Flower Pollination Algorithm with Bee Pollinator for cluster analysis

作     者：Wang, Rui Zhou, Yongquan Qiao, Shilei Huang, Kang 

作者机构：Guangxi Univ Nationalities Coll Informat Sci & Engn Nanning 530006 Peoples R China Guangxi High Sch Key Lab Complex Syst & Computat Nanning 530006 Peoples R China 

出 版 物：《INFORMATION PROCESSING LETTERS》 (信息处理快报)

年 卷 期：2016年第116卷第1期

页      面：1-14页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Science Foundation of China [61165015, 6143007, 61563008] Guangxi Science Foundation [2012GXNSFDA053028] Guangxi High School Science Foundation [20121ZD008] 

主　　题：Flower pollination algorithm Randomized algorithms Discard pollen operator Elite based mutation operator Crossover operator Clustering problem 

摘      要：Clustering is a popular data analysis and data mining technique. The k-means clustering algorithm is one of the most commonly used methods. However, it highly depends on the initial solution and is easy to trap into the local optimal. For overcoming these disadvantages of the k-means method, Flower Pollination Algorithm with Bee Pollinator is proposed. Discard pollen operator and crossover operator are applied to increase diversity of the population, and local searching ability is enhanced by using elite based mutation operator. Ten data sets are selected to evaluate the performance of proposed algorithm. Compared with DE, CS, ABC, PSO, FPA and k-Means, the experiment results show that Flower Pollination Algorithm with Bee Pollinator has not only higher accuracy but also higher level of stability. And the faster convergence speed can also be validated by statistical results. (C) 2015 Elsevier B.V. All rights reserved.