Looking for natural patterns in data - Part 1. Density-based approach

A density-based unsupervised clustering approach for detecting natural patt erns in data (further denoted as NP) is presented, and its performance is i llustrated for data sets with different types of clusters. NP works for arb itrary clusters, is a single-scan technique, requires no presumptions regar ding data distribution and requires only one input parameter, which describ es the minimal number of objects, considered as cluster. Moreover, a compar ison of NP with partitioning approaches is demonstrated. NP can be applied not only for data clustering, but also for the identification of outliers. (C) 2001 Elsevier Science B.V. All rights reserved.