A parallel algorithm for approximating the silhouette using a ball tree

doi:10.1016/j.jpdc.2022.11.001

2023-03-01

PRE

Ivan Šimeček *

Claudio Kozický

DOI：10.1016/j.jpdc.2022.11.001

原文链接

原文求助

摘要

En 中文

Clustering is widely used in many scientific fields. The contribution of enumerating the value of the silhouette is twofold: firstly it can help choosing a suitable cluster count and secondly it can be used to evaluate the quality of a clustering. Enumerating the silhouette exactly is an extremely time-consuming task, especially in big data applications; it is therefore common to approximate its value. This article presents an efficient shared-memory parallel algorithm for approximating the silhouette, which uses a ball tree. The process of initialising the ball tree and enumerating the silhouette are fully parallelised using the OpenMP API. The results of our experiments show that the proposed parallel algorithm substantially increases the speed of computing the silhouette whilst retaining necessary precision for real-world applications.(c) 2022 Elsevier Inc. All rights reserved.

Keyword:

Ball tree

Data mining

High-performance computing

k-means clustering

Silhouette