preocupación creciente entre las empresas proveedoras de servicios por la creación de lazos más fuertes con los clientes. Muchas de estas empresas están redirigiendo recursos de la captación de nuevos clientes hacia la retención de los ya existentes. En este contexto, el anticiparse a la intención del cliente a abandonar al proveedor, fenómeno también conocido como "churn", y el facilitar la puesta en marcha de acciones enfocadas a la retención de clientes, son elementos claros de ventaja competitiva.La minería de datos, aplicada a información obtenida de los mercados analizados, puede ayudar en procesos de gestión del "churn". En esta tesis, analizamos datos reales de mercado para la investigación del "churn", enfatizando la aplicabilidad y la interpretación de los resultados. Los análisis están basados en la aplicación de modelos de "Statistical Machine Learning" a problemas de "clustering" y visualización, de los cuales se obtiene una segmentación interpretable de los mercados estudiados. Para lograr tal interpretabilidad, se presta mucha atención a la visualización intuitiva de los resultados experimentales. Dado que las técnicas de modelado utilizadas son de naturaleza no lineal, lo que representa un reto no trivial. Presentamos técnicas desarrolladas recientemente para la visualización de datos en modelos latentes no lineales. Estas se inspiran en métodos de representación geográfica y son adecuadas tanto para datos estáticos como para la representación de datos dinámicos.

    The ongoing processes of globalization and deregulation are changing the competitive framework in the majority of economic sectors. The appearance of new competitors and technologies entails a sharp increase in competition and a growing preoccupation among service providing companies with creating stronger bonds with customers. Many of these companies are shifting resources away from the goal of capturing new customers and are instead focusing on retaining existing ones. In this context, anticipating the customer¿s intention to abandon, a phenomenon also known as churn, and facilitating the launch of retention-focused actions represent clear elements of competitive advantage. Data mining, as applied to market surveyed information, can provide assistance to churn management processes. In this thesis, we mine real market data for churn analysis, placing a strong emphasis on the applicability and interpretability of the results. Statistical Machine Learning models for simultaneous data clustering and visualization lay the foundations for the analyses, which yield an interpretable segmentation of the surveyed markets. To achieve interpretability, much attention is paid to the intuitive visualization of the experimental results. Given that the modelling techniques under consideration are nonlinear in nature, this represents a non-trivial challenge. Newly developed techniques for data visualization in nonlinear latent models are presented. They are inspired in geographical representation methods and suited to both static and dynamic data representation.

  • Hierarchical fuzzy inductive reasoning classifier

     Bagherpour, Solmaz; Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    International Conference on Simulation and Modeling Methodologies, Technologies and Applications
    p. 434-442
    Presentation's date: 2014-08-30
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    Many of the inductive reasoning algorithms and techniques, including Fuzzy Inductive Reasoning (FIR), that learn from labelled data don¿t provide the possibility of involving domain expert knowledge to induce rules. In those cases that learning fails, this capability can guide the learning mechanism towards a hypothesis that seems more promising to a domain expert. One of the main reasons for omitting such involvement is the difficulty of knowledge acquisition from experts and, also, the difficulty of combining it with induced hypothesis. One of the successful solutions to such a problem is an alternative approach in machine learning called Argument Based Machine Learning (ABML) which involves experts in providing specific explanations in the form of arguments to only specific cases that fail, rather than general knowledge on all cases. Inspired by this study, the idea of Hierarchical Fuzzy Inductive Reasoning (HFIR) is proposed in this paper as the first step towards design and development of an Argument Based Fuzzy Inductive Reasoning method capable of providing domain expert involvement in its induction process. Moreover, HFIR is able to obtain better classifications results than classical FIR methodology. In this work, the concept of Hierarchical Fuzzy Inductive Reasoning is introduced and explored by means of the Zoo UCI benchmark.

