一种基于用户需求的加权模糊聚类分析算法

从用户的实际需求出发，分析了聚类系统的使用者可能对系统提出的功能要求，提出了一种基于加权Eucfid距离的模糊C聚类分析算法。在该算法中，权值是由用户或领域的专家直接指定的，加在不同特征指标上的权值体现了用户对各个特征指标重视程度的差别。与传统的模糊C聚类分析相比，该算法增加了聚类的灵活性，能够产生令用户更加满意的聚类结果。

A Weighting Fuzzy Clustering Algorithm Based on User's Demand

Proceeds from the user's actual demand,analyzes the functional demand which may be advanced by a user of a clustering system,and puts forward a sort of fuzzy C clustering algorithm based on Euclidean distance.In this algorithm,weight are directly appointed by user or domanial expert and the different weight endowed on different character indexes show the distinction of user's recognition to different character indexes.Comparing with the traditional fuzzy C-means clustering method,this algorithm increases the clustering's flexibility and produces a much more satisfactory clustering result.