基于模糊C-means的多视角聚类算法

来源期刊:中南大学学报(自然科学版)2015年第6期

论文作者:杨欣欣 黄少滨

文章页码:2128 - 2134

关键词:多视角聚类;模糊C-means;数据挖掘

Key words:multi-view clustering; fuzzy C-means; data mining

摘    要:目前多数多视角聚类算法属于“刚性”划分算法,不适用于处理具有聚簇重叠结构的数据集,为此,提出一种基于模糊C-means的多视角聚类算法(简称FCM-MVC),该算法利用隶属度描述对象与类别的关系,能够更真实地描述具有聚簇重叠结构数据集的聚类结果。FCM-MVC算法同时利用多个视角信息,自动计算每个视角的权重。研究结果表明:FCM-MVC算法能够有效处理具有聚簇重叠结构的数据集;与已有的3种经典的多视角聚类算法相比,该算法获得的聚类精度更高。

Abstract: Considering that most exiting multi-view clustering algorithms focusing on hard-partition clustering methods, which are not suitable for analyzing dataset with overlapping clusters, a multi-view clustering algorithm based on fuzzy C-means (FCM-MVC) was developed. The membership degree was used to describe the relation between objects and clusters, so FCM-MVC algorithm could more truely describe clustering results of dataset with overlapping clusters. FCM-MVC algorithm simultaneously incorporated fearture information in multi-view space and automatically computes weight of each view. The results show that FCM-MVC can analyze overlapping clusters effectively and the precision of clustering results of FCM-MVC are superior to the three representative algorithms.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号