| 基于连通核的鲁棒模糊C-均值聚类算法 |
| |
| 引用本文： | 支晓斌,范九伦.基于连通核的鲁棒模糊C-均值聚类算法[J].数据采集与处理,2010,25(1). |
| |
| 作者姓名： | 支晓斌 范九伦 |
| |
| 作者单位： | 1. 西安电子科技大学电子工程学院,西安,710071;西安邮电学院应用数学与应用物理系,西安,710121
2. 西安邮电学院信息与控制系,西安,710121 |
| |
| 摘 要： | 提出一种新的鲁棒核模糊C-均值聚类算法.将连通核与AFCM(Alternative fuzzy C-means)聚类算法相结合,给出基于连通核的核AFCM:CRKFCM(Connectivity kernel based robust fuzzy C-means).CRKFCM一方面有效地利用了连通核,可以对任意形状数据聚类,且避免了核参数的选取问题;另一方面在特征空间使用非欧氏距离,可以有效地处理含噪声数据的聚类问题.实验结果表明,与原有的AFCM和连通核硬C-均值(CKHCM,Connectivity kernel based hard C-means)聚类算法相比,新算法在处理噪声环境中的任意形状聚类问题方面更有效.
|
| 关 键 词： | 核聚类 鲁棒聚类 连通核 |
Robust Fuzzy C-means Clustering Algorithm Based on Connectivity Kernel |
| |
| Zhi Xiaobin,Fan Jiulun.Robust Fuzzy C-means Clustering Algorithm Based on Connectivity Kernel[J].Journal of Data Acquisition & Processing,2010,25(1). |
| |
| Authors: | Zhi Xiaobin Fan Jiulun |
| |
| Abstract: | A new robust fuzzy C-means clustering algorithm is proposed.Combining the connectivity kernel and alternative fuzzy C-means clustering(AFCM) algorithm,this paper proposes a connectivity kernel based AFCM: CRKFCM.Using the connectivity kernel,CRKFCM can cluster arbitrary shaped data and avoid the problem of choosing kernel parameter.Non-Euclidean distance is used in the feature space and the noise data clustering problem can be solved.Experimental results show that CRKFCM has super performance over its prede... |
| |
| Keywords: | kernel clustering robust clustering connectivity kernel |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
