Research on the Calculation Method for Weight of the Feature Weighted Fuzzy Clustering Algorithm

摘要：

In the traditional fuzzy C-Means algorithm,each feature of the samples plays a uniform contribution for clustering.But in fact,due to the feature selection are not perfect,and their scalarization have some blindness,each feature of the feature vector is not uniform for clustering contribution,so we have to take into account the different effect of each feature seriously.In this paper,we get a method for calculating the feature weight based on the feature contribution balance principle and the most separate degree principle of intra-cluster.By the IRIS example,we find that the calculation method for weight can not only enhance the calculation speed,and also make the clustering result better than the existing result.

关键词： FCM the feature weigh the center of clustering

作者: Xiaojun Tong Qin Jiang Haitao Gan Shah Zeng Kai Zhao

作者单位: Department of Mathematics and Physics,Wuhan Polytechnic University,Wuhan 430074,China Depatment of C Department of Mathematics and Physics,Wuhan Polytechnic University,Wuhan 430074,China

会议类型: 国际会议

会议名称: 2008年国际电子商务、工程及科学领域的分布式计算和应用学术研讨会(2008 International Symposium on Distributed Computing and Applications for Business Engineering and Science)

会议地点: 大连

会议语种:英文

页码: 677-682

在线出版日期: 2008-07-27（万方平台首次上网日期，不代表论文的发表时间）