Density Peaks Clustering Based on Natural Search Neighbors and Manifold Distance Metric

Abstract

The famous density-based clustering approach Density Peaks Clustering (DPC) is getting more and more popular recently. However, DPC algorithm is vulnerable to the parameter <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d_c</i> and is incapable of obtaining desired clustering results when dealing with manifold data sets. Furthermore, the allocation strategy of the remaining data points can easily lead to domino chain reaction which means that when a data point is allocated improperly, the points around it will be allocated incorrectly too. To solve these deficiencies, in this paper, we put forward an algorithm named density peaks clustering based on natural search neighbors and manifold distance metric (DPC-NSN-MDM). In the beginning, we apply natural search method (NSM) to identify the natural neighbors and further calculate the local density ρ of each data point. Secondly, when calculating distance δ of each data point, we put the manifold distance metric with a scaling factor to replace the traditional Euclidean distance metric. At last, manifold distance is also used in the allocation strategy of remaining data points to reduce the effect of the domino chain reaction. The proposed DPC-NSN-MDM algorithm succeeds in getting superb experimental performance on both synthetic data sets and real-world data sets.