ConDPC: Data Connectivity-Based Density Peak Clustering

Abstract

As a relatively novel density-based clustering algorithm, Density peak clustering (DPC) has been widely studied in recent years. DPC sorts all points in descending order of local density and finds neighbors for each point in turn to assign all points to the appropriate clusters. The algorithm is simple and effective but has some limitations in applicable scenarios. If the density difference between clusters is large or the data distribution is in a nested structure, the clustering effect of this algorithm is poor. This study incorporates the idea of connectivity into the original algorithm and proposes an improved density peak clustering algorithm ConDPC. ConDPC modifies the strategy of obtaining clustering center points and assigning neighbors and improves the clustering accuracy of the original density peak clustering algorithm. In this study, clustering comparison experiments were conducted on synthetic data sets and real-world data sets. The compared algorithms include original DPC, DBSCAN, K-means and two improved algorithms over DPC. The comparison results prove the effectiveness of ConDPC.

A Density Peaking Clustering Algorithm for Differential Privacy Preservation

“…Ding et al [16] proposed an improved density peak clustering algorithm (IDPCNNMS) based on the natural neighborhood merging strategy, which could adaptively identify the natural neighbor set of each data, obtain its local density, and effectively eliminate the influence of truncation parameters on the final result. Zou and Wang [17] introduced the idea of connectivity on the basis of the original DPC algorithm, and proposed an improved density peak clustering algorithm (ConDPC), which improved the acquisition of clustering center points and the sample allocation strategy, and improved the clustering accuracy of the algorithm. Yin et al [18] improved the density peak clustering algorithm.…”