Effectively clustering by finding density backbone based-on kNN
详细信息 查看全文
- 作者：Mei Chena ; b ; mei.chen.lzjtu@hotmail.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Longjie Lia ; ljli@lzu.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Bo Wanga ; wangb2013@lzu.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Jianjun Chenga ; chengjianjun@lzu.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Lina Pana ; panln13@lzu.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Xiaoyun Chena ; chenxy@lzu.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Clustering algorithm ; Density backbone ; k nearest neighbours
- 刊名：Pattern Recognition
- 出版年：2016
- 出版时间：December 2016
- 年：2016
- 卷：60
- 期：Complete
- 页码：486-498
- 全文大小：7356 K
文摘
- •
CLUB can easily find clusters with various densities, shapes and sizes.
- •
A new density computing method is presented.
- •
A novel cluster backbones identification method is proposed.
- •
Comprehensive experiments are performed to verify the performance of CLUB.