A Gradient-Based Adaptive Quantum-behaved Particle Swarm Optimization

Based on the quantum-behaved particle swarm optimization and gradient-based methods, an improved particle swarm optimization algorithm is proposed. In this modified particle swarm algorithm, particles alternate between utilizing quantum behavior and gradient information to optimize parameters. The algorithm also incorporates local random search to enhance the search ability. Tests on some benchmark functions across various dimensions demonstrates its strong global search capabilities and precision. The experimental results indicate promising prospects for the application of this algorithm.