Completeness Proof and Implementation of Parallel k-means Clustering Algorithm
Tao Feng · Jisuanji gongcheng · 2010
This paper analyzes classical k-means clustering algorithm,proves the way that generated complete global clustering information from the local clustering information in the case of minimizing the cost of communication between computing nodes.The clustering quality of the way is equivalent to the corresponding serial algorithm,and has higher efficiency in the implementation.On this basis,this paper gives a credible parallel k-means algorithm based on Message Passing Interface(MPI).Experimental result shows that the algorithm is efficient and feasible.