A novel density peaks clustering with sensitivity of local density and density-adaptive metric

• Published in: Knowledge and information systems Vol. 59; no. 2; pp. 285 - 309
• Main Authors: Du, Mingjing, Ding, Shifei, Xue, Yu, Shi, Zhongzhi
• Format: Journal Article
• Language: English
• Published: London Springer London 01.05.2019; Springer Nature B.V
• Subjects: Algorithms; Clustering; Computer Science; Consistency; Data Mining and Knowledge Discovery; Database Management; Density; Information Storage and Retrieval; Information systems; Information Systems and Communication Service; Information Systems Applications (incl.Internet); IT in Business; Redesign; Regular Paper; Self organizing maps; Sensitivity; Sensitivity of local density; Clustering analysis; Density peaks clustering; Density-adaptive distance
• ISSN: 0219-1377; 0219-3116
• DOI: 10.1007/s10115-018-1189-7

The density peaks (DP) clustering approach is a novel density-based clustering algorithm. On the basis of the prior assumption of consistency for semi-supervised learning problems, we further make the assumptions of consistency for density-based clustering. The first one is the assumption of the local consistency, which means nearby points are likely to have the similar local density; the second one is the assumption of the global consistency, which means points on the same high-density area (or the same structure, i.e., the same cluster) are likely to have the same label. According to the first assumption, we provide a new option based on the sensitivity of the local density for the local density. In addition, we redefine δ and redesign the assignation strategy based on a new density-adaptive metric according to the second assumption. We compare the performance of our algorithm with traditional clustering schemes, including DP, K -means, fuzzy C-means, Gaussian mixture model, and self-organizing maps. Experiments on different benchmark data sets demonstrate the effectiveness of the proposed algorithm.