  • A holistic seismic risk scheme using fuzzy sets

     González, Rubén; Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Carreño Tibaduiza, Martha Liliana; Barbat Barbat, Horia Alejandro
    International Conference on Simulation and Modeling Methodologies, Technologies and Applications
    p. 828-835
    Presentation's date: 2014-08-29
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    Hazard related Risk is a strange concept since its represents something that has not happened yet, something which is blur and randomness related. Along its estimation, social vulnerability aspects come to arise. Such aspects are even more difficult to define in part because there is still missing a robust way to quantify them and, therefore, to establish a clear analytic framework useful to understand inherent complexities of a human society. In this paper, we build a social aggravation coefficient fuzzy model considering Cardona-Carreño aggravation descriptors. By reducing the number of aggravation descriptors and establishing fuzzy logic rules between them, we found similar results in tendency and spatial distribution for seismic resilience and fragility at Barcelona, Spain. We used a classical Mamdani fuzzy approach, supported by well established fuzzy theory, which is characterized by a high expressive power and an intuitive human-like manner. We believe that in this way, a more clear analyses of the resilience and fragility bond can be done exploiting in a more suitable way fuzzy logic capabilities, because the inference process to obtain an aggravation coefficient is based precisely on the establishment of rules (if-then type) directly over the involved variables in social vulnerability formation which allows a smooth application of risk management knowledge, encouraging debate over the used rules, besides the discussion among the employed membership functions.

  • Cartogram visualization for nonlinear manifold learning models

     Vellido Alcacena, Alfredo; Garcia Cortes, David; Nebot Castells, Maria Angela
    Data mining and knowledge discovery
    Vol. 27, num. 1, p. 22-54
    DOI: 10.1007/s10618-012-0294-6
    Date of publication: 2013-07-01
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Real-world applications of multivariate data analysis often stumble upon the barrier of interpretability. Simple data analysis methods are usually easy to interpret, but they risk providing poor data models. More involved methods may instead yield faithful data models, but limited interpretability. This is the case of linear and nonlinear methods for multivariate data visualization through dimensionality reduction. Even though the latter have provided some of the most exciting visualization developments, their practicality is hindered by the difficulty of explaining them in an intuitive manner. The interpretability, and therefore the practical applicability, of data visualization through nonlinear dimensionality reduction (NLDR) methods would improve if, first, we could accurately calculate the distortion introduced by these methods in the visual representation and, second, if we could faithfully reintroduce this distortion into such representation. In this paper, we describe a technique for the reintroduction of the distortion into the visualization space of NLDR models. It is based on the concept of density-equalizing maps, or cartograms, recently developed for the representation of geographic information. We illustrate it using Generative Topographic Mapping (GTM), a nonlinear manifold learning method that can provide both multivariate data visualization and a measure of the local distortion that the model generates. Although illustrated here with GTM, it could easily be extended to other NLDR visualization methods, provided a local distortion measure could be calculated. It could also serve as a guiding tool for interactive data visualization

  • Towards the development of the smart grid: fast electricity load forecasting using different hybrid approaches

     Jurado Gómez, Sergio; Mugica Alvarez, Francisco José; Nebot Castells, Maria Angela; Avellana, Narcís
    DOI: 10.3233/978-1-61499-320-9-185
    Date of publication: 2013
    Book chapter

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Short-term electric load forecasting using computational intelligence methods

     Jurado Gómez, Sergio; Peralta Donate, Juan; Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Cortez, Paulo
    IEEE International Conference on Fuzzy Systems
    p. 1-8
    DOI: 10.1109/FUZZ-IEEE.2013.6622523
    Presentation's date: 2013-07-09
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Accurate time series forecasting is a key issue to support individual and organizational decision making. In this paper, we introduce several methods for short-term electric load forecasting. All the presented methods stem from computational intelligence techniques: Random Forest, Nonlinear Autoregressive Neural Networks, Evolutionary Support Vector Machines and Fuzzy Inductive Reasoning. The performance of the suggested methods is experimentally justi¿ed with several experiments carried out, using a set of three time series from electricity consumption in the real-world domain, on different forecasting horizons.

