A Novel Supervised Clustering Based on the Feature Classification Weight

In the d-dimensional feature space, the classification weight is defined against the different contribution of every feature that used to classification on the training sample set. And the classification weight calculates the membership functions which set up unascertained classification. Then a novel supervised clustering algorithm based on above is given. The algorithm is concise in calculation, fast in speed and effective in decreasing the computational complexity dramatically. IRIS data training demonstrates that the algorithm is much better than other clustering methods.