Improvement of FCM Clustering Analysis Approach Based on the Weighted Indicator Variable

摘要

Similar degree is presented which could describe the degree of value similarity and the degree of shape similarity. Replaced conventional similar matrix by similar degree matrix, fuzzy clustering analysis method is improved. Then initial clustering centre is ascertained. Index weight is improved in FCM analysis approach; iterative formulas and corresponding algorithm are given. Improved FCM analysis approach is applied to the example of charge of tuition fees, and the clustering result has certain worthiness for the quoto of it.