Title: An efficient clustering method for mobile users based on hybrid PSO and ABC

Authors: Chong-huan Xu

Addresses: Business Administration College, Contemporary Business and Trade Research Center, Contemporary Business and Collaborative Innovation Research Center, Zhejiang Gongshang University, Hangzhou City, China

Abstract: With the rapid development of mobile commerce, more and more researchers focus on mobile users segmentation. In this paper, we present an efficient clustering method which involves three sub-algorithms: K-harmonic means, particle swarm optimisation (PSO) and artificial bee colony (ABC). In order to overcome the problem of convergence to the local optimum, we use a hybrid nature-inspired algorithm, namely hybrid PSO and ABC, to solve them. In the process of evolution, the population is divided into two sub-groups. One evolves by PSO algorithm, and the other evolves by ABC algorithm. By the comparison of two fitness values generated by these different algorithms, respectively, we can get a better value. Finally, we will obtain the optimal value by iterative calculation. Detailed simulation analysis demonstrates the efficiency and effectiveness of our approach.

Keywords: mobile users; K-harmonic means; KHM; particle swarm optimisation; PSO; artificial bee colony; ABC; clustering; mobile commerce; m-commerce; simulation.

DOI: 10.1504/IJICA.2015.073003

International Journal of Innovative Computing and Applications, 2015 Vol.6 No.3/4, pp.163 - 170

Received: 28 Jan 2015
Accepted: 14 Jul 2015

Published online: 11 Nov 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article