An Improved DBSCAN Clustering Algorithm for Multi-density Datasets
Cheng Tang · 2017
In this paper, we proposed a DBSCAN-based clustering algorithm called NNDD-DBSCAN with the main focus of handling multi-density datasets and reducing parameter sensitivity. The NNDD-DBSCAN used a new distance measuring method called nearest neighbor density distance (NNDD) which makes the new algorithm can clustering properly in multi-density datasets. By analyzing the relationship between the threshold of nearest neighbor density distance and the threshold of nearest neighborcollection, we give a heuristic method to find the appropriate nearest neighbor density distance threshold and reducing parameter sensitivity. Experimental results show that the NNDD-DBSCAN has a good robustadaptation and can get the ideal clustering result both in single density datasets and multi-density datasets.