Automatically Selecting Cluster Centers in Clustering by Fast Search and Find of Density Peaks with Data Field

Automatic selection of cluster centers is a successive research of "Clustering by Fast Search and Find of Density Peaks with Data Field". It is found that the change law of multilevel high order difference can locate the position of cluster centers and then separate them from other points. By higher-order difference operation acting on λ, which is accumulation sum of dot product of local density δ and distance ρ, cluster centers can be automatically extracted, which improves the problem of manual determination of cluster centers only by artificial observation. The validity and reliability of the novel approach we proposed are demonstrated by experiments of various test cases.