| 基于最小平方和残差的高阶模糊联合聚类算法 |
| |
| 引用本文： | 黄少滨,杨欣欣.基于最小平方和残差的高阶模糊联合聚类算法[J].武汉大学学报(信息科学版),2015,40(2):238-242. |
| |
| 作者姓名： | 黄少滨 杨欣欣 |
| |
| 作者单位： | 1哈尔滨工程大学计算机科与技术学院 黑龙江 哈尔滨 150001 |
| |
| 基金项目： | 国家自然科学基金资助项目(71272216,60903080);博士后科学基金资助项目(2012M5100480);国家科技支撑计划资助项目(2009BAH42B02,2012BAH08B02);中央高校基本科研业务费专项基金资助项目(HEUCFZ1212,HEUCF100603)~~ |
| |
| 摘 要： | 目前,多数高阶联合聚类算法属于硬划分方法,不考虑聚簇重叠问题。为了更有效地分析具有重叠聚簇结构的数据,提出了一种基于最小平方和残差的高阶模糊联合聚类算法(MSR-HFCC),该算法将聚类问题转化为最小化模糊平方和残差的优化问题,推导出求解优化问题的隶属度迭代更新公式,设计出聚类过程的迭代算法。实验结果表明,MSR-HFCC算法聚类效果优于目前已有的5种硬划分高阶联合聚类算法。
|
| 关 键 词： | 高阶异构数据 联合聚类 模糊聚类 平方和残差 |
| 收稿时间： | 2013-04-24 |
A Minimum Sum-squared Residue for High-order Fuzzy Co-clustering Algorithm |
| |
| HUANG Shaobin;YANG Xinxin.A Minimum Sum-squared Residue for High-order Fuzzy Co-clustering Algorithm[J].Geomatics and Information Science of Wuhan University,2015,40(2):238-242. |
| |
| Authors: | HUANG Shaobin;YANG Xinxin |
| |
| Institution: | 1College of Computer Science & Technology Harbin Engineering University Harbin 150001 China |
| |
| Abstract: | Most existing high-order co-clustering algorithms focus on hard clustering methods，which ignore the problem of overlaps in the clustering structures. In order to analyze the clustering results of data with overlapping clusters more efficiently，we developed a minimum sum-squared residue for high-order fuzzy co-clustering algorithm(MSR-HFCC).The clustering problem is formulated as the problem of minimizing fuzzy sum-squared residue.The update rules for fuzzy memberships were derived，and an iterative algorithm was designed for a co-clustering process.Finally，experimental recults show that the qualities of clustering results of MSR-HFCC are superior to five existing algorithms. |
| |
| Keywords: | |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《武汉大学学报(信息科学版)》浏览原始摘要信息 |
| 点击此处可从《武汉大学学报(信息科学版)》下载免费的PDF全文 |
