Function-shape-based particle swarm optimization and its application in maritime static target cooperative search

The application of particle swarm algorithm in optimization has been growing over the last few years, but this approach becomes computationally impracticable when the complexity of the problem increases. In this context, an improvement of the particle swarm algorithm-the function-shape-based particle swarm optimization (FSPSO) is presented. For a practical maritime cooperative search problem, FSPSO makes particles move around in the corresponding solution space according to certain rules to gather information firstly. Then FSPSO exploits the history data acquired during the first process to analyze the shape of the solution space. Based on the knowledge about the function shape, FSPSO generates solutions and iteration strategies. At last, the position and speed of each particle will be updated iteratively, aiming at producing a high quality solution to the optimization problem. The main idea behind FSPSO is to hybridize PSO with the search mode of a human being. This paper uses maritime static target cooperative search as a test domain. In order to evaluate the effectiveness of FSPSO, we perform a comparison between the performances of FSPSO with other approaches drawn from the scientific literature. Results demonstrate that FSPSO is able to produce statistically significantly higher quality solutions, outperforming many other approaches.