Adaptive grid-based forest-like clustering algorithm

Abstract

This paper presents an adaptive grid-based clustering algorithm called as “AGFC”, which uses a forest-like query structure to sequentially discovers multiple arbitrary-shaped clusters from the grid. The main advantage of AGFC is that it can effectively generate a reasonable grid division with a simple startup parameter. This method determines the appropriate grid division width through the minimum gap between the peaks and valleys of the density curve in a specific dimension, which depends on the distribution of the sample, to overcome the subjectivity of manual determination to a certain extent. Furthermore, in the forest-like query structure, it constructs a “Aggregation Judgment” criterion for high-density cells to find out the possible clusters through the merging of cells. Finally, using the “Re-clustering process” to eliminate very small clusters and further repairing the edge areas of the main clusters. The experimental results show that the proposed method can obtain competitive results under the premise of automatically determining the grid.