点击次数：

论文类型：会议论文

发表时间：2014-11-28

收录刊物：Scopus、EI、CPCI-S

页面范围：263-266

关键字：big data; incomplete data clustering; feature subset selection; cluster analysis

摘要：Incomplete data clustering plays an important role in the big data analysis and processing. Existing algorithms for clustering incomplete high-dimensional big data have low performances in both efficiency and effectiveness. The paper proposes an incomplete high-dimensional big data clustering algorithm based on feature selection and partial distance strategy. First, a hierarchical clustering-based feature subset selection algorithm is designed to reduce the dimensions of the data set. Next, a parallel k-means algorithm based on partial distance is derived to cluster the selected data subset in the first step. Experimental results demonstrate that the proposed algorithm achieves better clustering accuracy than the existing algorithms and takes significantly less time than other algorithms for clustering high-dimensional big data.