EEG Signal Radio Frequency Control Wheeled Robot Based on Bi-objective Chaotic Particle Swarm Optimization Algorithm

Abstract

Aiming at the EEG signal radio frequency control problem of EEG signal radio control wheeled robot traversing multiple objective points, a new method of EEG signal radio frequency control that integrates the bi-objective chaotic particle swarm optimization (BCPSO) is put forward. This method transforms the selection of objective points into the EEG signal radio frequency control problem and makes optimization by using the ant colony algorithm. The EEG signal control function between the two objective points is defined, and the particle swarm optimization algorithm is applied for optimization. Given the premature phenomenon of particle swarm optimization algorithm, the inverse learning strategy is introduced into the particle swarm optimization algorithm, and the inertia weight and learning factor of the particle swarm optimization algorithm are improved. The performance test results show that the bi-objective chaotic particle swarm optimization algorithm can effectively prevent the premature particle phenomenon and improve the optimization capacity and stability of the particle swarm optimization algorithm.