arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.08607cs.CG
收藏

低维欧氏空间中的快速DB扫描和HDB扫描

Faster DB-scan and HDB-scan in Low-Dimensional Euclidean Spaces

Mark de Berg, Ade Gunawan, Marcel Roeloffzen

摘要:

我们提出了一个新的算法,广泛使用的基于密度的聚类方法DBscan。我们的算法在$\mathbb{R}^2$中计算$O(n\log n)$时间中的DB扫描聚类,而与尺度参数$\varepsilon$无关(并且假设第二参数MinPts被设置为固定常数,如实践中的情况)。实验结果表明,新算法不仅在理论上速度快,而且在实际应用中具有一定的竞争力,而且对$\varepsilon$的选择不敏感。我们还提出了一个$O(n\log n)$随机算法HDBscan在平面上-HDBscan是一个层次版本的DBscan介绍最近-我们展示了如何计算一个近似版本的HDBscan在近线性时间在任何固定的维度。

英文摘要:

We present a new algorithm for the widely used density-based clustering method DBscan. Our algorithm computes the DBscan-clustering in $O(n\log n)$ time in $\mathbb{R}^2$, irrespective of the scale parameter $\varepsilon$ (and assuming the second parameter MinPts is set to a fixed constant, as is the case in practice). Experiments show that the new algorithm is not only fast in theory, but that a slightly simplified version is competitive in practice and much less sensitive to the choice of $\varepsilon$ than the original DBscan algorithm. We also present an $O(n\log n)$ randomized algorithm for HDBscan in the plane---HDBscan is a hierarchical version of DBscan introduced recently---and we show how to compute an approximate version of HDBscan in near-linear time in any fixed dimension.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