A novel clustering algorithm based on data transformation approaches

作者：

Highlights：

• A new initialization technique is proposed to improve the performance of K-means.

• A data transformation approach is proposed to solve empty cluster problem.

• An efficient method is proposed to estimate the optimal number of clusters.

• Proposed clustering method provides more accurate clustering results.

摘要

•A new initialization technique is proposed to improve the performance of K-means.•A data transformation approach is proposed to solve empty cluster problem.•An efficient method is proposed to estimate the optimal number of clusters.•Proposed clustering method provides more accurate clustering results.

论文关键词：Data mining,Clustering,K-means,Data transformation,Silhouette,Transformed K-means

论文评审过程：Received 28 November 2015, Revised 29 October 2016, Accepted 24 January 2017, Available online 25 January 2017, Version of Record 6 February 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.01.024