An Efficient Fuzzy Kohonen Clustering Network Algorithm

Fuzzy Kohonen clustering networks (FKCN) are well known for clustering analysis (unsupervised learning and self-organizing). This classification of FKCN algorithm is a set of iterative procedures that suffer some major problems, for example its constringency rate is not too fast for a large amount of datasets. To overcome these defects, an efficient fuzzy Kohonen network algorithm is proposed in this paper, which can significantly reduce the computation time required to partition a dataset into desired clusters. By introducing the threshold values and fuzzy convergence operators in the network learning procedure to adjust the learning rates dynamically, the network convergence rate is greatly improved and the error rates of dataset cluster are significantly decreased. Experimental results show the new algorithm is on average three times faster than the original FKCN algorithm. We also demonstrate that the quality of the improved FKCN is better than the original FKCN algorithm.