Research Area: Metaheuristic Computing
Salp swarm algorithm (SSA) is one of the recent meta-heuristic algorithms that imitate the behaviors of salps during the navigating and foraging in oceans to perform global optimization. However, the original study of this algorithm was proposed to solve continuous problems, and it cannot be applied to binary problems directly. In this paper, a new binary version of the SSA named BSSA is proposed based on a modified Arctan transformation. This modification has two features regarding the transfer function, namely multiplicity and mobility. By this modification, the exploration and exploitation capabilities can be enhanced. The proposed BSSA is compared among four variants of transfer functions for solving global optimization problems. Also, a comparative study with different binary algorithms including binary particle swarm, binary bat algorithm and binary sine–cosine algorithm on twenty-four benchmark problems is conducted. Furthermore, the nonparametric statistical test based on Wilcoxon’s rank-sum is carried out at 5% significance level to judge statistically the significant of the obtained results among the different algorithms. The results affirm the superior performance of the modified BSSA variant over the other variants as well as the existing approaches regarding solution quality.
Keywords:
Salp swarm algorithm
exploration
exploitation capabilities
particle swarm
bat algorithm
sine–cosine algorithm
Author(s) Name: Rizk-Allah, R.M., Hassanien, A.E., Elhoseny, M.Gunasekaran
Journal name: Neural Computing and Applications
Conferrence name:
Publisher name: Springer
DOI: 10.1007/s00521-018-3613-z
Volume Information: 31, pages 1641–1663
