A Novel Local Density Hierarchical Clustering Algorithm Based on Reverse Nearest Neighbors

Abstract

Clustering is widely used in data analysis, and density-based methods are developed rapidly in the recent 10 years. Although the state-of-art density peak clustering algorithms are efficient and can detect arbitrary shape clusters, they are nonsphere type of centroid-based methods essentially. In this paper, a novel local density hierarchical clustering algorithm based on reverse nearest neighbors, RNN-LDH, is proposed. By constructing and using a reverse nearest neighbor graph, the extended core regions are found out as initial clusters. Then, a new local density metric is defined to calculate the density of each object; meanwhile, the density hierarchical relationships among the objects are built according to their densities and neighbor relations. Finally, each unclustered object is classified to one of the initial clusters or noise. Results of experiments on synthetic and real data sets show that RNN-LDH outperforms the current clustering methods based on density peak or reverse nearest neighbors.

A Novel Convex Clustering Method for High-Dimensional Data Using Semiproximal ADMM

“…As an exploratory data analysis technique, it has been applied in many fields, such as image processing, energy engineering, and social networks [1][2][3]. To date, a wide variety of clustering methods have been introduced, including classical clustering methods such as K-means clustering [4,5] and hierarchical clustering [6,7]. However, the convexity of the corresponding optimization models cannot be guaranteed in general, so their global optimal solutions are hard to find.…”