  • Visualizing pay-per-view television customers churn using cartograms and flow maps

     García Gómez, David; Nebot Castells, Maria Angela; Vellido Alcacena, Alfredo
    European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
    p. 567-572
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Media companies aggressively compete for their share of the pay-per-view television market. Such share can only be kept or improved by avoiding customer defection, or churn. The analysis of customers' data should provide insight into customers' behavior over time and help preventing churn. Data visualization can be part of this analysis. Here, a database of pay-per-view television customers is visualized using a nonlinear manifold learning model. This visualization is enhanced through, first, the reintroduction of the local nonlinear distortion using a cartogram technique and, second, the visualization of customer migrations using flow maps. Both techniques are inspired by geographical representation.

  • Mobile App and Website for major depression monitoring

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Abdollahi, Luca
    International Conference on Simulation and Modeling Methodologies, Technologies and Applications
    p. 605-612
    Presentation's date: 2013-07-30
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    One of the challenges for the patients diagnosed with major depression is not to experience relapse or reoccurrence which are very common characteristics of major depression. Providing constant monitoring of these patients during their daily life for the first year of their depression can have a significant impact on preventing these patients to experience reoccurrence and relapse. In this paper we describe an intelligent remote monitoring system that is in the process of development and present the new research done centered on the interaction between the system and the actors involved, i.e. patients, psychiatrists and primary care physicians. This interaction is done through an android application for mobile telephones and a Website. The specification and design of the information requested and submitted to system actors through both platforms is performed by the communication module, which is also described in this research.

  • Fuzzy approaches improve predictions of energy performance of buildings

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    International Conference on Simulation and Modeling Methodologies, Technologies and Applications
    p. 504-511
    Presentation's date: 2013-07-31
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    The energy consumption in Europe is, to a considerable extent, due to heating and cooling used for domestic purposes. This energy is produced mostly by burning fossil fuels with a high negative environmental impact. The characteristics of a building are an important factor to determine the necessities of heating and cooling loads. Therefore, the study of the relevant characteristics of the buildings with respect to the heating and cooling needed to maintain comfortable indoor air conditions, could be very useful in order to design and construct energy efficient buildings. In previous studies, statistical machine learning approaches have been used to predict heating and cooling loads from eight variables describing the main characteristics of residential buildings which obtained good results. In this research, we present two fuzzy modelling approaches that study the same problem from a different perspective. The prediction results obtained while using fuzzy approaches outperform the ones described in the previous studies. Moreover, the feature selection process of one of the fuzzy methodologies provide interesting insights to the principal building variables causally related to heating and cooling loads.

  • Telecommunications customers churn monitoring using flow maps and cartogram visualization

     Garcia Cortes, David; Nebot Castells, Maria Angela; Vellido Alcacena, Alfredo
    International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications
    p. 451-460
    Presentation's date: 2013-02
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    Telecommunication companies compete in increasingly aggressive markets. Avoiding customer defection, or churn, should be at the core of successful management in such context. These companies store and manage abundant customer usage data. Their analysis using advanced techniques can be a source of valuable insight into customers' behavior over time. Exploratory data visualization can help in this task. Many important contributions to multivariate data visualization using nonlinear techniques have recently been made. In this paper, we analyze a database of customer landline telephone usage in Brazil. These data are first visualized using a nonlinear manifold learning model, Generative Topographic Mapping (GTM). This visualization is enhanced using a cartogram technique, inspired in geographical representation methods, that reintroduces the local nonlinear distortion into the representation space. Yet another geographical information visualization technique, namely the Flow Maps, is then used to visualize customer migrations over time periods in the GTM data representation space. The experimental results shown in this paper provide evidence to support that the use of these methods can assist experts in the process of useful knowledge extraction, with an impact on customer retention management strategies.

  • Towards the development of the smart grid: fast electricity load forecasting using different hybrid approaches

     Jurado Gómez, Sergio; Mugica Alvarez, Francisco José; Nebot Castells, Maria Angela; Avellana, Narcís
    Congrés Internacional de l¿Associació Catalana d¿Intel·ligència Artificial
    p. 185-188
    DOI: 10.3233/978-1-61499-320-9-185
    Presentation's date: 2013-10
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    Currently, worldwide scientific community is doing a great effort of research in the area of Smart Grids because energy production, distribution, and consumption play a critical role in the sustainability of the planet. In this context, electricity load forecasting methodologies with fast response is a key component for demand-side management and the emergence of prosumers in the electricity grid. In this research it is shown that the computational intelligence techniques presented can deal with real time forecast, cope with incomplete measurement data and forecast signals of great variability, when applied to three real locations, with distinctly different characteristics.

