The learning of a Fuzzy Rule-Based Classification System (FRBCS) by means of a supervised inductive process fundamentally implies four tasks that are complementary among them: the selection of the most informative variables to the classification problem to solve, the generation of a set of rules, the selection of the subset of rules with the best co-operation and the least redundancy, and the e...

Continuing to pursue a research direction that we already explored in connection with Gödel-Dummett logic and Ruspini partitions, we show here that Lukasiewicz logic is able to express the notion of pseudo-triangular basis of fuzzy sets, a mild weakening of the standard notion of triangular basis. En route to our main result we obtain an elementary, logic-independent characterisation of triangu...

The fundamental concept in the theory of fuzzy transform (F-transform) is that of fuzzy partition. The original definition assumes that each two fuzzy subsets overlap in such a way that sum of membership degrees in each point is equal to 1. However, this condition can be generalized to obtain a denser fuzzy partition that leads to improvement of approximation properties of Ftransform. However, ...

This work proposes a load balance algorithm to parallel processing based on a variation of the classical knapsack problem. The problem considers the distribution of a set of partitions, defined by the number of clusters, over a set of processors attempting to achieve a minimal overall processing cost. The work is an optimization for the parallel fuzzy c-means (FCM) clustering analysis algorithm...

In this paper, conventional validity indexes are reviewed and the shortcomings of the fuzzy cluster validation index based on intercluster proximity are examined. Based on these considerations, a new cluster validity index is proposed for fuzzy partitions obtained from the fuzzy c-means algorithm. The proposed validity index is defined as the average value of the relative intersections of all p...

A new clustering algorithm for proximity data, called RECM (Relational evidential c-means) is presented. This algorithm generates a credal partition, a new clustering structure based on the theory of belief functions, which extends the existing concepts of hard, fuzzy and possibilistic partitions. Two algorithms, EVCLUS (Evidential Clustering) and ECM (Evidential c-Means) were previously availa...

This work explores the applicability of fuzzy clustering methods to the segmentation of sea surface temperature (SST) images for the automatic identification of upwelling areas in the coastal ocean of Portugal. This has been done by exploring the fuzzy c-means algorithm. Visualization of fuzzy c-partitions is achieved by means of color mapping. Selection of the best c-partition that represents ...

Some methods of fuzzy clustering need to use a priori knowledge about the number of fuzzy classes or some other information about the possible distribution of the clusters. A way to improve these methods is to use hierarchical clustering as a preprocessing of the data. This approach does not provide a simple partition of the data set, but a hierarchy of them. In this paper we define several mea...