| 面向非球形分布数据的自适应K近邻聚类算法 |
| |
| 引用本文： | 黄晓斌,万建伟,张燕. 面向非球形分布数据的自适应K近邻聚类算法[J]. 计算机工程, 2003, 29(11): 21-22,165 |
| |
| 作者姓名： | 黄晓斌 万建伟 张燕 |
| |
| 作者单位： | 国防科技大学电子科学与工程学院,长沙,410073;空军雷达学院研究生队,武汉,430010 |
| |
| 摘 要： | 针对传统聚类算法处理非球形分布数据的不足,提出了一种新型的自适应K近邻聚类算法。该算法由数据集归一化、初始类别构造和初始类别融合3个步骤构成。仿真结果表明,该算法在无须聚类数目的前提下,对非球型分布数据具有很好的聚类效果。
|
| 关 键 词： | 非球形分布 模糊C均值聚类算法(FCA) 自适应K近邻聚类算法(AKNNCA) |
| 文章编号： | 1000-3428(2003)11-0021-02 |
Adaptive K Near Neighbor Clustering Algorithm for Data with Non-spherical-shape Distribution |
| |
| HUANG Xiaobin,WANG Jianwei,ZHANG Yan. Adaptive K Near Neighbor Clustering Algorithm for Data with Non-spherical-shape Distribution[J]. Computer Engineering, 2003, 29(11): 21-22,165 |
| |
| Authors: | HUANG Xiaobin WANG Jianwei ZHANG Yan |
| |
| Affiliation: | HUANG Xiaobin1,WANG Jianwei1,ZHANG Yan2 |
| |
| Abstract: | To the shortage of traditional clustering algorithm when dealing dat a with non-spherical-shape distribution, a novel adaptive K near neighbor cluste ring algorithm is presented in this paper. This algorithm is made up of three pa rts: (a)uniform for data; (b) constitution of initial patterns; (c)fusion of in itial patterns. The simulation results show that this algorithm has good cluster ing performance for data with non-spherical-shape distribution without knowing t he number of clustering. |
| |
| Keywords: | Non-spherical-shape distribution Fuzzy C-means algorithm(FCA) Ada ptive K near neighbor clustering algorithm(AKNNCA) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