  • Genetic learning of fuzzy parameters in predictive and decision support modelling

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Castro, Félix; Acosta, Jesús
    An international journal on computational intelligence techniques, methods and applications (Online)
    Vol. 5, num. 2, p. 387-402
    DOI: 10.1080/18756891.2012.685328
    Date of publication: 2012-04
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Fuzzy inductive reasoning: a consolidated approach to data-driven construction of complex dynamical systems

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    International journal of general systems
    Vol. 41, num. 7, p. 645-665
    DOI: 10.1080/03081079.2012.691203
    Date of publication: 2012
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Fuzzy inductive reasoning (FIR) is a modelling and simulation methodology derived from the General Systems Problem Solver. It compares favourably with other soft computing methodologies, such as neural networks, genetic or neuro-fuzzy systems, and with hard computing methodologies, such as AR, ARIMA, or NARMAX, when it is used to predict future behaviour of different kinds of systems. This paper contains an overview of the FIR methodology, its historical background, and its evolution.

    Fuzzy inductive reasoning (FIR) is a modelling and simulation methodology derived from the General Systems Problem Solver. It compares favourably with other soft computing methodologies, such as neural networks, genetic or neuro-fuzzy systems, and with hard computing methodologies, such as AR, ARIMA, or NARMAX, when it is used to predict future behaviour of different kinds of systems. This paper contains an overview of the FIR methodology, its historical background, and its evolution.

  • Quantitative and qualitative approaches for stock movement prediction

     Petchamé, Jordi; Nebot Castells, Maria Angela; Alquezar Mancho, Renato
    DOI: 10.3233/978-1-61499-139-7-233
    Date of publication: 2012
    Book chapter

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Generació de decisions davant d'incerteses  Open access

     Escobet Canal, Antoni
    Institute of Industrial and Control Engineering (IOC), Universitat Politècnica de Catalunya
    Theses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Aquesta tesi tracta sobre la metodologia del raonament inductiu difús (FIR, de l’anglès fuzzy inductive reasoning) aplicada a sistemes de detecció i diagnòstic de fallades. La metodologia FIR sorgeix de l’enfocament del general systems problem solver (GSPS) proposat per Klir l’any 1989 i és una eina per analitzar i estudiar els modes de comportament dels sistemes dinàmics. FIR és una metodologia de modelització i simulació qualitativa de sistemes basada principalment en l’observació del comportament del sistema. Aquesta metodologia ha anat evolucionant al llarg del temps amb l'objectiu d'ampliar la classe de problemes que es poden abordar amb FIR. El treball desenvolupat en aquesta tesi té el propòsit de contribuir a reduir els esforços de modelització i simulació de sistemes industrials reals complexos. En aquesta línia, s’ha aconseguit augmentar, mitjançant diferents aportacions, la robustesa de FIR i desenvolupar una nova metodologia que permeti crear sistemes de detecció i diagnòstic de fallades robustos i eficients. L’objectiu principal d’aquesta tesi és reduir tant com sigui possible la sensibilitat de la metodologia FIR, és a dir, maximitzar-ne la robustesa, de manera que esdevingui una eina cabdal per desenvolupar sistemes de detecció i diagnòstic de fallades eficients. Les contribucions principals de la tesi són: •Incrementar la robustesa del FIR creant una nova eina, anomenada Visual-FIR, que permet identificar models i predir comportaments futurs de sistemes dinàmics en un entorn molt senzill d’utilitzar i molt eficient. •Desenvolupar una nova metodologia per crear sistemes de detecció i diagnòstic de fallades basats en FIR. S’ha desenvolupat una tècnica de detecció, anomenada envolupant, i una mesura per al diagnòstic, anomenada mesura d’acceptabilitat del model, que han permès millorar i fer més sòlids els processos de detecció i diagnòstic de fallades del FIRFDDS (sistema de detecció i diagnòstic de fallades basat en FIR). •Desenvolupar una eina que permeti crear de manera senzilla i altament eficient FIRFDDS per a aplicacions específiques. S’ha desenvolupat una plataforma, anomenada VisualBlock-FIR, que permet que l’usuari creï, d’una manera senzilla, sistemes de detecció i diagnòstic de fallades basats en el FIR. Per validar la metodologia i les eines desenvolupades es mostren un parell de casos d’estudi. El primer correspon al problema de referència de la vàlvula automàtica de Damadics, en què es proposen quatre fallades de petita i mitjana magnitud que es detecten i s’aïllen/s’identifiquen d’una manera molt ràpida i eficient. En el segon es posa a prova el VisualBlock-FIR en una pila de combustible simulada a la qual s’apliquen cinc fallades diferents, les quals són detectades i identificades correctament. Finalment, es comprova la robustesa afegint soroll blanc, en diferents magnituds, a les sortides de la pila de combustible.

