Neuro--fuzzy classification systems offer means to obtain fuzzy classification rules by a learning algorithm. It is usually no problem to find a suitable fuzzy classifier by learning from data, however, it can be hard to obtain a classifier that can be interpreted conveniently. In this paper we discuss extensions to the learning algorithms of NEFCLASS, a neuro--fuzzy approach for data analysis that we have presented before. We show how interactive strategies for pruning rules and variables from a trained classifier can enhance its interpretability. 1 Introduction NEFCLASS is used to derive fuzzy rules from a set of data that can be separated in different crisp classes. The fuzzy rules describing the data are of the form: R : if x 1 is ¯ 1 and x 2 is ¯ 2 and : : : and xn is ¯n then the pattern (x 1 ; x 2 ; : : : ; xn ) belongs to class i, where ¯ 1 ; : : : ; ¯n are fuzzy sets. The task of the NEFCLASS model (NEuro Fuzzy CLASSification) is to discover these rules and to learn the sha...

The paper proposes a new Empirical Risk Functional as cost function for training neuro-fuzzy classifiers. This cost function, called Approximate Differentiable Empirical Risk Functional (ADERF), provides a differentiable approximation of the misclassification rate so that the Empirical Risk Minimization Principle formulated in Vapnik's Statistical Learning Theory can be applied. Also, based on the proposed ADERF, a learning algorithm is formulated. Experimental results on a number of benchmark classification tasks are provided and comparison to alternative approaches given.

This paper deals with a generic solution for combat control problem which is generally addressed using conventional methods and human decision making. The aim of this paper is to develop the soft computing approach to automate the decision making process for combat control operations. The automatic combat control system design usually consists of four stages. The first stage is to select the sensor or sensors to produce the target measurements. The next stage is the preprocessing of the data and the location of regions of interest within the data (segmentation). The third design step is feature extraction and selection. The last step is the processing of the features for decision making (classification and combat). This paper deals with only combat control part which is the most challenging problem to be solved in real battle field scenario. Usually this part is being done using decisions taken by human operators. In order to automate this process, generally hard classifiers are being used for combat control operations. These hard classification approaches does not give good performance in noisy environment. A relatively new and emerging soft computing approach, which is a combination of Neural Network and Fuzzy classification techniques, is proposed for performance improvement. The algorithm developed in this paper is tested for a typical combat control problem which deals with selecting a particular weapon against a target in optimum way. The soft computing approach proposed here has demonstrated a relatively complex decision making in noisy environment, with a large number of input parameters.

This document describes the hierarchical agglomerative cluster algorithm Pnc 2 in the context of direct generation of If-Then rules for classification tasks. As an agglomerative cluster algorithm, the Pnc 2 initializes each learn data tuple as a single cluster. Then, if a merge test is passed, iteratively always those two clusters with the same output value are merged, that are closest to each other. The merge test transforms the generalized cluster into a rule and evaluates it by a kind of hitrate. The rule's premise is the cuboid, that encloses the input vectors of all learn data tuples merged in the cluster. This representation su#ers in high dimensional input spaces due to the COD problem and thus a special mechanism is used to extend the cuboid during the merge test.

Fuzzy logic is a natural basis for modelling and solving problems involving imprecise knowledge and continuous systems. Unfortunately, fuzzy logic systems are invariably static (once created they do not change) and subjective (the creator imparts their beliefs on the system). In this paper we address the question of whether systems based on fuzzy logic can e#ectively adapt themselves to dynamic situations.

Neuro-fuzzy (NF) decision-making technology is designed and implemented to obtain the optimal daily currency trading rule. We find that a non-linear artificial neural network (ANN) exchange rate microstructure model combined with a fuzzy logic controller (FLC) generates a set of trading strategies that, on average, earn a higher rate of return compared to the simple buy-and-hold strategy. We also find that after including transaction costs, the gains from the NF technology do not decline and increase on some periods. Finally, we successfully apply the NF model to the problem of determining the FX market’s sentiment as reflected by the chartists ’ trading signals during periods of strong depreciation. 1.