Research on K-means initial clustering center optimal algorithm
K-means初始聚类中心优化算法研究

Since the dependence of K-means algorithm on the initial center may sink into the local minimum, the experimental result of the multi-seed clustering based on the density function method and merging small cluster obviously surpasses that of K-means clustering. Every iteration of this algorithm inclines to discover hyper-sphere cluster. The algorithm has better clustering ability especially for irregular and extendable clusters.