    This thesis deals with the Fuzzy Inductive Reasoning (FIR) methodology applied to fault detection and diagnosis systems. FIR, based on the General Systems Problem Solver (GSPS) proposed by Klir in 1989, is a methodological tool for data-driven construction of dynamical systems and for studying their conceptual modes of behavior. FIR is a qualitative modeling and simulation methodology that is based on observation of the input¿output behavior of the system to be modeled, rather than on structural knowledge about its internal composition. This methodology has evolved over time with the aim of enlarging the class of problems that can be dealt with by FIR. The work presented in this thesis aims to contribute to reducing modeling and simulation efforts of real industrial complex systems. Several methodological contributions have been made to increase FIR robustness as well as to develop a new methodology to create robust and efficient fault detection and diagnosis systems. The main objective of this thesis is to reduce as much as possible the sensitivity of the FIR methodology, by maximizing its robustness, in such a way that it becomes a fundamental tool for developing efficient fault detection and diagnosis systems. The main contributions of this thesis are: ¿To improve the robustness of FIR by creating a new tool, Visual-FIR, that identifies patterns and predicts future behavior of dynamical systems in a very efficient and simple to use environment. ¿To develop a new methodology for creating fault detection and diagnosis systems based on FIR. We have developed a detection technique, the enveloping, and a diagnosis measure, known as the acceptability measure, that allow improving and making more robust the fault detection and diagnosis processes of the FIRFDDS (fault detection and diagnosis system based on FIR). ¿To develop a tool that allows to easily create highly efficient FIRFDDS for specific applications. A platform, named VisualBlock-FIR, has been developed that allows the user to create, in a simple way, fault detection and diagnosis systems based on FIR. In order to validate the methodological contributions and the developed tools a couple of case studies have been presented in this dissertation. The first corresponds to the benchmark problem of the Damadics automatic valve system, which proposes four failures of small and medium sizes that are detected and isolated / identified in a quick and highly efficient way. The second is a simulated fuel cell where five different faults are applied. The five faults are detected and identified correctly. Finally, we check the robustness of the FIRFDDS by adding white noise, at different magnitudes, to the outputs of the fuel cell. Manresa

  • MADRIM: a major depression remote intelligent monitor

     Mugica Alvarez, Francisco José; Nebot Castells, Maria Angela; Bagherpour, Solmaz; Serrano-Blanco, Antoni; Baladón, Luisa
    IEEE International Conference on Fuzzy Systems
    DOI: 10.1109/FUZZ-IEEE.2012.6251148
    Presentation's date: 2012-06
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Quantitative and qualitative approaches for stock movement prediction

     Petchamé, Jordi; Nebot Castells, Maria Angela; Alquezar Mancho, Renato
    International Conference of the Catalan Association of Articial Intelligence
    p. 233-242
    DOI: 10.3233/978-1-61499-139-7-233
    Presentation's date: 2012
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Simple fuzzy logic models to estimate the global temperature change due to GHG emissions

