In this paper, we present a new clustering algorithm, NBC, i.e., Neighborhood Based Clustering, which discovers clusters based on the neighborhood characteristics of data. The NBC algorithm
has the following advantages: (1) NBC is effective in discovering clusters of arbitrary shape and different densities; (2)
NBC needs fewer input parameters than the existing clustering algorithms; (3) NBC can cluster both large and high-dimensional
databases efficiently.
This work is supported by the Natural Science Foundation of China under grant No. 60373019 and 60496325, and partially supported
by IBM-HKU Visiting Scholars Program.