如何在Matlab或R中进行重叠聚类分析?
我有一个大小为 20 x 300 的二进制矩阵。我想将 20 个变量分为五组或六组。到目前为止,我在 matlab 中使用了 kmeans 和层次聚类算法,具有不同的距离度量,但两者都给出了非重叠的聚类。我在数据中看到某些变量应该位于多个组中。有谁知道是否有办法在 matlab 或 R 中进行重叠聚类?非常感谢任何帮助。 提前致谢!
I have a binary matrix of size 20 by 300. I want to cluster the 20 variables into five or six groups. So far I used kmeans and hierarchical clustering algorithms in matlab with different distance metrics but both give me non-overlapping clusters. I see on my data that some of the variables should be located in more than one group. Does anyone know if there is a way to do overlapping clusters either in matlab ot R? Any help is greatly appreciated.
Thanks in advance!
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论
评论(2)
查看 MATLAB 文档中的模糊聚类 http://www.mathworks.com/帮助/工具箱/模糊/fp310.html
Have a look at Fuzzy clustering in MATLAB documentation http://www.mathworks.com/help/toolbox/fuzzy/fp310.html
寻找能够构建重叠集群的 Weka4OC (java) 或 ADPROCLUS(R)
look for Weka4OC (java) or ADPROCLUS(R) which are able to build overlapping clusters