     Gay García, Carlos; Sánchez Meneses, O.; Martínez López, B.; Nebot Castells, Maria Angela; Estrada Fernandez, Fco. Javier
    International Conference on Simulation and Modeling Methodologies, Technologies and Applications
    p. 518-526
    Presentation's date: 2012
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    Future scenarios (through 2100) developed by the Intergovernmental Panel on Climate Change (IPCC) indicate a wide range of concentrations of greenhouse gases (GHG) and aerosols, and the corresponding range of temperatures. These data, allow inferring that higher temperature increases are directly related to higher emission levels of GHG and to the increase in their atmospheric concentrations. It is evident that lower temperature increases are related to smaller amounts of emissions and, to lower GHG concentrations. In this work, simple linguistic rules are extracted from results obtained through the use of simple linear scenarios of emissions of GHG in the Magicc model. These rules describe the relations between the GHG, their concentrations, the radiative forcing associated with these concentrations, and the corresponding temperature changes. These rules are used to build a fuzzy model, which uses concentration values of GHG as input variables and gives, as output, the temperature increase projected for year 2100. A second fuzzy model is presented on the temperature increases obtained from the same model but including a second source of uncertainty: climate sensitivity. Both models are very attractive because their simplicity and capability to integrate the uncertainties to the input (emissions, sensitivity) and the output (temperature).

  • Prediction of PM2.5 concentrations using fuzzy inductive reasoning in Mexico city

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    International Conference on Simulation and Modeling Methodologies, Technologies and Applications
    p. 527-533
    Presentation's date: 2012
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    The research presented in this paper is focused on the study and development of fuzzy inductive reasoning models that allow the forecasting of daily particulate matter with diameter of 2.5 micrometres or less (PM2.5). FIR offers a model-based approach to modelling and predicting either univariate or multivariate time series. In this research, predictions of PM2.5 concentration at hour 12 of the next day, in the downtown of Mexico City Metropolitan Area, are performed. The data were registered every hour and include missing values. In this work the hourly modelling perspective is analyzed. The results are compared with the ones obtained using persistence models showing that the FIR models are able to predict PM2.5 concentrations more accurately than persistence models.

  • A framework to provide real time useful knowledge in e-learning environments

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Castro, Félix
    International Conference on Simulation and Modeling Methodologies, Technologies and Applications
    p. 103-108
    Presentation's date: 2012
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    This research presents a framework that provides valuable knowledge to teachers and students, mainly based on fuzzy logic methodologies. The framework offers the following knowledge: (1) gives a sets of rules describing the students' learning behaviour; (2) provides a relative assessment of the features involved in the students' evaluation performance, i.e. detects and assess the most important topics involved in the course evaluation process; (3) groups the learning behaviour of the students involved in online courses, in an incremental and dynamical way, with the ultimate goal to timely detect failing students, and properly provide them with a suitable and actionable feedback. In this paper the proposed framework is applied to the Didactic Planning course of Centre of Studies in Communication and Educational Technologies virtual campus. The application shows it usefulness, improving the course understanding and providing valuable knowledge to teachers about the course performance

  • Fault diagnosis system based on fuzzy logic: application to a valve actuator benchmark

     Escobet Canal, Antoni; Nebot Castells, Maria Angela; Cellier, François E.
    Journal of intelligent and fuzzy systems
    Vol. 22, num. 4, p. 155-171
    DOI: 10.3233/IFS-2011-0473
    Date of publication: 2011-05-09
    Journal article

     Share Reference managers Reference managers Open in new window

  • On the extraction of decision support rules from fuzzy predictive models

     Castro, Félix; Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    Applied soft computing
    Vol. 11, num. 4, p. 3463-3475
    DOI: 10.1016/j.asoc.2011.01.018
    Date of publication: 2011
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Fuzzy approaches for modeling dynamical ecological systems

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Martínez-López, Benjamín; Gay, Carlos
    International Conference on Simulation and Modeling Methodologies, Technologies and Applications
    p. 374-379
    Presentation's date: 2011-07-30
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Robust fault detection and identification in a fuel cell system via fuzzy models

     Escobet Canal, Antoni; Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    International Conference on Control Systems and Computer Science
    p. 150-257
    Presentation's date: 2011-05-26
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • A major depression patient evolution model based on qualitative reasoning

