A neuro-fuzzy approach to agglomerative clustering

In this paper, we introduce a new agglomerative clustering algorithm in which each pattern cluster is represented by a collection of fuzzy hyperboxes. Initially, a number of such hyperboxes are calculated to represent the pattern samples. Then, the algorithm applies multi-resolution techniques to progressively "combine" these hyperboxes in a hierarchial manner. Such an agglomerative scheme has been found to yield encouraging results in real-world clustering problems.