| 李丹,顾宏,张立勇.基于属性加权的不完全数模糊 c 均值聚类算法[J].,2012,(5):749-754 |
| 基于属性加权的不完全数模糊 c 均值聚类算法 |
| An attribute weighted fuzzy c -means algorithm for incomplete data clustering |
| |
| DOI：10.7511/dllgxb201205021 |
| 中文关键词: 模糊聚类 模糊 c 均值 属性加权 不完全数据 缺失属性 |
| 英文关键词: fuzzy clustering fuzzy c -means attribute weighting incomplete data missing attribute |
| 基金项目:国家地震行业科研专项基金资助项目(200808075). |
|
| 摘要点击次数: 1470 |
| 全文下载次数: 1386 |
| 中文摘要: |
| 针对现有的不完全数模糊聚类算法未考虑样本各维属性对聚类贡献不同的问题,提出了基于属性加权的不完全数模糊 c 均值聚类算法．利用ReliefF算法评价各维属性的重要程度,通过加权欧式距离将属性权重结合入聚类,并能实现在聚类迭代过程中的缺失属性、隶属度及聚类中心的一体化求解．实验结果表明,该算法强调了重要属性在不完全数模糊聚类中的作用,能够得到更为准确的聚类结果． |
| 英文摘要: |
| In view of the problem that the existing algorithms for incomplete data fuzzy clustering generally view each dimensional attribute as equally important in contribution of clustering, an attribute weighted fuzzy c -means algorithm for incomplete data clustering is proposed. In the proposed algorithm, the important degree of each dimensional attribute is evaluated by the ReliefF algorithm and combined into fuzzy clustering by weighted Euclidean distance, and missing attribute values, membership and clustering centers can be obtained simultaneously. The experimental results show that the proposed algorithm can emphasize the important attributes in clustering, and better clustering results can be obtained. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|