Novel K-medoids clustering algorithm based on dense regional block
ZHAO Xiangmin1，2, CHEN Xi1, PAN Chu3
1.Institute of Computer and Communication Engineering, Changsha University of Sciences and Technology, Changsha 410114, China
2.Changsha College of Commerce & Tourism, Changsha 410004, China
3.College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China
In view of the traditional K-medoids clustering algorithm is sensitive to the initial center, as well as the shortcoming of high number of iterations, put forward a feasible initialization method and a center search update strategy. New algorithm firstly using the density-reachable thought to establish a dense regional block for each object of the data set, select [K] dense regional blocks which their densities are larger and the distance are far away for each selected dense regional blocks, put the core object of the corresponding dense regional blocks as the K initial centers；Secondly, the centers search update scope is locking the [K] selected effective dense regional blocks. Tested on Iris, Wine and PId standard data sets, this new algorithm obtains ideal initial centers and dense regional blocks, what’s more, converges to the optimal solution or approximate optimum solution within less number of iterations.