For the problem of how to high precision restructure source signals, when laser chaotic signal under the interference of a variety of noise intensities, this paper proposes a blind source separation algorithm based on phase space reconstructed chaotic stream signal. This algorithm firstly makes time delay reconstruction on phase space of separation signals, and then regards the separation matrix as parameter to be optimized, through constructing objective function in phase space to convert

more »

... source separation to an optimization problem, using particle swarm optimization algorithm to solve the optimal separation matrix, and then the observation data is multiplied by optimal separation matrix to reconstruct the source signals. The experimental results show that the algorithm not only has the characteristics of rapid convergence and its accuracy is obviously superior to the existing independent component analysis method under various noise intensities.