     Mugica Alvarez, Francisco José; Bagherpour, Solmaz; Nebot Castells, Maria Angela; Serrano-Blanco, Antoni; Baladón, Luisa
    Congrés Internacional de l¿Associació Catalana d¿Intel·ligència Artificial
    p. 147-156
    Presentation's date: 2011-10-27
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Confidence measures for predictions in fuzzy inductive reasoning

     Cellier, François E.; Lopez Herrera, Josefina; Nebot Castells, Maria Angela; Cembrano Gennari, M.gabriela Elena
    International journal of general systems
    Vol. 39, num. 8, p. 839-853
    DOI: 10.1080/03081079.2010.506180
    Date of publication: 2010
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Clustering educational data

     Vellido Alcacena, Alfredo; Castro, Félix; Nebot Castells, Maria Angela
    Date of publication: 2010
    Book chapter

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Detecció de fallades en un sistema de piles de combustible

     Escobet Canal, Antoni; Nebot Castells, Maria Angela
    Date: 2010-02-15
    Report

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • AIDTUMOUR: HERRAMIENTAS BASADAS EN METODOS DE INTELIGENCIA ARTIFICIAL PARA EL APOYO A LA DECISION EN

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Belanche Muñoz, Luis Antonio; Vellido Alcacena, Alfredo
    Competitive project

     Share

  • Fuzzy predictive models to help teachers in e-learning courses

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Castro, Félix
    IEEE World Congress on Computational Intelligence: IEEE International Joint Conference on Neural Networks (IJCNN)
    p. 2077-2083
    DOI: 10.1109/IJCNN.2010.5596582
    Presentation's date: 2010
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Genetic fuzzy system for predictive and decision support modelling in e-learning

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Castro, Félix; Acosta, Jesús
    International Conference on Complex Medical Engineering
    p. 1804-1811
    DOI: 10.1109/FUZZY.2010.5584229
    Presentation's date: 2010
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Causal relevance to improve the prediction accuracy of dynamical systems using inductive reasoning

     Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José; Castro, Félix
    International journal of general systems
    Vol. 38, num. 3, p. 331-358
    DOI: 10.1080/03081070802614247
    Date of publication: 2009
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • PM composition and source reconciliation in Mexico City

     Mugica, Violeta; Ortiz, E.; Molina, L.; De Vizcaya-Ruiz, A.; Nebot Castells, Maria Angela; Quintana, Robert; Aguilar, J.; Alcántara, E.
    Atmospheric environment
    Vol. 43, num. 32, p. 5068-5074
    DOI: 10.1016/j.atmosenv.2009.06.051
    Date of publication: 2009
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Fuzzy inductive reasoning for variable selection analysis and modelling of biological systems

     Nebot Castells, Maria Angela; Carvajal Valdes, Raul; Mugica Alvarez, Francisco José; Cellier, François E.
    International journal of general systems
    Vol. 38, num. 8, p. 793-811
    DOI: 10.1080/03081070903271095
    Date of publication: 2009
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Rule-based assistance to brain tumour diagnosis using LR-FIR

     Nebot Castells, Maria Angela; Castro, Félix; Vellido Alcacena, Alfredo; Julià Sapé, Margarida; Arús, Carles
    Date of publication: 2009-01-31
    Book chapter

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Machine learning is a powerful paradigm within which to analyze 1HMRS spectral data for the classification of tumour pathologies. An important characteristic of this task is the high dimensionality of the involved data sets. In this work we apply specific feature selection methods in order to reduce the complexity of the problem on two types of 1H-MRS spectral data: long-echo and short-echo time, which present considerable differences in the spectrum for the same cases. The experimental findings show that the feature selection methods enhance the classification performance of the models induced by several off-the-shelf classifiers and are able to offer very attractive solutions both in terms of prediction accuracy and number of involved spectral frequencies.

