Quantum-like mutation-induced dragonfly-inspired optimization approach

This study proposed an improved dragonfly algorithm (DA). This algorithm is a recently proposed metaheuristic optimizer inspired by swarming behaviors of dragonflies, which has reasonably achieved satisfactory results in dealing with engineering, education, and other fields. However, the original method will show some shortcomings in convergence speed or falling into local optimum. Given these shortcomings, this paper proposes an improved optimizer to balance the relationship between exploitation and exploration and mitigate any deficiency. First, by implementing the idea of the quantum rotation gate, the swarm of agents can be shifted to a position more conducive to the optimal value. Then, Gaussian mutation is adopted to improve the swarm’s ability to mutate and realize its diversity, which enables the primary method to have a strong local search capability. The proposed method was compared against six other common meta-heuristics and five state-of-the-art algorithms on a comprehensive set of nineteen functions selected from twenty-three classic benchmark problems and thirty IEEE (Institute of Electrical and Electronics Engineers) CEC (Congress on Evolutionary Computation) 2014 benchmark tasks. To verify the effectiveness of the approach, the non-parametric statistical Wilcoxon signed-rank and Friedman tests were performed to validate the significance of the proposed method against other counterparts. The results of experimental simulations demonstrate that two introduced strategies can significantly improve the exploitative and exploratory tendencies of the original algorithm. Furthermore, the convergence speed of the conventional approach has been improved to a large extent. Additionally, quantum-behaved and Gaussian mutational dragonfly algorithm (QGDA) is utilized as a searching core in a wrapper feature selection technique, and it is compared with other advanced feature selection methods. The results show that QGDA achieves substantial superiority in feature selection through optimum fitness and minimum error rate. Also, the results of QGDA on the three classical engineering design problems have demonstrated that the proposed method can effectively solve these constraints problems. It is encouraging that the proposed method can be used as a useful, auxiliary tool for solving complex optimization problems.