An improved density peaks clustering algorithm by automatic determination of cluster centres

Abstract

The fast search and find of density peaks clustering (FDP) is an algorithm that can gain satisfactory clustering results with manual selection of the cluster centres. However, this manual selection is difficult for larger and more complex datasets, and it is easy to split a cluster into multiple subclusters. We propose an automatic determination of cluster centres algorithm (A-FDP). On the one hand, a new decision threshold is designed in A-FDP combined with the InterQuartile Range and standard deviation. We select the points larger than the decision threshold as the cluster centres. On the other hand, these cluster centres are made as nodes to construct the connected graphs. These subclusters are merged by finding the connected components of the connected graph. The results show that the A-FDP can obtain better clustering results and have higher accuracy than other classical clustering algorithms on synthetic and UCI datasets.