  • Fault detection and identification in a fuel cell system

     Escobet Canal, Antoni; Nebot Castells, Maria Angela
    International Conference of the Catalan Association for Artificial Intelligence
    p. 399-408
    Presentation's date: 2009-10
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Visual-FIR: a tool for model identification and prediction of dynamical complex systems

     Escobet Canal, Antoni; Nebot Castells, Maria Angela; Cellier, François E.
    Simulation modelling practice and theory
    Vol. 16, num. 1, p. 76-92
    DOI: 10.1016/j.simpat.2007.10.006
    Date of publication: 2008-01
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • dETECCIÓN DE ESTUDIANTES CON COMPORTAMIENTO ATÍPICO

     Vellido Alcacena, Alfredo; Nebot Castells, Maria Angela; Castro, F; Minguillón, J
    Date of publication: 2008-10-31
    Book chapter

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Detección de Estudiantes con Comportamiento Atípico en Entornos de Aprendizaje e-Learning

     Castro Espinoza, Felix Agustin; Vellido Alcacena, Alfredo; Nebot Castells, Maria Angela
    Date of publication: 2008-09-30
    Book chapter

     Share Reference managers Reference managers Open in new window

  • Rule-based assistance to brain tumour diagnosis using LR-FIR

     Nebot Castells, Maria Angela; Castro Espinoza, Felix Agustin; Vellido Alcacena, Alfredo; Julià Sapé, Margarida; Arús, Carles
    Lecture notes in computer science
    Vol. 5178, p. 173-180
    DOI: 10.1007/978-3-540-85565-1_22
    Date of publication: 2008-09
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This paper describes a process of rule-extraction from a multi-centre brain tumour database consisting of nuclear magnetic res- onance spectroscopic signals. The expert diagnosis of human brain tumours can benefit from computer-aided assistance, which has to be readily interpretable by clinicians. Interpretation can be achieved through rule extraction, which is here performed using the LR-FIR algorithm, a method based on fuzzy logic. The experimental results of the classiffication of three groups of tumours indicate in this study that just three spectral frequencies, out of the 195 from a range pre-selected by experts, are enough to represent, in a simple and intuitive manner, most of the knowledge required to discriminate these groups.

  • Fuzzy rules model for global warming decision suport

     Nebot Castells, Maria Angela
    VI Congreso internacional de la asociación española de climatología: Cambio climático regional y sus impactos
    Presentation's date: 2008-10-09
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Modelo difuso para la evaluación de la vulnerabilidad y la adaptación de los productores agrícolas Mexicanos

     Vermonden, A C Conde; Nebot Castells, Maria Angela; Gay, C
    Reunion anual 2008: Unión Geofísica Mexicana
    p. 314
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • A soft computing decision support framework to improve the e-learning experience

     Castro, Félix; Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    Modeling and Simulation in Education
    p. 781-788
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Generación de escenarios de emisiones mediante un controlador basado en lógica difusa

     Martínez, B; Nebot Castells, Maria Angela; Gay, C
    Reunión anual 2008: Unión Geofísica Mexicana
    p. 312
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Estimating the global temperature change by means of a fuzzy logic model abtained from IPCC published data

     Gay, C; Martínez, B; Nebot Castells, Maria Angela
    VI Congreso internacional de la asociación española de climatología: Cambio climático regional y sus impactos
    p. 543-551
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Fuzzy rules model for global warming decision suport

     Nebot Castells, Maria Angela; Benjamín, Martínez; Castro, Félix; Carlos, Gay
    VI Congreso internacional de la asociación española de climatología: Cambio climático regional y sus impactos
    p. 565-576
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • A soft computing decision support framework to improve the e-learning experience

     Castro, F; Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    Spring Simulation Multiconference - Modeling and Simulation Education
    p. 781-788
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Estimating the global temperature change by means of fuzzy logic models obtained from a simple climate model

     Benjamín, Martínez; Carlos, Gay; Nebot Castells, Maria Angela
    VI Congreso internacional de la asociación española de climatología: Cambio climático regional y sus impactos
    p. 553-563
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Applying data mining techniques to e-learning problems

     Castro, Félix; Vellido Alcacena, Alfredo; Nebot Castells, Maria Angela; Mugica Alvarez, Francisco José
    Studies in computational intelligence
    Vol. 62, p. 183-221
    DOI: 10.1007/978-3-540-71974-8_8
    Date of publication: 2007
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window