Title: Human group optimiser for global numerical optimisation

Authors: Chaohua Dai; Jiajun Ouyang; Weirong Chen; Yunfang Zhu; Lei Ma

Addresses: The School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China ' The School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China ' The School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China ' The School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China ' The School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China

Abstract: In this paper, the previously proposed seeker optimisation algorithm (SOA) is renamed as human group optimisation (HGO) algorithm, which is a novel population-based heuristic stochastic search algorithm by simulating human group searching behaviours. In this algorithm, the choice of search direction is based on empirical gradients by evaluating the responses to the position changes, and the decision of step length is based on human-unique uncertainty reasoning by using a simple fuzzy rule. Furthermore, a canonical version of HGO is proposed. Based on the benchmark functions provided by CEC2005, the canonical HGO is compared with differential evolution (DE) algorithms, particle swarm optimisation (PSO) algorithms and covariance matrix adaptation evolution strategy (CMA-ES). The simulation results show that the proposed HGO is competitive or even superior to the listed other algorithms for some employed functions.

Keywords: global optimisation; heuristics; human group optimisation; HGO; human group searching behaviours; swarm intelligence; simulation; position changes; uncertainty reasoning; fuzzy rules.

DOI: 10.1504/IJBIC.2014.065586

International Journal of Bio-Inspired Computation, 2014 Vol.6 No.5, pp.333 - 349

Received: 05 Sep 2013
Accepted: 06 Sep 2013

Published online: 08 Nov 2014 *

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