标题:Improved fuzzy C-means algorithm based on density peak
作者:Liu, Xiang-yi; Fan, Jian-cong; Chen, Zi-wen
作者机构:[Liu, Xiang-yi; Fan, Jian-cong; Chen, Zi-wen] Shandong Univ Sci, Coll Comp Sci, Engn, Technology, Qingdao, Peoples R China.; [Fan, Jian-cong] Shando 更多
通讯作者:Fan, Jiancong;Fan, JC;Fan, JC;Fan, JC
通讯作者地址:[Fan, JC]Shandong Univ Sci, Coll Comp Sci, Engn, Technology, Qingdao, Peoples R China;[Fan, JC]Shandong Univ Sci, Prov Key Lab Informat Technol Wisdom 更多
来源:INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
出版年:2020
卷:11
期:3
页码:545-552
DOI:10.1007/s13042-019-00993-8
关键词:Fuzzy C-means algorithm; Density peak; Clustering
摘要:Fuzzy C-means (FCM) algorithm is a fuzzy clustering algorithm based on objective function compared with typical "hard clustering" such as k-means algorithm. FCM algorithm calculates the membership degree of each sample to all classes and obtain more reliable and accurate classification results. However, in the process of clustering, FCM algorithm needs to determine the number of clusters manually, and is sensitive to the initial clustering center. It is easy to generate problems such as multiple clustering iterations, slow convergence speed and local optimal solution. To address those problems, we propose to combine the FCM algorithm and DPC (Clustering by fast search and find of density peaks) algorithm. First, DPC algorithm is used to automatically select the center and number of clusters, and then FCM algorithm is used to realize clustering. The comparison experiments show that the improved FCM algorithm has a faster convergence speed and higher accuracy.
收录类别:EI;SCIE
资源类型:期刊论文
TOP