Please use this identifier to cite or link to this item:
Title: Clustering for Probability Density Functions by New k-Medoids Method
Authors: Ho-Kieu, D.
Võ, Văn Tài
Nguyen-Trang, T.
Issue Date: 2018
Series/Report no.: Scientific Programming;p.1-7
Abstract: Tis paper proposes a novel and efcient clustering algorithm for probability density functions based on k- -Medoids. Further, a scheme used for selecting the powerful initial medoids is suggested, which speeds up the computational time signifcantly. Also, a general proof for convergence of the proposed algorithm is presented. Te efectiveness and feasibility of the proposed algorithm are verifed and compared with various existing algorithms through both artifcial and real datasets in terms of adjusted Rand index, computational time, and iteration number. Te numerical results reveal an outstanding performance of the proposed algorithm as well as its potential applications in real life.
Appears in Collections:Tạp chí quốc tế

Files in This Item:
File Description SizeFormat 
_file_2.57 MBAdobe PDFView/Open
Your IP:

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.