Dealing with missing data is of great practical and theoretical interest in forecasting applications. In this study, we deal with the problem of forecasting with missing data in smart grid and BEMS applications, where the information from home area sensors and/or smart meters is sometimes missing, which may hinder or even prevent the forecasting of the next hours and days. In concrete, we focus in a Soft Computing technique called Fuzzy Inductive Reasoning (FIR) and its improved version that can cope with missing information in the forecasting process: flexible FIR. In this article eight different strategies for flexible FIR forecasting are defined and studied taking into account: causal relevance of input variables, consistency of predictions, inertia criterion and K-Nearest Neighbours. Furthermore, we evaluate the implications of prediction accuracy and number of predictions, when the number of Missing Values (MVs) in the training dataset is increased progressively. To this end, a real smart grid forecasting application, i.e. electricity load forecasting, has been chosen in this study. The results show that all eight strategies proposed are able to cope with MVs and take advantage of the inherent information in the data, with better results in those strategies making use of causal relevance. In addition, the robustness of flexible FIR and its eight strategies are proved taking into account that the percentage of electricity load predictions from the test dataset is on average 96.15% when the %MVs in training dataset was around 73%.
BACKGROUND AND OBJECTIVE: Major depressive disorder causes more human suffering than any other disease affecting humankind. It has a high prevalence and it is predicted that it will be among the three leading causes of disease burden by 2030. The prevalence of depression, all of its social and personal costs, and its recurrent characteristics, put heavy constraints on the ability of the public healthcare system to provide sufficient support for patients with depression. In this research, a model for continuous monitoring and tracking of depression in both short-term and long-term periods is presented. This model is based on a new qualitative reasoning approach. METHOD: This paper describes the patient assessment unit of a major depression monitoring system that has three modules: a patient progress module, based on a qualitative reasoning model; an analysis module, based on expert knowledge and a rules-based system; and the communication module. These modules base their reasoning mainly on data of the patient's mood and life events that are obtained from the patient's responses to specific questionnaires (PHQ-9, M.I.N.I. and Brugha). The patient assessment unit provides synthetic and useful information for both patients and physicians, keeps them informed of the progress of patients, and alerts them in the case of necessity. RESULTS: A set of hypothetical patients has been defined based on clinically possible cases in order to perform a complete scenario evaluation. The results that have been verified by psychiatrists suggest the utility of the platform. CONCLUSION: The proposed major depression monitoring system takes advantage of current technologies and facilitates more frequent follow-up of the progress of patients during their home stay after being diagnosed with depression by a psychiatrist.
González, R.; Nebot, M.; Mugica, F. International Conference on Simulation and Modeling Methodologies, Technologies and Applications p. 376-382 DOI: 10.5220/0006031703760382 Data de presentació: 2016-07-30 Presentació treball a congrés
We aim towards the implementation of a set of fuzzy controllers capable to perform automated estimation of the period of time necessary to recover a resilience level through the non-linear influence of a set of interrelated climate change resilience indicators constrained by social-based variables. This fuzzy controller set, working together with a fuzzy inference system type Mamdani, will be capable to estimate the proper adjustments to be done onto system’s elements in order to achieve a certain resilience level, while a general estimation of required costs is appraised. The final tool can then be used to provide guidelines for strategic vulnerability planning and monitoring through a clear understanding between investments and results, while an open evaluation and scrutiny of applied policies is made. In this paper the main strategy to achieve the mentioned objectives is
presented and discussed.
In this paper a fuzzy controller capable to perform an automated estimation of the period of time necessary to recover a resilience level is proposed. Estimations where made by considering realistic time-dependent action changes for a set of resilience indicators originally proposed by Cardona (2001) and modified by Cardenas et al (2015). The fuzzy resilience controller works using two output control variables and four input variables designed to resemble politics decisions made over resilience recovery while considering an economical national growth factor. We applied the fuzzy controller onto Barcelona Spain, where different recovery times where estimated in terms of variations in Spaniard GDP (Gross domestic product) inter anual rate of change. This Decision Support System might be helpful to assist disaster reduction planning by allowing decision takers, governs or institutions to achieve reliable recovery time estimations while a proper supervision and control of resilience indicators progress is performed and an open evaluation and scrutiny of applied policies is made.
