Pablo Carmona

FRIwE: fuzzy rule identification with exceptions

In this paper, the FRIwE method is proposed to identify fuzzy models from examples. Such a method has been developed trying to achieve a double goal:accuracy and interpretability. In order to do that, maximal structure fuzzy rules are firstly obtained based on a method proposed by Castro et al. In a second stage, the conflicts generated by the maximal rules are solved, thus increasing the model accuracy. The resolution of conflicts are carried out by including exceptions in the rules. This strategy has been identified by psychologists with the learning mechanism employed by the human being, thus improving the model interpretability. Besides, in order to improve the interpretability even more, several methods are presented based on reducing and merging rules and exceptions in the model. The exhaustive use of the training examples gives the method a special suitability for problems with small training sets or high dimensionality. Finally, the method is applied to an example in order to analyze the achievement of the goals.

Strategies to identify fuzzy rules directly from certainty degrees: a comparison and a proposal

With identification methods that learn fuzzy rules directly from certainty degrees, we refer to methods that select the most promising rules from the training examples in only one pass. In order to do that, these methods employ a certainty measure to assess the goodness of each rule. This paper aims to analyze in depth the behaviors and features of two different strategies for identifying fuzzy models from certainty degrees, each of both combined with one of two well-known alternatives for measuring the certainty degrees of the rules. With this aim, the advantages and drawbacks of each method are analyzed experimentally by considering the model error when applied to several systems. Besides, the robustness of the results is investigated by applying the methods to noisy data. As a conclusion, a new method combining the best components of the previously considered methods is proposed and its results are analyzed. The achieved performance in accuracy and computational cost shows the benefit of this new method.

Using Ant Colony Optimization for Learning Maximal Structure Fuzzy Rules

Usually, the rules in a fuzzy model contain in the antecedent a set of propositions each of which restricts a fuzzy variable to a single fuzzy value by means of the predicate equal-to. That way, each rule covers a single fuzzy region of the fuzzy grid. This paper proposes to extent this structure in order to provide more general fuzzy rules, in the sense of covering the input space as much as possible. In order to do this, new predicates are considered and an ant colony optimization algorithm is proposed to learn such fuzzy rules. The obtained fuzzy models provide two benefits: they are described with a lower number of rules and their accuracy improves with the increase in generalization introduced. Some experimental results illustrate these facts

Learning maximal structure fuzzy rules with exceptions

This paper proposes a method to solve the conflicts that arise in the framework of fuzzy model identification with maximal rules (Fuzzy Sets and Systems 101 (1999) 331) where rules are selected as general as possible. This resolution is expressed by including exceptions in the rules, that way achieving a higher model interpretability with respect to other techniques and a more accurate model. Besides, several methods are presented to improve the interpretability, based on compacting the rules and exceptions of the model. Furthermore, in order to reduce the number of conflicts that arise from the maximal rules, a heuristic strategy is proposed to generate those maximal rules. Finally, the method is applied to an example and the results are compared with other identification methods.

Contradiction sensitive fuzzy model-based adaptive control

A simulated rain on a window pane panel assembly that can be used as a room divider, a head-board for a bed, a window replacement, or a door. It has a minor frame assembly having a pair of vertical side frame members interconnected adjacent their respective bottom ends by a bottom frame member. A pair of clear plastic panels cover the front and rear of the minor frame assembly to form a water tight chamber therebetween. A primary tubular member extends substantially across the width of the minor frame assembly adjacent its top and the primary tubular member is also positioned between the laterally spaced clear plastic panels. A plurality of apertures are formed in the bottom surface of the primary tubular member across its length. A major frame assembly laterally surrounds the minor frame assembly, and it contains shelves, speaker cabinets, a built in psychodelic light system, and a storage area beneath the minor frame assembly. The water pump is located in the storage area and flexible tubing connected between the pump and the primary tubular member. A water evacuation port is formed adjacent the bottom of the water tight chamber and a tube is connected between this port and the water pump. A secondary tubular member extends substantially across the width of the minor frame assembly adjacent its bottom and the tubular member has a plurality of apertures across its length along its top surface. An air pump is located in the storage area and flexible tubing is connected between one end of the secondary tubular member and the air pump.

An Ant Colony Optimization plug-in to Enhance the Interpretability of Fuzzy Rule Bases with Exceptions

Usually, fuzzy rules contain in the antecedent propositions that restrict a variable to a fuzzy value by means of an equal-to predicate. We propose to improve the interpretability of fuzzy models by extending the syntax of their rules. With this aim, on one hand, new predicates are considered in the rule antecedents and, on the other hand, rules can be associated with exceptions that modify the output of those rules in a region of their covered input space. The method stems from an initial fuzzy model described with the usual fuzzy rules and uses an ACO algorithm to search the optimal set of extended rules that describes this model.

An MDA Approach to Develop Web Components

Model-Driven Development (MDD) supports the automating of code generation by performing a set of transfomations between models. This approach is currently been applied to specific domains and in particular in the web domain, and this is because web aplications have evolved with the appearance of AJAX and Web 2.0 technology, and a new breed of applications for the Internet has emerged. However, as web applications become more and more complex, the performance degree is negatively affected, since the initial stages of software life cycle are not incorporated into the development process of this type of applications. In order to solve this problem, this paper proposes a model-driven architecture to support web application development from the design to the implementation model. With this objective, the following tasks have been performed: first a new profile extends UML with new concepts from the web domain, next a new framework supports web application development by composing web components, and finally, a transformation model generates web applications from the UML extension proposed. The main contributions of this work is a cost and complexity reduction of web applications, and a high reusability degree achieved, since web components can be reused in different web applications.

An Improved ACO Based Plug-in to Enhance the Interpretability of Fuzzy Rule Bases with Exceptions

In a previous work, the authors proposed, on one hand, an extension on the syntax of fuzzy rules by including new predicates and exceptional rules and, on the other hand, the use of an ant colony optimization algorithm to obtain an optimal set of such rules that describes an initial fuzzy model. The present work proposes several extensions on that algorithm in order to improve the interpretability of the obtained fuzzy model, as well as the computational cost of the algorithm. Experimental results on several initial fuzzy models reveal the gain obtained with each extension and when applied altogether.

Improvements in the identification of interpretable fuzzy models with exceptions based on ant colony optimization

In a previous work, the authors proposed, on one hand, an extension on the syntax of fuzzy rules by including new predicates and exceptional rules and, on the other hand, the use of an ant to obtain an optimal set of such rules that describes an initial fuzzy model. The present work proposes several extensions on that algorithm in order to improve the interpretability of the obtained fuzzy model, as well as the computational cost of the algorithm. Experimental results on several initial fuzzy models reveal the gain obtained with each extension and when applied altogether.

Commutativity as prior knowledge in fuzzy modeling

This paper faces with the integration of mathematical properties satisfied by the system as prior knowledge in fuzzy modeling (FM), focusing on the commutativity as a starting point. The underlying idea is to reward the rules in each input fuzzy region that provide good commutativity degrees respecting its complementary --commutatively related-- input fuzzy region. With this aim, the similarity between the outputs in both regions will be obtained. The experimental results show the accuracy improvement gained by the proposed method.