An New Fuzzy Clustering Algorithm Based on Entropy Weighting

In the paper, the traditional FCM (Fuzzy C-Means) clustering algorithm is very sensitive to the initial center values, requirements on the data set too high, and cannot handle noisy data. So, the paper proposes the method of using information entropy to initialize cluster centers and introduces weighting parameter to adjust the location of cluster centers and noise problem in order to reduce the algorithm's dependence on the initial cluster centers and data sets. Meanwhile, in order to make algorithm to clusters of arbitrary shape clustering, the paper quoted the merger idea, which splits into clusters of arbitrary shape categories, and then sorts through some of the rules on the merger.

Provided by: Binary Information Press Topic: Data Management Date Added: Oct 2010 Format: PDF

Find By Topic