An adaptive clustering algorithm by neighbourhood search for large-scale data

Adaptive cluster sampling (ACS) is a sampling method relies on the neighbourhood search on a grid structure. It has an adaptive selection process of units and recursively added units reveal the batched individuals easily and quickly. In this paper, we propose a new clustering method called spatial adaptive clustering (SAC) based on the idea of ACS design. The SAC algorithm forms clusters based on neighbourhood search using grid structures and is able to detect noise points. The performance of the proposed algorithm is evaluated through comparison with the results from well-known density-based clustering approaches in the literature using real and artificial data sets. Computational results indicate that the proposed algorithm is effective in terms of external validation measures for clustering of arbitrary shaped data with noise. Additionally, the SAC algorithm is tested on artificial data sets of varying sizes for the runtime criterion. The results reveal that it also performs superbly for the objective of reducing the runtime.