Fuzzy clustering algorithms and their cluster validity

A non metric clustering algorithm based on a fuzzy objective function which reflects proximity based on some global dissimilarity measure is proposed. The global optimal solution is shown to be difficult to obtain and an alternative iterative procedure is presented. This procedure is easily implemented and converges to a local optimum. Some validity functionals which measure the effectiveness with which cluster structure has been identified are compared in relation with the iterative procedures described in the paper.