Clustering by Fast Searching Density Peaks Based on Parameter Optimization

DOI

10.2991/icmmcce-17.2017.270How to use a DOI?

Keywords

clustering; density peak; cut-off distance parameter; local density

Abstract

An effective density clustering algorithm, called Clustering by Fast Search and Find of Density Peaks (CFSFDP), is appeared on science in 2014, which is simple and efficient and doesn't need many parameters. However, it needs make sure of cut-off distance parameter artificially. For the above problems, a new algorithm, called Clustering by Searching Density Peaks based on Parameter Optimization (CSDPPO), is proposed in this paper, which can estimate cut-off distance parameter adaptively. Firstly, local density information entropy function is constructed with cut-off distance parameter. And then cut-off distance parameter is estimated by solving minimization problem of local density information entropy. Because CSDPPO can obtain suitable cut-off distance parameter, its clustering performance is better than CFSFDP. Our experimental results validate the effectiveness of the proposed algorithm.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zheng-hua Lv
AU  - Jun-hua Wang
AU  - Xia Shi
AU  - Ya-de Zhuang
AU  - Shou-fu Ge
PY  - 2017/09
DA  - 2017/09
TI  - Clustering by Fast Searching Density Peaks Based on Parameter Optimization
BT  - Proceedings of the 2017 5th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2017)
PB  - Atlantis Press
SP  - 1537
EP  - 1542
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmcce-17.2017.270
DO  - 10.2991/icmmcce-17.2017.270
ID  - Lv2017/09
ER  -