An Improved K-means Clustering Algorithm
SUI Xinyi
WANG Ruigang
ZHANG Hongxiang
Abstract：A modified K-means clustering algorithm is proposed to improve poor stability of algorithm owing to random selec-tion of the initial clustering centers,which is based on the sample space distribution density.In this paper,the sample space divide into several subspaces of the same size,calculated the sample density in the subspace and determined the first clustering center.Ex-periments show the proposed can effectively improve the stability,reduce iteration and carry out quite satisfying results.
Keywords：clustering algorithmk-meansinitial cluster centersspatial distribution
Publication Date：2018-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 682-685 )