Adaptive Density Peak Clustering Algorithm
Yane Wang, Mary Jane C. Samonte · 2024
In view of the situation that the cutoff distance needs to be manually specified in the density peak algorithm and the cluster center is wrongly selected, an adaptive density peak clustering algorithm is proposed. This algorithm can select the cutoff distance according to the natural distribution of the sample and redefine the local density. Effectively realize the selection of the initial central cluster, and then complete the clustering of the remaining samples based on the reintroduced similar clustering Sim_D. Comparing this algorithm with other algorithms on artificial data sets and UCI data sets, the ADPC algorithm achieves 100% correct clustering on artificial data sets, and its partial clustering effect on UCI data sets is also significantly better than the other four. Clustering Algorithm.