Sensitivity Analysis and Optimization of FCM Initial Clustering Centers

DOI

10.2991/sschd-17.2017.97How to use a DOI?

Keywords

fuzzy C- means clustering, sensitivity analysis, clustering centers move with fuzzy exponent

Abstract

Some researches show that fuzzy C- means clustering is sensitive to initial clustering centers. Related variables include cluster number, data characteristics and fuzzy exponent are affect the sensitivity of the algorithm. This paper provided the definition of the sensitivity of the algorithm. Selecting data sets of different characteristics, experimental analyzed the sensitivity of the algorithm to the initial clustering centers under different clustering case, and compared the convergence speed of different initial clustering centers reach the specific clustering distance. The results show that the algorithm is not absolutely sensitive to the initial clustering centers, the sensitivity is related to the number of clustering for the same data set. This paper proposed the clustering centers move with fuzzy exponent algorithm for FCM algorithm by combining the maximum distances product method, and anlyzed the validity of the optimization 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  - Yong Wang
AU  - Jiao Cheng
AU  - Ling Zhang
AU  - Qiu-Hua Tang
PY  - 2017/09
DA  - 2017/09
TI  - Sensitivity Analysis and Optimization of FCM Initial Clustering Centers
BT  - Proceedings of the 3rd Annual International Conference on Social Science and Contemporary Humanity Development
PB  - Atlantis Press
SP  - 506
EP  - 513
SN  - 2352-5398
UR  - https://doi.org/10.2991/sschd-17.2017.97
DO  - 10.2991/sschd-17.2017.97
ID  - Wang2017/09
ER  -