Efficient Density-Peaks Clustering Algorithms on Static and Dynamic Data in Euclidean Space

Clustering multi-dimensional points is a fundamental task in many fields, and density-based clustering supports applications because it can discover clusters of arbitrary shapes. This article addresses the problem Density-Peaks (DPC) Euclidean space. DPC already has applications, but its straightforward implementation incurs O ( n 2 ) time, where number points, thereby does not scale to large datasets. To enable on datasets, we first propose empirically efficient exact algorithm, Ex-DPC. Although this algorithm much faster than implementation, still suffers from time theoretically. We hence new Ex-DPC++, that runs o time. accelerate their efficiencies by leveraging multi-threading. Moreover, real-world datasets may have updates (point insertions deletions). It important support cluster updates. end, D-DPC for fully dynamic DPC. conduct extensive experiments using real our experimental results demonstrate algorithms are scalable.