点击次数：

论文类型：会议论文

发表时间：2016-08-08

收录刊物：EI、CPCI-S、Scopus

页面范围：537-543

关键字：Improved CFS; cutoff distance; density peaks; allocation strategy; merging; splitting

摘要：Clustering is a fundamental and important technique under many circumstances including data mining, pattern recognition, image processing and other industrial applications. During the past decades, many clustering algorithms have been developed, such as DBSCAN, AP and CFS. As the latest clustering algorithm proposed in Science magazine in 2014, clustering by fast search and find of density peaks, named as CFS, is a simple and outstanding algorithm for its promising performance on data sets of arbitrary shape. However, CFS's performance is usually affected by the cutoff distance d(c), the density peaks, the selection of cluster centers and the allocation strategy of data points. In this paper, we propose an improved algorithm (ICFS) to deal with the several weaknesses of it. Unlike CFS, the proposed algorithm designs a formula for the cutoff distance calculation and a method for cluster centers selection to improve its robustness. Moreover, a new non-center point's allocation strategy and the cluster merging and splitting processes are developed to adapt to the density peaks and adjust the clusters dynamically, which can improve the clustering accuracy and scalability. The ICFS method is evaluated on several datasets by comparison with the original CFS algorithm. Results demonstrate the effectiveness of the proposed method.