Paz-Ortiz, I.; Nebot, M.; Romero, E.; Mugica, F.; Vellido, A. IEEE Congress on Evolutionary Computation p. 1317-1323 DOI: 10.1109/CEC.2016.7743940 Data de presentació: 2016-07-26 Presentació treball a congrés
Algorithmic composition is the process of creating musical material by means of formal methods. As a consequence of its design, algorithmic composition systems are (explicitly or implicitly) described in terms of parameters. Thus, parameter space exploration plays a key role in learning the system's capabilities. However, in the computer music field, this task has received little attention. This is due in part, because the produced changes on the human perception of the outputs, as a response to changes on the parameters, could be highly nonlinear, therefore models with strongly predictable outputs are needed. The present work describes a methodology for the human perceptual (or aesthetic) exploration of generative systems' parameter spaces. As the systems' outputs are intended to produce an aesthetic experience on humans, audition plays a central role in the process. The methodology starts from a set of parameter combinations which are perceptually evaluated by the user. The sampling process of such combinations depends on the system under study and possible on heuristic considerations. The evaluated set is processed by a compaction algorithm able to generate linguistic rules describing the distinct perceptions (classes) of the user evaluation. The semantic level of the extracted rules allows for interpretability, while showing great potential in describing high and low-level musical entities. As the resulting rules represent discrete points in the parameter space, further possible extensions for interpolation between points are also discussed. Finally, some practical implementations and paths for further research are presented.
In this paper we are investigating the potentiality of the Fuzzy Inductive Reasoning (FIR) methodology as classifier applied to real world dataset. FIR is a modeling and simulation methodology that is best suited for dealing with regression and time series prediction. It has been shown in previous works that FIR methodology is a powerful tool for the identification and prediction of real systems, especially when poor or non-structural knowledge is available. FIR methodology falls under rule base supervised learning techniques. In this study we are studying the performance of the basic FIR classifier applied to imbalanced classification problems and comparing its results with well-known instance based and rule based approaches.
The present work describes an algorithm for human perceptual exploration of algorithmic composition systems' parameter spaces. It works by considering the values of the system parameters, together with the perceptual user evaluation of the system output corresponding to such parameter configuration, as input-output relations. Then, the algorithm iteratively searches in the data to find combinations of parameters with the same classification (evaluation) and differing only in the values of one parameter. If the absolute difference between them is less than a pre-established threshold, the combinations are compressed into one rule. The rules have the if-then standard form. As the parameters commonly express different physical dimensions (like amplitude and frequency), the threshold is set independently for each one. Finally, an example applied to the parameter space of a band limited impulse oscillator is presented.
The present thesis inquires about the use of artificial intelligent and soft computing methodologies to address topics related with risk to natural hazard and especially social vulnerability assessment. We propose a model based in fuzzy logic theory that is capable to produce reliable holistic or integral seismic risk estimations at urban level by mean of fuzzy composite indices. The model does not assume a linear interdependence between indices components when aggregation is performed. Moreover, since model’s inputs are converted into fuzzy sets, a large amount of indicator’s related uncertainty can be handled by fuzzy theory methods, allowing inferences based in logic rules can be obtained. We compared the proposed model’s performance with two different methodologies by conducting seismic risk estimations over the cities of Barcelona, Spain and Bogotá, Colombia. In order to show the potential of this methodology, we use different sub modules of the main fuzzy risk model to estimate the influence of the 2008 world economic crisis in Barcelona’s social aggravation over a period of time. Finally we developed a decision taking assistance tool in the form of a fuzzy controller. The designed tool can estimate resilience recovery times considering budget limitations and political constrains. The fuzzy controller was then used to estimate resilience recovery times for a city as Barcelona, considering a recession economic landscape.
Jurado, S.; Nebot, M.; Mugica, F. International Conference on Simulation Tools and Techniques p. 349-356 DOI: 10.4108/eai.24-8-2015.2261022 Data de presentació: 2015-08-25 Presentació treball a congrés
Load forecasting in buildings and homes has been in recent years a task of increasing importance. New services and functionalities can be offered in the home environment due to this predictions, for instance, the detection of potential demand response programs and peaks that may increase the energy bill in a dynamic tariff framework. Almost real-time predictions are key for these services but missing values can dramatically affect the performance of the energy forecasting or distort the prediction significantly. Fuzzy Inductive Reasoning has been proven to model load consumptions with high accuracy compared to other typical AI and statistical techniques. Nevertheless, it has several limitations when missing data is presented in the training data of the model and during prediction. In this paper, we present an improved version of Fuzzy Inductive Reasoning, called Flexible FIR Prediction that can cope with missing information in the input pattern as well as, in situations where patterns are not found in the behaviour matrix. The new technique has been tested with real data from one building of the Universitat Politècnica de Catalunya (UPC) and the results show that Flexible FIR Prediction is able to generate good predictions with low errors (less than 15%) although missing data is present in the training and online prediction phases.
