Classification of sonar data set using the gray wolf optimizer algorithm

This paper uses a new meta-heuristic called Grey Wolf Optimizer (GWO) for classifying sonar data set. The GWO algorithm imitates the leadership hierarchy and hunting mechanism of grey wolves in nature. It also employs four types of grey wolves including alpha, beta, delta and omega for simulating the leadership hierarchy. In addition, the three main steps of hunting including searching for prey, encircling prey and attacking prey, are simulated. The algorithm is then benchmarked on 23 well-known test functions and the results are compared with Particle Swarm Optimization (PSO). The results show that the GWO algorithm provides better results in finding total minimum of functions, convergence speed and local minima avoidance compared to PSO. In addition, in this paper a real application of proposed method in the field of sonar data set classification is presented. The results show that the designed classifier inspired by grey wolves can classify the sonar data with accuracy of 96.67%; whereas the PSO presents the accuracy of 92.23%.