基于leader的k-means改进算法

Improved k-means Algorithm Based on Leader Algorithm

针对传统k-means算法中初始聚类中心选取的随意性对于聚类结果影响较大的问题,提出了基于Leader算法的k-means改进算法——Lk-means算法.该算法有效避免了初始聚类中心选取的边缘化和随意性.实验证明,Lk-means算法的聚类结果更加有效合理.

To the problem of the signi ficant effect on the cluster results owing to the randomicity of traditional k-means on determining the initial cluster centers, we propose an improved k-means algorithm, Lk-means, which is based on leader algorithm. The Lk-means algorithm is effective to avoid the marginalization and randomicity emerged in determining the initial cluster centers. Experiment proves that the algorithm makes the cluster results more objective and reasonable.