Generalizing hypotheses based on the past data in order to predict the future is the essential core of human learning. Various successful methods and techniques have been developed so far that perform some sort of classification of current data in order to predict future unseen cases. Multi class classification problems are among them as well. In many domains in spite of these automatic techniques, involvement of human experts is crucial. In this paper we are proposing a Hierarchical perspective to Fuzzy Inductive Reasoning (FIR) method as a classifier, in order to provide more insights for experts to the predictive model offered by FIR. Also, This method puts a hierarchical constrain on FIR's generalization which might be useful in finding and predicting exceptional cases of data that don't follow the general rule offered by the model.
Algorithmic composition systems are now widely understood. However, its capacity for producing outputs consistently showing high level structures is still a field of research. In the present work, the Fuzzy Inductive Reasoning (FIR) methodology and an extension of it, the Linguistic rules in FIR (LR-FIR) are the main tools chosen for modeling such features. FIR/LR-FIR operates over the produced outputs of an algorithmic composition system, and through qualitative user evaluation is able to extract rules using configurations of low level characteristics that models high level features. Subsequently, the rules are used for the exploration of all possible outputs of an algorithmic system finding a subset of outputs showing the desired property. Finally extracted rules are evaluated and discussed in the context of musical knowledge.
González, R.; Nebot, M.; Mugica, F.; Crowley, H. International Conference on Simulation and Modeling Methodologies, Technologies and Applications p. 532-541 Data de presentació: 2015-07-23 Presentació treball a congrés
Traditional approaches to measure risk to natural hazards considers the use of composite indices. However, most of the times such indices are built assuming linear interrelations (interdependencies) between the aggregated components in such a way that the final index value is based only on an accumulative or scalable structure. In this paper we propose the use of Fuzzy Inference Systems type Mamdami in order to aggregate physical seismic risk and social vulnerability indicators. The aggregation is made by establishing rules (ifthen type) over the indicators in order to get an index. Finally a quantitative seismic risk estimation is made though the convolution of these two main factors by means of fuzzy inferences, in such a way that no linear assumptions are used along the estimation. We applied the fuzzy model over the city of Bogota Colombia.
We consider that this approach is a useful way to estimate a measure of an intangible reality such as seismic risk, by assuming the urban settlement’s complexity where the interrelations between the associated risk components are inherently non-linear. The proposed model possess a practical use over the risk management field, since the design of the logic rules uses a smooth application of risk management knowledge following a multidisciplinary approach, thus making the model easily adapted to a particular circumstance or context regardless the background of the final user.
Nebot, M.; Mugica, F.; Escobet, A. International Conference on Simulation and Modeling Methodologies, Technologies and Applications p. 501-507 Data de presentació: 2015-07-22 Presentació treball a congrés
Wine classification is a difficult task since taste is the least understood of the human senses. In this research we propose to use hybrid fuzzy logic techniques to predict human wine test preferences based on
physicochemical properties from wine analyses. Data obtained from Portuguese white wines are used in this study. The fuzzy inductive reasoning technique achieved promising results, outperforming not only the other fuzzy approaches studied but also other data mining techniques previously applied to the same dataset, such are neural networks, support vector machines and multiple regression. Modeling wine preferences may be useful not only for marketing purposes but also to improve wine production or support the oenologist wine tasting evaluations.
Scientific community is currently 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. The main challenge lies in intelligently integrating the actions of all users connected to the grid. In this context, electricity load forecasting methodologies is a key component for demand-side management. This research compares the accuracy of different Machine Learning methodologies for the hourly energy forecasting in buildings. The main goal of this work is to demonstrate the performance of these models and their scalability for different consumption profiles. We propose a hybrid methodology that combines feature selection based on entropies with soft computing and machine learning approaches, he. Fuzzy Inductive Reasoning, Random Forest and Neural Networks. They are also compared with a traditional statistical technique ARIMA (Auto Regressive Integrated Moving Average). In addition, in contrast to the general approaches where offline modelling takes considerable time, the approaches discussed in this work generate fast and reliable models, with low computational costs. These approaches could be embedded, for instance, in a second generation of smart meters, where they could generate on-site electricity forecasting of the next hours, or even trade the excess of energy.
