| 基于两种加权方式的模糊聚类算法* |
| |
| 引用本文： | 刘强,夏士雄,周勇,刘兵.基于两种加权方式的模糊聚类算法*[J].计算机应用研究,2011,28(12):4437-4439. |
| |
| 作者姓名： | 刘强 夏士雄 周勇 刘兵 |
| |
| 作者单位： | 中国矿业大学计算机科学与技术学院,江苏徐州,221116 |
| |
| 基金项目： | 国家自然科学基金资助项目（50674086） |
| |
| 摘 要： | 模糊聚类是一种应用广泛的数据分析和建模的无监督方法,但该算法受离群点影响较大,并且没有考虑样本数据中各维特征对聚类贡献程度的不同.针对这两个问题,提出了基于两种加权方式的聚类算法,该算法定义了一种新的样本加权的概念,减弱了离群点对聚类的干扰,同时为数据样本的每一维特征赋予一个权值,使聚类更加准确.仿真实验结果验证了该算...
|
| 关 键 词： | 聚类分析 聚类中心 离群点 特征加权 样本加权 |
Fuzzy clustering algorithm using two weighting methods |
| |
| LIU Qiang,XIA Shi-xiong,ZHOU Yong,LIU Bing.Fuzzy clustering algorithm using two weighting methods[J].Application Research of Computers,2011,28(12):4437-4439. |
| |
| Authors: | LIU Qiang XIA Shi-xiong ZHOU Yong LIU Bing |
| |
| Affiliation: | LIU Qiang,XIA Shi-xiong,ZHOU Yong,LIU Bing(School of Computer Science & Technology,China University of Mining & Technology,Xuzhou Jiangsu 221116,China) |
| |
| Abstract: | Fuzzy clustering is an important unsupervised method of data analysis and modeling,which is widely used.But the algorithm is not only greatly and easily influenced by the outliers,but also doesn't consider that each dimension feature of data sample has different dynamic-force for clustering.To solve the two problems,this paper proposed a new fuzzy clustering algorithm using two weighting methods.Meanwhile introduced a new idea about fuzzy clustering based on sample-weighted,which weakened the interference f... |
| |
| Keywords: | clustering analysis clustering center outliers feature-weighted sample-weighted |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
|
