An improved overlapping k-means clustering method for medical applications
详细信息 查看全文
- 作者：Sina Khanmohammadi ; a ; skhanmo1@binghamton.edu" class="auth_mail" title="E-mail the corresponding author ; Naiier Adibeigb ; adibeig.n@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Samaneh Shanehbandyb ; samane.shanebandy@gmail.com" class="auth_mail" title="E-mail the corresponding author
- 关键词：Overlapping clustering ; Overlapping k-means ; K-harmonic means ; FBCubed ; Data Mining ; Medical informatics
- 刊名：Expert Systems with Applications
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：67
- 期：Complete
- 页码：12-18
- 全文大小：1113 K
文摘
- •
The sensitivity of overlapping k-means algorithm to initialization is considered.
- •
The k-harmonic means method is effective for identifying initial cluster centroids.
- •
The proposed approach outperforms the original overlapping k-means algorithm.