In the last years, from a disasters perspective, risk has been dimensioned to allow a better management. However, this conceptualization turns out to be limited or constrained, by the generalized use of a fragmented risk scheme, which always consider first, the approach and applicability of each discipline involved. To be congruent with risk definition, it is necessary to consider an integral frame, and social factors must be included. Even those indicators that could tell something about the organizational and institutional capacity to withstand natural hazards, should be invited to the table. In this article, we analyze one of the most important elements in risk formation: the social aggravation, which can be regarded as the convolution of the resilience capacity and social fragility of an urban center. We performed a social aggravation estimation over Barcelona, Spain and Bogota, Colombia considering a particular hazard in the form of seismic activity. The Aggravation coefficient was achieved through a Mamdami fuzzy approach, supported by well-established fuzzy theory, which is characterized by a high expressive power and an intuitive human-like manner.
In the present work, the Fuzzy Inductive Reasoning methodology (FIR) is used to improve coherence among beat patterns, structured in a musical A-B form. Patterns were generated based on a probability matrix, encoding a particular musical style, designed by experts. Then, all possible patterns were generated and the most probables were selected. A-B musical forms were created and the coherence of the sequence was evaluated by experts by using linguistic quantities. The output pairs (A-B pattern and its qualification) were used as inputs to train a FIR system, and the variables that produce “coherent” outputs and the relations among
them where identified as rules. The extracted rules are discussed in the context of the musical form and from the psychological perception.
In the present work, the Fuzzy Inductive Reasoning methodology (FIR) is used to improve coherence among beat patterns, structured in a musical A-B form. Patterns were generated based on a probability matrix, encoding a particular musical style, designed by experts. Then, all possible patterns were generated and the most probables were selected. A-B musical forms were created and the coherence of the sequence was evaluated by experts by using linguistic quantities. The output pairs (A-B pattern and its qualification) were used as inputs to train a FIR system, and the variables that produce “coherent” outputs and the relations among them where identified as rules. The extracted rules are discussed in the context of the musical form and from the psychological perception.
Bagherpour, S.; Nebot, M.; Mugica, F. International Conference on Simulation and Modeling Methodologies, Technologies and Applications p. 434-442 Data de presentació: 2014-08-30 Presentació treball a congrés
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.
González, R.; Nebot, M.; Mugica, F.; Carreño, M.L.; Barbat, A. H. International Conference on Simulation and Modeling Methodologies, Technologies and Applications p. 828-835 Data de presentació: 2014-08-29 Presentació treball a congrés
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.
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.
Greenhouse gas emission scenarios (through 2100) developed by the Intergovernmental Panel on Climate Change when converted to concentrations and atmospheric temperatures through the use of climate models result in a wide range of concentrations and temperatures with a rather simple interpretation: the higher the emissions the higher the concentrations and temperatures. Therefore the uncertainty in the projected temperature due to the uncertainty in the emissions is large. Linguistic rules are obtained through the use of linear emission scenarios and the Magicc model. These rules describe the relations between the concentrations (input) and the temperature increase for the year 2100 (output) and are used to build a fuzzy model. Another model is presented that includes, as a second source of uncertainty in input, the climate sensitivity to explore its effects on the temperature. Models are attractive because their simplicity and capability to integrate the uncertainties to the input and the output.
Air pollution caused by small particles is a major public health problem in many cities of the world. One of the most contaminated cities is Mexico City. The fact that it is located in a volcanic crater surrounded by mountains helps thermal inversion and imply a huge pollution problem by trapping a thick
layer of smog that float over the city. Modeling air pollution is a political and
administrative important issue due to the fact that the prediction of critical events should guide decision making. The need for countermeasures against such episodes requires predicting with accuracy and in advance relevant indicators of air pollution, such are particles smaller than 2.5 microns (PM 2.5). In this work two different fuzzy approaches for modeling PM
2.5 concentrations in Mexico City metropolitan area are compared with respect the simple persistence method.
