Main Image
Volume 299 - The 7th International Conference on Computer Engineering and Networks (CENet2017) - Session I - Machine Learning
A Fuzzy Density Peak Optimization Initial Centers Selection for K-medoids Clustering Algorithm
C. Liu,* X. He, Q. Xu
*corresponding author
Full text: pdf
Pre-published on: 2017 July 17
Published on: 2017 September 06
Abstract
In order to solve the problem that the traditional K-medoids clustering algorithm needs to specify the number of clusters, which is sensitive to the initial cluster center and the slowconvergence speed, the method of density peak optimization is used for solution. In this paper, we propose Fuzzy density peak K-medoids (FDP_K-mediods) algorithm. In the improved K-medoids algorithm, the local clustering center is obtained by calculating the local density and the high density distance, and then merged into the global clustering center, which canadaptively generate the initial clustering center and determine the number of clusters. The experimental results show that our scheme can adaptively generate the initial clustering center
and determine the number of clusters with some practical and artificial data sets. Compared with the traditional K-medoids algorithm, the improved algorithm can accurately obtain the numberof clusters and improve the algorithm’s performance
DOI: https://doi.org/10.22323/1.299.0006
Open Access
Creative Commons LicenseCopyright owned by the author(s) under the term of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.