科研之友
微信
新浪微博
Facebook
分享链接
摘要
A clustering algorithm based on Sparse Projection (SP), called Sparse Projection Clustering (SPC), is proposed in this letter. The basic idea is applying SP to project the observed data onto a high-dimensional sparse space, which is a nonlinear mapping with an explicit form and the K-means clustering algorithm can be therefore used to explore the inherent data patterns in the new space. The proposed algorithm is applied to cluster a complete artificial dataset and an incomplete real dataset. In comparison with the kernel K-means clustering algorithm, the proposed algorithm is more efficient.
- 出版日期2009
- 单位华南理工大学