Jurado, S.; Mugica, F.; Nebot, M.; Avellana, N. Congrés Internacional de l’Associació Catalana d’Intel·ligència Artificial p. 185-188 DOI: 10.3233/978-1-61499-320-9-185 Data de presentació: 2013-10 Presentació treball a congrés
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.
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.
Nebot, M.; Mugica, F.; Abdollahi, L. International Conference on Simulation and Modeling Methodologies, Technologies and Applications p. 605-612 Data de presentació: 2013-07-30 Presentació treball a congrés
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.
Jurado, S.; Peralta, J.; Nebot, M.; Mugica, F.; Cortez, P. IEEE International Conference on Fuzzy Systems p. 1-8 DOI: 10.1109/FUZZ-IEEE.2013.6622523 Data de presentació: 2013-07-09 Presentació treball a congrés
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.
Mugica, F.; Nebot, M.; Bagherpour, S.; Serrano-Blanco, A.; Baladón, L. IEEE International Conference on Fuzzy Systems DOI: 10.1109/FUZZ-IEEE.2012.6251148 Data de presentació: 2012-06 Presentació treball a congrés
Nebot, M.; Mugica, F.; Castro, F.; Acosta, J. An international journal on computational intelligence techniques, methods and applications (Online) Vol. 5, num. 2, p. 387-402 DOI: 10.1080/18756891.2012.685328 Data de publicació: 2012-04 Article en revista
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.
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.
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
Mugica, F.; Bagherpour, S.; Nebot, M.; Serrano-Blanco, A.; Baladón, L. Congrés Internacional de l’Associació Catalana d’Intel·ligència Artificial p. 147-156 Data de presentació: 2011-10-27 Presentació treball a congrés
Nebot, M.; Mugica, F.; Martínez-López, B.; Gay, C. International Conference on Simulation and Modeling Methodologies, Technologies and Applications p. 374-379 Data de presentació: 2011-07-30 Presentació treball a congrés
In this paper an e-learning decision support framework based on a set of soft computing techniques is presented. The framework is mainly based on the FIR methodology and two of its key extensions: a set of Causal Relevance approaches (CR-FIR), that allow to reduce uncertainty during the forecast stage; and a Rule Extraction algorithm (LR-FIR), that extracts comprehensible, actionable and consistent sets of rules describing the student learning behavior. The data set analyzed was gathered from the data generated from user’s interaction with an e-learning environment. The introductory course data set was analyzed with the proposed framework with the goal to help virtual teachers to understand the underlying relations between the actions of the learners, and make more interpretable the student learning behavior. The results obtained improve system understanding and provide valuable knowledge to teachers about the course performance.
MILAGRO project was conducted in Mexico City during March 2006 with the main objective of study the local and global impact of pollution generated by megacities. The research presented in this paper is framed in MILAGRO project and is focused on the study and development of modeling methodologies that allow the forecasting of daily ozone concentrations. The present work aims to develop Fuzzy Inductive Reasoning (FIR) models using the Visual-FIR platform. FIR offers a model-based approach to modeling and predicting either univariate or multivariate time series. Visual-FIR offers an easy-friendly environment to perform this task. In this research, long term prediction of maximum ozone concentration in the downtown of Mexico City Metropolitan Area is performed. The data were registered every hour and include missing values. Two modeling perspectives are analyzed, i.e. monthly and seasonal models. The results show that the developed models are able to predict the diurnal variation of ozone, including its maximum daily value in an accurate manner.
The aim of this research is to develop a new methodology called UNFIR (uncertainty in FIR) as an extension of the fuzzy inductive reasoning (FIR) technique. The main idea behind UNFIR is to expand the modeling capacity of the FIR methodology allowing it to work with classical fuzzy rules. On the one hand, UNFIR is able to automatically construct fuzzy rules starting from a set of pattern rules obtained by FIR. On the other hand, UNFIR affords the prediction of systems behavior by using a mixed pattern/fuzzy inference system that takes advantage of the uncertainty inherent to the data. The pattern rule base that the FIR methodology generates can be very large, obstructing the prediction process and reducing its efficiency. The new methodology preserves as much as possible the knowledge of the pattern rules in a compact fuzzy rule base. In this process some precision is lost but the robustness is considerably increased.
The performance of UNFIR methodology as a systems’ prediction tool is also studied in this work. Three different applications are used for this purpose, i.e., a linear system, a non-linear system and an industrial process.